Explainable artificial intelligence in disaster risk management: Achievements and prospective futures

International Journal of Disaster Risk Reduction, Journal Year: 2023, Volume and Issue: 98, P. 104123 - 104123

Published: Nov. 1, 2023

Disasters can have devastating impacts on communities and economies, underscoring the urgent need for effective strategic disaster risk management (DRM). Although Artificial Intelligence (AI) holds potential to enhance DRM through improved decision-making processes, its inherent complexity "black box" nature led a growing demand Explainable AI (XAI) techniques. These techniques facilitate interpretation understanding of decisions made by models, promoting transparency trust. However, current state XAI applications in DRM, their achievements, challenges they face remain underexplored. In this systematic literature review, we delve into burgeoning domain XAI-DRM, extracting 195 publications from Scopus ISI Web Knowledge databases, selecting 68 detailed analysis based predefined exclusion criteria. Our study addresses pertinent research questions, identifies various hazard types, components, methods, uncovers limitations these approaches, provides synthesized insights explainability effectiveness decision-making. Notably, observed significant increase use 2022 2023, emphasizing interpretability. Through rigorous methodology, offer key directions that serve as guide future studies. recommendations highlight importance multi-hazard analysis, integration early warning systems digital twins, incorporation causal inference methods strategy planning effectiveness. This serves beacon researchers practitioners alike, illuminating intricate interplay between revealing profound solutions revolutionizing management.

Language: Английский

---

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, Journal Year: 2024, Volume and Issue: 35, P. 103655 - 103655

Published: May 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.

Language: Английский

---

An Accurate Approach for Predicting Soil Quality Based on Machine Learning in Drylands

Agriculture, Journal Year: 2024, Volume and Issue: 14(4), P. 627 - 627

Published: April 18, 2024

Nowadays, machine learning (ML) is a useful technology due to its high accuracy in constructing non-linear models and algorithms that can adapt the complexity diversity of data. Thus, current work aimed predict soil quality index (SQI) from extensive data, achieving with artificial neural networks (ANN) model. However, efficiency ANN depends on data prepared for training. For this purpose, MATLAB programming language was used enable calculation, classification, compilation results into databases within few minutes. The proposed program highly efficient, accurate, quick calculating big training compared traditional methods. database contains 306 vector sets, 80% them are remaining 20% reserved testing. optimal model obtained comprises one hidden layer 250 neurons output sigmoid function. achieved coefficient determination (R2) values SQI estimation, around 0.97 0.98 testing, respectively. indicate 36.93% total samples belonged very class (C1). In contrast, (C2), moderate (C3), low (C4), (C5) classes accounted 10.46%, 31.37%, 20.92%, 0.33% samples, contents CaCO3, pH, sodium saturation, salinity, clay content were identified as limiting factors certain areas. study indicated assessment using physical, chemical, fertility features regression analysis ANN. This method, which suitable arid zones, enhances agricultural productivity decision-making by identifying critical categories constraints.

Language: Английский

---

Quantifying soil erosion and influential factors in Guwahati's urban watershed using statistical analysis, machine and deep learning

Remote Sensing Applications Society and Environment, Journal Year: 2023, Volume and Issue: 33, P. 101088 - 101088

Published: Nov. 10, 2023

Language: Английский

---

Erosivity density as an indicator of soil erosion risk in South Asia

CATENA, Journal Year: 2025, Volume and Issue: 251, P. 108766 - 108766

Published: Feb. 11, 2025

Language: Английский

---

Estimation of soil erodibility in Peninsular Malaysia: A case study using multiple linear regression and artificial neural networks

Heliyon, Journal Year: 2024, Volume and Issue: 10(7), P. e28854 - e28854

Published: March 29, 2024

Soil erodibility (K) is an essential component in estimating soil loss indicating the soil's susceptibility to detach and transport. Data Computing processing methods, such as artificial neural networks (ANNs) multiple linear regression (MLR), have proven be helpful development of predictive models for natural hazards. The present case study aims assess efficiency MLR ANN forecast Peninsular Malaysia. A total 103 samples were collected from various sites K values calculated using Tew equation developed Malaysian soil. From several extracted parameters, outcomes correlation principal analysis (PCA) revealed influencing factors used models. Based on PCA results, two sets employed develop Two (MLR-1 MLR-2) four (NN-1, NN-2, NN-3, NN-4) optimized Levenberg-Marquardt (LM) scaled conjugate gradient (SCG) evaluated. model performance validation was conducted coefficient determination (R2), mean squared error (MSE), root (RMSE), Nash-Sutcliffe (NSE). showed that outperformed R2 0.446 (MLR-1), 0.430 (MLR-2), 0.894 (NN-1), 0.855 (NN-2), 0.940 (NN-3), 0.826 (NN-4); MSE 0.0000306 0.0000315 0.0000158 0.0000261 0.0000318 0.0000216 (NN-4) suggested higher accuracy lower modelling compared with MLR. This could provide empirical basis methodological support factor estimation region.

Language: Английский

---

Hydrolytic and soil degradation of cellulosic material (paper): optimization of parameters using ANN and RSM

Polymer Bulletin, Journal Year: 2024, Volume and Issue: 81(14), P. 12893 - 12920

Published: May 26, 2024

Language: Английский

---

Review of multihazards research with the basis of soil erosion

Elsevier eBooks, Journal Year: 2024, Volume and Issue: unknown, P. 295 - 306

Published: Jan. 1, 2024

Language: Английский

---

Integrating Explainable Artificial Intelligence and Machine Learning for Understanding Water Pollution and Its Management

Published: Jan. 1, 2024

Language: Английский

---

Financial Analytics with Artificial Neural Networks: Predicting Loan Repayment

Published: Oct. 3, 2024

Language: Английский

---