GEE中加权总和5个植被指数的代码

以下是在GEE中加权总和5个植被指数的代码：

// Load MODIS collection
var modis = ee.ImageCollection('MODIS/006/MOD13A2');

// Define region of interest (ROI)
var roi = ee.Geometry.Point([0, 0]).buffer(100);

// Define start and end date
var start = ee.Date('2018-01-01');
var end = ee.Date('2018-12-31');

// Filter collection by date and ROI
var modisFiltered = modis.filterDate(start, end).filterBounds(roi);

// Define weights for each vegetation index
var ndviWeight = 0.4;
var eviWeight = 0.2;
var ndwiWeight = 0.1;
var lswiWeight = 0.2;
var ndmiWeight = 0.1;

// Calculate weighted sum of vegetation indices
var weightedSum = modisFiltered.map(function(image) {
  var ndvi = image.select('NDVI').multiply(ndviWeight);
  var evi = image.select('EVI').multiply(eviWeight);
  var ndwi = image.select('NDWI').multiply(ndwiWeight);
  var lswi = image.select('LSWI').multiply(lswiWeight);
  var ndmi = image.select('NDMI').multiply(ndmiWeight);
  var sum = ndvi.add(evi).add(ndwi).add(lswi).add(ndmi);
  return sum.copyProperties(image, image.propertyNames());
});

// Compute mean of weighted sum
var meanWeightedSum = weightedSum.mean();

// Display result
Map.addLayer(meanWeightedSum, {min: -2000, max: 10000}, 'Mean Weighted Sum');

在这个例子中，我们加载了MODIS植被指数集合，并定义了一个感兴趣区域（ROI），然后按日期和ROI过滤了集合。接下来，我们为每个植被指数定义了一个权重，并计算了每个像素的加权总和。最后，我们计算了加权总和的平均值，并在地图上显示了结果。