Update app.py

app.py

@@ -1,130 +1,109 @@
-import ee
 import streamlit as st
-import folium
 import pandas as pd
+import folium
+import ee
+import json
+from datetime import datetime
 import requests
-from datetime import datetime, timedelta
+import geemap.foliumap as geemap
+from streamlit_folium import st_folium
+import plotly.express as px
+import plotly.graph_objects as go
 
-# احراز هویت با Google Earth Engine
+# Set up the Google Earth Engine with service account
 service_account = 'dehkhodamap-e9f0da4ce9f6514021@ee-esmaeilkiani13877.iam.gserviceaccount.com'
 credentials = ee.ServiceAccountCredentials(service_account, 'ee-esmaeilkiani13877-cfdea6eaf411.json')
 ee.Initialize(credentials)
 
-# جمع‌آوری داده‌ها از Google Earth Engine
-def get_indices(aoi, start_date, end_date):
-    sentinel2 = ee.ImageCollection('COPERNICUS/S2') \
-        .filterBounds(aoi) \
-        .filterDate(start_date, end_date) \
-        .filter(ee.Filter.lt('CLOUDY_PIXEL_PERCENTAGE', 20))
-
+# Function to fetch weather data from OpenWeather API
+def get_weather_data(lat, lon, api_key):
+    url = f'http://api.openweathermap.org/data/2.5/weather?lat={lat}&lon={lon}&appid={api_key}&units=metric'
+    response = requests.get(url)
+    return response.json()
+
+# Function to fetch satellite data and calculate indices
+def get_sentinel_data(aoi, start_date, end_date):
+    collection = ee.ImageCollection('COPERNICUS/S2') \
+                    .filterBounds(aoi) \
+                    .filterDate(start_date, end_date) \
+                    .filter(ee.Filter.lt('CLOUDY_PIXEL_PERCENTAGE', 20))
+    
     def calculate_indices(image):
         ndvi = image.normalizedDifference(['B8', 'B4']).rename('NDVI')
         ndwi = image.normalizedDifference(['B3', 'B8']).rename('NDWI')
         ndre = image.normalizedDifference(['B8', 'B5']).rename('NDRE')
-        lai = image.expression('2.76 * (NDVI / (1 - NDVI))', {'NDVI': ndvi}).rename('LAI')
-        chl = image.expression('(NIR / RED) - 1', {'NIR': image.select('B8'), 'RED': image.select('B4')}).rename('CHL')
+        lai = image.expression('3.618 * ((NIR / RED) - 1)', {'NIR': image.select('B8'), 'RED': image.select('B4')}).rename('LAI')
+        chl = image.expression('1.5 * ((NIR / RED) - 1)', {'NIR': image.select('B8'), 'RED': image.select('B4')}).rename('CHL')
         return image.addBands([ndvi, ndwi, ndre, lai, chl])
+    
+    return collection.map(calculate_indices)
 
-    indices = sentinel2.map(calculate_indices)
-    return indices
-
-# خواندن فایل CSV برای مشخصات مزارع
-farm_coordinates = pd.read_csv('farm_coordinates.csv')
-
-# خواندن فایل CSV برای داده‌های روزانه مزارع
+# Load farm coordinates and daily data
+farm_coords = pd.read_csv('farm_coordinates.csv')
 daily_data = pd.read_csv('پایگاه داده (1).csv')
 
-# نمایش نقشه و شاخص‌ها
-def display_map(indices, aoi):
-    map_center = [aoi.centroid().coordinates().getInfo()[1], aoi.centroid().coordinates().getInfo()[0]]
-    m = folium.Map(location=map_center, zoom_start=12)
-
-    ndvi_image = indices.select('NDVI').mean()
-    ndwi_image = indices.select('NDWI').mean()
-
-    ndvi_vis_params = {
-        'min': 0, 'max': 1, 'palette': ['red', 'yellow', 'green']
-    }
-    ndwi_vis_params = {
-        'min': -1, 'max': 1, 'palette': ['blue', 'white', 'green']
-    }
+# Streamlit UI
+st.title('Sugarcane Farm Monitoring System')
 
-    ndvi_url = ndvi_image.getMapId(ndvi_vis_params)['tile_fetcher'].url_format
-    ndwi_url = ndwi_image.getMapId(ndwi_vis_params)['tile_fetcher'].url_format
+# Select farm
+farm_name = st.selectbox('Select a farm', farm_coords['name'].unique())
+selected_farm = farm_coords[farm_coords['name'] == farm_name].iloc[0]
 
-    folium.TileLayer(tiles=ndvi_url, attr='NDVI', overlay=True, name='NDVI').add_to(m)
-    folium.TileLayer(tiles=ndwi_url, attr='NDWI', overlay=True, name='NDWI').add_to(m)
-    folium.LayerControl().add_to(m)
+# Display weather data
+weather_data = get_weather_data(selected_farm['latitude'], selected_farm['longitude'], 'ed47316a45379e2221a75f813229fb46')
+st.subheader('Weather Data')
+st.write(f"Temperature: {weather_data['main']['temp']} °C")
+st.write(f"Humidity: {weather_data['main']['humidity']} %")
+st.write(f"Wind Speed: {weather_data['wind']['speed']} m/s")
 
-    return m
+# Define Area of Interest (AOI)
+aoi = ee.Geometry.Point([selected_farm['longitude'], selected_farm['latitude']]).buffer(1000).bounds()
 
