Update app.py

app.py

@@ -18,10 +18,12 @@ import os
 import json
 from PIL import Image
 import time
+import base64
+from io import BytesIO
 
 # Set page configuration
 st.set_page_config(
-    page_title="Smart Sugarcane Farm Monitoring",
+    page_title="سامانه هوشمند مانیتورینگ مزارع نیشکر",
     page_icon="🌱",
     layout="wide",
     initial_sidebar_state="collapsed"
@@ -30,19 +32,36 @@ st.set_page_config(
 # Custom CSS for styling
 st.markdown("""
 <style>
+    @font-face {
+        font-family: 'Vazir';
+        src: url('https://cdn.jsdelivr.net/gh/rastikerdar/[email protected]/dist/Vazir.woff2') format('woff2');
+        font-weight: normal;
+        font-style: normal;
+    }
+    
+    * {
+        font-family: 'Vazir', sans-serif !important;
+    }
+    
     .main {
-        background-color: #1E2130;
+        background-color: #0F1923;
         color: white;
+        direction: rtl;
+        text-align: right;
     }
+    
     .stApp {
-        background-image: linear-gradient(to bottom, #1E2130, #2D3747);
+        background-image: linear-gradient(to bottom, #0F1923, #1A2634);
     }
+    
     .css-18e3th9 {
         padding-top: 0;
     }
+    
     .css-1d391kg {
         padding-top: 1rem;
     }
+    
     .stButton>button {
         background-color: #2EC4B6;
         color: white;
@@ -51,83 +70,118 @@ st.markdown("""
         padding: 10px 20px;
         transition: all 0.3s;
     }
+    
     .stButton>button:hover {
         background-color: #1A9E8F;
         transform: scale(1.05);
     }
+    
     .metric-card {
-        background-color: rgba(30, 33, 48, 0.8);
+        background-color: rgba(15, 25, 35, 0.8);
         border-radius: 10px;
         padding: 15px;
         border: 1px solid #2EC4B6;
         text-align: center;
+        box-shadow: 0 4px 6px rgba(0, 0, 0, 0.1);
+        transition: all 0.3s ease;
+    }
+    
+    .metric-card:hover {
+        transform: translateY(-5px);
+        box-shadow: 0 8px 15px rgba(0, 0, 0, 0.2);
     }
+    
     .metric-value {
-        font-size: 24px;
+        font-size: 28px;
         font-weight: bold;
         color: #2EC4B6;
+        text-shadow: 0 0 10px rgba(46, 196, 182, 0.5);
     }
+    
     .metric-label {
-        font-size: 14px;
+        font-size: 16px;
         color: #CCC;
+        margin-top: 5px;
     }
+    
     .chart-container {
-        background-color: rgba(30, 33, 48, 0.8);
+        background-color: rgba(15, 25, 35, 0.8);
         border-radius: 10px;
         padding: 15px;
         border: 1px solid #2EC4B6;
+        box-shadow: 0 4px 6px rgba(0, 0, 0, 0.1);
     }
+    
     .table-container {
-        background-color: rgba(30, 33, 48, 0.8);
+        background-color: rgba(15, 25, 35, 0.8);
         border-radius: 10px;
         padding: 15px;
         border: 1px solid #2EC4B6;
+        box-shadow: 0 4px 6px rgba(0, 0, 0, 0.1);
     }
+    
     .compass {
         position: relative;
         width: 200px;
         height: 200px;
         margin: 0 auto;
+        animation: rotate 60s linear infinite;
     }
+    
+    @keyframes rotate {
+        from { transform: rotate(0deg); }
+        to { transform: rotate(360deg); }
+    }
+    
     .compass-img {
         width: 100%;
         height: 100%;
     }
+    
     .stDataFrame {
-        background-color: rgba(30, 33, 48, 0.8) !important;
+        background-color: rgba(15, 25, 35, 0.8) !important;
     }
+    
     div[data-testid="stDataFrameResizable"] {
-        background-color: rgba(30, 33, 48, 0.8) !important;
+        background-color: rgba(15, 25, 35, 0.8) !important;
     }
+    
     div[data-testid="stDataFrameResizable"] > div {
-        background-color: rgba(30, 33, 48, 0.8) !important;
+        background-color: rgba(15, 25, 35, 0.8) !important;
     }
+    
     div[data-testid="stDataFrameResizable"] td {
-        background-color: rgba(30, 33, 48, 0.8) !important;
+        background-color: rgba(15, 25, 35, 0.8) !important;
         color: white !important;
     }
+    
     div[data-testid="stDataFrameResizable"] th {
         background-color: rgba(46, 196, 182, 0.3) !important;
         color: white !important;
     }
+    
     .stTabs [data-baseweb="tab-list"] {
         gap: 10px;
     }
+    
     .stTabs [data-baseweb="tab"] {
-        background-color: rgba(30, 33, 48, 0.8);
+        background-color: rgba(15, 25, 35, 0.8);
         border-radius: 4px 4px 0px 0px;
         padding: 10px 20px;
         color: white;
     }
+    
     .stTabs [aria-selected="true"] {
         background-color: #2EC4B6 !important;
         color: white !important;
     }
+    
     .gauge-chart {
         margin: 0 auto;
         width: 200px;
         height: 200px;
     }
+    
     @keyframes pulse {
         0% {
             box-shadow: 0 0 0 0 rgba(46, 196, 182, 0.7);
@@ -139,18 +193,357 @@ st.markdown("""
             box-shadow: 0 0 0 0 rgba(46, 196, 182, 0);
         }
     }
+    
     .pulsing {
         animation: pulse 2s infinite;
     }
+    
     .logo-container {
         text-align: center;
         margin-bottom: 20px;
     }
+    
     .logo-text {
         font-size: 24px;
         font-weight: bold;
         color: #2EC4B6;
     }
+    
+    .dashboard-container {
+        background-color: rgba(15, 25, 35, 0.7);
+        border-radius: 15px;
+        padding: 20px;
+        border: 1px solid #2EC4B6;
+        box-shadow: 0 0 20px rgba(46, 196, 182, 0.2);
+        margin-bottom: 20px;
+    }
+    
+    .dashboard-header {
+        display: flex;
+        justify-content: space-between;
+        align-items: center;
+        margin-bottom: 20px;
+        border-bottom: 1px solid rgba(46, 196, 182, 0.3);
+        padding-bottom: 10px;
+    }
+    
+    .dashboard-title {
+        color: #2EC4B6;
+        font-size: 24px;
+        font-weight: bold;
+        margin: 0;
+    }
+    
+    .dashboard-subtitle {
+        color: #CCC;
+        font-size: 14px;
+        margin: 0;
+    }
+    
+    .circular-button {
+        width: 60px;
+        height: 60px;
+        border-radius: 50%;
+        background-color: rgba(46, 196, 182, 0.2);
+        display: flex;
+        justify-content: center;
+        align-items: center;
+        color: #2EC4B6;
+        font-size: 24px;
+        border: 2px solid #2EC4B6;
+        cursor: pointer;
+        transition: all 0.3s;
+        margin: 0 auto;
+        box-shadow: 0 0 10px rgba(46, 196, 182, 0.5);
+    }
+    
+    .circular-button:hover {
+        background-color: rgba(46, 196, 182, 0.4);
+        transform: scale(1.1);
+    }
+    
+    .circular-value {
+        font-size: 18px;
+        font-weight: bold;
+        color: #2EC4B6;
+        text-align: center;
+        margin-top: 10px;
+    }
+    
+    .circular-label {
+        font-size: 14px;
+        color: #CCC;
+        text-align: center;
+    }
+    
+    .blinking {
+        animation: blink 1.5s infinite;
+    }
+    
+    @keyframes blink {
+        0% { opacity: 1; }
+        50% { opacity: 0.3; }
+        100% { opacity: 1; }
+    }
+    
+    .rotating {
+        animation: rotate 10s linear infinite;
+    }
+    
+    .glowing {
+        box-shadow: 0 0 10px #2EC4B6, 0 0 20px #2EC4B6, 0 0 30px #2EC4B6;
+        animation: glow 2s infinite alternate;
+    }
+    
+    @keyframes glow {
+        from { box-shadow: 0 0 10px #2EC4B6, 0 0 20px #2EC4B6; }
+        to { box-shadow: 0 0 20px #2EC4B6, 0 0 30px #2EC4B6, 0 0 40px #2EC4B6; }
+    }
+    
+    .stSelectbox [data-baseweb=select] {
+        background-color: rgba(15, 25, 35, 0.8);
+        border-color: #2EC4B6;
+    }
+    
+    .stSelectbox [data-baseweb=select] > div {
+        background-color: rgba(15, 25, 35, 0.8);
+        color: white;
+    }
+    
+    .stDateInput > div > div {
+        background-color: rgba(15, 25, 35, 0.8);
+        border-color: #2EC4B6;
+        color: white;
+    }
+    
+    .stDateInput input {
+        color: white;
+    }
+    
+    /* Custom scrollbar */
+    ::-webkit-scrollbar {
+        width: 8px;
+        height: 8px;
+    }
+    
+    ::-webkit-scrollbar-track {
+        background: rgba(15, 25, 35, 0.8);
+    }
+    
+    ::-webkit-scrollbar-thumb {
+        background: #2EC4B6;
+        border-radius: 4px;
+    }
+    
+    ::-webkit-scrollbar-thumb:hover {
+        background: #1A9E8F;
+    }
+    
+    /* Animated buttons */
+    .animated-button {
+        background-color: rgba(46, 196, 182, 0.2);
+        color: #2EC4B6;
+        border: 2px solid #2EC4B6;
+        border-radius: 10px;
+        padding: 10px 15px;
+        margin: 5px;
+        transition: all 0.3s;
+        cursor: pointer;
+        text-align: center;
+        font-weight: bold;
+        box-shadow: 0 0 10px rgba(46, 196, 182, 0.3);
+    }
+    
+    .animated-button:hover {
+        background-color: rgba(46, 196, 182, 0.4);
+        transform: translateY(-3px);
+        box-shadow: 0 5px 15px rgba(46, 196, 182, 0.5);
+    }
+    
+    /* Tooltip styling */
+    .tooltip {
+        position: relative;
+        display: inline-block;
+    }
+    
+    .tooltip .tooltiptext {
+        visibility: hidden;
+        width: 120px;
+        background-color: rgba(15, 25, 35, 0.9);
+        color: #fff;
+        text-align: center;
+        border-radius: 6px;
+        padding: 5px;
+        position: absolute;
+        z-index: 1;
+        bottom: 125%;
+        left: 50%;
+        margin-left: -60px;
+        opacity: 0;
+        transition: opacity 0.3s;
+        border: 1px solid #2EC4B6;
+    }
+    
+    .tooltip:hover .tooltiptext {
+        visibility: visible;
+        opacity: 1;
+    }
+    
+    /* Progress bar styling */
+    .stProgress > div > div > div {
+        background-color: #2EC4B6;
+    }
+    
+    /* Header styling */
+    .header-container {
+        display: flex;
+        justify-content: space-between;
+        align-items: center;
+        padding: 10px 20px;
+        background-color: rgba(15, 25, 35, 0.8);
+        border-radius: 10px;
+        margin-bottom: 20px;
+        border-bottom: 2px solid #2EC4B6;
+    }
+    
+    .header-title {
+        color: #2EC4B6;
+        font-size: 28px;
+        font-weight: bold;
+        margin: 0;
+        text-shadow: 0 0 10px rgba(46, 196, 182, 0.5);
+    }
+    
+    .header-subtitle {
+        color: #CCC;
+        font-size: 16px;
+        margin: 0;
+    }
+    
+    /* Card styling */
+    .card {
+        background-color: rgba(15, 25, 35, 0.8);
+        border-radius: 10px;
+        padding: 15px;
+        border: 1px solid #2EC4B6;
+        margin-bottom: 15px;
+        transition: all 0.3s;
+    }
+    
+    .card:hover {
+        transform: translateY(-5px);
+        box-shadow: 0 5px 15px rgba(46, 196, 182, 0.3);
+    }
+    
+    .card-title {
+        color: #2EC4B6;
+        font-size: 18px;
+        font-weight: bold;
+        margin-bottom: 10px;
+        border-bottom: 1px solid rgba(46, 196, 182, 0.3);
+        padding-bottom: 5px;
+    }
+    
+    /* Weather icon styling */
+    .weather-icon {
+        font-size: 36px;
+        color: #2EC4B6;
+        text-align: center;
+        margin-bottom: 10px;
+    }
+    
+    /* Farm status indicators */
+    .status-indicator {
+        width: 15px;
+        height: 15px;
+        border-radius: 50%;
+        display: inline-block;
+        margin-right: 5px;
+    }
+    
+    .status-good {
+        background-color: #4CAF50;
+        box-shadow: 0 0 5px #4CAF50;
+    }
+    
+    .status-warning {
+        background-color: #FFC107;
+        box-shadow: 0 0 5px #FFC107;
+    }
+    
+    .status-alert {
+        background-color: #F44336;
+        box-shadow: 0 0 5px #F44336;
+    }
+    
+    /* Custom radio buttons */
+    .stRadio [data-testid="stMarkdownContainer"] > div {
+        display: flex;
+        flex-direction: row;
+    }
+    
+    .stRadio label {
+        background-color: rgba(15, 25, 35, 0.8);
+        border: 1px solid #2EC4B6;
+        border-radius: 5px;
+        padding: 10px 15px;
+        margin: 0 5px;
+        transition: all 0.3s;
+    }
+    
+    .stRadio label:hover {
+        background-color: rgba(46, 196, 182, 0.2);
+    }
+    
+    .stRadio label[data-checked="true"] {
+        background-color: #2EC4B6;
+        color: white;
+    }
+    
+    /* Animated loading spinner */
+    @keyframes spinner {
+        0% { transform: rotate(0deg); }
+        100% { transform: rotate(360deg); }
+    }
+    
+    .loading-spinner {
+        width: 40px;
+        height: 40px;
+        border: 4px solid rgba(46, 196, 182, 0.3);
+        border-radius: 50%;
+        border-top: 4px solid #2EC4B6;
+        animation: spinner 1s linear infinite;
+        margin: 20px auto;
+    }
+    
+    /* Custom slider */
+    .stSlider [data-baseweb="slider"] {
+        margin-top: 10px;
+    }
+    
+    .stSlider [data-baseweb="slider"] [data-testid="stThumbValue"] {
+        background-color: #2EC4B6;
+        color: white;
+    }
+    
+    .stSlider [data-baseweb="slider"] [data-testid="stTrack"] > div {
+        background-color: #2EC4B6;
+    }
+    
+    /* Responsive design adjustments */
+    @media (max-width: 768px) {
+        .metric-value {
+            font-size: 20px;
+        }
+        
+        .metric-label {
+            font-size: 12px;
+        }
+        
+        .dashboard-title {
+            font-size: 20px;
+        }
+    }
 </style>
 """, unsafe_allow_html=True)
 
