Google Earth Engine ——2001-2017年使用坡度、化学和物理土壤特性得出的土壤肥力能力分类，预测平均值和标准偏差数据集

iSDAsoil Fertility Capability Classification

Soil fertility capability classification derived using slope, chemical, and physical soil properties. For more information about this layer, please visit this page.

The classes for the 'fcc' band apply to pixel values that must be back-transformed with x modulo 3000.

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.

使用坡度、化学和物理土壤特性得出的土壤肥力能力分类。有关此层的更多信息，请访问此页面。

“fcc”波段的类适用于必须使用 x 模 3000 进行反向转换的像素值。

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/fcc")

Resolution

30 meters

Bands Table

Class Table: fcc

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 raw = ee.Image("ISDASOIL/Africa/v1/fcc").select(0);
var converted = ee.Image(raw.mod(3000).copyProperties(raw));
Map.setCenter(25, -3, 2);
Map.addLayer(converted, {}, "Fertility Capability Classification");