Fei Guo, Cheng Chen, Hao Fang, Qingshan Ma, Tao Huang, Hongtao Tian, Qiaoyi Dai
{"title":"考虑未来土地利用和植被变化的动态滑坡易感性评价:基于元胞自动机马尔可夫模型和机器学习的秭归县研究","authors":"Fei Guo, Cheng Chen, Hao Fang, Qingshan Ma, Tao Huang, Hongtao Tian, Qiaoyi Dai","doi":"10.1007/s12665-025-12494-9","DOIUrl":null,"url":null,"abstract":"<div><p>Landslide susceptibility assessment involves numerous dynamic factors that can influence the predictive accuracy. This study targets Zigui County, located at the head of the Three Gorges Reservoir Area, a region prone to landslides due to its complex geological and environmental conditions. To incorporate temporal variability, the Cellular Automata-Markov (CA-Markov) model is employed to simulate and predict dynamic factors, specifically land use/land cover (LULC) changes and the normalized difference vegetation index (NDVI). The GeoDetector tool is then applied to construct an evaluation index system. Logistic regression (LR), support vector machine (SVM), and random forest (RF) models are utilized to assess landslide susceptibility, followed by a comparative analysis of their results. The results confirm the effectiveness of the CA–Markov model in predicting dynamic factors. For the 2023 land use/land cover (LULC) prediction, the proportion of cultivated land, grassland, and construction land increased by 0.49%, 0.01%, and 1.61%, respectively, while forest land and water area decreased by 1.54% and 0.56%. Additionally, the 2023 NDVI prediction, the NDVI forecast shows a 1.93% reduction in areas with positive vegetation coverage. Among the models, the RF model demonstrates higher predictive accuracy and reliability compared to the LR and SVM models. The areas with extremely high and high landslide susceptibility are mainly located along on the Yangtze River and its tributaries, including Xietan, Zhaxi, Xiangxi, Qinggan (Luogudong) and Tongzhuang Rivers, as well as along major highways such as Provincial Highway S363 and National Highway G348.</p></div>","PeriodicalId":542,"journal":{"name":"Environmental Earth Sciences","volume":"84 18","pages":""},"PeriodicalIF":2.8000,"publicationDate":"2025-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Dynamic landslide susceptibility Assessment integrating future land use and vegetation changes: Cellular-automata markov-models and machine learning for zigui county, China\",\"authors\":\"Fei Guo, Cheng Chen, Hao Fang, Qingshan Ma, Tao Huang, Hongtao Tian, Qiaoyi Dai\",\"doi\":\"10.1007/s12665-025-12494-9\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p>Landslide susceptibility assessment involves numerous dynamic factors that can influence the predictive accuracy. This study targets Zigui County, located at the head of the Three Gorges Reservoir Area, a region prone to landslides due to its complex geological and environmental conditions. To incorporate temporal variability, the Cellular Automata-Markov (CA-Markov) model is employed to simulate and predict dynamic factors, specifically land use/land cover (LULC) changes and the normalized difference vegetation index (NDVI). The GeoDetector tool is then applied to construct an evaluation index system. Logistic regression (LR), support vector machine (SVM), and random forest (RF) models are utilized to assess landslide susceptibility, followed by a comparative analysis of their results. The results confirm the effectiveness of the CA–Markov model in predicting dynamic factors. For the 2023 land use/land cover (LULC) prediction, the proportion of cultivated land, grassland, and construction land increased by 0.49%, 0.01%, and 1.61%, respectively, while forest land and water area decreased by 1.54% and 0.56%. Additionally, the 2023 NDVI prediction, the NDVI forecast shows a 1.93% reduction in areas with positive vegetation coverage. Among the models, the RF model demonstrates higher predictive accuracy and reliability compared to the LR and SVM models. The areas with extremely high and high landslide susceptibility are mainly located along on the Yangtze River and its tributaries, including Xietan, Zhaxi, Xiangxi, Qinggan (Luogudong) and Tongzhuang Rivers, as well as along major highways such as Provincial Highway S363 and National Highway G348.</p></div>\",\"PeriodicalId\":542,\"journal\":{\"name\":\"Environmental Earth Sciences\",\"volume\":\"84 18\",\"pages\":\"\"},\"PeriodicalIF\":2.8000,\"publicationDate\":\"2025-09-15\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Environmental Earth Sciences\",\"FirstCategoryId\":\"93\",\"ListUrlMain\":\"https://link.springer.com/article/10.1007/s12665-025-12494-9\",\"RegionNum\":4,\"RegionCategory\":\"环境科学与生态学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"ENVIRONMENTAL SCIENCES\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Environmental Earth Sciences","FirstCategoryId":"93","ListUrlMain":"https://link.springer.com/article/10.1007/s12665-025-12494-9","RegionNum":4,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"ENVIRONMENTAL SCIENCES","Score":null,"Total":0}
Dynamic landslide susceptibility Assessment integrating future land use and vegetation changes: Cellular-automata markov-models and machine learning for zigui county, China
Landslide susceptibility assessment involves numerous dynamic factors that can influence the predictive accuracy. This study targets Zigui County, located at the head of the Three Gorges Reservoir Area, a region prone to landslides due to its complex geological and environmental conditions. To incorporate temporal variability, the Cellular Automata-Markov (CA-Markov) model is employed to simulate and predict dynamic factors, specifically land use/land cover (LULC) changes and the normalized difference vegetation index (NDVI). The GeoDetector tool is then applied to construct an evaluation index system. Logistic regression (LR), support vector machine (SVM), and random forest (RF) models are utilized to assess landslide susceptibility, followed by a comparative analysis of their results. The results confirm the effectiveness of the CA–Markov model in predicting dynamic factors. For the 2023 land use/land cover (LULC) prediction, the proportion of cultivated land, grassland, and construction land increased by 0.49%, 0.01%, and 1.61%, respectively, while forest land and water area decreased by 1.54% and 0.56%. Additionally, the 2023 NDVI prediction, the NDVI forecast shows a 1.93% reduction in areas with positive vegetation coverage. Among the models, the RF model demonstrates higher predictive accuracy and reliability compared to the LR and SVM models. The areas with extremely high and high landslide susceptibility are mainly located along on the Yangtze River and its tributaries, including Xietan, Zhaxi, Xiangxi, Qinggan (Luogudong) and Tongzhuang Rivers, as well as along major highways such as Provincial Highway S363 and National Highway G348.
期刊介绍:
Environmental Earth Sciences is an international multidisciplinary journal concerned with all aspects of interaction between humans, natural resources, ecosystems, special climates or unique geographic zones, and the earth:
Water and soil contamination caused by waste management and disposal practices
Environmental problems associated with transportation by land, air, or water
Geological processes that may impact biosystems or humans
Man-made or naturally occurring geological or hydrological hazards
Environmental problems associated with the recovery of materials from the earth
Environmental problems caused by extraction of minerals, coal, and ores, as well as oil and gas, water and alternative energy sources
Environmental impacts of exploration and recultivation – Environmental impacts of hazardous materials
Management of environmental data and information in data banks and information systems
Dissemination of knowledge on techniques, methods, approaches and experiences to improve and remediate the environment
In pursuit of these topics, the geoscientific disciplines are invited to contribute their knowledge and experience. Major disciplines include: hydrogeology, hydrochemistry, geochemistry, geophysics, engineering geology, remediation science, natural resources management, environmental climatology and biota, environmental geography, soil science and geomicrobiology.