Google Earth Engine ——2001-2017年非洲土壤在 0-20 厘米和 20-50 厘米的土壤深度处可提取的含砂量数据，预测平均值和标准偏差-阿里云开发者社区

Google Earth Engine ——2001-2017年非洲土壤在 0-20 厘米和 20-50 厘米的土壤深度处可提取的含砂量数据，预测平均值和标准偏差

2022-04-27 109

版权

本文内容由阿里云实名注册用户自发贡献，版权归原作者所有，阿里云开发者社区不拥有其著作权，亦不承担相应法律责任。具体规则请查看《阿里云开发者社区用户服务协议》和《阿里云开发者社区知识产权保护指引》。如果您发现本社区中有涉嫌抄袭的内容，填写侵权投诉表单进行举报，一经查实，本社区将立刻删除涉嫌侵权内容。

简介： Google Earth Engine ——2001-2017年非洲土壤在 0-20 厘米和 20-50 厘米的土壤深度处可提取的含砂量数据，预测平均值和标准偏差

Sand content at soil depths of 0-20 cm and 20-50 cm, predicted mean and standard deviation.

Pixel values must be back-transformed with exp(x/10)-1.

In areas of dense jungle (generally over central Africa), model accuracy is low and therefore artefacts such as banding (striping) might be seen.

Soil property predictions were made by Innovative Solutions for Decision Agriculture Ltd. (iSDA) at 30 m pixel size using machine learning coupled with remote sensing data and a training set of over 100,000 analyzed soil samples.

Further information can be found in the FAQ and technical information documentation. To submit an issue or request support, please visit the iSDAsoil site.

土壤深度为 0-20 厘米和 20-50 厘米的可提取含砂量，预测平均值和标准偏差。

像素值必须使用 exp(x/10)-1 进行反向转换。

在茂密的丛林地区（通常在非洲中部），模型精度较低，因此可能会看到条带（条纹）等伪影。

决策农业创新解决方案有限公司 (iSDA) 使用机器学习、遥感数据和超过 100,000 个分析土壤样本的训练集，以 30 m 像素大小对土壤特性进行了预测。

更多信息可以在常见问题和技术信息文档中找到。要提交问题或请求支持，请访问 iSDAsoil 站点。

Dataset Availability

2001-01-01T00:00:00 - 2017-01-01T00:00:00

Dataset Provider

iSDA

Collection Snippet

ee.Image("ISDASOIL/Africa/v1/phosphorus_extractable")

Resolution

30 meters

Bands Table

Name	Description	Min	Max	Units
mean_0_20	Phosphorus, extractable, predicted mean at 0-20 cm depth	1	55	ppm
mean_20_50	Phosphorus, extractable, predicted mean at 20-50 cm depth	0	52	ppm
stdev_0_20	Phosphorus, extractable, standard deviation at 0-20 cm depth	0	19	ppm
stdev_20_50	Phosphorus, extractable, standard deviation at 20-50 cm depth	0	20	ppm

数据引用：

Hengl, T., Miller, M.A.E., Križan, J., et al. African soil properties and nutrients mapped at 30 m spatial resolution using two-scale ensemble machine learning. Sci Rep 11, 6130 (2021). doi:10.1038/s41598-021-85639-y