@@ -168,7 +561,7 @@ def initialize_ee():
             ee.Initialize(credentials)
             return True
         else:
-            st.error("GEE credentials file not found. Please upload the credentials file.")
+            st.error("فایل اعتبارنامه GEE یافت نشد. لطفاً فایل اعتبارنامه را آپلود کنید.")
             return False
 
 # Load farm coordinates
@@ -176,16 +569,18 @@ def initialize_ee():
 def load_farm_data():
     try:
         farm_data = pd.read_csv('farm_coordinates.csv')
+        # Rename columns to Persian
+        farm_data.columns = ['نام مزرعه', 'سن', 'تنوع', 'طول جغرافیایی', 'عرض جغرافیایی']
         return farm_data
     except Exception as e:
-        st.error(f"Error loading farm coordinates: {e}")
+        st.error(f"خطا در بارگذاری مختصات مزارع: {e}")
         # Create sample data if file not found
         sample_data = pd.DataFrame({
-            'farm_name': [f'Farm_{i}' for i in range(1, 11)],
-            'age': np.random.randint(1, 6, 10),
-            'variety': np.random.choice(['Type A', 'Type B', 'Type C'], 10),
-            'longitude': np.random.uniform(51.0, 51.5, 10),
-            'latitude': np.random.uniform(32.0, 32.5, 10)
+            'نام مزرعه': [f'مزرعه_{i}' for i in range(1, 11)],
+            'سن': np.random.randint(1, 6, 10),
+            'تنوع': np.random.choice(['نوع A', 'نوع B', 'نوع C'], 10),
+            'طول جغرافیایی': np.random.uniform(51.0, 51.5, 10),
+            'عرض جغرافیایی': np.random.uniform(32.0, 32.5, 10)
         })
         return sample_data
 
@@ -194,14 +589,17 @@ def load_farm_data():
 def load_day_schedule():
     try:
         schedule_data = pd.read_csv('پایگاه داده (1).csv')
+        # Ensure the column names are in Persian
+        if 'day' in schedule_data.columns and 'farm_name' in schedule_data.columns:
+            schedule_data.columns = ['روز', 'نام مزرعه']
         return schedule_data
     except Exception as e:
-        st.error(f"Error loading day schedule: {e}")
+        st.error(f"خطا در بارگذاری برنامه روزانه: {e}")
         # Create sample data if file not found
-        days = ['Monday', 'Tuesday', 'Wednesday', 'Thursday', 'Friday', 'Saturday', 'Sunday']
+        days = ['دوشنبه', 'سه‌شنبه', 'چهارشنبه', 'پنج‌شنبه', 'جمعه', 'شنبه', 'یکشنبه']
         sample_data = pd.DataFrame({
-            'day': np.random.choice(days, 10),
-            'farm_name': [f'Farm_{i}' for i in range(1, 11)]
+            'روز': np.random.choice(days, 10),
+            'نام مزرعه': [f'مزرعه_{i}' for i in range(1, 11)]
         })
         return sample_data
 
@@ -226,34 +624,32 @@ def calculate_indices(image):
     # NDRE = (NIR - Red Edge) / (NIR + Red Edge)
     ndre = image.normalizedDifference(['B8', 'B5']).rename('NDRE')
     
-    # LAI calculation (simplified model)
-    # LAI = 3.618 * EVI - 0.118
-    nir = image.select('B8')
-    red = image.select('B4')
-    blue = image.select('B2')
-    evi = image.expression(
-        '2.5 * ((NIR - RED) / (NIR + 6 * RED - 7.5 * BLUE + 1))', 
-        {'NIR': nir, 'RED': red, 'BLUE': blue}
-    ).rename('EVI')
-    lai = evi.multiply(3.618).subtract(0.118).rename('LAI')
+    # LAI calculation (more realistic model based on NDVI)
+    # LAI = 0.57 * exp(2.33 * NDVI)
+    lai = ndvi.expression(
+        '0.57 * exp(2.33 * NDVI)',
+        {'NDVI': ndvi}
+    ).rename('LAI')
     
     # Chlorophyll index
+    nir = image.select('B8')
+    red = image.select('B4')
     chlorophyll = image.expression(
         '(NIR / RED) - 1',
         {'NIR': nir, 'RED': red}
     ).rename('CHL')
     
     # Add all indices to the image
-    return image.addBands([ndvi, ndre, lai, evi, chlorophyll])
+    return image.addBands([ndvi, ndre, lai, chlorophyll])
 
