GEE:使用MODIS数据和随机森林方法完成生物量估算

举报
此星光明 发表于 2023/01/24 18:24:28 2023/01/24
【摘要】 ​本文提出了一个处理链,利用谷歌地球引擎(GEE)云平台的能力,从15年的MODIS数据中推导出全球叶面积指数(LAI)、光合有效辐射吸收分数(FAPAR)、植被覆盖分数(FVC)和冠层含水量(CWC)地图。检索链是基于一种混合方法,将PROSAIL辐射传输模型(RTM)与随机森林(RF)回归进行倒置。这项工作的一个主要特点是实施了一个检索链,利用全球和气候数据记录(CDR)的MODIS表面...

本文提出了一个处理链,利用谷歌地球引擎(GEE)云平台的能力,从15年的MODIS数据中推导出全球叶面积指数(LAI)、光合有效辐射吸收分数(FAPAR)、植被覆盖分数(FVC)和冠层含水量(CWC)地图。检索链是基于一种混合方法,将PROSAIL辐射传输模型(RTM)与随机森林(RF)回归进行倒置。这项工作的一个主要特点是实施了一个检索链,利用全球和气候数据记录(CDR)的MODIS表面反射率和LAI/FAPAR数据集的GEE能力,允许以前所未有的及时性对生物物理变量进行全球估算。我们将大量的全球叶片性状测量汇编(TRY)与GEE摄取的大量遥感数据结合起来,后者是所考虑的RTM的更现实的叶片参数化的基线。此外,拟议的检索链包括对FVC和CWC的估计,这些数据在操作上并不为MODIS传感器所产生。通过与GEE中的MODIS LAI/FAPAR产品相互比较,在BELMANIP2.1站点网络上验证了所得出的全球估计值。总的来说,检索链与参考的MODIS产品表现出极大的一致性(LAI的R2=0.87,RMSE=0.54 m2/m2,ME=0.03 m2/m2;FAPAR的R2=0.92,RMSE=0.09,ME=0.05)。按土地覆盖类型分析的结果显示,我们的检索结果与MODIS参考估计值之间的相关性最低(LAI和FAPAR分别为R2=0.42和R2=0.41),为常绿阔叶林。这些差异可能主要归因于文献中不同的产品定义。所提供的结果证明,GEE是一个适用于全球生物物理变量检索的高性能处理工具,可用于广泛的应用。

本次用到的数据

Terra和Aqua结合的中分辨率成像分光仪(MODIS)土地覆盖类型(MCD12Q1)第6.1版数据产品按年度提供全球土地覆盖类型。MCD12Q1版本6.1数据产品是利用MODIS Terra和Aqua反射率数据的监督分类得出的。土地覆盖类型来自国际地圈生物圈计划(IGBP)、马里兰大学(UMD)、叶面积指数(LAI)、BIOME-生物地球化学循环(BGC)和植物功能类型(PFT)分类方案。监督下的分类随后进行了额外的后处理,纳入了先前的知识和辅助信息,以进一步完善特定类别。额外的土地覆盖物属性评估层由粮食及农业组织(FAO)土地覆盖物分类系统(LCCS)提供,用于土地覆盖、土地利用和地表水文。

还提供了土地覆被类型1-5、土地覆被属性1-3、土地覆被属性评估1-3、土地覆被质量控制(QC)的图层,以及一个土地水掩码。

Dataset Availability

2001-01-01T00:00:00 -

Dataset Provider

NASA LP DAAC at the USGS EROS Center

Collection Snippet

ee.ImageCollection("MODIS/061/MCD12Q1")

Resolution

500 meters

Bands Table

Name Description Min Max Units
LC_Type1 Land Cover Type 1: Annual International Geosphere-Biosphere Programme (IGBP) classification
LC_Type2 Land Cover Type 2: Annual University of Maryland (UMD) classification
LC_Type3 Land Cover Type 3: Annual Leaf Area Index (LAI) classification
LC_Type4 Land Cover Type 4: Annual BIOME-Biogeochemical Cycles (BGC) classification
LC_Type5 Land Cover Type 5: Annual Plant Functional Types classification
LC_Prop1_Assessment LCCS1 land cover layer confidence 0 100 %
LC_Prop2_Assessment LCCS2 land use layer confidence 0 100 %
LC_Prop3_Assessment LCCS3 surface hydrology layer confidence 0 100 %
LC_Prop1 FAO-Land Cover Classification System 1 (LCCS1) land cover layer
LC_Prop2 FAO-LCCS2 land use layer
LC_Prop3 FAO-LCCS3 surface hydrology layer
QC Product quality flags
LW Binary land (class 2) / water (class 1) mask derived from MOD44W

