Delete ee_utils.py

ee_utils.py

@@ -1,144 +0,0 @@
-import ee
-import datetime
-import streamlit as st
-
-@st.cache_resource
-def initialize_gee():
-    """Initialize Google Earth Engine with service account credentials"""
-    try:
-        service_account = 'dehkhodamap-e9f0da4ce9f6514021@ee-esmaeilkiani13877.iam.gserviceaccount.com'
-        credentials_file = 'ee-esmaeilkiani13877-cfdea6eaf411 (4).json'
-        credentials = ee.ServiceAccountCredentials(service_account, credentials_file)
-        ee.Initialize(credentials)
-        return True
-    except Exception as e:
-        st.error(f"Error connecting to Google Earth Engine: {e}")
-        return False
-
-def calculate_indices(image):
-    """Calculate various vegetation and moisture indices from Sentinel-2 imagery"""
-    # NDVI (Normalized Difference Vegetation Index)
-    ndvi = image.normalizedDifference(['B8', 'B4']).rename('NDVI')
-    
-    # EVI (Enhanced Vegetation Index)
-    evi = image.expression(
-        '2.5 * ((NIR - RED) / (NIR + 6 * RED - 7.5 * BLUE + 1))',
-        {
-            'NIR': image.select('B8'),
-            'RED': image.select('B4'),
-            'BLUE': image.select('B2')
-        }
-    ).rename('EVI')
-    
-    # NDMI (Normalized Difference Moisture Index)
-    ndmi = image.normalizedDifference(['B8', 'B11']).rename('NDMI')
-    
-    # LAI (Leaf Area Index) - simplified model
-    lai = image.expression(
-        '3.618 * EVI - 0.118',
-        {
-            'EVI': evi
-        }
-    ).rename('LAI')
-    
-    # Biomass - simplified model based on LAI
-    biomass = image.expression(
-        '0.8 * LAI + 0.2',
-        {
-            'LAI': lai
-        }
-    ).rename('Biomass')
-    
-    # MSI (Moisture Stress Index)
-    msi = image.expression(
-        'SWIR1 / NIR',
-        {
-            'SWIR1': image.select('B11'),
-            'NIR': image.select('B8')
-        }
-    ).rename('MSI')
-    
-    # Chlorophyll Index
-    chlorophyll = image.expression(
-        'NIR / RED - 1',
-        {
-            'NIR': image.select('B8'),
-            'RED': image.select('B4')
-        }
-    ).rename('Chlorophyll')
-    
-    # Add all indices to the image
-    return image.addBands([ndvi, evi, ndmi, lai, biomass, msi, chlorophyll])
-
-def get_sentinel_imagery(start_date, end_date, aoi):
-    """Retrieve and process Sentinel-2 imagery for the specified time period and area"""
-    # Filter Sentinel-2 collection
-    s2 = ee.ImageCollection('COPERNICUS/S2_SR') \
-        .filterDate(start_date, end_date) \
-        .filterBounds(aoi) \
-        .filter(ee.Filter.lt('CLOUDY_PIXEL_PERCENTAGE', 20))
-    
-    if s2.size().getInfo() == 0:
-        return None
-    
-    # Calculate median image
-    s2_median = s2.median()
-    
-    # Calculate indices
-    s2_indices = calculate_indices(s2_median)
-    
-    return s2_indices
-
-def create_time_series(aoi, index_name, start_date, end_date, interval='day'):
-    """Create a time series of index values for the specified area and time period"""
-    # Define time intervals
-    if interval == 'day':
-        step = 1
-        unit = 'day'
-    elif interval == 'week':
-        step = 7
-        unit = 'day'
-    elif interval == 'month':
-        step = 1
-        unit = 'month'
-    
-    # Create lists for dates and values
-    dates = []
-    values = []
-    
-    current_date = start_date
-    while current_date <= end_date:
-        next_date = current_date + datetime.timedelta(days=step) if unit == 'day' else \
-                   datetime.date(current_date.year + (current_date.month + step - 1) // 12,
-                                 (current_date.month + step - 1) % 12 + 1,
-                                 1)
-        
-        # Get imagery for this time period
-        image = get_sentinel_imagery(current_date.strftime('%Y-%m-%d'), 
-                                    next_date.strftime('%Y-%m-%d'), 
-                                    aoi)
-        
-        if image is not None:
-            # Calculate mean index value for the area
-            mean_value = image.select(index_name).reduceRegion(
-                reducer=ee.Reducer.mean(),
-                geometry=aoi,
-                scale=10
-            ).get(index_name).getInfo()
-            
-            if mean_value is not None:
-                dates.append(current_date.strftime('%Y-%m-%d'))
-                values.append(mean_value)
-        
-        current_date = next_date
-    
-    # Create dataframe for plotting
-    if len(dates) > 0:
-        import pandas as pd
-        df = pd.DataFrame({
-            'Date': dates,
-            index_name: values
-        })
-        return df
-    else:
-        return None