 # Function to create LSTM model
 def create_lstm_model(input_shape):
     model = Sequential()
-    model.add(LSTM(50, return_sequences=True, input_shape=input_shape))
+    model.add(LSTM(64, return_sequences=True, input_shape=input_shape))
     model.add(Dropout(0.2))
-    model.add(LSTM(50, return_sequences=False))
+    model.add(LSTM(64, return_sequences=False))
     model.add(Dropout(0.2))
-    model.add(Dense(25))
+    model.add(Dense(32))
     model.add(Dense(3))  # Predict LAI, NDVI, NDRE
     
     model.compile(optimizer='adam', loss='mse')
@@ -323,7 +719,7 @@ def create_gauge_chart(value, title, min_val=0, max_val=1):
         gauge={
             'axis': {'range': [min_val, max_val], 'tickcolor': 'white'},
             'bar': {'color': "#2EC4B6"},
-            'bgcolor': "rgba(30, 33, 48, 0.8)",
+            'bgcolor': "rgba(15, 25, 35, 0.8)",
             'borderwidth': 2,
             'bordercolor': "#2EC4B6",
             'steps': [
@@ -348,20 +744,22 @@ def create_gauge_chart(value, title, min_val=0, max_val=1):
 def create_line_chart(data, x_col, y_cols, title):
     fig = go.Figure()
     
-    for col in y_cols:
+    colors = ['#2EC4B6', '#FF9F1C', '#E71D36', '#4361EE', '#7209B7']
+    
+    for i, col in enumerate(y_cols):
         fig.add_trace(go.Scatter(
             x=data[x_col],
             y=data[col],
             mode='lines+markers',
             name=col,
-            line=dict(width=3),
-            marker=dict(size=8)
+            line=dict(width=3, color=colors[i % len(colors)]),
+            marker=dict(size=8, color=colors[i % len(colors)])
         ))
     
     fig.update_layout(
         title=title,
-        xaxis_title='Date',
-        yaxis_title='Value',
+        xaxis_title='تاریخ',
+        yaxis_title='مقدار',
         legend=dict(
             orientation="h",
             yanchor="bottom",
@@ -370,7 +768,7 @@ def create_line_chart(data, x_col, y_cols, title):
             x=1
         ),
         template="plotly_dark",
-        plot_bgcolor='rgba(30, 33, 48, 0.8)',
+        plot_bgcolor='rgba(15, 25, 35, 0.8)',
         paper_bgcolor='rgba(0,0,0,0)',
         font=dict(color='white'),
         margin=dict(l=20, r=20, t=50, b=20),
@@ -386,7 +784,10 @@ def create_bar_chart(data, x_col, y_col, title):
     fig.add_trace(go.Bar(
         x=data[x_col],
         y=data[y_col],
-        marker_color='#2EC4B6'
+        marker_color='#2EC4B6',
+        marker_line_color='#1A9E8F',
+        marker_line_width=1.5,
+        opacity=0.8
     ))
     
     fig.update_layout(
@@ -394,7 +795,7 @@ def create_bar_chart(data, x_col, y_col, title):
         xaxis_title=x_col,
         yaxis_title=y_col,
         template="plotly_dark",
-        plot_bgcolor='rgba(30, 33, 48, 0.8)',
+        plot_bgcolor='rgba(15, 25, 35, 0.8)',
         paper_bgcolor='rgba(0,0,0,0)',
         font=dict(color='white'),
         margin=dict(l=20, r=20, t=50, b=20),
@@ -421,7 +822,7 @@ def create_area_chart(data, x_col, y_col, title):
         xaxis_title=x_col,
         yaxis_title=y_col,
         template="plotly_dark",
-        plot_bgcolor='rgba(30, 33, 48, 0.8)',
+        plot_bgcolor='rgba(15, 25, 35, 0.8)',
         paper_bgcolor='rgba(0,0,0,0)',
         font=dict(color='white'),
         margin=dict(l=20, r=20, t=50, b=20),
@@ -430,64 +831,118 @@ def create_area_chart(data, x_col, y_col, title):
     
     return fig
 
+# Create a compass image
+def get_compass_image():
+    # Create a base64 encoded compass image
+    compass_html = f"""
+    <div style="width:200px; height:200px; margin:0 auto; position:relative;">
+        <svg width="200" height="200" viewBox="0 0 200 200" xmlns="http://www.w3.org/2000/svg" class="rotating">
+            <circle cx="100" cy="100" r="90" fill="rgba(15, 25, 35, 0.8)" stroke="#2EC4B6" stroke-width="2"/>
+            <circle cx="100" cy="100" r="5" fill="#2EC4B6"/>
+            <path d="M100,10 L100,30" stroke="#2EC4B6" stroke-width="2" transform="rotate(0 100 100)"/>
+            <path d="M100,10 L100,30" stroke="#2EC4B6" stroke-width="2" transform="rotate(90 100 100)"/>
+            <path d="M100,10 L100,30" stroke="#2EC4B6" stroke-width="2" transform="rotate(180 100 100)"/>
+            <path d="M100,10 L100,30" stroke="#2EC4B6" stroke-width="2" transform="rotate(270 100 100)"/>
+            <path d="M100,10 L100,20" stroke="#2EC4B6" stroke-width="1" transform="rotate(30 100 100)"/>
+            <path d="M100,10 L100,20" stroke="#2EC4B6" stroke-width="1" transform="rotate(60 100 100)"/>
+            <path d="M100,10 L100,20" stroke="#2EC4B6" stroke-width="1" transform="rotate(120 100 100)"/>
+            <path d="M100,10 L100,20" stroke="#2EC4B6" stroke-width="1" transform="rotate(150 100 100)"/>
+            <path d="M100,10 L100,20" stroke="#2EC4B6" stroke-width="1" transform="rotate(210 100 100)"/>
+            <path d="M100,10 L100,20" stroke="#2EC4B6" stroke-width="1" transform="rotate(240 100 100)"/>
+            <path d="M100,10 L100,20" stroke="#2EC4B6" stroke-width="1" transform="rotate(300 100 100)"/>
+            <path d="M100,10 L100,20" stroke="#2EC4B6" stroke-width="1" transform="rotate(330 100 100)"/>
+            <text x="100" y="45" text-anchor="middle" fill="#2EC4B6" font-size="12">N</text>
+            <text x="155" y="105" text-anchor="middle" fill="#2EC4B6" font-size="12">E</text>
+            <text x="100" y="165" text-anchor="middle" fill="#2EC4B6" font-size="12">S</text>
+            <text x="45" y="105" text-anchor="middle" fill="#2EC4B6" font-size="12">W</text>
+            <path d="M100,40 L90,90 L100,80 L110,90 Z" fill="#E71D36" stroke="#2EC4B6" stroke-width="1"/>
+            <path d="M100,160 L90,110 L100,120 L110,110 Z" fill="#2EC4B6" stroke="#2EC4B6" stroke-width="1"/>
+        </svg>
+    </div>
+    """
+    return compass_html
+
+# Create a circular metric
+def create_circular_metric(value, label, icon, min_val=0, max_val=100):
+    # Calculate percentage for the circular progress
+    percentage = min(max(value / max_val, 0), 1) * 100
+    
+    # Create the HTML for the circular metric
+    html = f"""
+    <div style="text-align: center; margin-bottom: 20px;">
+        <div class="circular-button" style="background: conic-gradient(#2EC4B6 {percentage}%, rgba(15, 25, 35, 0.8) 0%);">
+            {icon}
+        </div>
+        <div class="circular-value">{value}</div>
+        <div class="circular-label">{label}</div>
+    </div>
+    """
+    return html
+
 # Main application
 def main():
     # Initialize Earth Engine
     ee_initialized = initialize_ee()
     if not ee_initialized:
-        st.warning("Earth Engine initialization failed. Some features may not work.")
+        st.warning("مقداردهی اولیه Earth Engine با مشکل مواجه شد. برخی از ویژگی‌ها ممکن است کار نکنند.")
     
     # Load data
     farm_data = load_farm_data()
     day_schedule = load_day_schedule()
     
     # Header with logo
-    col1, col2, col3 = st.columns([1, 3, 1])
-    with col1:
-        st.markdown("""
-        <div class="logo-container">
+    st.markdown("""
+    <div class="header-container">
+        <div>
+            <h1 class="header-title">سامانه هوشمند مانیتورینگ مزارع نیشکر</h1>
+            <p class="header-subtitle">پایش و پیش‌بینی رشد با استفاده از تصاویر ماهواره‌ای و هوش مصنوعی</p>
+        </div>
+        <div style="text-align: center;">
             <div style="font-size: 40px; color: #2EC4B6;">✦</div>
-            <div class="logo-text">SMART<br>Sugarcane</div>
-            <div style="color: #CCC; font-size: 16px;">FARM</div>
+            <div style="font-size: 18px; font-weight: bold; color: #2EC4B6;">SMART<br>Sugarcane</div>
+            <div style="color: #CCC; font-size: 14px;">FARM</div>
         </div>
-        """, unsafe_allow_html=True)
-    
-    with col2:
-        st.markdown("""
-        <h1 style="text-align: center; color: #2EC4B6; margin-bottom: 20px;">
-            <span style="margin-right: 10px;">��</span> Smart Sugarcane Farm Monitoring <span style="margin-left: 10px;">🌱</span>
-        </h1>
-        """, unsafe_allow_html=True)
+    </div>
+    """, unsafe_allow_html=True)
     
     # Date selection
     today = datetime.now()
     start_date = today - timedelta(days=30)
     end_date = today
     
-    col1, col2 = st.columns(2)
+    st.markdown('<div class="dashboard-container">', unsafe_allow_html=True)
+    
+    col1, col2, col3 = st.columns([2, 1, 2])
     with col1:
-        start_date = st.date_input("Start Date", start_date)
+        start_date = st.date_input("تاریخ شروع", start_date)
     with col2:
-        end_date = st.date_input("End Date", end_date)
+        # Day selection
+        days_persian = ['دوشنبه', 'سه‌شنبه', 'چهارشنبه', 'پنج‌شنبه', 'جمعه', 'شنبه', 'یکشنبه']
+        selected_day = st.selectbox("انتخاب روز", days_persian)
+    with col3:
+        end_date = st.date_input("تاریخ پایان", end_date)
     