Class Table: LC_Type1

Value Color Color Value Description
1 #05450a Evergreen Needleleaf Forests: dominated by evergreen conifer trees (canopy >2m). Tree cover >60%.
2 #086a10 Evergreen Broadleaf Forests: dominated by evergreen broadleaf and palmate trees (canopy >2m). Tree cover >60%.
3 #54a708 Deciduous Needleleaf Forests: dominated by deciduous needleleaf (larch) trees (canopy >2m). Tree cover >60%.
4 #78d203 Deciduous Broadleaf Forests: dominated by deciduous broadleaf trees (canopy >2m). Tree cover >60%.
5 #009900 Mixed Forests: dominated by neither deciduous nor evergreen (40-60% of each) tree type (canopy >2m). Tree cover >60%.
6 #c6b044 Closed Shrublands: dominated by woody perennials (1-2m height) >60% cover.
7 #dcd159 Open Shrublands: dominated by woody perennials (1-2m height) 10-60% cover.
8 #dade48 Woody Savannas: tree cover 30-60% (canopy >2m).
9 #fbff13 Savannas: tree cover 10-30% (canopy >2m).
10 #b6ff05 Grasslands: dominated by herbaceous annuals (<2m).
11 #27ff87 Permanent Wetlands: permanently inundated lands with 30-60% water cover and >10% vegetated cover.
12 #c24f44 Croplands: at least 60% of area is cultivated cropland.
13 #a5a5a5 Urban and Built-up Lands: at least 30% impervious surface area including building materials, asphalt and vehicles.
14 #ff6d4c Cropland/Natural Vegetation Mosaics: mosaics of small-scale cultivation 40-60% with natural tree, shrub, or herbaceous vegetation.
15 #69fff8 Permanent Snow and Ice: at least 60% of area is covered by snow and ice for at least 10 months of the year.
16 #f9ffa4 Barren: at least 60% of area is non-vegetated barren (sand, rock, soil) areas with less than 10% vegetation.
17 #1c0dff Water Bodies: at least 60% of area is covered by permanent water bodies.

Class Table: LC_Type2

Value Color Color Value Description
0 #1c0dff Water Bodies: at least 60% of area is covered by permanent water bodies.
1 #05450a Evergreen Needleleaf Forests: dominated by evergreen conifer trees (canopy >2m). Tree cover >60%.
2 #086a10 Evergreen Broadleaf Forests: dominated by evergreen broadleaf and palmate trees (canopy >2m). Tree cover >60%.
3 #54a708 Deciduous Needleleaf Forests: dominated by deciduous needleleaf (larch) trees (canopy >2m). Tree cover >60%.
4 #78d203 Deciduous Broadleaf Forests: dominated by deciduous broadleaf trees (canopy >2m). Tree cover >60%.
5 #009900 Mixed Forests: dominated by neither deciduous nor evergreen (40-60% of each) tree type (canopy >2m). Tree cover >60%.
6 #c6b044 Closed Shrublands: dominated by woody perennials (1-2m height) >60% cover.
7 #dcd159 Open Shrublands: dominated by woody perennials (1-2m height) 10-60% cover.
8 #dade48 Woody Savannas: tree cover 30-60% (canopy >2m).
9 #fbff13 Savannas: tree cover 10-30% (canopy >2m).
10 #b6ff05 Grasslands: dominated by herbaceous annuals (<2m).
11 #27ff87 Permanent Wetlands: permanently inundated lands with 30-60% water cover and >10% vegetated cover.
12 #c24f44 Croplands: at least 60% of area is cultivated cropland.
13 #a5a5a5 Urban and Built-up Lands: at least 30% impervious surface area including building materials, asphalt and vehicles.
14 #ff6d4c Cropland/Natural Vegetation Mosaics: mosaics of small-scale cultivation 40-60% with natural tree, shrub, or herbaceous vegetation.
15 #f9ffa4 Non-Vegetated Lands: at least 60% of area is non-vegetated barren (sand, rock, soil) or permanent snow and ice with less than 10% vegetation.

