Exploring forest fire susceptibility and management strategies in Western Himalaya: Integrating ensemble machine learning and explainable AI for accurate prediction and comprehensive analysis

Environmental Technology & Innovation, Год журнала: 2024, Номер 35, С. 103655 - 103655

Опубликована: Май 5, 2024

Forest fires pose a significant threat to ecosystems and socio-economic activities, necessitating the development of accurate predictive models for effective management mitigation. In this study, we present novel machine learning approach combined with Explainable Artificial Intelligence (XAI) techniques predict forest fire susceptibility in Nainital district. Our innovative methodology integrates several robust — AdaBoost, Gradient Boosting Machine (GBM), XGBoost Random Deep Neural Network (DNN) as meta-model stacking framework. This not only utilises individual strengths these models, but also improves overall prediction performance reliability. By using XAI techniques, particular SHAP (SHapley Additive exPlanations) LIME (Local Interpretable Model-agnostic Explanations), improve interpretability provide insights into decision-making processes. results show effectiveness ensemble model categorising different zones: very low, moderate, high high. particular, identified extensive areas susceptibility, precision, recall F1 values underpinning their effectiveness. These achieved ROC AUC above 0.90, performing exceptionally well an 0.94. The are remarkably inclusion confidence intervals most important metrics all emphasises robustness reliability supports practical use management. Through summary plots, analyze global variable importance, revealing annual rainfall Evapotranspiration (ET) key factors influencing susceptibility. Local analysis consistently highlights importance rainfall, ET, distance from roads across models. study fills research gap by providing comprehensive interpretable modelling that our ability effectively manage risk is consistent environmental protection sustainable goals.

Язык: Английский

---

Landslide susceptibility modeling using bivariate statistical-based logistic regression, naïve Bayes, and alternating decision tree models

Bulletin of Engineering Geology and the Environment, Год журнала: 2023, Номер 82(5)

Опубликована: Апрель 26, 2023

Язык: Английский

---

Landslide susceptibility assessment through TrAdaBoost transfer learning models using two landslide inventories

CATENA, Год журнала: 2022, Номер 222, С. 106799 - 106799

Опубликована: Ноя. 30, 2022

Язык: Английский

---

Effects of the probability of pulse-like ground motions on landslide susceptibility assessment in near-fault areas

Journal of Mountain Science, Год журнала: 2023, Номер 20(1), С. 31 - 48

Опубликована: Янв. 1, 2023

Язык: Английский

---

Research on the influence of different sampling resolution and spatial resolution in sampling strategy on landslide susceptibility mapping results

Scientific Reports, Год журнала: 2024, Номер 14(1)

Опубликована: Янв. 18, 2024

Abstract Landslides, recognized as a significant global natural disaster, necessitate an exploration of the impact various resolution types in sampling strategies on Landslide Susceptibility Mapping (LSM) results. This study focuses segment from Zigui to Badong within Three Gorges Reservoir Area, utilizing two types: and spatial resolution, The Support Vector Machine (SVM) is employed obtain LSM results, which are then analyzed using Receiver Operating Characteristic (ROC) curve, specific category accuracy statistical methods. Artificial Neural Network (ANN) Convolutional (CNN) were used verify reliability Additionally, five common machine learning models, including Logistic Regression (LR), conduct experiments four resolutions (10 m,30 m,50 m 70 m) further investigate effect These evaluated comprehensive quantitative method. results reveal that increasing improves prediction accuracy, while produces contrary effect. Furthermore, more pronounced than resolution. Finally, Fanjiaping landslide Huangtupo selected references for comparative analysis, with aligning engineering reality.

Язык: Английский

---

Risk assessment of nitrate groundwater contamination using GIS-based machine learning methods: A case study in the northern Anhui plain, China

Journal of Contaminant Hydrology, Год журнала: 2024, Номер 261, С. 104300 - 104300

Опубликована: Янв. 18, 2024

Язык: Английский

---

Landslide susceptibility mapping and sensitivity analysis using various machine learning models: a case study of Beas valley, Indian Himalaya

Bulletin of Engineering Geology and the Environment, Год журнала: 2024, Номер 83(6)

Опубликована: Май 13, 2024

Язык: Английский

---

A robust discretization method of factor screening for landslide susceptibility mapping using convolution neural network, random forest, and logistic regression models

International Journal of Digital Earth, Год журнала: 2023, Номер 16(1), С. 408 - 429

Опубликована: Фев. 27, 2023

The selection of discretization criteria and interval numbers landslide-related environmental factors generally fails to quantitatively determine or filter, resulting in uncertainties limitations the performance machine learning (ML) methods for landslide susceptibility mapping (LSM). aim this study is propose a robust criterion (RDC) quantify explore uncertainty subjectivity different methods. RDC consists two steps: raw classification dataset generation optimal extraction. To evaluate robustness proposed method, Lushan County Sichuan Province China was chosen as area generate LSM based on three datasets (optimal dataset, original with continuous values, statistical dataset) using popular ML methods, namely, convolution neural network, random forest, logistic regression. results show that areas under receiver operating characteristic curve (AUCs) abovementioned models are 0.963, 0.961, 0.930 which higher than those (0.938, 0.947, 0.900) (0.948, 0.954, 0.897). In conclusion, method can extract more representative features from outperform other conventional

Язык: Английский

---

Sustainable flood risk assessment using deep learning-based algorithms with a blockchain technology

Geocarto International, Год журнала: 2022, Номер 38(1), С. 1 - 29

Опубликована: Авг. 19, 2022

Formulae display:?Mathematical formulae have been encoded as MathML and are displayed in this HTML version using MathJax order to improve their display. Uncheck the box turn off. This feature requires Javascript. Click on a formula zoom.

Язык: Английский

---

Landslide susceptibility assessment using triangular fuzzy number-analytic hierarchy processing (TFN-AHP), contributing weight (CW) and random forest weighted frequency ratio (RF weighted FR) at the Pengyang county, Northwest China

Environmental Earth Sciences, Год журнала: 2022, Номер 81(3)

Опубликована: Янв. 29, 2022

Язык: Английский

---