-    # Day selection
-    days = ['Monday', 'Tuesday', 'Wednesday', 'Thursday', 'Friday', 'Saturday', 'Sunday']
-    selected_day = st.selectbox("Select Day", days)
+    st.markdown('</div>', unsafe_allow_html=True)
     
     # Filter farms for selected day
-    day_farms = day_schedule[day_schedule['day'] == selected_day]['farm_name'].tolist()
-    selected_farms = farm_data[farm_data['farm_name'].isin(day_farms)]
+    day_farms = day_schedule[day_schedule['روز'] == selected_day]['نام مزرعه'].tolist()
+    selected_farms = farm_data[farm_data['نام مزرعه'].isin(day_farms)]
     
     if selected_farms.empty:
-        st.warning(f"No farms scheduled for {selected_day}. Please select another day.")
+        st.warning(f"هیچ مزرعه‌ای برای روز {selected_day} برنامه‌ریزی نشده است. لطفاً روز دیگری را انتخاب کنید.")
     else:
         # Create tabs for different sections
-        tabs = st.tabs(["Dashboard", "Farm Analysis", "Growth Prediction", "Data Tables"])
+        tabs = st.tabs(["داشبورد", "تحلیل مزرعه", "پیش‌بینی رشد", "جداول داده"])
         
         # Dashboard Tab
         with tabs[0]:
+            st.markdown('<div class="dashboard-container">', unsafe_allow_html=True)
+            
             # Main metrics row
-            st.markdown("### Current Farm Metrics")
+            st.markdown('<div class="dashboard-header">', unsafe_allow_html=True)
+            st.markdown('<h2 class="dashboard-title">شاخص‌های فعلی مزارع</h2>', unsafe_allow_html=True)
+            st.markdown('</div>', unsafe_allow_html=True)
+            
             metric_cols = st.columns(5)
             
             # Generate sample metrics for demonstration
@@ -501,7 +956,7 @@ def main():
                 st.markdown(f"""
                 <div class="metric-card">
                     <div class="metric-value">{avg_ndvi}</div>
-                    <div class="metric-label">Avg. NDVI</div>
+                    <div class="metric-label">میانگین NDVI</div>
                 </div>
                 """, unsafe_allow_html=True)
             
@@ -509,7 +964,7 @@ def main():
                 st.markdown(f"""
                 <div class="metric-card">
                     <div class="metric-value">{avg_lai}</div>
-                    <div class="metric-label">Avg. LAI</div>
+                    <div class="metric-label">میانگین LAI</div>
                 </div>
                 """, unsafe_allow_html=True)
             
@@ -517,7 +972,7 @@ def main():
                 st.markdown(f"""
                 <div class="metric-card">
                     <div class="metric-value">{avg_ndre}</div>
-                    <div class="metric-label">Avg. NDRE</div>
+                    <div class="metric-label">میانگین NDRE</div>
                 </div>
                 """, unsafe_allow_html=True)
             
@@ -525,7 +980,7 @@ def main():
                 st.markdown(f"""
                 <div class="metric-card">
                     <div class="metric-value">{avg_chl}</div>
-                    <div class="metric-label">Chlorophyll</div>
+                    <div class="metric-label">شاخص کلروفیل</div>
                 </div>
                 """, unsafe_allow_html=True)
             
@@ -533,19 +988,25 @@ def main():
                 st.markdown(f"""
                 <div class="metric-card pulsing">
                     <div class="metric-value">{avg_growth}%</div>
-                    <div class="metric-label">Growth Rate</div>
+                    <div class="metric-label">نرخ رشد</div>
                 </div>
                 """, unsafe_allow_html=True)
             
+            st.markdown('</div>', unsafe_allow_html=True)
+            
             # Map and compass row
+            st.markdown('<div class="dashboard-container">', unsafe_allow_html=True)
+            
             map_col, compass_col = st.columns([3, 1])
             
             with map_col:
-                st.markdown("### Farm Map (NDVI)")
+                st.markdown('<div class="dashboard-header">', unsafe_allow_html=True)
+                st.markdown('<h2 class="dashboard-title">نقشه مزارع (NDVI)</h2>', unsafe_allow_html=True)
+                st.markdown('</div>', unsafe_allow_html=True)
                 
                 # Create a map centered at the mean of farm coordinates
-                center_lat = selected_farms['latitude'].mean()
-                center_lon = selected_farms['longitude'].mean()
+                center_lat = selected_farms['عرض جغرافیایی'].mean()
+                center_lon = selected_farms['طول جغرافیایی'].mean()
                 
                 m = geemap.Map(center=[center_lat, center_lon], zoom=12)
                 
@@ -554,7 +1015,7 @@ def main():
                 
                 # Create features for farms
                 for _, farm in selected_farms.iterrows():
-                    point = ee.Geometry.Point([farm['longitude'], farm['latitude']])
+                    point = ee.Geometry.Point([farm['طول جغرافیایی'], farm['عرض جغرافیایی']])
                     buffer = point.buffer(500)  # 500m buffer around point
                     
                     # Get Sentinel imagery
@@ -575,16 +1036,16 @@ def main():
                             'max': 1,
                             'palette': ['#d73027', '#f46d43', '#fdae61', '#fee08b', '#d9ef8b', '#a6d96a', '#66bd63', '#1a9850']
                         }
-                        m.addLayer(image_with_indices.select('NDVI'), ndvi_vis, f'NDVI - {farm["farm_name"]}')
+                        m.addLayer(image_with_indices.select('NDVI'), ndvi_vis, f'NDVI - {farm["نام مزرعه"]}')
                         
                         # Add farm marker with pulsing effect
                         folium.Marker(
-                            location=[farm['latitude'], farm['longitude']],
+                            location=[farm['عرض جغرافیایی'], farm['طول جغرافیایی']],
                             popup=f"""
-                            <div style='width: 200px'>
-                                <h4>{farm['farm_name']}</h4>
-                                <p>Age: {farm['age']} years</p>
-                                <p>Variety: {farm['variety']}</p>
+                            <div style='width: 200px; direction: rtl; text-align: right;'>
+                                <h4>{farm['نام مزرعه']}</h4>
+                                <p>سن: {farm['سن']} سال</p>
+                                <p>تنوع: {farm['تنوع']}</p>
                             </div>
                             """,
                             icon=folium.Icon(color='green', icon='leaf')
@@ -594,20 +1055,30 @@ def main():
                 folium_static(m)
             
             with compass_col:
-                st.markdown("### Navigation")
-                st.markdown("""
-                <div class="compass">
-                    <img src="https://i.imgur.com/JSnB9ks.png" class="compass-img">
-                </div>
-                """, unsafe_allow_html=True)
+                st.markdown('<div class="dashboard-header">', unsafe_allow_html=True)
+                st.markdown('<h2 class="dashboard-title">ناوبری</h2>', unsafe_allow_html=True)
+                st.markdown('</div>', unsafe_allow_html=True)
+                
+                # Display compass
+                st.markdown(get_compass_image(), unsafe_allow_html=True)
                 
                 # Add a gauge chart for overall farm health
-                st.markdown("### Farm Health")
-                gauge_fig = create_gauge_chart(avg_growth/100, "Health Index", 0, 1)
+                st.markdown('<div class="dashboard-header">', unsafe_allow_html=True)
+                st.markdown('<h2 class="dashboard-title">سلامت مزرعه</h2>', unsafe_allow_html=True)
+                st.markdown('</div>', unsafe_allow_html=True)
+                
+                gauge_fig = create_gauge_chart(avg_growth/100, "شاخص سلامت", 0, 1)
                 st.plotly_chart(gauge_fig, use_container_width=True)
             
+            st.markdown('</div>', unsafe_allow_html=True)
+            
             # Charts row
-            st.markdown("### Farm Analytics")
+            st.markdown('<div class="dashboard-container">', unsafe_allow_html=True)
+            
+            st.markdown('<div class="dashboard-header">', unsafe_allow_html=True)
+            st.markdown('<h2 class="dashboard-title">تحلیل مزارع</h2>', unsafe_allow_html=True)
+            st.markdown('</div>', unsafe_allow_html=True)
+            
             chart_col1, chart_col2 = st.columns(2)
             
             with chart_col1:
@@ -622,43 +1093,58 @@ def main():
                 ndvi_values = np.clip(ndvi_values, 0, 1)
                 
                 ts_data = pd.DataFrame({
-                    'Date': dates,
+                    'تاریخ': dates,
                     'NDVI': ndvi_values,
                     'NDRE': ndvi_values * 0.7 + np.random.normal(0, 0.05, size=len(dates)),
                     'LAI': ndvi_values * 5 + np.random.normal(0, 0.3, size=len(dates))
                 })
                 
                 # Create and display line chart
-                line_fig = create_line_chart(ts_data, 'Date', ['NDVI', 'NDRE'], 'Vegetation Indices Over Time')
+                line_fig = create_line_chart(ts_data, 'تاریخ', ['NDVI', 'NDRE'], 'شاخص‌های گیاهی در طول زمان')
                 st.plotly_chart(line_fig, use_container_width=True)
             
             with chart_col2:
                 # Create sample area chart data
                 area_data = pd.DataFrame({
-                    'Date': dates,
-                    'Growth': np.cumsum(np.random.normal(0.1, 0.03, size=len(dates)))
+                    'تاریخ': dates,
+                    'رشد': np.cumsum(np.random.normal(0.1, 0.03, size=len(dates)))
                 })
                 
                 # Create and display area chart
-                area_fig = create_area_chart(area_data, 'Date', 'Growth', 'Cumulative Growth')
+                area_fig = create_area_chart(area_data, 'تاریخ', 'رشد', 'رشد تجمعی')
                 st.plotly_chart(area_fig, use_container_width=True)
             
