GEE學習筆記5：随機森林

在GEE中，随機森林的介紹如下圖：

/***********************已分好訓練樣本和實驗樣本******************************/
print("sam1_trainingPartition:",sam1_trainingPartition);
print("sam1_testingPartition:",sam1_testingPartition);

// 通過選取樣本，把landcover屬性賦予樣本
//bands為資料集中波段組合
var trainingPartition = S1S2.select(bands).sampleRegions({
  collection: sam1_trainingPartition,
  properties: ['landcover'],
  scale: 10,
  tileScale:16
});

var testingPartition = S1S2.select(bands).sampleRegions({
  collection: sam1_testingPartition,
  properties: ['landcover'],
  scale: 10,
  tileScale:16
});
//先把棵樹設定成10，後面會選擇最優棵樹
var trainedClassifier = ee.Classifier.smileRandomForest(10).train({
  features: trainingPartition,
  classProperty: 'landcover',
  inputProperties: bands
});
//對資料集進行分類
var class_img = S1S2.select(bands).classify(trainedClassifier).clip(roi);
           

選取随機森林的棵樹

//選取森林棵樹 
var numTrees = ee.List.sequence(5, 50, 5); 
var accuracies = numTrees.map(function(t)
{ 
  var classifier = ee.Classifier.smileRandomForest(t)
                    .train({
                     features: trainingPartition,
                     classProperty: 'landcover',
                     inputProperties: bands
                    });
  return testingPartition
      .classify(classifier)
      .errorMatrix('landcover', 'classification')
      .accuracy();
}); 
print(ui.Chart.array.values({
  array: ee.Array(accuracies),
  axis: 0,
  xLabels: numTrees
}));
           

從圖中可以看到當棵樹為25，準确率最高，是以，可以把 ee.Classifier.smileRandomForest(10).train裡面的參數設定成25，重新運作。

随機森林特征重要性,可以導出結果進行分析

//随機森林特征重要性
var dict = trainedClassifier.explain();
print('Explain:',dict);
 
var variable_importance = ee.Feature(null, ee.Dictionary(dict).get('importance'));
var chart =
ui.Chart.feature.byProperty(variable_importance)
.setChartType('ColumnChart')
.setOptions({
title: 'Random Forest Variable Importance',
legend: {position: 'none'},
hAxis: {title: 'Bands'},
vAxis: {title: 'Importance'}
});
 
print(chart);
           

hAxis: {title: ‘Bands’},

vAxis: {title: ‘Importance’}

});

print(chart);