Soil nutrient maps of Sub-Saharan Africa: assessment of soil nutrient content at 250 m spatial resolution using machine learning.
Soil nutrient maps of Sub-Saharan Africa: assessment of soil nutrient content at 250 m spatial resolution using machine learning.
复制标题
撒哈拉以南非洲的土壤养分图：使用机器学习以250 m空间分辨率评估土壤养分含量。
DOI：
10.1007/s10705-017-9870-x
复制
发表时间：
2017-08-02
影响因子：
3.1
通讯作者：
Kwabena NA
中科院分区：
文献类型：
--
作者：
Hengl T;Leenaars JGB;Shepherd KD;Walsh MG;Heuvelink GBM;Mamo T;Tilahun H;Berkhout E;Cooper M;Fegraus E;Wheeler I;Kwabena NA
在250米的空间分辨率和0-30厘米的深度间隔，整个撒哈拉以南非洲地区的土壤宏观和微观养分含量的空间预测。对15种目标营养物质进行了预测：有机碳（C）和总（有机）氮（N）、总磷（P）、可提取磷（P）、钾（K）、钙（Ca）、镁（Mg）、硫（S）、钠（Na）、铁（Fe）、锰（Mn）、锌（Zn）、铜（Cu）、铝（Al）和硼（B）。模型训练使用的土壤样品从CA。59，000个地点（来自AfSIS，ECONOSIS，One Acre Fund，VitalSigns和遗留土壤数据的土壤样本汇编）和大量遥感协变量以及地形，岩性和土地覆盖图。然后通过两种机器学习算法为每种营养素创建一个集成模型-随机森林和梯度提升，如R包ranger和xgboost中实现的那样-然后用于在完全优化的计算系统中生成预测。交叉验证表明，除了S、P和B外，可以为大多数目标营养素生成显著模型（R方在40-85%之间）。与OFRA田间试验数据库的进一步比较表明，土壤养分确实对农业发展至关重要，Mn、Zn、Al、B和Na是预测作物产量的最重要养分。利用非洲现有点数据绘制营养物图的一个限制因素似乎是（1）采样地点的高度空间聚集，以及（2）缺少更详细的母质/地质图。提高预测准确性的合理步骤包括：进一步收集输入（训练）点样本，进一步统一测量方法，增加非洲特有的更详细的协变量，以及实施完整的时空统计建模框架。
Spatial predictions of soil macro and micro-nutrient content across Sub-Saharan Africa at 250 m spatial resolution and for 0–30 cm depth interval are presented. Predictions were produced for 15 target nutrients: organic carbon (C) and total (organic) nitrogen (N), total phosphorus (P), and extractable—phosphorus (P), potassium (K), calcium (Ca), magnesium (Mg), sulfur (S), sodium (Na), iron (Fe), manganese (Mn), zinc (Zn), copper (Cu), aluminum (Al) and boron (B). Model training was performed using soil samples from ca. 59,000 locations (a compilation of soil samples from the AfSIS, EthioSIS, One Acre Fund, VitalSigns and legacy soil data) and an extensive stack of remote sensing covariates in addition to landform, lithologic and land cover maps. An ensemble model was then created for each nutrient from two machine learning algorithms— random forest and gradient boosting, as implemented in R packages ranger and xgboost—and then used to generate predictions in a fully-optimized computing system. Cross-validation revealed that apart from S, P and B, significant models can be produced for most targeted nutrients (R-square between 40–85%). Further comparison with OFRA field trial database shows that soil nutrients are indeed critical for agricultural development, with Mn, Zn, Al, B and Na, appearing as the most important nutrients for predicting crop yield. A limiting factor for mapping nutrients using the existing point data in Africa appears to be (1) the high spatial clustering of sampling locations, and (2) missing more detailed parent material/geological maps. Logical steps towards improving prediction accuracies include: further collection of input (training) point samples, further harmonization of measurement methods, addition of more detailed covariates specific to Africa, and implementation of a full spatiotemporal statistical modeling framework.
登录
查看更多内容
影响因子：
56.9
作者：
Fan, Y.;Li, H.;Miguez-Macho, G.
通讯作者：
Miguez-Macho, G.
影响因子：
5.1
作者：
Conrad, O.;Bechtel, B.;Boehner, J.
通讯作者：
Boehner, J.
影响因子：
3.3
作者：
Drechsel, P;Kunze, D;de Vries, FP
通讯作者：
de Vries, FP
影响因子：
6.9
作者：
Jayne, T. S.;Mather, David;Mghenyi, Elliot
通讯作者：
Mghenyi, Elliot
影响因子：
3.7
作者：
Hengl T;Mendes de Jesus J;Heuvelink GB;Ruiperez Gonzalez M;Kilibarda M;Blagotić A;Shangguan W;Wright MN;Geng X;Bauer-Marschallinger B;Guevara MA;Vargas R;MacMillan RA;Batjes NH;Leenaars JG;Ribeiro E;Wheeler I;Mantel S;Kempen B
通讯作者：
Kempen B