+            st.markdown('</div>', unsafe_allow_html=True)
+            
             # Farm ranking row
-            st.markdown("### Farm Rankings")
+            st.markdown('<div class="dashboard-container">', unsafe_allow_html=True)
+            
+            st.markdown('<div class="dashboard-header">', unsafe_allow_html=True)
+            st.markdown('<h2 class="dashboard-title">رتبه‌بندی مزارع</h2>', unsafe_allow_html=True)
+            st.markdown('</div>', unsafe_allow_html=True)
+            
             rank_col1, rank_col2 = st.columns(2)
             
             with rank_col1:
-                # Create sample farm ranking data
-                farm_names = selected_farms['farm_name'].tolist()
-                farm_ndvi = np.random.uniform(0.5, 0.9, size=len(farm_names))
+                # Create sample farm ranking data for the last 7 days
+                farm_names = selected_farms['نام مزرعه'].tolist()
+                
+                # Calculate LAI for each farm based on realistic formula
+                farm_lai_values = []
+                for _, farm in selected_farms.iterrows():
+                    # Base NDVI with some randomness related to farm age
+                    base_ndvi = min(0.5 + 0.08 * farm['سن'] + np.random.normal(0, 0.05), 0.95)
+                    # LAI calculation: LAI = 0.57 * exp(2.33 * NDVI)
+                    lai_value = 0.57 * np.exp(2.33 * base_ndvi)
+                    farm_lai_values.append(round(lai_value, 2))
                 
                 rank_data = pd.DataFrame({
-                    'Farm': farm_names,
-                    'NDVI': farm_ndvi
-                }).sort_values('NDVI', ascending=False)
+                    'مزرعه': farm_names,
+                    'شاخص سطح برگ': farm_lai_values
+                }).sort_values('شاخص سطح برگ', ascending=False)
                 
                 # Create and display bar chart
-                bar_fig = create_bar_chart(rank_data, 'Farm', 'NDVI', 'Farms by NDVI')
+                bar_fig = create_bar_chart(rank_data, 'مزرعه', 'شاخص سطح برگ', 'مزارع بر اساس شاخص سطح برگ')
                 st.plotly_chart(bar_fig, use_container_width=True)
             
             with rank_col2:
@@ -666,78 +1152,139 @@ def main():
                 st.markdown('<div class="table-container">', unsafe_allow_html=True)
                 st.dataframe(
                     rank_data.reset_index(drop=True).style.background_gradient(
-                        cmap='Greens', subset=['NDVI']
+                        cmap='Greens', subset=['شاخص سطح برگ']
                     ),
                     use_container_width=True
                 )
                 st.markdown('</div>', unsafe_allow_html=True)
+            
+            st.markdown('</div>', unsafe_allow_html=True)
+            
+            # Circular metrics row
+            st.markdown('<div class="dashboard-container">', unsafe_allow_html=True)
+            
+            st.markdown('<div class="dashboard-header">', unsafe_allow_html=True)
+            st.markdown('<h2 class="dashboard-title">شاخص‌های کلیدی</h2>', unsafe_allow_html=True)
+            st.markdown('</div>', unsafe_allow_html=True)
+            
+            circ_cols = st.columns(4)
+            
+            with circ_cols[0]:
+                st.markdown(create_circular_metric(
+                    round(np.random.uniform(20, 30), 1), 
+                    "دما (°C)", 
+                    "🌡️", 
+                    0, 
+                    50
+                ), unsafe_allow_html=True)
+            
+            with circ_cols[1]:
+                st.markdown(create_circular_metric(
+                    round(np.random.uniform(40, 80), 1), 
+                    "رطوبت (%)", 
+                    "💧", 
+                    0, 
+                    100
+                ), unsafe_allow_html=True)
+            
+            with circ_cols[2]:
+                st.markdown(create_circular_metric(
+                    round(np.random.uniform(3, 8), 1), 
+                    "بریکس", 
+                    "🍯", 
+                    0, 
+                    15
+                ), unsafe_allow_html=True)
+            
+            with circ_cols[3]:
+                st.markdown(create_circular_metric(
+                    round(np.random.uniform(70, 95), 1), 
+                    "خلوص (%)", 
+                    "✨", 
+                    0, 
+                    100
+                ), unsafe_allow_html=True)
+            
+            st.markdown('</div>', unsafe_allow_html=True)
         
         # Farm Analysis Tab
         with tabs[1]:
-            st.markdown("## Detailed Farm Analysis")
+            st.markdown('<div class="dashboard-container">', unsafe_allow_html=True)
+            
+            st.markdown('<div class="dashboard-header">', unsafe_allow_html=True)
+            st.markdown('<h2 class="dashboard-title">تحلیل تفصیلی مزرعه</h2>', unsafe_allow_html=True)
+            st.markdown('</div>', unsafe_allow_html=True)
             
             # Farm selection
-            selected_farm = st.selectbox("Select Farm for Analysis", selected_farms['farm_name'].tolist())
-            farm_row = selected_farms[selected_farms['farm_name'] == selected_farm].iloc[0]
+            selected_farm = st.selectbox("انتخاب مزرعه برای تحلیل", selected_farms['نام مزرعه'].tolist())
+            farm_row = selected_farms[selected_farms['نام مزرعه'] == selected_farm].iloc[0]
             
             # Farm details
             st.markdown(f"""
             <div class="metric-card" style="margin-bottom: 20px;">
                 <h3>{selected_farm}</h3>
-                <p>Age: {farm_row['age']} years | Variety: {farm_row['variety']}</p>
-                <p>Location: {farm_row['latitude']:.4f}, {farm_row['longitude']:.4f}</p>
+                <p>سن: {farm_row['سن']} سال | تنوع: {farm_row['تنوع']}</p>
+                <p>موقعیت: {farm_row['عرض جغرافیایی']:.4f}, {farm_row['طول جغرافیایی']:.4f}</p>
             </div>
             """, unsafe_allow_html=True)
             
+            st.markdown('</div>', unsafe_allow_html=True)
+            
             # Create tabs for different analysis views
-            analysis_tabs = st.tabs(["Vegetation Indices", "Growth Trends", "Environmental Factors"])
+            analysis_tabs = st.tabs(["شاخص‌های گیاهی", "روند رشد", "عوامل محیطی"])
             
             # Vegetation Indices tab
             with analysis_tabs[0]:
+                st.markdown('<div class="dashboard-container">', unsafe_allow_html=True)
+                
                 # Generate sample time series data for the selected farm
                 dates = pd.date_range(start=start_date, end=end_date, freq='D')
                 
                 # Base values with some randomness
                 base_ndvi = np.random.uniform(0.6, 0.8)
                 base_ndre = np.random.uniform(0.4, 0.6)
-                base_lai = np.random.uniform(3.0, 4.5)
                 
                 # Add daily variations
                 ndvi_values = base_ndvi + np.random.normal(0, 0.05, size=len(dates))
                 ndre_values = base_ndre + np.random.normal(0, 0.04, size=len(dates))
-                lai_values = base_lai + np.random.normal(0, 0.3, size=len(dates))
                 
                 # Add trend
                 trend = np.linspace(0, 0.15, len(dates))
                 ndvi_values += trend
                 ndre_values += trend * 0.8
-                lai_values += trend * 2
                 
                 # Clip to valid ranges
                 ndvi_values = np.clip(ndvi_values, 0, 1)
                 ndre_values = np.clip(ndre_values, 0, 1)
-                lai_values = np.clip(lai_values, 0, 5)
+                
+                # Calculate LAI using the realistic formula: LAI = 0.57 * exp(2.33 * NDVI)
+                lai_values = 0.57 * np.exp(2.33 * ndvi_values)
                 
                 # Create dataframe
                 farm_ts_data = pd.DataFrame({
-                    'Date': dates,
+                    'تاریخ': dates,
                     'NDVI': ndvi_values,
                     'NDRE': ndre_values,
                     'LAI': lai_values
                 })
                 
                 # Display charts
-                st.markdown("### Vegetation Indices Over Time")
+                st.markdown('<div class="dashboard-header">', unsafe_allow_html=True)
+                st.markdown('<h2 class="dashboard-title">شاخص‌های گیاهی در طول زمان</h2>', unsafe_allow_html=True)
+                st.markdown('</div>', unsafe_allow_html=True)
                 
                 # Create line chart for all indices
                 vi_fig = create_line_chart(
-                    farm_ts_data, 'Date', ['NDVI', 'NDRE', 'LAI'], 
-                    f'Vegetation Indices for {selected_farm}'
+                    farm_ts_data, 'تاریخ', ['NDVI', 'NDRE', 'LAI'], 
+                    f'شاخص‌های گیاهی برای {selected_farm}'
                 )
                 st.plotly_chart(vi_fig, use_container_width=True)
                 
                 # Display individual metrics with small charts
-                st.markdown("### Current Vegetation Status")
+                st.markdown('<div class="dashboard-header">', unsafe_allow_html=True)
+                st.markdown('<h2 class="dashboard-title">وضعیت فعلی گیاه</h2>', unsafe_allow_html=True)
+                st.markdown('</div>', unsafe_allow_html=True)
+                
                 vi_cols = st.columns(3)
                 
                 with vi_cols[0]:
@@ -752,11 +1299,15 @@ def main():
                 
                 with vi_cols[2]:
                     current_lai = lai_values[-1]
-                    lai_gauge = create_gauge_chart(current_lai, "LAI", 0, 5)
+                    lai_gauge = create_gauge_chart(current_lai, "LAI", 0, 7)
                     st.plotly_chart(lai_gauge, use_container_width=True)
+                
+                st.markdown('</div>', unsafe_allow_html=True)
             
             # Growth Trends tab
             with analysis_tabs[1]:
+                st.markdown('<div class="dashboard-container">', unsafe_allow_html=True)
+                
                 # Generate sample growth data
                 growth_dates = pd.date_range(start=start_date, end=end_date, freq='D')
                 
@@ -773,32 +1324,37 @@ def main():
                 
