Mapping Malaria Risk With Google Earth Engine For Effective Disease Control

[@YHWH979]

sir kindly share code

[@techhive.2023]

// Load the Tamil Nadu boundary
var tamilNadu = ee.FeatureCollection('FAO/GAUL_SIMPLIFIED_500m/2015/level1')
.filter(ee.Filter.eq('ADM1_NAME', 'Tamil Nadu'));
// Center the map
Map.centerObject(tamilNadu, 7);
Map.addLayer(tamilNadu, {color: 'red'}, 'Tamil Nadu Boundary');
// Load environmental data
// 1. Temperature (MODIS)
var temperature = ee.ImageCollection('MODIS/061/MOD11A2')
.filterDate('2023-01-01', '2023-12-31')
.select('LST_Day_1km')
.map(function(image) {
return image.multiply(0.02).subtract(273.15)
.copyProperties(image, ['system:time_start']);
});
var meanTemperature = temperature.mean().clip(tamilNadu);
// 2. Precipitation (CHIRPS)
var precipitation = ee.ImageCollection('UCSB-CHG/CHIRPS/DAILY')
.filterDate('2023-01-01', '2023-12-31');
var totalPrecipitation = precipitation.sum().clip(tamilNadu);
// 3. Vegetation Index (NDVI from Sentinel-2)
var sentinel2 = ee.ImageCollection('COPERNICUS/S2')
.filterDate('2023-01-01', '2023-12-31')
.filterBounds(tamilNadu)
.filter(ee.Filter.lt('CLOUDY_PIXEL_PERCENTAGE', 20))
.map(function(image) {
var ndvi = image.normalizedDifference(['B8', 'B4']).rename('NDVI');
return image.addBands(ndvi);
});
var meanNDVI = sentinel2.select('NDVI').mean().clip(tamilNadu);
// 4. Water Bodies (JRC Global Surface Water)
var waterOccurrence = ee.ImageCollection('JRC/GSW1_4/MonthlyHistory')
.select('water') // Corrected from 'occurrence' to 'water'
.mean()
.clip(tamilNadu);
// Combine the variables into a single multiband image
var predictors = meanTemperature.rename('Temperature')
.addBands(totalPrecipitation.rename('Precipitation'))
.addBands(meanNDVI.rename('NDVI'))
.addBands(waterOccurrence.rename('WaterOccurrence'));
// Visualize the environmental layers
Map.addLayer(meanTemperature, {min: 20, max: 40, palette: ['blue', 'yellow', 'red']}, 'Mean Temperature');
Map.addLayer(totalPrecipitation, {min: 0, max: 1000, palette: ['white', 'blue']}, 'Total Precipitation');
Map.addLayer(meanNDVI, {min: 0, max: 1, palette: ['brown', 'green']}, 'Mean NDVI');
Map.addLayer(waterOccurrence, {min: 0, max: 100, palette: ['white', 'blue']}, 'Water Occurrence');
// Sample the predictors for training data
// Add training points based on known malaria cases or hotspots in Tamil Nadu
var malariaCases = ee.FeatureCollection([
ee.Feature(ee.Geometry.Point([78.1198, 11.6643]), {'Malaria': 1}), // Example: Salem
ee.Feature(ee.Geometry.Point([78.7047, 10.7905]), {'Malaria': 1}), // Example: Trichy
ee.Feature(ee.Geometry.Point([79.1325, 12.9716]), {'Malaria': 1}), // Example: Chennai
ee.Feature(ee.Geometry.Point([77.1025, 11.2558]), {'Malaria': 0}), // Example: Coimbatore
ee.Feature(ee.Geometry.Point([78.7047, 9.9252]), {'Malaria': 0}) // Example: Madurai
]);
// Overlay predictors on malaria cases
var trainingData = predictors.sampleRegions({
collection: malariaCases,
properties: ['Malaria'],
scale: 1000
});
// Train a Random Forest Classifier
var classifier = ee.Classifier.smileRandomForest(50).train({
features: trainingData,
classProperty: 'Malaria',
inputProperties: ['Temperature', 'Precipitation', 'NDVI', 'WaterOccurrence']
});
// Classify the region
var malariaRisk = predictors.classify(classifier).rename('MalariaRisk');
// Visualize predicted malaria risk
Map.addLayer(malariaRisk, {min: 0, max: 1, palette: ['green', 'red']}, 'Malaria Risk');
// Export predicted malaria risk map
Export.image.toDrive({
image: malariaRisk,
description: 'TamilNadu_Malaria_Risk_Map',
scale: 1000,
region: tamilNadu,
fileFormat: 'GeoTIFF'
});