A comparative assessment of support vector regression, artificial neural networks, and random forests for predicting and mapping soil organic carbon stocks across an Afromontane landscape. (May 2015)

• Record Type: Journal Article
• Authors: Were, Kennedy; Bui, Dieu Tien; Dick, Øystein B.; Singh, Bal Ram
• Is Part Of: Ecological indicators. Volume 52(2015)
• Page Start: 394
• Page End: 403
• Publication Date: 2015-05
• Subjects: Random forests -- Artificial neural networks -- Support vector regression -- Soil organic carbon -- Digital soil mapping -- Eastern Mau -- Kenya; Environmental monitoring -- Periodicals; Environmental management -- Periodicals; Environmental impact analysis -- Periodicals; Environmental risk assessment -- Periodicals; Sustainable development -- Periodicals; 333.71405
• DOI: 10.1016/j.ecolind.2014.12.028
• Languages: English
• ISSNs: 1470-160X

Abstract

Highlights: Support vector regression model emerged the best in spatially predicting SOC stocks. Artificial neural network model followed closely behind. Total nitrogen concentrations contributed the most in explaining the spatial patterns of SOC stocks. Abstract: Soil organic carbon (SOC) is a key indicator of ecosystem health, with a great potential to affect climate change. This study aimed to develop, evaluate, and compare the performance of support vector regression (SVR), artificial neural network (ANN), and random forest (RF) models in predicting and mapping SOC stocks in the Eastern Mau Forest Reserve, Kenya. Auxiliary data, including soil sampling, climatic, topographic, and remotely-sensed data were used for model calibration. The calibrated models were applied to create prediction maps of SOC stocks that were validated using independent testing data. The results showed that the models overestimated SOC stocks. Random forest model with a mean error (ME) of −6.5 Mg C ha −1 had the highest tendency for overestimation, while SVR model with an ME of −4.4 Mg C ha −1 had the lowest tendency. Support vector regression model also had the lowest root mean squared error (RMSE) and the highest R 2 values (14.9 Mg C ha −1 and 0.6, respectively); hence, it was the best method to predict SOC stocks. Artificial neural network predictions followed closely with RMSE, ME, and R 2 values of 15.5, −4.7, and 0.6, respectively. The three prediction maps broadly depicted similar spatial patterns of SOC stocks, with an increasing gradient of SOC stocks from east to west. The highest stocks were on the forest-dominated western and north-western parts, while the lowest stocks were on the cropland-dominated eastern part. The most important variable for explaining the observed spatial patterns of SOC stocks was total nitrogen concentration. Based on the close performance of SVR and ANN models, we proposed that both models should be calibrated, and then the best result applied for spatial prediction of target soil properties in other contexts.