Article
Environmental Sciences
Lanbing Yu, Chao Zhou, Yang Wang, Ying Cao, David J. Peres
Summary: This study aims to establish a novel procedure for landslide susceptibility mapping (LSM) in areas with limited availability of data. By combining knowledge-driven and data-driven models, the proposed approach improves the accuracy of landslide susceptibility assessment. Results show that the method allows identifying new landslide-prone areas and enhancing the predictive performance of LSM.
Article
Engineering, Environmental
Jingjing Long, Yong Liu, Changdong Li, Zhiyong Fu, Haikuan Zhang
Summary: This study identified Jurassic facility-sliding strata as a fundamental factor affecting rainfall-reservoir induced landslides in western Hubei Province, China Three Gorges Reservoir area. A novel hybrid model based on the two steps self-organizing mapping-random forest (two steps SOM-RF) algorithm was proposed to address the problem of identifying true landslides and non-landslides. The results showed that considering true landslides and non-landslides is effective in producing a more accurate landslide susceptibility map with superior prediction skill and higher reliability.
STOCHASTIC ENVIRONMENTAL RESEARCH AND RISK ASSESSMENT
(2021)
Article
Geochemistry & Geophysics
Cheng Chen, Lei Fan
Summary: This study proposes an interpretable DL model called Deep-Attention-LSF, which assigns significance scores to contributing factors at local levels for attributing landslide susceptibility. The Deep-Attention-LSF model outperforms other models in predicting landslide occurrence and provides reasonable explanations for landslide attributions.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2023)
Article
Engineering, Environmental
Fasheng Miao, Fancheng Zhao, Yiping Wu, Linwei Li, Akos Torok
Summary: In this study, a boosting-C5.0 decision tree model is used to prepare regional landslide susceptibility mapping (LSM) in the Three Gorges Reservoir area. The results show that landslide susceptibility is divided into four levels: low, moderate, high, and very high, with the boosting-C5.0 model performing the best. This study demonstrates the feasibility of machine learning in landslide susceptibility assessment and provides a basis for risk management and control of geological disasters.
STOCHASTIC ENVIRONMENTAL RESEARCH AND RISK ASSESSMENT
(2023)
Article
Environmental Sciences
Junying Cheng, Xiaoai Dai, Zekun Wang, Jingzhong Li, Ge Qu, Weile Li, Jinxing She, Youlin Wang
Summary: This study analyzed the landslide susceptibility in the Three Gorges Reservoir region of the Yangtze River using machine learning models. The results identified five categories of influencing factors and showed that SVM model performed the best in terms of generalization ability and robustness, making it suitable for real-time assessment of regional landslide susceptibility.
Article
Geosciences, Multidisciplinary
Junwei Ma, Dongze Lei, Zhiyuan Ren, Chunhai Tan, Ding Xia, Haixiang Guo
Summary: This study adopts automated machine learning (AutoML) technique for landslide susceptibility mapping (LSM) in the Three Gorges Reservoir area, achieving good performance and assisting users in selecting the best model with minimal intervention.
MATHEMATICAL GEOSCIENCES
(2023)
Article
Environmental Sciences
Xiaojun Wu, Lunche Wang, Qian Cao, Zigeng Niu, Xin Dai
Summary: This study analyzed the long-term trend changes in temperature, precipitation, and humidity over the Three Gorges Reservoir Area (TGRA) using meteorological station data, remote sensing data, and reanalysis products. The results showed overall warming and drying trends in the TGRA, with significant impacts of land cover changes on climate changes. It was found that land cover changes had warming and drying effects on the middle and upper reaches, and cooling and moistening effects on the lower reaches of the TGRA.
SCIENCE OF THE TOTAL ENVIRONMENT
(2023)
Article
Geosciences, Multidisciplinary
Reda Sahrane, Ali Bounab, Younes EL Kharim
Summary: This research quantifies the impact of landslide inventory map (LIM) size variability on Landslide Susceptibility Mapping (LSM) results. In heterogeneous areas, LSM and Frequency Area Distribution (FAD) distributions are significantly impacted, while in homogenous areas, little variance is observed. Additionally, the choice of algorithm used in LSM preparation also influences susceptibility assessment results, with Logistic Regression (LR) being the most stable algorithm and Artificial Neural Networks (ANN) presenting the most sensitive model.
