Predicting the Spatial Distribution of Geological Hazards in Southern Sichuan, China, Using Machine Learning and ArcGIS

Land, Год журнала: 2025, Номер 14(3), С. 577 - 577

Опубликована: Март 10, 2025

Geological hazards in Southern Sichuan have become increasingly frequent, posing severe risks to local communities and infrastructure. This study aims predict the spatial distribution of potential geological using machine learning models ArcGIS-based analysis. A dataset comprising 2700 known hazard locations Yibin City was analyzed extract key environmental topographic features influencing susceptibility. Several were evaluated, including random forest, XGBoost, CatBoost, with model optimization performed Sparrow Search Algorithm (SSA) enhance prediction accuracy. produced high-resolution susceptibility maps identifying high-risk zones, revealing a distinct pattern characterized by concentration mountainous areas such as Pingshan County, Junlian Gong while plains exhibited relatively lower risk. Among different types, landslides found be most prevalent. The results further indicate strong overlap between predicted zones existing rural settlements, highlighting challenges resilience these areas. research provides refined methodological framework for integrating geospatial analysis prediction. findings offer valuable insights land use planning mitigation strategies, emphasizing necessity adopting “small aggregations multi-point placement” approach settlement Sichuan’s regions.

Язык: Английский

---

Multi-scenario landslide probabilistic hazard analysis based on a single rainfall event: A case of the Zhuzhou-Guangzhou section of Beijing-Guangzhou railway in China

Research Square (Research Square), Год журнала: 2025, Номер unknown

Опубликована: Март 10, 2025

This study calculates the absolute probability of landslides under varying rainfall scenarios along Beijing-Guangzhou Railway from Zhuzhou to Guangzhou, aiming enhance railway transportation safety. Using a Bayesian sampling strategy, Logistic Regression (LR) model was developed for landslide hazard assessment based on geological conditions and data railway. The demonstrated strong predictive performance with an AUC value 0.86 both training testing sets, showing no overfitting. Results indicated that when is less than 150 mm, over 70% area has below 0.1%. However, exceeding hazards increase significantly, rapid rise in areas where ranges 0.1–1%. When reaches 500 about 60% region exhibits 1%. Under real (e.g., cumulative during 10 days before June 7, 2020), probabilities greater 1% are mainly concentrated Fogang County, northeast eastern Zhuzhou, aligning heavy distributions. relationship between occurrence highly non-linear, increasing exponentially as rises. These results provide effective tool offer valuable support disaster warning prevention measures.

Язык: Английский

---

Comparative Study on the Effectiveness of Landslide Susceptibility Assessment Based on Different Evaluation Units and Models

Geological Journal, Год журнала: 2025, Номер unknown

Опубликована: Март 23, 2025

ABSTRACT To investigate the evaluation performance of different models across various units, 174 landslide samples were selected from Xide County, Sichuan Province, China, as study area, considering 12 conditioning factors such aspect, slope and elevation. Using software tools ArcGIS SPSS, susceptibility in area was assessed units (12.5 30 m grid units). Four employed for this evaluation: information value model (IV), logistic regression (LR), value–logistic coupled (IV‐LR) decision tree (DT). The accuracy analysed using rationality testing ROC curves. results indicate that, within same model, assessment 12.5 unit surpasses that other two with an average AUC 0.849. Under unit, IV‐LR consistently demonstrated strong all achieving highest 0.881 unit.

Язык: Английский

---

Increasing Landslide Susceptibility in Urbanized Areas of Petrópolis Identified Through Spatio-Temporal Analysis

Journal of South American Earth Sciences, Год журнала: 2025, Номер unknown, С. 105509 - 105509

Опубликована: Апрель 1, 2025

Язык: Английский

---

Machine Learning Algorithms to Study the Impact of Sustainability on Financial Success: Evidence from US Stock Market

Contributions to finance and accounting, Год журнала: 2025, Номер unknown, С. 119 - 134

Опубликована: Янв. 1, 2025

Язык: Английский

---

Least cost path analysis for alternative road network assessment of landslide-prone NH-2, Mizoram, NE India

Geocarto International, Год журнала: 2025, Номер 40(1)

Опубликована: Апрель 25, 2025

Язык: Английский

---

Landslide-induced vulnerability of road networks in Lahaul and Spiti, India: a geospatial study

Bulletin of Engineering Geology and the Environment, Год журнала: 2025, Номер 84(6)

Опубликована: Май 24, 2025

Язык: Английский

---