An explainable integrated machine learning model for mapping soil erosion by wind and water in a catchment with three desiccated lakes

IF 3.1 3区 地球科学 Q2 GEOGRAPHY, PHYSICAL Aeolian Research Pub Date : 2024-04-27 DOI:10.1016/j.aeolia.2024.100924
Hamid Gholami , Mehdi Jalali , Marzieh Rezaei , Aliakbar Mohamadifar , Yougui Song , Yue Li , Yanping Wang , Baicheng Niu , Ebrahim Omidvar , Dimitris G. Kaskaoutis
{"title":"An explainable integrated machine learning model for mapping soil erosion by wind and water in a catchment with three desiccated lakes","authors":"Hamid Gholami ,&nbsp;Mehdi Jalali ,&nbsp;Marzieh Rezaei ,&nbsp;Aliakbar Mohamadifar ,&nbsp;Yougui Song ,&nbsp;Yue Li ,&nbsp;Yanping Wang ,&nbsp;Baicheng Niu ,&nbsp;Ebrahim Omidvar ,&nbsp;Dimitris G. Kaskaoutis","doi":"10.1016/j.aeolia.2024.100924","DOIUrl":null,"url":null,"abstract":"<div><p>Soil erosion by water and wind is a critical challenge for sustainable management of catchments in drylands and accurate spatial information can help in mitigation of its destructive consequences. Here, seven machine learning (ML) models were applied to map simultaneously the water and wind erosions in the Bakhtegan catchment, south Iran, with three dried lakes in its southern part and three dams established in upstream parts of the lakes. The analysis identified 10 and 11 effective variables controlling water and wind erosions, among 20 and 17 potential variables, respectively, via the MARS feature selection algorithm. According to the most accurate ML models (artificial neural network for water erosion, and Cubist for wind erosion), an integrated model was developed to map soil erosion by water and wind simultaneously. Permutation feature importance (PFI) and Shapley additive exPlanation (SHAP) interpretation techniques were employed to explain the model outputs, revealing that 19.7 % of the total area belonged to high and very high susceptibility classes to soil erosion by water and wind. The PFI plot revealed that the slope and wind speed were the most influencing factors for water and wind erosion, respectively. According to SHAP decision plot, slope had the highest contribution on the predictive water erosion model’s output, whereas vegetation cover exhibited the highest contribution on the predictive wind erosion model’s output. Due to climate change and intensified drought during the recent years, as well as due to construction of dams upstream of the lakes, the southern part of the study area was converted to a source of sand and dust storms. The hotspots with severe water erosion are distributed all over the study area, rendering it quite vulnerable to adverse climate change projections.</p></div>","PeriodicalId":49246,"journal":{"name":"Aeolian Research","volume":null,"pages":null},"PeriodicalIF":3.1000,"publicationDate":"2024-04-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Aeolian Research","FirstCategoryId":"89","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S1875963724000351","RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"GEOGRAPHY, PHYSICAL","Score":null,"Total":0}
引用次数: 0

Abstract

Soil erosion by water and wind is a critical challenge for sustainable management of catchments in drylands and accurate spatial information can help in mitigation of its destructive consequences. Here, seven machine learning (ML) models were applied to map simultaneously the water and wind erosions in the Bakhtegan catchment, south Iran, with three dried lakes in its southern part and three dams established in upstream parts of the lakes. The analysis identified 10 and 11 effective variables controlling water and wind erosions, among 20 and 17 potential variables, respectively, via the MARS feature selection algorithm. According to the most accurate ML models (artificial neural network for water erosion, and Cubist for wind erosion), an integrated model was developed to map soil erosion by water and wind simultaneously. Permutation feature importance (PFI) and Shapley additive exPlanation (SHAP) interpretation techniques were employed to explain the model outputs, revealing that 19.7 % of the total area belonged to high and very high susceptibility classes to soil erosion by water and wind. The PFI plot revealed that the slope and wind speed were the most influencing factors for water and wind erosion, respectively. According to SHAP decision plot, slope had the highest contribution on the predictive water erosion model’s output, whereas vegetation cover exhibited the highest contribution on the predictive wind erosion model’s output. Due to climate change and intensified drought during the recent years, as well as due to construction of dams upstream of the lakes, the southern part of the study area was converted to a source of sand and dust storms. The hotspots with severe water erosion are distributed all over the study area, rendering it quite vulnerable to adverse climate change projections.

查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
用于绘制有三个干涸湖泊的集水区风蚀和水蚀土壤侵蚀图的可解释综合机器学习模型
水和风造成的土壤侵蚀是旱地集水区可持续管理面临的严峻挑战,而准确的空间信息有助于减轻其破坏性后果。伊朗南部的巴赫特甘集水区南部有三个干涸的湖泊,湖泊上游建有三座水坝,本文应用七个机器学习(ML)模型同时绘制了该集水区的水蚀和风蚀图。分析通过 MARS 特征选择算法,在 20 个和 17 个潜在变量中分别确定了 10 个和 11 个控制水蚀和风蚀的有效变量。根据最精确的 ML 模型(人工神经网络用于水蚀,Cubist 用于风蚀),建立了一个综合模型,以同时绘制水蚀和风蚀的土壤侵蚀图。模型输出结果显示,19.7% 的总面积属于水蚀和风蚀的高易感等级和极高易感等级。PFI 图显示,坡度和风速分别是水蚀和风蚀的最大影响因素。根据 SHAP 决策图,坡度对水蚀预测模型输出的贡献最大,而植被覆盖对风蚀预测模型输出的贡献最大。由于近年来气候变化和干旱加剧,以及在湖泊上游修建水坝,研究区南部已成为沙尘暴的源头。水土流失严重的热点地区遍布研究区,使其很容易受到不利气候变化预测的影响。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
Aeolian Research
Aeolian Research GEOGRAPHY, PHYSICAL-
CiteScore
7.10
自引率
6.10%
发文量
43
审稿时长
>12 weeks
期刊介绍: The scope of Aeolian Research includes the following topics: • Fundamental Aeolian processes, including sand and dust entrainment, transport and deposition of sediment • Modeling and field studies of Aeolian processes • Instrumentation/measurement in the field and lab • Practical applications including environmental impacts and erosion control • Aeolian landforms, geomorphology and paleoenvironments • Dust-atmosphere/cloud interactions.
期刊最新文献
Aeolian sand cover on a granite peninsula (Hammeren, Bornholm, Baltic Sea) formed in three episodes during the past 11,600 years Speculation on an early Pleistocene origin of the Parker dunes of southwest Arizona, USA Transport and deposition of microplastics and microrubbers during a dust storm (Sarakhs, northeast Iran) Automatic identification of saltating tracks driven by strong wind in high-speed video using multiple statistical quantities of instant particle velocity Characterizing variability in geochemistry and mineralogy of western US dust sources
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1