Class Table: LC_Type3

Value Color Color Value Description
0 #1c0dff Water Bodies: at least 60% of area is covered by permanent water bodies.
1 #b6ff05 Grasslands: dominated by herbaceous annuals (<2m) including cereal croplands.
2 #dcd159 Shrublands: shrub (1-2m) cover >10%.
3 #c24f44 Broadleaf Croplands: bominated by herbaceous annuals (<2m) that are cultivated with broadleaf crops.
4 #fbff13 Savannas: between 10-60% tree cover (>2m).
5 #086a10 Evergreen Broadleaf Forests: dominated by evergreen broadleaf and palmate trees (canopy >2m). Tree cover >60%.
6 #78d203 Deciduous Broadleaf Forests: dominated by deciduous broadleaf trees (canopy >2m). Tree cover >60%.
7 #05450a Evergreen Needleleaf Forests: dominated by evergreen conifer trees (canopy >2m). Tree cover >60%.
8 #54a708 Deciduous Needleleaf Forests: dominated by deciduous needleleaf (larch) trees (canopy >2m). Tree cover >60%.
9 #f9ffa4 Non-Vegetated Lands: at least 60% of area is non-vegetated barren (sand, rock, soil) or permanent snow and ice with less than 10% vegetation.
10 #a5a5a5 Urban and Built-up Lands: at least 30% impervious surface area including building materials, asphalt and vehicles.

Class Table: LC_Type4

Value Color Color Value Description
0 #1c0dff Water Bodies: at least 60% of area is covered by permanent water bodies.
1 #05450a Evergreen Needleleaf Vegetation: dominated by evergreen conifer trees and shrubs (>1m). Woody vegetation cover >10%.
2 #086a10 Evergreen Broadleaf Vegetation: dominated by evergreen broadleaf and palmate trees and shrubs (>1m). Woody vegetation cover >10%.
3 #54a708 Deciduous Needleleaf Vegetation: dominated by deciduous needleleaf (larch) trees and shrubs (>1m). Woody vegetation cover >10%.
4 #78d203 Deciduous Broadleaf Vegetation: dominated by deciduous broadleaf trees and shrubs (>1m). Woody vegetation cover >10%.
5 #009900 Annual Broadleaf Vegetation: dominated by herbaceous annuals (<2m). At least 60% cultivated broadleaf crops.
6 #b6ff05 Annual Grass Vegetation: dominated by herbaceous annuals (<2m) including cereal croplands.
7 #f9ffa4 Non-Vegetated Lands: at least 60% of area is non-vegetated barren (sand, rock, soil) or permanent snow/ice with less than 10% vegetation.
8 #a5a5a5 Urban and Built-up Lands: at least 30% impervious surface area including building materials, asphalt, and vehicles.

Class Table: LC_Type5

Value Color Color Value Description
0 #1c0dff Water Bodies: at least 60% of area is covered by permanent water bodies.
1 #05450a Evergreen Needleleaf Trees: dominated by evergreen conifer trees (>2m). Tree cover >10%.
2 #086a10 Evergreen Broadleaf Trees: dominated by evergreen broadleaf and palmate trees (>2m). Tree cover >10%.
3 #54a708 Deciduous Needleleaf Trees: dominated by deciduous needleleaf (larch) trees (>2m). Tree cover >10%.
4 #78d203 Deciduous Broadleaf Trees: dominated by deciduous broadleaf trees (>2m). Tree cover >10%.
5 #dcd159 Shrub: Shrub (1-2m) cover >10%.
6 #b6ff05 Grass: dominated by herbaceous annuals (<2m) that are not cultivated.
7 #dade48 Cereal Croplands: dominated by herbaceous annuals (<2m). At least 60% cultivated cereal crops.
8 #c24f44 Broadleaf Croplands: dominated by herbaceous annuals (<2m). At least 60% cultivated broadleaf crops.
9 #a5a5a5 Urban and Built-up Lands: at least 30% impervious surface area including building materials, asphalt, and vehicles.
10 #69fff8 Permanent Snow and Ice: at least 60% of area is covered by snow and ice for at least 10 months of the year.
11 #f9ffa4 Non-Vegetated Lands: at least 60% of area is non-vegetated barren (sand, rock, soil) with less than 10% vegetation.

