A physics-informed machine learning solution for landslide susceptibility mapping based on three-dimensional slope stability evaluation

Journal of Central South University, Год журнала: 2024, Номер unknown

Опубликована: Авг. 5, 2024

Язык: Английский

---

Integrating a multi-dimensional deep convolutional neural network with optimized sample selection for landslide susceptibility assessment

Geo-spatial Information Science, Год журнала: 2025, Номер unknown, С. 1 - 21

Опубликована: Янв. 17, 2025

To address the errors of negative samples in landslide susceptibility modeling and traditional methods exploring regularities hidden evaluation factors, this paper proposes a stacking one- three-dimensional Convolutional Neural Network (Stacking-1D-3D-CNN) assessment method considering sample optimization selection. First, order to select rationally, adopts Relative Frequency Ratio combined with Certainty Factor Method (RFR-CFM) determine samples; secondly, Stacking-1D-3D-CNN proposed is RFR-CFM for first time assessment. In work, determined by Information Quality Model (IQM) were historical disaster points form total sample, modeled at different ratios. Finally, it compared several other models terms hazard zoning results, prone zone statistics, model performance. The findings show that degree spatial aggregation training testing has much greater impact on accuracy than their proportions. Furthermore, models, RFR-CFM-Stacking-1D-3D-CNN highest AUC value, precision, recall, F-score, accuracy, which are 0.95, 0.83, 0.89, 0.85, 84.76%, respectively, lowest RMSE MAE, 0.39 0.15, respectively. This proves selection method's rationality model's effectiveness.

Язык: Английский

---

Spatiotemporal variation and driving factors of vegetation net primary productivity in the Guanzhong Plain Urban Agglomeration, China from 2001 to 2020

Journal of Arid Land, Год журнала: 2025, Номер 17(1), С. 74 - 92

Опубликована: Янв. 1, 2025

Язык: Английский

---

Population amount risk assessment of extreme precipitation-induced landslides based on integrated machine learning model and scenario simulation

Geoscience Frontiers, Год журнала: 2023, Номер 14(3), С. 101541 - 101541

Опубликована: Янв. 18, 2023

In this study, the future landslide population amount risk (LPAR) is assessed based on integrated machine learning models (MLMs) and scenario simulation techniques in Shuicheng County, China. Firstly, multiple MLMs were selected hyperparameters optimized, generated 11 cross-integrated to select best model calculate susceptibility; by calculating precipitation for different extreme recurrence periods combining susceptibility results assess hazard. Using town as basic unit, exposure vulnerability of under Shared Socioeconomic Pathways (SSPs) scenarios each assessed, then combined with hazard estimate LPAR 2050. The showed that optimized random forest combination strategy had comprehensive performance assessment. distribution classes similar susceptibility, an increase precipitation, low-hazard area high-hazard decrease shift medium-hazard very classes. high-risk areas populations County are mainly concentrated three southwestern towns high vulnerability, whereas northern Baohua Qinglin at lowest class. increased intensity precipitation. differs significantly among SSPs scenarios, "fossil-fueled development (SSP5)" highest "regional rivalry (SSP3)" scenario. summary, proposed study has a predictive capability. assessment can provide theoretical guidance relevant departments cope socioeconomic challenges make corresponding disaster prevention mitigation plans prevent risks from developmental perspective.

Язык: Английский

---

Exploring the decision-making process of ensemble learning algorithms in landslide susceptibility mapping: Insights from local and global explainable AI analyses

Advances in Space Research, Год журнала: 2024, Номер 74(8), С. 3765 - 3785

Опубликована: Июль 6, 2024

Язык: Английский

---