                 # Create dataframe
                 growth_data = pd.DataFrame({
-                    'Date': growth_dates,
-                    'Daily Growth': growth_values,
-                    'Cumulative Growth': cumulative_growth
+                    'تاریخ': growth_dates,
+                    'رشد روزانه': growth_values,
+                    'رشد تجمعی': cumulative_growth
                 })
                 
                 # Display charts
-                st.markdown("### Growth Patterns")
+                st.markdown('<div class="dashboard-header">', unsafe_allow_html=True)
+                st.markdown('<h2 class="dashboard-title">الگوهای رشد</h2>', unsafe_allow_html=True)
+                st.markdown('</div>', unsafe_allow_html=True)
                 
-                growth_tabs = st.tabs(["Daily Growth", "Cumulative Growth"])
+                growth_tabs = st.tabs(["رشد روزانه", "رشد تجمعی"])
                 
                 with growth_tabs[0]:
                     daily_fig = create_bar_chart(
-                        growth_data, 'Date', 'Daily Growth', 
-                        f'Daily Growth Rate for {selected_farm}'
+                        growth_data, 'تاریخ', 'رشد روزانه', 
+                        f'نرخ رشد روزانه برای {selected_farm}'
                     )
                     st.plotly_chart(daily_fig, use_container_width=True)
                 
                 with growth_tabs[1]:
                     cumulative_fig = create_area_chart(
-                        growth_data, 'Date', 'Cumulative Growth', 
-                        f'Cumulative Growth for {selected_farm}'
+                        growth_data, 'تاریخ', 'رشد تجمعی', 
+                        f'رشد تجمعی برای {selected_farm}'
                     )
                     st.plotly_chart(cumulative_fig, use_container_width=True)
                 
                 # Growth statistics
-                st.markdown("### Growth Statistics")
+                st.markdown('<div class="dashboard-header">', unsafe_allow_html=True)
+                st.markdown('<h2 class="dashboard-title">آمار رشد</h2>', unsafe_allow_html=True)
+                st.markdown('</div>', unsafe_allow_html=True)
+                
                 stats_cols = st.columns(3)
                 
                 with stats_cols[0]:
@@ -806,7 +1362,7 @@ def main():
                     st.markdown(f"""
                     <div class="metric-card">
                         <div class="metric-value">{avg_growth:.3f}</div>
-                        <div class="metric-label">Average Daily Growth</div>
+                        <div class="metric-label">میانگین رشد روزانه</div>
                     </div>
                     """, unsafe_allow_html=True)
                 
@@ -816,7 +1372,7 @@ def main():
                     st.markdown(f"""
                     <div class="metric-card">
                         <div class="metric-value">{max_growth:.3f}</div>
-                        <div class="metric-label">Max Growth ({max_day})</div>
+                        <div class="metric-label">حداکثر رشد ({max_day})</div>
                     </div>
                     """, unsafe_allow_html=True)
                 
@@ -825,12 +1381,16 @@ def main():
                     st.markdown(f"""
                     <div class="metric-card">
                         <div class="metric-value">{total_growth:.2f}</div>
-                        <div class="metric-label">Total Growth</div>
+                        <div class="metric-label">رشد کل</div>
                     </div>
                     """, unsafe_allow_html=True)
+                
+                st.markdown('</div>', unsafe_allow_html=True)
             
             # Environmental Factors tab
             with analysis_tabs[2]:
+                st.markdown('<div class="dashboard-container">', unsafe_allow_html=True)
+                
                 # Generate sample environmental data
                 env_dates = pd.date_range(start=start_date, end=end_date, freq='D')
                 
@@ -850,52 +1410,56 @@ def main():
                 
                 # Create dataframe
                 env_data = pd.DataFrame({
-                    'Date': env_dates,
-                    'Temperature (°C)': temp_values,
-                    'Humidity (%)': humidity_values,
-                    'Rainfall (mm)': rainfall_values
+                    'تاریخ': env_dates,
+                    'دما (°C)': temp_values,
+                    'رطوبت (%)': humidity_values,
+                    'بارندگی (mm)': rainfall_values
                 })
                 
                 # Display charts
-                st.markdown("### Environmental Conditions")
+                st.markdown('<div class="dashboard-header">', unsafe_allow_html=True)
+                st.markdown('<h2 class="dashboard-title">شرایط محیطی</h2>', unsafe_allow_html=True)
+                st.markdown('</div>', unsafe_allow_html=True)
                 
-                env_tabs = st.tabs(["Temperature", "Humidity", "Rainfall"])
+                env_tabs = st.tabs(["دما", "رطوبت", "بارندگی"])
                 
                 with env_tabs[0]:
                     temp_fig = create_line_chart(
-                        env_data, 'Date', ['Temperature (°C)'], 
-                        f'Temperature for {selected_farm}'
+                        env_data, 'تاریخ', ['دما (°C)'], 
+                        f'دما برای {selected_farm}'
                     )
                     st.plotly_chart(temp_fig, use_container_width=True)
                 
                 with env_tabs[1]:
                     humidity_fig = create_line_chart(
-                        env_data, 'Date', ['Humidity (%)'], 
-                        f'Humidity for {selected_farm}'
+                        env_data, 'تاریخ', ['رطوبت (%)'], 
+                        f'رطوبت برای {selected_farm}'
                     )
                     st.plotly_chart(humidity_fig, use_container_width=True)
                 
                 with env_tabs[2]:
                     rainfall_fig = create_bar_chart(
-                        env_data, 'Date', 'Rainfall (mm)', 
-                        f'Rainfall for {selected_farm}'
+                        env_data, 'تاریخ', 'بارندگی (mm)', 
+                        f'بارندگی برای {selected_farm}'
                     )
                     st.plotly_chart(rainfall_fig, use_container_width=True)
                 
                 # Correlation analysis
-                st.markdown("### Environmental Impact on Growth")
+                st.markdown('<div class="dashboard-header">', unsafe_allow_html=True)
+                st.markdown('<h2 class="dashboard-title">تأثیر محیط بر رشد</h2>', unsafe_allow_html=True)
+                st.markdown('</div>', unsafe_allow_html=True)
                 
                 # Merge environmental and growth data
                 merged_data = pd.merge(
                     env_data, 
-                    growth_data[['Date', 'Daily Growth']], 
-                    on='Date'
+                    growth_data[['تاریخ', 'رشد روزانه']], 
+                    on='تاریخ'
                 )
                 
                 # Calculate correlations
-                corr_temp = np.corrcoef(merged_data['Temperature (°C)'], merged_data['Daily Growth'])[0, 1]
-                corr_humidity = np.corrcoef(merged_data['Humidity (%)'], merged_data['Daily Growth'])[0, 1]
-                corr_rainfall = np.corrcoef(merged_data['Rainfall (mm)'], merged_data['Daily Growth'])[0, 1]
+                corr_temp = np.corrcoef(merged_data['دما (°C)'], merged_data['رشد روزانه'])[0, 1]
+                corr_humidity = np.corrcoef(merged_data['رطوبت (%)'], merged_data['رشد روزانه'])[0, 1]
+                corr_rainfall = np.corrcoef(merged_data['بارندگی (mm)'], merged_data['رشد روزانه'])[0, 1]
                 
                 # Display correlation metrics
                 corr_cols = st.columns(3)
@@ -904,7 +1468,7 @@ def main():
                     st.markdown(f"""
                     <div class="metric-card">
                         <div class="metric-value">{corr_temp:.2f}</div>
-                        <div class="metric-label">Temperature Correlation</div>
+                        <div class="metric-label">همبستگی دما</div>
                     </div>
                     """, unsafe_allow_html=True)
                 
@@ -912,7 +1476,7 @@ def main():
                     st.markdown(f"""
                     <div class="metric-card">
                         <div class="metric-value">{corr_humidity:.2f}</div>
-                        <div class="metric-label">Humidity Correlation</div>
+                        <div class="metric-label">همبستگی رطوبت</div>
                     </div>
                     """, unsafe_allow_html=True)
                 
@@ -920,16 +1484,24 @@ def main():
                     st.markdown(f"""
                     <div class="metric-card">
                         <div class="metric-value">{corr_rainfall:.2f}</div>
-                        <div class="metric-label">Rainfall Correlation</div>
+                        <div class="metric-label">همبستگی بارندگی</div>
                     </div>
                     """, unsafe_allow_html=True)
+                
+                st.markdown('</div>', unsafe_allow_html=True)
         
         # Growth Prediction Tab
         with tabs[2]:
-            st.markdown("## Growth Prediction with LSTM")
+            st.markdown('<div class="dashboard-container">', unsafe_allow_html=True)
+            
+            st.markdown('<div class="dashboard-header">', unsafe_allow_html=True)
+            st.markdown('<h2 class="dashboard-title">پیش‌ب��نی رشد با LSTM</h2>', unsafe_allow_html=True)
+            st.markdown('</div>', unsafe_allow_html=True)
             
             # Farm selection for prediction
-            pred_farm = st.selectbox("Select Farm for Prediction", selected_farms['farm_name'].tolist(), key="pred_farm")
+            pred_farm = st.selectbox("انتخاب مزرعه برای پیش‌بینی", selected_farms['نام مزرعه'].tolist(), key="pred_farm")
+            
+            st.markdown('</div>', unsafe_allow_html=True)
             
             # Generate sample historical data for LSTM
             hist_dates = pd.date_range(start=start_date - timedelta(days=60), end=end_date, freq='D')
@@ -956,57 +1528,67 @@ def main():
             rainfall[rain_days] = np.random.exponential(5, size=len(rain_days))
             
             # Age (constant for a farm)
-            farm_age = selected_farms[selected_farms['farm_name'] == pred_farm]['age'].values[0]
+            farm_age = selected_farms[selected_farms['نام مزرعه'] == pred_farm]['سن'].values[0]
             age = np.ones(len(hist_dates)) * farm_age
             