Class Table: LC_Prop1

Value Color Color Value Description
1 #f9ffa4 Barren: at least of area 60% is non-vegetated barren (sand, rock, soil) or permanent snow/ice with less than 10% vegetation.
2 #69fff8 Permanent Snow and Ice: at least 60% of area is covered by snow and ice for at least 10 months of the year.
3 #1c0dff Water Bodies: at least 60% of area is covered by permanent water bodies.
11 #05450a Evergreen Needleleaf Forests: dominated by evergreen conifer trees (>2m). Tree cover >60%.
12 #086a10 Evergreen Broadleaf Forests: dominated by evergreen broadleaf and palmate trees (>2m). Tree cover >60%.
13 #54a708 Deciduous Needleleaf Forests: dominated by deciduous needleleaf (larch) trees (>2m). Tree cover >60%.
14 #78d203 Deciduous Broadleaf Forests: dominated by deciduous broadleaf trees (>2m). Tree cover >60%.
15 #005a00 Mixed Broadleaf/Needleleaf Forests: co-dominated (40-60%) by broadleaf deciduous and evergreen needleleaf tree (>2m) types. Tree cover >60%.
16 #009900 Mixed Broadleaf Evergreen/Deciduous Forests: co-dominated (40-60%) by broadleaf evergreen and deciduous tree (>2m) types. Tree cover >60%.
21 #006c00 Open Forests: tree cover 30-60% (canopy >2m).
22 #00d000 Sparse Forests: tree cover 10-30% (canopy >2m).
31 #b6ff05 Dense Herbaceous: dominated by herbaceous annuals (<2m) at least 60% cover.
32 #98d604 Sparse Herbaceous: dominated by herbaceous annuals (<2m) 10-60% cover.
41 #dcd159 Dense Shrublands: dominated by woody perennials (1-2m) >60% cover.
42 #f1fb58 Shrubland/Grassland Mosaics: dominated by woody perennials (1-2m) 10-60% cover with dense herbaceous annual understory.
43 #fbee65 Sparse Shrublands: dominated by woody perennials (1-2m) 10-60% cover with minimal herbaceous understory.

Class Table: LC_Prop2

Value Color Color Value Description
1 #f9ffa4 Barren: at least of area 60% is non-vegetated barren (sand, rock, soil) or permanent snow/ice with less than 10% vegetation.
2 #69fff8 Permanent Snow and Ice: at least 60% of area is covered by snow and ice for at least 10 months of the year.
3 #1c0dff Water Bodies: at least 60% of area is covered by permanent water bodies.
9 #a5a5a5 Urban and Built-up Lands: at least 30% of area is made up ofimpervious surfaces including building materials, asphalt, and vehicles.
10 #003f00 Dense Forests: tree cover >60% (canopy >2m).
20 #006c00 Open Forests: tree cover 10-60% (canopy >2m).
25 #e3ff77 Forest/Cropland Mosaics: mosaics of small-scale cultivation 40-60% with >10% natural tree cover.
30 #b6ff05 Natural Herbaceous: dominated by herbaceous annuals (<2m). At least 10% cover.
35 #93ce04 Natural Herbaceous/Croplands Mosaics: mosaics of small-scale cultivation 40-60% with natural shrub or herbaceous vegetation.
36 #77a703 Herbaceous Croplands: dominated by herbaceous annuals (<2m). At least 60% cover. Cultivated fraction >60%.
40 #dcd159 Shrublands: shrub cover >60% (1-2m).

Class Table: LC_Prop3

Value Color Color Value Description
1 #f9ffa4 Barren: at least of area 60% is non-vegetated barren (sand, rock, soil) or permanent snow/ice with less than 10% vegetation.
2 #69fff8 Permanent Snow and Ice: at least 60% of area is covered by snow and ice for at least 10 months of the year.
3 #1c0dff Water Bodies: at least 60% of area is covered by permanent water bodies.
10 #003f00 Dense Forests: tree cover >60% (canopy >2m).
20 #006c00 Open Forests: tree cover 10-60% (canopy >2m).
27 #72834a Woody Wetlands: shrub and tree cover >10% (>1m). Permanently or seasonally inundated.
30 #b6ff05 Grasslands: dominated by herbaceous annuals (<2m) >10% cover.
40 #c6b044 Shrublands: shrub cover >60% (1-2m).
50 #3aba73 Herbaceous Wetlands: dominated by herbaceous annuals (<2m) >10% cover. Permanently or seasonally inundated.
51 #1e9db3 Tundra: tree cover <10%. Snow-covered for at least 8 months of the year.