-# مقایسه شاخص‌ها
-def compare_indices(indices):
-    ndvi_chart = indices.select('NDVI').getRegion(aoi, 30).getInfo()
-    ndwi_chart = indices.select('NDWI').getRegion(aoi, 30).getInfo()
-    ndre_chart = indices.select('NDRE').getRegion(aoi, 30).getInfo()
-    lai_chart = indices.select('LAI').getRegion(aoi, 30).getInfo()
-
-    return ndvi_chart, ndwi_chart, ndre_chart, lai_chart
-
-# نمایش داده‌های آب و هوا
-def get_weather_data(lat, lon):
-    api_key = 'ed47316a45379e2221a75f813229fb46'
-    url = f'http://api.openweathermap.org/data/2.5/weather?lat={lat}&lon={lon}&appid={api_key}'
-    response = requests.get(url)
-    data = response.json()
-    return data
-
-# گزارش‌های هفتگی
-def weekly_report(indices, aoi):
-    lai_chart = indices.select('LAI').getRegion(aoi, 30).getInfo()
-    return lai_chart
-
-# کد Streamlit برای نمایش نتایج
-st.title('مانیتورینگ مزارع نیشکر')
-
-# انتخاب مزرعه
-farm_name = st.selectbox('انتخاب مزرعه', farm_coordinates['name'].unique())
-farm_info = farm_coordinates[farm_coordinates['name'] == farm_name].iloc[0]
-
-# انتخاب روز هفته
-day_of_week = st.selectbox('انتخاب روز هفته', daily_data['روز'].unique())
-daily_info = daily_data[daily_data['روز'] == day_of_week]
-
-# تعیین منطقه جغرافیایی
-aoi = ee.Geometry.Point([farm_info['longitude'], farm_info['latitude']]).buffer(500)
-
-# تعیین دوره زمانی
+# Fetch satellite data for the year 2023
 start_date = '2023-01-01'
 end_date = '2023-12-31'
-
-# جمع‌آوری داده‌ها
-indices = get_indices(aoi, start_date, end_date)
-
-# نمایش نقشه
-st.subheader('نقشه شاخص‌ها')
-m = display_map(indices, aoi)
-st_folium = folium.Map(location=[farm_info['latitude'], farm_info['longitude']], zoom_start=12)
-st_folium.add_child(m)
-st_data = st_folium._repr_html_()
-st.components.v1.html(st_data, height=600)
-
-# مقایسه شاخص‌ها
-st.subheader('مقایسه شاخص‌ها')
-ndvi_chart, ndwi_chart, ndre_chart, lai_chart = compare_indices(indices)
-st.line_chart(ndvi_chart)
-st.line_chart(ndwi_chart)
-st.line_chart(ndre_chart)
-st.line_chart(lai_chart)
-
-# نمایش داده‌های آب و هوا
-st.subheader('داده‌های آب و هوا')
-weather_data = get_weather_data(farm_info['latitude'], farm_info['longitude'])
-st.write(f"دما: {weather_data['main']['temp']}°C")
-st.write(f"رطوبت: {weather_data['main']['humidity']}%")
-st.write(f"سرعت باد: {weather_data['wind']['speed']} m/s")
-
-# گزارش‌های هفتگی
-st.subheader('گزارش‌های هفتگی')
-lai_chart = weekly_report(indices, aoi)
-st.line_chart(lai_chart)
+sentinel_data = get_sentinel_data(aoi, start_date, end_date)
+
+# Function to display map with indices
+def display_map(image, index, vis_params):
+    map_ = geemap.Map(center=[selected_farm['latitude'], selected_farm['longitude']], zoom=13)
+    map_.addLayer(image.select(index), vis_params, index)
+    map_.setCenter(selected_farm['longitude'], selected_farm['latitude'], 13)
+    return map_
+
+# Display maps for NDVI and NDWI
+ndvi_map = display_map(sentinel_data.mean(), 'NDVI', {'min': 0, 'max': 1, 'palette': ['red', 'yellow', 'green']})
+ndwi_map = display_map(sentinel_data.mean(), 'NDWI', {'min': -1, 'max': 1, 'palette': ['blue', 'white', 'green']})
+
+st.subheader('NDVI Map')
+st_folium(ndvi_map)
+
+st.subheader('NDWI Map')
+st_folium(ndwi_map)
+
+# Function to generate comparison charts
+def generate_comparison_charts(data, indices):
+    fig = go.Figure()
+    for index in indices:
+        fig.add_trace(go.Scatter(x=data['date'], y=data[index], mode='lines', name=index))
+    return fig
+
+# Generate comparison charts
+indices = ['NDVI', 'NDWI', 'NDRE', 'LAI', 'CHL']
+index_data = sentinel_data.reduceRegions(reducer=ee.Reducer.mean(), collection=aoi, scale=10).getInfo()
+index_df = pd.DataFrame(index_data['features'])
+index_df['date'] = pd.to_datetime(index_df['properties.date'])
+index_df.set_index('date', inplace=True)
+
+fig = generate_comparison_charts(index_df, indices)
+st.subheader('Index Comparison')
+st.plotly_chart(fig)
+
+# Weekly reports
+st.subheader('Weekly Reports')
+weekly_report = index_df.resample('W').mean()
+st.table(weekly_report)
+
+# Run the Streamlit app
+if __name__ == '__main__':
+    st.run()