当前位置: X-MOL 学术Catena › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Assessment of the interpretability of data mining for the spatial modelling of water erosion using game theory
Catena ( IF 5.4 ) Pub Date : 2021-01-27 , DOI: 10.1016/j.catena.2021.105178
Aliakbar Mohammadifar , Hamid Gholami , Jesús Rodrigo Comino , Adrian L. Collins

This study undertook a comprehensive application of 15 data mining (DM) models, most of which have, thus far, not been commonly used in environmental sciences, to predict land susceptibility to water erosion hazard in the Kahorestan catchment, southern Iran. The DM models were BGLM, BGAM, Cforest, CITree, GAMS, LRSS, NCPQR, PLS, PLSGLM, QR, RLM, SGB, SVM, BCART and BTR. We identified 18 factors usually considered as key controls for water erosion, comprising 10 factors extracted from a digital elevation model (DEM), three indices extracted from Landsat 8 images, a sediment connectivity index (SCI) and three other intrinsic factors. Three indicators consisting of MAE, MBE, RMSE, and a Taylor diagram were applied to assess model performance and accuracy. Game theory was applied to assess the interpretability of the DM models for predicting water erosion hazard. Among the 15 predictive models, BGAM and PLS respectively returned the best and worst performance in predicting water erosion hazard in the study area. The most accurate model, BGAM predicted that 22%, 8.2%, 9.4% and 60.4% of the total area should be classified as low, moderate, high and very high susceptibility to soil erosion by water, respectively. Based on BGAM and game theory, the factors extracted from the DEM (e.g., DEM, TWI, Slope, TST, TRI, and SPI) were considered the most important ones controlling the predicted severity of soil erosion by water. We conclude that overall, game theory is a valuable technique for assessing the interpretability of predictive models because this theory through SHAP (Shapley additive explanations) and PFIM (permutation feature importance measure) addresses the important concerns regarding the interpretability of more complex DM models.



中文翻译:

利用博弈论评估水蚀空间模型数据挖掘的可解释性

这项研究对15种数据挖掘(DM)模型进行了全面的应用,到目前为止,大多数模型尚未在环境科学中普遍使用,以预测伊朗南部Kahorestan流域的土地易遭受水蚀危害。DM模型是BGLM,BGAM,Cforest,CITree,GAMS,LRSS,NCPQR,PLS,PLSGLM,QR,RLM,SGB,SVM,BCART和BTR。我们确定了18个通常被认为是水蚀的关键控制因素,包括从数字高程模型(DEM)提取的10个因素,从Landsat 8图像提取的三个指标,沉积物连通性指数(SCI)和其他三个内在因素。应用了由MAE,MBE,RMSE和泰勒图组成的三个指标来评估模型的性能和准确性。运用博弈论评估DM模型在预测水蚀危害方面的可解释性。在15个预测模型中,BGAM和PLS在预测研究区域的水蚀危害方面分别返回最佳和最差表现。最准确的模型BGAM预测,应将总面积的22%,8.2%,9.4%和60.4%分别划分为对水土流失的敏感性低,中度,高和极高。基于BGAM和博弈论,从DEM中提取的因素(例如DEM,TWI,坡度,TST,TRI和SPI)被认为是控制预测的水土流失严重程度的最重要因素。我们得出结论,总体而言,

更新日期:2021-01-28
down
wechat
bug