Knowledge Resource Center for Ecological Environment in Arid Area
DOI | 10.3390/rs12071095 |
Improving the Spatial Prediction of Soil Organic Carbon Content in Two Contrasting Climatic Regions by Stacking Machine Learning Models and Rescanning Covariate Space | |
Taghizadeh-Mehrjardi, Ruhollah; Schmidt, Karsten; Amirian-Chakan, Alireza; Rentschler, Tobias; Zeraatpisheh, Mojtaba; Sarmadian, Fereydoon; Valavi, Roozbeh; Davatgar, Naser; Behrens, Thorsten; Scholten, Thomas | |
通讯作者 | Schmidt, K |
来源期刊 | REMOTE SENSING |
EISSN | 2072-4292 |
出版年 | 2020 |
卷号 | 12期号:7 |
英文摘要 | Understanding the spatial distribution of soil organic carbon (SOC) content over different climatic regions will enhance our knowledge of carbon gains and losses due to climatic change. However, little is known about the SOC content in the contrasting arid and sub-humid regions of Iran, whose complex SOC-landscape relationships pose a challenge to spatial analysis. Machine learning (ML) models with a digital soil mapping framework can solve such complex relationships. Current research focusses on ensemble ML models to increase the accuracy of prediction. The usual ensemble method is boosting or weighted averaging. This study proposes a novel ensemble technique: the stacking of multiple ML models through a meta-learning model. In addition, we tested the ensemble through rescanning the covariate space to maximize the prediction accuracy. We first applied six state-of-the-art ML models (i.e., Cubist, random forests (RF), extreme gradient boosting (XGBoost), classical artificial neural network models (ANN), neural network ensemble based on model averaging (AvNNet), and deep learning neural networks (DNN)) to predict and map the spatial distribution of SOC content at six soil depth intervals for both regions. In addition, the stacking of multiple ML models through a meta-learning model with/without rescanning the covariate space were tested and applied to maximize the prediction accuracy. Out of six ML models, the DNN resulted in the best modeling accuracies, followed by RF, XGBoost, AvNNet, ANN, and Cubist. Importantly, the stacking of models indicated a significant improvement in the prediction of SOC content, especially when combined with rescanning the covariate space. For instance, the RMSE values for SOC content prediction of the upper 0-5 cm of the soil profiles of the arid site and the sub-humid site by the proposed stacking approaches were 17% and 9% respectively, less than that obtained by the DNN models-the best individual model. This indicates that rescanning the original covariate space by a meta-learning model can extract more information and improve the SOC content prediction accuracy. Overall, our results suggest that the stacking of diverse sets of models could be used to more accurately estimate the spatial distribution of SOC content in different climatic regions. |
英文关键词 | digital soil mapping machine learning models stacking of models spatial block cross-validation deep learning |
类型 | Article |
语种 | 英语 |
开放获取类型 | Green Submitted, gold |
收录类别 | SCI-E |
WOS记录号 | WOS:000537709600045 |
WOS关键词 | ARTIFICIAL NEURAL-NETWORKS ; RANDOM FORESTS ; SEMIARID RANGELANDS ; PROFILE DEPTH ; STOCKS ; MATTER ; REGRESSION ; MAPS ; TOPOGRAPHY ; LANDSCAPE |
WOS类目 | Environmental Sciences ; Geosciences, Multidisciplinary ; Remote Sensing ; Imaging Science & Photographic Technology |
WOS研究方向 | Environmental Sciences & Ecology ; Geology ; Remote Sensing ; Imaging Science & Photographic Technology |
资源类型 | 期刊论文 |
条目标识符 | http://119.78.100.177/qdio/handle/2XILL650/324628 |
作者单位 | [Taghizadeh-Mehrjardi, Ruhollah; Rentschler, Tobias; Behrens, Thorsten; Scholten, Thomas] Univ Tubingen, Dept Geosci Soil Sci & Geomorphol, D-72070 Tubingen, Germany; [Taghizadeh-Mehrjardi, Ruhollah] Ardakan Univ, Fac Agr & Nat Resources, Ardakan 8951656767, Iran; [Schmidt, Karsten] Univ Tubingen, eSci Ctr, D-72070 Tubingen, Germany; [Schmidt, Karsten; Behrens, Thorsten; Scholten, Thomas] Univ Tubingen, DFG Cluster Excellence Machine Learning, D-72070 Tubingen, Germany; [Amirian-Chakan, Alireza] Lorestan Univ, Dept Soil Sci, Khorramabad 6815144316, Iran; [Rentschler, Tobias; Behrens, Thorsten; Scholten, Thomas] Univ Tubingen, CRC ResourceCultures 1070, D-72070 Tubingen, Germany; [Zeraatpisheh, Mojtaba] Henan Univ, Coll Environm & Planning, Key Lab Geospatial Technol Middle & Lower Yellow, Kaifeng 475004, Peoples R China; [Sarmadian, Fereydoon] Univ Tehran, Dept Soil Sci, Coll Agr, Karaj 7787131587, Iran; [Valavi, Roozbeh] Univ Melbourne, Sch BioSci, Quantitat & Appl Ecol Grp, Melbourne, Vic 3010, Australi... |
推荐引用方式 GB/T 7714 | Taghizadeh-Mehrjardi, Ruhollah,Schmidt, Karsten,Amirian-Chakan, Alireza,et al. Improving the Spatial Prediction of Soil Organic Carbon Content in Two Contrasting Climatic Regions by Stacking Machine Learning Models and Rescanning Covariate Space[J],2020,12(7). |
APA | Taghizadeh-Mehrjardi, Ruhollah.,Schmidt, Karsten.,Amirian-Chakan, Alireza.,Rentschler, Tobias.,Zeraatpisheh, Mojtaba.,...&Scholten, Thomas.(2020).Improving the Spatial Prediction of Soil Organic Carbon Content in Two Contrasting Climatic Regions by Stacking Machine Learning Models and Rescanning Covariate Space.REMOTE SENSING,12(7). |
MLA | Taghizadeh-Mehrjardi, Ruhollah,et al."Improving the Spatial Prediction of Soil Organic Carbon Content in Two Contrasting Climatic Regions by Stacking Machine Learning Models and Rescanning Covariate Space".REMOTE SENSING 12.7(2020). |
条目包含的文件 | 条目无相关文件。 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。