Class Table: QC

Value Color Color Value Description
0 # Classified land: has a classification label and is land according to the water mask.
1 # Unclassified land: not classified because of missing data but land according to the water mask, labeled as barren.
2 # Classified water: has a classification label and is water according to the water mask.
3 # Unclassified water: not classified because of missing data but water according to the water mask.
4 # Classified sea ice: classified as snow/ice but water mask says it is water and less than 100m elevation, switched to water.
5 # Misclassified water: classified as water but water mask says it is land, switched to secondary label.
6 # Omitted snow/ice: land according to the water mask that was classified as something other than snow but with a maximum annual temperature below 1◦C, relabeled as snow/ice.
7 # Misclassified snow/ice: land according to the water mask that was classified as snow but with a minimum annual temperature greater than 1◦C, relabeled as barren.
8 # Backfilled label: missing label from stabilization, filled with the pre-stabilized result.
9 # Forest type changed: climate-based change to forest class.

Class Table: LW

Value Color Color Value Description
1 #1c0dff Water
2 #f9ffa4 Land,

代码:

///                   PROSAIL inversion by means of RF regression.                               //////////
///                                  Important !!!!!!                                            //////////
///   Results are not realiable due to the reduced amount of training data (500samples), the     //////////
///   origial training data set contains around 15000 samples. This code is only intended for    //////////
///   ilustrative purposes only.                                                                 //////////
/// 通过 RF 回归进行 PROSAIL 反演。 //////////
/// 重要的 !!!!!! //////////
/// 由于训练数据量减少(500 个样本),结果不可靠, //////////
/// 原始训练数据集包含大约 15000 个样本。此代码仅适用于 //////////
/// 仅供参考。 //////////



//Geographical Location of the selected pixel
//所选像素的地理位置

var exportarea = /* color: #ffc82d */ee.Geometry.Point([-1.10893, 42.65113]);
//The default location conrresponds with a forested area in northern part of spain.


Map.centerObject(exportarea, 14)
var modisLC = ee.Image('MODIS/051/MCD12Q1/2010_01_01')
    .select(['Land_Cover_Type_5']).reduceResolution(ee.Reducer.mode(),true,200);
    
var maskLC=modisLC.gt(0).and(modisLC.lt(9));

var mcdscale=0.0001;



Map.addLayer(exportarea,null,'Location',true)

var trainingfeatures=ee.FeatureCollection('ft:1POjOubAf8ZSvmMW3Ml3Ka3EUBt-5wY1eUg_J-04E'); //FAPAR LAI (500 samples)
var trainingfeatures2=ee.FeatureCollection('ft:1goDR2acd9mOOaY3ha092MU_NOOMRvTh0sIApn_od'); //FVC CWC EWT (500 samples)






//INPUT: Ref Nadir MODIS 
var MODIS_MCD43A4 = ee.ImageCollection("MODIS/MCD43A4").filterDate('2012-01-01','2016-12-31')//.select([0,3,6,9,12,15,18])//.first();
var MODIS_MDC43A2 = ee.ImageCollection("MODIS/MCD43A2").filterDate('2012-01-04','2016-12-31').select(0);




var idJoin = ee.Filter.equals({leftField: 'system:time_end', rightField: 'system:time_end'});
var innerJoin = ee.Join.inner('NBAR', 'QA');
var combinedCol = innerJoin.apply(MODIS_MCD43A4, MODIS_MDC43A2, idJoin);
var addQABands = function(image){
    var nbar = ee.Image(image.get('NBAR'));
    var qa = ee.Image(image.get('QA')).select(['BRDF_Albedo_Quality']);
    return nbar.addBands(qa);
};

var MODISFiltered = ee.ImageCollection(combinedCol.map(addQABands));






var inputnames=['B1','B2','B3','B4','B5','B6','B7'];


//Let's train the classifier
var RFtrained = ee.Classifier.randomForest({
 numberOfTrees: 74,
 minLeafPopulation: 3,
 bagFraction: 1, 
 outOfBagMode: false,
 seed: 123
})
.setOutputMode('REGRESSION') 
    .train({
    features: trainingfeatures,
    inputProperties: inputnames,
    classProperty: 'LAI'});   
    
print(RFtrained)      

