Status, advancements and prospects of deep learning methods applied in forest studies

International Journal of Applied Earth Observation and Geoinformation, Год журнала: 2024, Номер 131, С. 103938 - 103938

Опубликована: Июнь 4, 2024

Язык: Английский

---

Integrating geospatial, remote sensing, and machine learning for climate-induced forest fire susceptibility mapping in Similipal Tiger Reserve, India

Forest Ecology and Management, Год журнала: 2024, Номер 555, С. 121729 - 121729

Опубликована: Янв. 31, 2024

Accurately assessing forest fire susceptibility (FFS) in the Similipal Tiger Reserve (STR) is essential for biodiversity conservation, climate change mitigation, and community safety. Most existing studies have primarily focused on climatic topographical factors, while this research expands scope by employing a synergistic approach that integrates geographical information systems (GIS), remote sensing (RS), machine learning (ML) methodologies identifying fire-prone areas STR their vulnerability to change. To achieve this, study employed comprehensive dataset of forty-four influencing including topographic, climate-hydrologic, health, vegetation indices, radar features, anthropogenic interference, into ten ML models: neural net (nnet), AdaBag, Extreme Gradient Boosting (XGBTree), Machine (GBM), Random Forest (RF), its hybrid variants with differential evolution algorithm (RF-DEA), Gravitational Based Search (RF-GBS), Grey Wolf Optimization (RF-GWO), Particle Swarm (RF-PSO), genetic (RF-GA). The revealed high FFS both northern southern portions area, nnet RF-PSO models demonstrating percentages 12.44% 12.89%, respectively. Conversely, very low zones consistently displayed scores approximately 23.41% 18.57% models. robust mapping methodology was validated impressive AUROC (>0.88) kappa coefficient (>0.62) across all validation metrics. Future (ssp245 ssp585, 2022–2100) indicated along edges STR, central zone categorized from susceptibility. Boruta analysis identified actual evapotranspiration (AET) relative humidity as key factors ignition. SHAP evaluation reinforced influence these FFS, also highlighting significant role distance road, settlement, dNBR, slope, prediction accuracy. These results emphasize critical importance proposed provide invaluable insights firefighting teams, management, planning, qualification strategies address future sustainability.

Язык: Английский

---

Spatial analysis and machine learning prediction of forest fire susceptibility: a comprehensive approach for effective management and mitigation

The Science of The Total Environment, Год журнала: 2024, Номер 926, С. 171713 - 171713

Опубликована: Март 18, 2024

Язык: Английский

---

Coupling Machine and Deep Learning with Explainable Artificial Intelligence for Improving Prediction of Groundwater Quality and Decision-Making in Arid Region, Saudi Arabia

Water, Год журнала: 2023, Номер 15(12), С. 2298 - 2298

Опубликована: Июнь 20, 2023

Recently, machine learning (ML) and deep (DL) models based on artificial intelligence (AI) have emerged as fast reliable tools for predicting water quality index (WQI) in various regions worldwide. In this study, we propose a novel stacking framework DL WQI prediction, employing convolutional neural network (CNN) model. Additionally, introduce explainable AI (XAI) through XGBoost-based SHAP (SHapley Additive exPlanations) values to gain valuable insights that can enhance decision-making strategies management. Our findings demonstrate the model achieves highest accuracy prediction (R2: 0.99, MAPE: 15.99%), outperforming CNN 0.90, 58.97%). Although shows relatively high R2 value, other statistical measures indicate it is actually worst-performing among five tested. This discrepancy may be attributed limited training data available Furthermore, application of techniques, specifically values, allows us into extract information management purposes. The interaction plot reveal elevated levels total dissolved solids (TDS), zinc, electrical conductivity (EC) are primary drivers poor quality. These parameters exhibit nonlinear relationship with index, implying even minor increases their concentrations significantly impact Overall, study presents comprehensive integrated approach management, emphasizing need collaborative efforts all stakeholders mitigate pollution uphold By leveraging XAI, our proposed not only provides powerful tool accurate but also offers models, enabling informed strategies.

Язык: 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, 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

---

Comparison of diverse machine learning algorithms for forest fire susceptibility mapping in Antalya, Türkiye

Advances in Space Research, Год журнала: 2024, Номер 74(2), С. 647 - 667

Опубликована: Апрель 16, 2024

Язык: Английский

---

A New Approach Based on TensorFlow Deep Neural Networks with ADAM Optimizer and GIS for Spatial Prediction of Forest Fire Danger in Tropical Areas

Remote Sensing, Год журнала: 2023, Номер 15(14), С. 3458 - 3458

Опубликована: Июль 8, 2023

Frequent forest fires are causing severe harm to the natural environment, such as decreasing air quality and threatening different species; therefore, developing accurate prediction models for fire danger is vital mitigate these impacts. This research proposes evaluates a new modeling approach based on TensorFlow deep neural networks (TFDeepNN) geographic information systems (GIS) modeling. Herein, TFDeepNN was used create model, whereas adaptive moment estimation (ADAM) optimization algorithm optimize GIS with Python programming process, classify, code input output. The focused tropical forests of Phu Yen Province (Vietnam), which incorporates 306 historical locations from 2019 2023 ten forest-fire-driving factors. Random (RF), support vector machines (SVM), logistic regression (LR) were baseline model comparison. Different statistical metrics, F-score, accuracy, area under ROC curve (AUC), employed evaluate models’ predictive performance. According results, (with F-score 0.806, accuracy 79.3%, AUC 0.873) exhibits high performance surpasses three models: RF, SVM, LR; represents novel tool spatially predicting danger. map this study can be helpful policymakers authorities in Province, aiding sustainable land-use planning management.

Язык: Английский

---

Improving the prediction of wildfire susceptibility on Hawaiʻi Island, Hawaiʻi, using explainable hybrid machine learning models

Journal of Environmental Management, Год журнала: 2023, Номер 351, С. 119724 - 119724

Опубликована: Дек. 6, 2023

Язык: Английский

---

Optimized Machine Learning Model for Fire Consequence Prediction

Fire, Год журнала: 2024, Номер 7(4), С. 114 - 114

Опубликована: Апрель 1, 2024

This article focuses on using machine learning to predict the distance at which a chemical storage tank fire reaches specified thermal radiation intensity. DNV’s Process Hazard Analysis Software Tool (PHAST) is used simulate different scenarios of leakage and establish database accidents. Backpropagation (BP) neural networks, random forest models, optimized model K-R are for training consequence prediction. The regression performance models evaluated mean squared error (MSE) R2. results indicate that prediction outperforms other two algorithms, accurately predicting intensity reached after fire. Compared with simulation results, demonstrates higher accuracy in consequences, proving effectiveness algorithms range consequences area events.

Язык: Английский

---

Game-theoretic optimization of landslide susceptibility mapping: a comparative study between Bayesian-optimized basic neural network and new generation neural network models

Environmental Science and Pollution Research, Год журнала: 2024, Номер 31(20), С. 29811 - 29835

Опубликована: Апрель 9, 2024

Язык: Английский

---