GEE、PIE和AI Earth平台差异对比：NDVI平均值计算

//加载北京市边界
var roi = pie.FeatureCollection("NGCC/CHINA_PROVINCE_BOUNDARY")
    .filter(pie.Filter.eq("name", "北京市"))
    .first()
    .geometry();
Map.centerObject(roi, 6);
Map.addLayer(roi, { color: "ff0000", fillColor: "00000000", width: 3 }, "北京市");
//按区域、时间筛选影像
var imgCol = pie.ImageCollection("LC08/01/T1")
    .filterBounds(roi)
    .filterDate("2019-8-01", "2019-8-30");
print("imgCol", imgCol);
Map.addLayer(imgCol.select(["B2", "B3", "B4"]).mosaic().clip(roi), { min: 0, max: 2500, bands: ["B4", "B3", "B2"] }, "imgCol", false);
 
//获取影像数量
var count = imgCol.size();
print(count);

 function imgCalculate (image1) {
     var ndvi1=image1.normalizedDifference(["B5","B4"]);
     return image1.addBands(ndvi1).rename("NDVI")
 }

var redc = imgCol.map(imgCalculate).mosaic().clip(roi)
print("redc",redc)

var jisuan = redc.select("NDVI").reduceRegion(pie.Reducer.mean(),geometry0,300)
print("jisuan",jisuan)

//这里ROI是我自己的矢量，这里就不共享了，大家可以换其它地方测试
/*color:#5f9ea0*/
var geometry0 = ee.Geometry.Polygon([
    [
        [
            117.1224239290218,
            40.20026024458343
        ],
        [
            117.2502681492852,
            40.20026024458343
        ],
        [
            117.2502681492852,
            40.13354201708273
        ],
        [
            117.1224239290218,
            40.13354201708273
        ],
        [
            117.1224239290218,
            40.20026024458343
        ]
    ]
], null);

 function imgCalculate (image1) {
     var ndvi1=image1.normalizedDifference(["B5","B4"]);
     return image1.addBands(ndvi1).rename("NDVI");
 }
function ndv_LANDSAT_8(image) {
              var ndvi = image.normalizedDifference(['B5', 'B4']);
  return image.addBands(ndvi.rename('NDVI'));
}
var  imgCol = ee.ImageCollection("LANDSAT/LC08/C01/T1_SR").filterBounds(roi)
    .filterDate("2019-8-01", "2019-8-30").map(ndv_LANDSAT_8);
print("imgCol", imgCol);
Map.addLayer(imgCol.select(["B2", "B3", "B4"]).mosaic().clip(roi), { min: 0, max: 2500, bands: ["B4", "B3", "B2"] }, "imgCol", false);
 
//获取影像数量
var count = imgCol.size();
print(count);
var redc = imgCol.mosaic().clip(roi)
print("redc",redc)

var jisuan = redc.select("NDVI").reduceRegion(ee.Reducer.mean(),geometry0,300)
print("jisuan",jisuan)

 
//PIE——NDVI函数
function imgCalculate (image1) {
     var ndvi1=image1.normalizedDifference(["B5","B4"]);
     return image1.addBands(ndvi1).rename("NDVI");
 }
//GEE——NDVI函数
function ndv_LANDSAT_8(image) {
              var ndvi = image.normalizedDifference(['B5', 'B4']);
  return image.addBands(ndvi.rename('NDVI'));
}

import aie

aie.Authenticate()
aie.Initialize()
region = aie.Geometry.Polygon([
    [
        [
            117.1224239290218,
            40.20026024458343
        ],
        [
            117.2502681492852,
            40.20026024458343
        ],
        [
            117.2502681492852,
            40.13354201708273
        ],
        [
            117.1224239290218,
            40.13354201708273
        ],
        [
            117.1224239290218,
            40.20026024458343
        ]
    ]]
)

# 归一化植被指数
def getNDVI(image):
    ndvi = image.normalizedDifference(['SR_B5', 'SR_B4']).rename(['NDVI'])
    return ndvi

# 指定需要检索的区域
feature_collection = aie.FeatureCollection('China_Province') \
                        .filter(aie.Filter.eq('province', '北京市'))

geometry = feature_collection.geometry()

#print("feature_collection",feature_collection.getInfo())
dataset = aie.ImageCollection('LANDSAT_LC08_C02_T1_L2') \
             .filterBounds(geometry) \
             .filterDate('2019-08-01', '2019-08-31')\
             .map(getNDVI).mosaic().clip(region)

print("dataset",dataset.getInfo())
result =  dataset.select("NDVI").reduceRegion(aie.Reducer.mean(), region, 30)
print(result)
print(result.getInfo())