Article
Engineering, Environmental
Wenjuan Li, Zhice Fang, Yi Wang
Summary: This paper introduces a hybrid framework integrating stacking ensemble with convolutional neural network (CNN) and recurrent neural network (RNN) for landslide spatial prediction in the Three Gorges Reservoir area, China. Experimental results demonstrate that the proposed framework achieves the best predictive capability in terms of AUC compared to CNN, RNN, and logistic regression, which is significant for landslide disaster management and assessment.
STOCHASTIC ENVIRONMENTAL RESEARCH AND RISK ASSESSMENT
(2022)
Article
Engineering, Geological
Chao Zhou, Ying Cao, Kunlong Yin, Emanuele Intrieri, Filippo Catani, Lixing Wu
Summary: This study investigates the reservoir landslides in the Three Gorges area using long term in-situ monitoring, numerical simulation, and field investigation methods. The analysis reveals that different types of landslides exhibit distinct deformation patterns during water level fluctuations. Classification criteria for seepage-driven and buoyancy-driven landslides in the Three Gorges area are proposed based on cumulative displacement curves, sliding mass permeability, and sliding surface analysis.
ENGINEERING GEOLOGY
(2022)
Article
Engineering, Environmental
Xudong Hu, Cheng Huang, Hongbo Mei, Han Zhang
Summary: A novel machine learning ensemble model, BRSNBtree, was proposed to predict landslide susceptibility in Zigui County of the Three Gorges Reservoir Area. The results showed that the distance to rivers was the most important factor in predicting landslide susceptibility, and BRSNBtree outperformed other methods in terms of prediction performance.
BULLETIN OF ENGINEERING GEOLOGY AND THE ENVIRONMENT
(2021)
Article
Environmental Sciences
Shaojun Tan, Deti Xie, Jiupai Ni, Lei Chen, Chengsheng Ni, Wei Ye, Guangyao Zhao, Jingan Shao, Fangxin Chen
Summary: Although physical models have achieved important results in assessing non-point source pollution (NPSP), their application is limited due to the need for large volumes of data and accuracy. Constructing a scientific evaluation model of N and P output in NPSP is significant for identifying sources and preventing pollution. We constructed an input-migration-output (IMO) model based on the export coefficient model (ECM) and identified the main drivers of NPSP using geographical detector (GD) in Three Gorges Reservoir area (TGRA). The results showed that the improved model increased the prediction accuracy for total nitrogen (TN) and total phosphorus (TP) and had implications for NPSP prevention and control.
SCIENCE OF THE TOTAL ENVIRONMENT
(2023)
Article
Engineering, Environmental
Xuebing Wang, Luqi Wang, Wengang Zhang, Chunshan Zhang, Chengxuan Tan, Pei Yan, Zhihua Zhang, Jian Guo
Summary: This study developed a hybrid model based on factor optimization and support vector machines (SVM) to accurately evaluate ground fissure susceptibility (GFS). By establishing an evaluation index system, normalizing data samples, reducing dimensionality, and utilizing SVM modeling, the model achieved high prediction accuracy and produced a GFS map.
BULLETIN OF ENGINEERING GEOLOGY AND THE ENVIRONMENT
(2022)
Article
Environmental Sciences
Aiying Zhang, Zongqiang Xie
Summary: In the Three Gorges Reservoir Area in China, dam construction has led to a significant decrease in riparian plant diversity and an increase in alien species invasion. The proportion of C-4 plant species has also significantly increased, with these plants becoming dominant species in the RFA.
SCIENCE OF THE TOTAL ENVIRONMENT
(2021)
Article
Environmental Sciences
Zhenling Shen, Wanshun Zhang, Hong Peng, Gaohong Xu, Xiaomin Chen, Xiao Zhang, Yanxin Zhao
Summary: This study developed a town-scale nutrient budget framework and analyzed the spatial characteristics of nutrient budget in the Three Gorges Reservoir area in China. The results showed spatial correlation and consistency of total nitrogen and total phosphorus inputs and outputs. This spatial pattern was mainly influenced by population density, elevation, vegetation index, and soil erosion factor.