             # Variety (encoded as 0, 1, 2)
-            variety_map = {'Type A': 0, 'Type B': 1, 'Type C': 2}
-            farm_variety = selected_farms[selected_farms['farm_name'] == pred_farm]['variety'].values[0]
+            variety_map = {'نوع A': 0, 'نوع B': 1, 'نوع C': 2}
+            farm_variety = selected_farms[selected_farms['نام مزرعه'] == pred_farm]['تنوع'].values[0]
             variety_encoded = np.ones(len(hist_dates)) * variety_map.get(farm_variety, 0)
             
             # Target variables with relationship to features
-            # LAI increases with rainfall and temperature within optimal range
-            lai_base = 0.01 * temp + 0.02 * rainfall - 0.005 * np.abs(temp - 28)
-            lai = 3 + lai_base + 0.05 * np.arange(len(hist_dates)) + np.random.normal(0, 0.2, len(hist_dates))
-            lai = np.clip(lai, 0, 7)
-            
-            # NDVI follows similar pattern but scaled
-            ndvi = 0.5 + 0.07 * lai / 7 + np.random.normal(0, 0.03, len(hist_dates))
+            # NDVI increases with rainfall and temperature within optimal range
+            ndvi_base = 0.01 * (temp - 15) / 15 + 0.02 * rainfall / 5 - 0.005 * np.abs(temp - 28) / 10
+            ndvi = 0.6 + ndvi_base + 0.001 * np.arange(len(hist_dates)) + np.random.normal(0, 0.02, len(hist_dates))
             ndvi = np.clip(ndvi, 0, 1)
             
             # NDRE correlated with NDVI but lower values
             ndre = 0.7 * ndvi + np.random.normal(0, 0.02, len(hist_dates))
             ndre = np.clip(ndre, 0, 1)
             
+            # LAI calculation using the realistic formula: LAI = 0.57 * exp(2.33 * NDVI)
+            lai = 0.57 * np.exp(2.33 * ndvi)
+            
             # Create dataframe
             hist_data = pd.DataFrame({
-                'Date': hist_dates,
-                'Temperature': temp,
-                'Humidity': humidity,
-                'Rainfall': rainfall,
-                'Age': age,
-                'Variety': variety_encoded,
+                'تاریخ': hist_dates,
+                'دما': temp,
+                'رطوبت': humidity,
+                'بارندگی': rainfall,
+                'سن': age,
+                'تنوع': variety_encoded,
                 'LAI': lai,
                 'NDVI': ndvi,
                 'NDRE': ndre
             })
             
             # Display historical data
-            st.markdown("### Historical Data")
+            st.markdown('<div class="dashboard-container">', unsafe_allow_html=True)
+            
+            st.markdown('<div class="dashboard-header">', unsafe_allow_html=True)
+            st.markdown('<h2 class="dashboard-title">داده‌های تاریخی</h2>', unsafe_allow_html=True)
+            st.markdown('</div>', unsafe_allow_html=True)
+            
             hist_fig = create_line_chart(
-                hist_data, 'Date', ['LAI', 'NDVI', 'NDRE'], 
-                f'Historical Vegetation Indices for {pred_farm}'
+                hist_data, 'تاریخ', ['LAI', 'NDVI', 'NDRE'], 
+                f'شاخص‌های گیاهی تاریخی برای {pred_farm}'
             )
             st.plotly_chart(hist_fig, use_container_width=True)
             
+            st.markdown('</div>', unsafe_allow_html=True)
+            
             # LSTM Model Training
-            st.markdown("### LSTM Model Training")
+            st.markdown('<div class="dashboard-container">', unsafe_allow_html=True)
+            
+            st.markdown('<div class="dashboard-header">', unsafe_allow_html=True)
+            st.markdown('<h2 class="dashboard-title">آموزش مدل LSTM</h2>', unsafe_allow_html=True)
+            st.markdown('</div>', unsafe_allow_html=True)
             
             # Button to trigger training
-            if st.button("Train LSTM Model and Predict"):
-                with st.spinner("Training LSTM model..."):
+            if st.button("آموزش مدل LSTM و پیش‌بینی"):
+                with st.spinner("در حال آموزش مدل LSTM..."):
                     # Prepare data for LSTM
-                    features = hist_data[['Temperature', 'Humidity', 'Rainfall', 'Age', 'Variety']].values
+                    features = hist_data[['دما', 'رطوبت', 'بارندگی', 'سن', 'تنوع']].values
                     targets = hist_data[['LAI', 'NDVI', 'NDRE']].values
                     
                     # Combine features and targets
@@ -1026,7 +1608,7 @@ def main():
                     
                     # Create prediction dataframe
                     pred_data = pd.DataFrame({
-                        'Date': pred_dates,
+                        'تاریخ': pred_dates,
                         'LAI': predictions[:, 0],
                         'NDVI': predictions[:, 1],
                         'NDRE': predictions[:, 2]
@@ -1034,35 +1616,37 @@ def main():
                     
                     # Combine historical and prediction data
                     combined_data = pd.concat([
-                        hist_data[['Date', 'LAI', 'NDVI', 'NDRE']].tail(30),  # Last 30 days of historical data
+                        hist_data[['تاریخ', 'LAI', 'NDVI', 'NDRE']].tail(30),  # Last 30 days of historical data
                         pred_data
                     ])
                     
                     # Display prediction results
-                    st.markdown("### Prediction Results")
+                    st.markdown('<div class="dashboard-header">', unsafe_allow_html=True)
+                    st.markdown('<h2 class="dashboard-title">نتایج پیش‌بینی</h2>', unsafe_allow_html=True)
+                    st.markdown('</div>', unsafe_allow_html=True)
                     
                     # Create line chart with historical and predicted values
                     pred_fig = go.Figure()
                     
                     # Historical data (solid lines)
-                    for col, color in zip(['LAI', 'NDVI', 'NDRE'], ['#1f77b4', '#ff7f0e', '#2ca02c']):
-                        hist_part = combined_data[combined_data['Date'] <= end_date]
+                    for col, color in zip(['LAI', 'NDVI', 'NDRE'], ['#2EC4B6', '#FF9F1C', '#E71D36']):
+                        hist_part = combined_data[combined_data['تاریخ'] <= end_date]
                         pred_fig.add_trace(go.Scatter(
-                            x=hist_part['Date'],
+                            x=hist_part['تاریخ'],
                             y=hist_part[col],
                             mode='lines',
-                            name=f'Historical {col}',
+                            name=f'تاریخی {col}',
                             line=dict(color=color)
                         ))
                     
                     # Predicted data (dashed lines)
-                    for col, color in zip(['LAI', 'NDVI', 'NDRE'], ['#1f77b4', '#ff7f0e', '#2ca02c']):
-                        pred_part = combined_data[combined_data['Date'] > end_date]
+                    for col, color in zip(['LAI', 'NDVI', 'NDRE'], ['#2EC4B6', '#FF9F1C', '#E71D36']):
+                        pred_part = combined_data[combined_data['تاریخ'] > end_date]
                         pred_fig.add_trace(go.Scatter(
-                            x=pred_part['Date'],
+                            x=pred_part['تاریخ'],
                             y=pred_part[col],
                             mode='lines+markers',
-                            name=f'Predicted {col}',
+                            name=f'پیش‌بینی {col}',
                             line=dict(color=color, dash='dash'),
                             marker=dict(size=8)
                         ))
@@ -1073,14 +1657,14 @@ def main():
                         line_width=2, 
                         line_dash="dash", 
                         line_color="red",
-                        annotation_text="Prediction Start",
+                        annotation_text="شروع پیش‌بینی",
                         annotation_position="top right"
                     )
                     
                     pred_fig.update_layout(
-                        title=f'7-Day Growth Prediction for {pred_farm}',
-                        xaxis_title='Date',
-                        yaxis_title='Value',
+                        title=f'پیش‌بینی رشد 7 روزه برای {pred_farm}',
+                        xaxis_title='تاریخ',
+                        yaxis_title='مقدار',
                         legend=dict(
                             orientation="h",
                             yanchor="bottom",
@@ -1089,7 +1673,7 @@ def main():
                             x=1
                         ),
                         template="plotly_dark",
-                        plot_bgcolor='rgba(30, 33, 48, 0.8)',
+                        plot_bgcolor='rgba(15, 25, 35, 0.8)',
                         paper_bgcolor='rgba(0,0,0,0)',
                         font=dict(color='white'),
                         height=500
@@ -1098,7 +1682,10 @@ def main():
                     st.plotly_chart(pred_fig, use_container_width=True)
                     
                     # Display prediction table
-                    st.markdown("### Predicted Values")
+                    st.markdown('<div class="dashboard-header">', unsafe_allow_html=True)
+                    st.markdown('<h2 class="dashboard-title">مقادیر پیش‌بینی شده</h2>', unsafe_allow_html=True)
+                    st.markdown('</div>', unsafe_allow_html=True)
+                    
                     st.dataframe(
                         pred_data.style.background_gradient(
                             cmap='Greens', subset=['LAI', 'NDVI', 'NDRE']
@@ -1107,7 +1694,9 @@ def main():
                     )
                     
                     # Growth summary
-                    st.markdown("### Growth Summary")
+                    st.markdown('<div class="dashboard-header">', unsafe_allow_html=True)
+                    st.markdown('<h2 class="dashboard-title">خلاصه رشد</h2>', unsafe_allow_html=True)
+                    st.markdown('</div>', unsafe_allow_html=True)
                     
                     # Calculate growth rates
                     lai_growth = (pred_data['LAI'].iloc[-1] - hist_data['LAI'].iloc[-1]) / hist_data['LAI'].iloc[-1] * 100
@@ -1120,7 +1709,7 @@ def main():
                         st.markdown(f"""
                         <div class="metric-card">
                             <div class="metric-value">{lai_growth:.1f}%</div>
-                            <div class="metric-label">LAI Growth (7 days)</div>
+                            <div class="metric-label">رشد LAI (7 روز)</div>
                         </div>
                         """, unsafe_allow_html=True)
                     