////END of the training part of the code:


var maps =  MODISFiltered.map(function(img){
  var scaled=img.select([0,1,2,3,4,5,6],['B1','B2','B3','B4','B5','B6','B7']).toFloat().multiply(mcdscale);
  var estimation=scaled.mask(maskLC)
  .mask((img.select(7).eq(0)).or(img.select(7).eq(1)))
  .classify(RFtrained)
  return estimation.copyProperties(img, ['system:time_start']) ;
});




// Create an image time series chart.
var chart = ui.Chart.image.series({
  imageCollection: maps,
  region: exportarea,
  reducer: ee.Reducer.first(),
  scale: 500
}).setOptions({
          title: 'LAI temporal profile',
          vAxis: {title: 'LAI'},
          hAxis: {title: 'Time'},
          series: {
            0: {color: '008000', lineWidth: 2, pointSize: 4, curveType: 'function'}}
});

// Add the chart to the map.
chart.style().set({
  position: 'bottom-right',
  width: '300px',
  height: '200px'
});
Map.add(chart);




/////////////////Let's do the same with the FAPAR



var inputnames1=['B1','B2','B3','B4','B5','B6','B7'];


//Let's train the classifier
var RFtrained1 = ee.Classifier.randomForest({
 numberOfTrees: 58,
 minLeafPopulation: 3,
 bagFraction: 1, 
 outOfBagMode: false,
 seed: 123
})
.setOutputMode('REGRESSION') 
    .train({
    features: trainingfeatures,
    inputProperties: inputnames1,
    classProperty: 'FAPAR'});   
      
print(RFtrained1)     



var maps1 =  MODISFiltered.map(function(img){
  var scaled=img.select([0,1,2,3,4,5,6],['B1','B2','B3','B4','B5','B6','B7']).toFloat().multiply(mcdscale);
  var estimation=scaled.mask(maskLC).mask((img.select(7)).eq(0)).classify(RFtrained1)
  return estimation.copyProperties(img, ['system:time_start']) ;
});


////END of the training part of the code:






// Create an image time series chart.
var chart = ui.Chart.image.series({
  imageCollection: maps1,
  region: exportarea,
  reducer: ee.Reducer.first(),
  scale: 500
}).setOptions({
          title: 'FAPAR temporal profile',
          vAxis: {title: 'FAPAR'},
          hAxis: {title: 'Time'},
          series: {
            0: {color: 'B22222', lineWidth: 2, pointSize: 4, curveType: 'function'}}
});

// Add the chart to the map.
chart.style().set({
  position: 'bottom-left',
  width: '300px',
  height: '200px'
});
Map.add(chart);




/////////////////Let's do the same with the FVC


var inputnames1=['B1','B2','B3','B4','B5','B6','B7'];


//Let's train the classifier
var RFtrained2 = ee.Classifier.randomForest({
 numberOfTrees: 75,
 minLeafPopulation: 3,
 bagFraction: 1, //1.0 MATLAB
 outOfBagMode: false,
 seed: 123
})
.setOutputMode('REGRESSION') 
    .train({
    features: trainingfeatures2,
    inputProperties: inputnames1,
    classProperty: 'FVC'});   
      
print(RFtrained2)     


var maps2 =  MODISFiltered.map(function(img){
  var scaled=img.select([0,1,2,3,4,5,6],['B1','B2','B3','B4','B5','B6','B7']).toFloat().multiply(mcdscale);
  var estimation=scaled.mask(maskLC).mask((img.select(7)).eq(0)).classify(RFtrained2)
  return estimation.copyProperties(img, ['system:time_start']) ;
});


////END of the training part of the code:







// Create an image time series chart.
var chart2 = ui.Chart.image.series({
  imageCollection: maps2,
  region: exportarea,
  reducer: ee.Reducer.first(),
  scale: 500
}).setOptions({
          title: 'FVC temporal profile',
          vAxis: {title: 'FVC'},
          hAxis: {title: 'Time'},
          series: {
            0: {color: 'B22222', lineWidth: 2, pointSize: 4, curveType: 'function'}}
});

// Add the chart to the map.
chart2.style().set({
  position: 'bottom-center',
  width: '300px',
  height: '200px'
});
Map.add(chart2);





/////////////////Let's do the same with the CWC



var inputnames1=['B1','B2','B3','B4','B5','B6','B7'];