代码：

var mean_0_20 =
'<RasterSymbolizer>' +
 '<ColorMap type="ramp">' +
  '<ColorMapEntry color="#00204D" label="0-31" opacity="1" quantity="31"/>' +
  '<ColorMapEntry color="#002D6C" label="31-39" opacity="1" quantity="39"/>' +
  '<ColorMapEntry color="#16396D" label="39-43" opacity="1" quantity="43"/>' +
  '<ColorMapEntry color="#36476B" label="43-46" opacity="1" quantity="46"/>' +
  '<ColorMapEntry color="#4B546C" label="46-49" opacity="1" quantity="49"/>' +
  '<ColorMapEntry color="#5C616E" label="49-52" opacity="1" quantity="52"/>' +
  '<ColorMapEntry color="#6C6E72" label="52-54" opacity="1" quantity="54"/>' +
  '<ColorMapEntry color="#7C7B78" label="54-56" opacity="1" quantity="56"/>' +
  '<ColorMapEntry color="#8E8A79" label="56-58" opacity="1" quantity="58"/>' +
  '<ColorMapEntry color="#A09877" label="58-60" opacity="1" quantity="60"/>' +
  '<ColorMapEntry color="#B3A772" label="60-63" opacity="1" quantity="63"/>' +
  '<ColorMapEntry color="#C6B66B" label="63-65" opacity="1" quantity="65"/>' +
  '<ColorMapEntry color="#DBC761" label="65-68" opacity="1" quantity="68"/>' +
  '<ColorMapEntry color="#F0D852" label="68-71" opacity="1" quantity="71"/>' +
  '<ColorMapEntry color="#FFEA46" label="71-100" opacity="1" quantity="75"/>' +
 '</ColorMap>' +
 '<ContrastEnhancement/>' +
'</RasterSymbolizer>';
var mean_20_50 =
'<RasterSymbolizer>' +
 '<ColorMap type="ramp">' +
  '<ColorMapEntry color="#00204D" label="0-31" opacity="1" quantity="31"/>' +
  '<ColorMapEntry color="#002D6C" label="31-39" opacity="1" quantity="39"/>' +
  '<ColorMapEntry color="#16396D" label="39-43" opacity="1" quantity="43"/>' +
  '<ColorMapEntry color="#36476B" label="43-46" opacity="1" quantity="46"/>' +
  '<ColorMapEntry color="#4B546C" label="46-49" opacity="1" quantity="49"/>' +
  '<ColorMapEntry color="#5C616E" label="49-52" opacity="1" quantity="52"/>' +
  '<ColorMapEntry color="#6C6E72" label="52-54" opacity="1" quantity="54"/>' +
  '<ColorMapEntry color="#7C7B78" label="54-56" opacity="1" quantity="56"/>' +
  '<ColorMapEntry color="#8E8A79" label="56-58" opacity="1" quantity="58"/>' +
  '<ColorMapEntry color="#A09877" label="58-60" opacity="1" quantity="60"/>' +
  '<ColorMapEntry color="#B3A772" label="60-63" opacity="1" quantity="63"/>' +
  '<ColorMapEntry color="#C6B66B" label="63-65" opacity="1" quantity="65"/>' +
  '<ColorMapEntry color="#DBC761" label="65-68" opacity="1" quantity="68"/>' +
  '<ColorMapEntry color="#F0D852" label="68-71" opacity="1" quantity="71"/>' +
  '<ColorMapEntry color="#FFEA46" label="71-100" opacity="1" quantity="75"/>' +
 '</ColorMap>' +
 '<ContrastEnhancement/>' +
'</RasterSymbolizer>';
var stdev_0_20 =
'<RasterSymbolizer>' +
 '<ColorMap type="ramp">' +
  '<ColorMapEntry color="#fde725" label="low" opacity="1" quantity="2"/>' +
  '<ColorMapEntry color="#5dc962" label=" " opacity="1" quantity="3"/>' +
  '<ColorMapEntry color="#20908d" label=" " opacity="1" quantity="4"/>' +
  '<ColorMapEntry color="#3a528b" label=" " opacity="1" quantity="6"/>' +
  '<ColorMapEntry color="#440154" label="high" opacity="1" quantity="7"/>' +
 '</ColorMap>' +
 '<ContrastEnhancement/>' +
'</RasterSymbolizer>';
var stdev_20_50 =
'<RasterSymbolizer>' +
 '<ColorMap type="ramp">' +
  '<ColorMapEntry color="#fde725" label="low" opacity="1" quantity="2"/>' +
  '<ColorMapEntry color="#5dc962" label=" " opacity="1" quantity="3"/>' +
  '<ColorMapEntry color="#20908d" label=" " opacity="1" quantity="4"/>' +
  '<ColorMapEntry color="#3a528b" label=" " opacity="1" quantity="6"/>' +
  '<ColorMapEntry color="#440154" label="high" opacity="1" quantity="7"/>' +
 '</ColorMap>' +
 '<ContrastEnhancement/>' +
'</RasterSymbolizer>';
var raw = ee.Image("ISDASOIL/Africa/v1/sand_content");
Map.addLayer(
    raw.select(0).sldStyle(mean_0_20), {},
    "Sand content, mean visualization, 0-20 cm");
Map.addLayer(
    raw.select(1).sldStyle(mean_20_50), {},
    "Sand content, mean visualization, 20-50 cm");
Map.addLayer(
    raw.select(2).sldStyle(stdev_0_20), {},
    "Sand content, stdev visualization, 0-20 cm");
Map.addLayer(
    raw.select(3).sldStyle(stdev_20_50), {},
    "Sand content, stdev visualization, 20-50 cm");
var converted = raw.divide(10).exp().subtract(1);
var visualization = {min: 0, max: 3000};
Map.setCenter(25, -3, 2);
Map.addLayer(converted.select(0), visualization, "Sand content, mean, 0-20 cm");