SCIENCE OF THE TOTAL ENVIRONMENT
(2022)
Article
Computer Science, Interdisciplinary Applications
Chao Zhou, Kunlong Yin, Ying Cao, Bayes Ahmed, Yuanyao Li, Filippo Catani, Hamid Reza Pourghasemi
COMPUTERS & GEOSCIENCES
(2018)
Article
Engineering, Geological
Xuguo Shi, Lu Zhang, Chao Zhou, Menghua Li, Mingsheng Liao
Article
Engineering, Geological
Chao Zhou, Kunlong Yin, Ying Cao, Emanuele Intrieri, Bayes Ahmed, Filippo Catani
Article
Multidisciplinary Sciences
Chao Zhou, Kunlong Yin, Ying Cao, Bayes Ahmed, Xiaolin Fu
SCIENTIFIC REPORTS
(2018)
Article
Chemistry, Analytical
Ying Cao, Kunlong Yin, Chao Zhou, Bayes Ahmed
Article
Environmental Sciences
Chao Zhou, Ying Cao, Kunlong Yin, Yang Wang, Xuguo Shi, Filippo Catani, Bayes Ahmed
Article
Chemistry, Multidisciplinary
Shuhao Liu, Samuele Segoni, Federico Raspini, Kunlong Yin, Chao Zhou, Yiyue Zhang, Nicola Casagli
APPLIED SCIENCES-BASEL
(2020)
Article
Environmental Sciences
Shuhao Liu, Kunlong Yin, Chao Zhou, Lei Gui, Xin Liang, Wei Lin, Binbin Zhao
Summary: This study compared different data-driven methods for landslide susceptibility assessment along power transmission network, using a case study from China. The findings showed that machine learning techniques are suitable for assessing landslide susceptibility along grid cell units of the power network, while multivariate statistical logistic regression methods perform better on heterogeneous slope terrain units with reduced unit count. High model predictive performances do not guarantee high plausibility and applicability of susceptibility maps generated.
Article
Environmental Sciences
Lanbing Yu, Chao Zhou, Yang Wang, Ying Cao, David J. Peres
Summary: This study aims to establish a novel procedure for landslide susceptibility mapping (LSM) in areas with limited availability of data. By combining knowledge-driven and data-driven models, the proposed approach improves the accuracy of landslide susceptibility assessment. Results show that the method allows identifying new landslide-prone areas and enhancing the predictive performance of LSM.
Article
Engineering, Geological
Chao Zhou, Ying Cao, Kunlong Yin, Emanuele Intrieri, Filippo Catani, Lixing Wu
Summary: This study investigates the reservoir landslides in the Three Gorges area using long term in-situ monitoring, numerical simulation, and field investigation methods. The analysis reveals that different types of landslides exhibit distinct deformation patterns during water level fluctuations. Classification criteria for seepage-driven and buoyancy-driven landslides in the Three Gorges area are proposed based on cumulative displacement curves, sliding mass permeability, and sliding surface analysis.
ENGINEERING GEOLOGY
(2022)
Article
Engineering, Geological
Chao Zhou, Ying Cao, Xie Hu, Kunlong Yin, Yue Wang, Filippo Catani
Summary: This study proposes a new method to obtain dynamic landslide hazard maps by utilizing ground deformation measured by SAR imagery. By combining spatial probability of landslide occurrence and temporal probability under different rainfall conditions, a preliminary hazard map is initialized. The final hazard map is determined by considering deformation velocities. The proposed method reduces false-negative and false-positive errors in landslide hazard mapping and provides higher accuracy.
Article
Environmental Sciences
Xingchen Zhang, Lixia Chen, Chao Zhou
Summary: Landslides along the Three Gorges Reservoir in China are a threat to coastal residents and waterway safety. This paper proposes an effective method for predicting the deformation trend of reservoir bank landslides to reduce false positive misjudgments. The Time-Series InSAR method and Sentinel-1A images from 2018 to 2022 were used for landslide deformation monitoring, and the Hurst index was calculated to characterize the deformation trend. The combination of Time-Series InSAR and the Hurst index can effectively monitor deformation and predict the stability trend of reservoir bank landslides.
Article
Chemistry, Multidisciplinary
Hongwei Jiang, Yuanyao Li, Chao Zhou, Haoyuan Hong, Thomas Glade, Kunlong Yin
APPLIED SCIENCES-BASEL
(2020)
Article
Geosciences, Multidisciplinary
Sheng Fu, Lixia Chen, Tsehaie Woldai, Kunlong Yin, Lei Gui, Deying Li, Juan Du, Chao Zhou, Yong Xu, Zhipeng Lian
NATURAL HAZARDS AND EARTH SYSTEM SCIENCES
(2020)