@@ -1128,7 +1717,7 @@ def main():
                         st.markdown(f"""
                         <div class="metric-card">
                             <div class="metric-value">{ndvi_growth:.1f}%</div>
-                            <div class="metric-label">NDVI Growth (7 days)</div>
+                            <div class="metric-label">رشد NDVI (7 روز)</div>
                         </div>
                         """, unsafe_allow_html=True)
                     
@@ -1136,22 +1725,31 @@ def main():
                         st.markdown(f"""
                         <div class="metric-card">
                             <div class="metric-value">{ndre_growth:.1f}%</div>
-                            <div class="metric-label">NDRE Growth (7 days)</div>
+                            <div class="metric-label">رشد NDRE (7 روز)</div>
                         </div>
                         """, unsafe_allow_html=True)
             else:
-                st.info("Click the button above to train the LSTM model and generate predictions.")
+                st.info("برای آموزش مدل LSTM و تولید پیش‌بینی‌ها، روی دکمه بالا کلیک کنید.")
+            
+            st.markdown('</div>', unsafe_allow_html=True)
         
         # Data Tables Tab
         with tabs[3]:
-            st.markdown("## Farm Data Tables")
+            st.markdown('<div class="dashboard-container">', unsafe_allow_html=True)
+            
+            st.markdown('<div class="dashboard-header">', unsafe_allow_html=True)
+            st.markdown('<h2 class="dashboard-title">جداول داده مزارع</h2>', unsafe_allow_html=True)
+            st.markdown('</div>', unsafe_allow_html=True)
             
             # Create tabs for different data tables
-            data_tabs = st.tabs(["Farm Information", "Vegetation Indices", "Growth Rankings"])
+            data_tabs = st.tabs(["اطلاعات مزرعه", "شاخص‌های گیاهی", "رتبه‌بندی رشد"])
             
             # Farm Information tab
             with data_tabs[0]:
-                st.markdown("### Farm Details")
+                st.markdown('<div class="dashboard-header">', unsafe_allow_html=True)
+                st.markdown('<h2 class="dashboard-title">جزئیات مزرعه</h2>', unsafe_allow_html=True)
+                st.markdown('</div>', unsafe_allow_html=True)
+                
                 st.dataframe(
                     selected_farms,
                     use_container_width=True
@@ -1159,26 +1757,30 @@ def main():
             
             # Vegetation Indices tab
             with data_tabs[1]:
-                st.markdown("### Vegetation Indices by Farm")
+                st.markdown('<div class="dashboard-header">', unsafe_allow_html=True)
+                st.markdown('<h2 class="dashboard-title">شاخص‌های گیاهی بر اساس مزرعه</h2>', unsafe_allow_html=True)
+                st.markdown('</div>', unsafe_allow_html=True)
                 
                 # Generate sample vegetation indices for all farms
                 vi_data = []
                 
                 for _, farm in selected_farms.iterrows():
                     # Generate random indices with some correlation to farm age
-                    farm_age = farm['age']
+                    farm_age = farm['سن']
                     base_ndvi = min(0.5 + 0.08 * farm_age + np.random.normal(0, 0.05), 0.95)
                     base_ndre = base_ndvi * 0.7 + np.random.normal(0, 0.03)
-                    base_lai = base_ndvi * 6 + np.random.normal(0, 0.3)
+                    
+                    # Calculate LAI using the realistic formula: LAI = 0.57 * exp(2.33 * NDVI)
+                    base_lai = 0.57 * np.exp(2.33 * base_ndvi)
                     
                     vi_data.append({
-                        'Farm': farm['farm_name'],
-                        'Age': farm_age,
-                        'Variety': farm['variety'],
+                        'مزرعه': farm['نام مزرعه'],
+                        'سن': farm_age,
+                        'تنوع': farm['تنوع'],
                         'NDVI': round(base_ndvi, 2),
                         'NDRE': round(base_ndre, 2),
                         'LAI': round(base_lai, 1),
-                        'Chlorophyll Index': round(base_ndvi * 4 + np.random.normal(0, 0.2), 1)
+                        'شاخص کلروفیل': round(base_ndvi * 4 + np.random.normal(0, 0.2), 1)
                     })
                 
                 vi_df = pd.DataFrame(vi_data)
@@ -1186,16 +1788,18 @@ def main():
                 # Display the data
                 st.dataframe(
                     vi_df.style.background_gradient(
-                        cmap='Greens', subset=['NDVI', 'NDRE', 'LAI', 'Chlorophyll Index']
+                        cmap='Greens', subset=['NDVI', 'NDRE', 'LAI', 'شاخص کلروفیل']
                     ),
                     use_container_width=True
                 )
             
             # Growth Rankings tab
             with data_tabs[2]:
-                st.markdown("### Farm Growth Rankings")
+                st.markdown('<div class="dashboard-header">', unsafe_allow_html=True)
+                st.markdown('<h2 class="dashboard-title">رتبه‌بندی رشد مزارع</h2>', unsafe_allow_html=True)
+                st.markdown('</div>', unsafe_allow_html=True)
                 
-                # Generate sample growth data for all farms
+                # Generate sample growth data for all farms for the last 7 days
                 growth_data = []
                 
                 for _, farm in selected_farms.iterrows():
@@ -1203,25 +1807,25 @@ def main():
                     base_growth = np.random.uniform(2.0, 5.0)
                     
                     # Adjust based on farm age (younger farms grow faster)
-                    age_factor = max(1.0, 6 - farm['age']) / 3
+                    age_factor = max(1.0, 6 - farm['سن']) / 3
                     
                     growth_data.append({
-                        'Farm': farm['farm_name'],
-                        'Age': farm['age'],
-                        'Variety': farm['variety'],
-                        'Growth Rate (%)': round(base_growth * age_factor, 1),
-                        'Health Index': round(np.random.uniform(0.7, 1.0), 2),
-                        'Stress Level': round(np.random.uniform(0.0, 0.3), 2)
+                        'مزرعه': farm['نام مزرعه'],
+                        'سن': farm['سن'],
+                        'تنوع': farm['تنوع'],
+                        'نرخ رشد (%)': round(base_growth * age_factor, 1),
+                        'شاخص سلامت': round(np.random.uniform(0.7, 1.0), 2),
+                        'سطح استرس': round(np.random.uniform(0.0, 0.3), 2)
                     })
                 
-                growth_df = pd.DataFrame(growth_data).sort_values('Growth Rate (%)', ascending=False)
+                growth_df = pd.DataFrame(growth_data).sort_values('نرخ رشد (%)', ascending=False)
                 
                 # Display the data
                 st.dataframe(
                     growth_df.style.background_gradient(
-                        cmap='Greens', subset=['Growth Rate (%)', 'Health Index']
+                        cmap='Greens', subset=['نرخ رشد (%)', 'شاخص سلامت']
                     ).background_gradient(
-                        cmap='Reds_r', subset=['Stress Level']
+                        cmap='Reds_r', subset=['سطح استرس']
                     ),
                     use_container_width=True
                 )
@@ -1230,34 +1834,41 @@ def main():
                 col1, col2 = st.columns(2)
                 
                 with col1:
-                    st.markdown("### Top Performers")
+                    st.markdown('<div class="dashboard-header">', unsafe_allow_html=True)
+                    st.markdown('<h2 class="dashboard-title">بهترین عملکردها</h2>', unsafe_allow_html=True)
+                    st.markdown('</div>', unsafe_allow_html=True)
+                    
                     top_farms = growth_df.head(3)
                     
                     for i, (_, farm) in enumerate(top_farms.iterrows()):
                         st.markdown(f"""
                         <div class="metric-card" style="margin-bottom: 10px;">
-                            <h4>#{i+1}: {farm['Farm']}</h4>
-                            <div class="metric-value">{farm['Growth Rate (%)']}%</div>
-                            <div class="metric-label">Growth Rate</div>
-                            <p>Health Index: {farm['Health Index']} | Stress: {farm['Stress Level']}</p>
+                            <h4>#{i+1}: {farm['مزرعه']}</h4>
+                            <div class="metric-value">{farm['نرخ رشد (%)']}%</div>
+                            <div class="metric-label">نرخ رشد</div>
+                            <p>شاخص سلامت: {farm['شاخص سلامت']} | استرس: {farm['سطح استرس']}</p>
                         </div>
                         """, unsafe_allow_html=True)
                 
                 with col2:
-                    st.markdown("### Needs Attention")
+                    st.markdown('<div class="dashboard-header">', unsafe_allow_html=True)
+                    st.markdown('<h2 class="dashboard-title">نیازمند توجه</h2>', unsafe_allow_html=True)
+                    st.markdown('</div>', unsafe_allow_html=True)
+                    
                     bottom_farms = growth_df.tail(3).iloc[::-1]
                     
                     for i, (_, farm) in enumerate(bottom_farms.iterrows()):
                         st.markdown(f"""
                         <div class="metric-card" style="margin-bottom: 10px; border-color: #ff6b6b;">
-                            <h4>#{i+1}: {farm['Farm']}</h4>
-                            <div class="metric-value" style="color: #ff6b6b;">{farm['Growth Rate (%)']}%</div>
-                            <div class="metric-label">Growth Rate</div>
-                            <p>Health Index: {farm['Health Index']} | Stress: {farm['Stress Level']}</p>
+                            <h4>#{i+1}: {farm['مزرعه']}</h4>
+                            <div class="metric-value" style="color: #ff6b6b;">{farm['نرخ رشد (%)']}%</div>
+                            <div class="metric-label">نرخ رشد</div>
+                            <p>شاخص سلامت: {farm['شاخص سلامت']} | استرس: {farm['سطح استرس']}</p>
                         </div>
                         """, unsafe_allow_html=True)
+            
+            st.markdown('</div>', unsafe_allow_html=True)
 
 # Run the app
 if __name__ == "__main__":
-    main()
-
+    main()