Soil pH in H2O [-] for continental Europe at 30 m spatial resolution for period 2000-2020: Open Soil Data Cube for Europe
收藏资源简介:
Predictions are based on the 3D Ensemble Machine Learning framework, as implemented in the R environment for statistical computing (Hengl & MacMillan, 2019; Hengl, et al., 2021). For each pixel we provide prediction errors as 1 standard deviation in either log or the original variable scale. The short description of currently available soil properties: soil pH in H2O; Soil properties were predicted at fixed depths: Surface soil = s0..0cm,<br> Subsoil 1 = s30..30cm,<br> Subsoil 2 = s60..60cm,<br> Subsoil 3 = s100..100cm. To produce estimates for depth intervals e.g. 0–30 cm, 0–100 cm best use the trapezoidal rule formula. Periods: 2000 (2000–2003), 2004 (2004–2007), 2008 (2008–2011), 2012 (2012–2015), 2016 (2016–2019), 2020;
本预测基于三维集成机器学习(3D Ensemble Machine Learning)框架,该框架实现在用于统计计算的R语言环境中(Hengl & MacMillan, 2019; Hengl等, 2021)。对每个像元,我们提供以对数尺度或原始变量尺度计算的1倍标准差形式的预测误差。当前可用土壤属性简要说明如下:水浸式土壤pH值(soil pH in H2O)。土壤属性按固定深度预测: 表层土壤 = s0..0cm, 亚表层土壤1 = s30..30cm, 亚表层土壤2 = s60..60cm, 亚表层土壤3 = s100..100cm。若需生成0–30 cm、0–100 cm等深度区间的估算值,建议采用梯形积分公式进行计算。时间周期涵盖:2000年(2000–2003年)、2004年(2004–2007年)、2008年(2008–2011年)、2012年(2012–2015年)、2016年(2016–2019年)及2020年。