//Let's train the classifier
var RFtrained3 = ee.Classifier.randomForest({
 numberOfTrees: 74,
 minLeafPopulation: 2,
 bagFraction: 1,
 outOfBagMode: false,
 seed: 123
})
.setOutputMode('REGRESSION') 
    .train({
    features: trainingfeatures2,
    inputProperties: inputnames1,
    classProperty: 'CWC'});   
      
print(RFtrained3)     


var maps3 =  MODISFiltered.map(function(img){
  var scaled=img.select([0,1,2,3,4,5,6],['B1','B2','B3','B4','B5','B6','B7']).toFloat().multiply(mcdscale);
  var estimation=scaled.mask(maskLC).mask((img.select(7)).eq(0)).classify(RFtrained3)
  return estimation.copyProperties(img, ['system:time_start']) ;
});


////END of the training part of the code:






// Create an image time series chart.
var chart3 = ui.Chart.image.series({
  imageCollection: maps3,
  region: exportarea,
  reducer: ee.Reducer.first(),
  scale: 500
}).setOptions({
          title: 'CWC temporal profile',
          vAxis: {title: 'CWC'},
          hAxis: {title: 'Time'},
          series: {
            0: {color: 'B22222', lineWidth: 2, pointSize: 4, curveType: 'function'}}
});

// Add the chart to the map.
chart3.style().set({
  position: 'top-left',
  width: '300px',
  height: '200px'
});
Map.add(chart3);





编辑

 本文提出了一个在GEE中从长期(15年)MODIS数据中估计全球生物物理变量(LAI、FAPAR、FVC和CWC)的处理链。该方法利用了通过GEE云存储和并行计算能力快速有效地利用地球观测数据的优势。检索方法是基于一种混合方法,结合基于物理的辐射传输模型(PROSAIL)和随机森林回归。
辐射传输建模步骤中采用的叶子参数共同分布是通过利用TRY数据库获得的。这使得基于叶绿素、水和干物质含量地面测量的数以千计的PROSAIL参数化得以实现。TRY中越来越多的可用植物性状数据(包含数千条记录)缓解了对辐射传输模型中一些输入参数的更现实的表述的需要。
在BELMANIP2.1站点网络上进行了验证工作,方法是将得出的LAI和FAPAR与GEE上的MODIS参考LAI/FAPAR产品进行相互比较。获得的结果强调了由检索链提供的估计值与MODIS参考产品的一致性。然而,与其他生物群落相比,常绿阔叶林的相关性更低/更差。这些差异主要归因于不同的检索方法和变量定义,因为得出的LAI估计值更接近LAIeff,而不是由MOD15A3H产品得出的LAIactual。此外,得出的FAPAR只代表冠层的光合作用元素,而MODIS提供的FAPAR也包括非光合作用元素。拟议的检索链还在全球范围内得出了任何GEE数据集都没有提供的FVC和CWC变量。
这些结果证明了GEE在全球生物物理参数检索方面的实用性,并为用户在GEE中自行提供叶片和冠层参数打开了大门,以用于包括数据同化和传感器融合在内的广泛应用。


文章引用:

Campos-Taberner, M.; Moreno-Martínez, Á.; García-Haro, F.J.; Camps-Valls, G.; Robinson, N.P.; Kattge, J.; Running, S.W. Global Estimation of Biophysical Variables from Google Earth Engine Platform. Remote Sens. 201810, 1167. https://doi.org/10.3390/rs10081167

GEE初学者:如何快速找到正确学习GEE 的方法和网址,以及如何选择JavaScript和python?

GEE:geoBoundaries全球政治行政边界数据库是世界上每个国家的边界(即州、县)

GEE 下载错误:Error: Export too large: specified 3xxx pixels()

GEE:世界人口网格化第4版行政单位中心点与人口数据集

GEE:原有主成分分析PCA过程中,分量下载出现的错误

【版权声明】本文为华为云社区用户原创内容,转载时必须标注文章的来源(华为云社区)、文章链接、文章作者等基本信息, 否则作者和本社区有权追究责任。如果您发现本社区中有涉嫌抄袭的内容,欢迎发送邮件进行举报,并提供相关证据,一经查实,本社区将立刻删除涉嫌侵权内容,举报邮箱: cloudbbs@huaweicloud.com
  • 点赞
  • 收藏
  • 关注作者

评论(0

0/1000
抱歉,系统识别当前为高风险访问,暂不支持该操作

全部回复

上滑加载中

设置昵称

在此一键设置昵称,即可参与社区互动!

*长度不超过10个汉字或20个英文字符,设置后3个月内不可修改。

*长度不超过10个汉字或20个英文字符,设置后3个月内不可修改。