SHAP-Driven Explainable Artificial Intelligence Framework for Wildfire Susceptibility Mapping Using MODIS Active Fire Pixels: An In-Depth Interpretation of Contributing Factors in Izmir, Türkiye

Remote Sensing, Journal Year: 2024, Volume and Issue: 16(15), P. 2842 - 2842

Published: Aug. 2, 2024

Wildfire susceptibility maps play a crucial role in preemptively identifying regions at risk of future fires and informing decisions related to wildfire management, thereby aiding mitigating the risks potential damage posed by wildfires. This study employs eXplainable Artificial Intelligence (XAI) techniques, particularly SHapley Additive exPlanations (SHAP), map Izmir Province, Türkiye. Incorporating fifteen conditioning factors spanning topography, climate, anthropogenic influences, vegetation characteristics, machine learning (ML) models (Random Forest, XGBoost, LightGBM) were used predict wildfire-prone areas using freely available active fire pixel data (MODIS Active Fire Collection 6 MCD14ML product). The evaluation trained ML showed that Random Forest (RF) model outperformed XGBoost LightGBM, achieving highest test accuracy (95.6%). All classifiers demonstrated strong predictive performance, but RF excelled sensitivity, specificity, precision, F-1 score, making it preferred for generating conducting SHAP analysis. Unlike prevailing approaches focusing solely on global feature importance, this fills critical gap employing summary dependence plots comprehensively assess each factor’s contribution, enhancing explainability reliability results. analysis reveals clear associations between such as wind speed, temperature, NDVI, slope, distance villages with increased susceptibility, while rainfall streams exhibit nuanced effects. spatial distribution classes highlights areas, flat coastal near settlements agricultural lands, emphasizing need enhanced awareness preventive measures. These insights inform targeted management strategies, highlighting importance tailored interventions like firebreaks management. However, challenges remain, including ensuring selected factors’ adequacy across diverse regions, addressing biases from resampling spatially varied data, refining broader applicability.

Language: Английский

---

Study on Carbon Emission Influencing Factors and Carbon Emission Reduction Potential in China's Food Production Industry

Environmental Research, Journal Year: 2024, Volume and Issue: 261, P. 119702 - 119702

Published: July 31, 2024

Language: Английский

---

Enhancing forest fire susceptibility mapping in Xichang City, China using DBSCAN-based non-fire point selection integrated with deep neural network

Geomatics Natural Hazards and Risk, Journal Year: 2025, Volume and Issue: 16(1)

Published: Jan. 2, 2025

Forest fire susceptibility mapping plays a crucial role in forest management and disaster prevention. However, existing research often neglects the selection of non-fire data during model construction, resulting limited prediction accuracy. To address this issue, we propose an innovative DBSCAN-DNN that optimizes to enhance precision. Using VIIRS GLC_FCS30D datasets, created spatial database for Xichang's dry seasons from 2012 2022, incorporating topography, meteorology, vegetation, human activities. Based on this, employed DBSCAN algorithm cluster points accurately delineated affected areas. Subsequently, selected samples outside these regions training DNN model. Through comparative experiments, found exhibited excellent performance predicting Xichang City, with AUC value 0.925 significant improvements accuracy (0.834), precision (0.800), recall (0.891), F1-score (0.843), Kappa coefficient (0.669). Additionally, conducted SHAP analysis delve into contributions interactions various factors influencing susceptibility. This finding offers valuable insights selecting sample

Language: Английский

---

PREDICTION OF FOREST FIRE SUSCEPTIBILITY USING MACHINE LEARNING TOOLS IN THE TRIUNFO DO XINGU ENVIRONMENTAL PROTECTION AREA, AMAZON, BRAZIL

Journal of South American Earth Sciences, Journal Year: 2025, Volume and Issue: unknown, P. 105366 - 105366

Published: Jan. 1, 2025

Language: Английский

---

Nepal's carbon stock and biodiversity are under threat from climate change exacerbated forest fires

Published: Feb. 1, 2025

Language: Английский

---

Assessment of forest fire vulnerability prediction in Indonesia: Seasonal variability analysis using machine learning techniques

International Journal of Applied Earth Observation and Geoinformation, Journal Year: 2025, Volume and Issue: 138, P. 104435 - 104435

Published: Feb. 28, 2025

Language: Английский

---

Global lightning-ignited wildfires prediction and climate change projections based on explainable machine learning models

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: March 6, 2025

Wildfires pose a significant natural disaster risk to populations and contribute accelerated climate change. As wildfires are also affected by change, extreme becoming increasingly frequent. Although they occur less frequently globally than those sparked human activities, lightning-ignited play substantial role in carbon emissions account for the majority of burned areas certain regions. While existing computational models, especially based on machine learning, aim predict wildfires, typically tailored specific regions with unique characteristics, limiting their global applicability. In this study, we present learning models designed characterize scale. Our approach involves classifying versus anthropogenic estimating high accuracy probability lightning ignite fire wide spectrum factors such as meteorological conditions vegetation. Utilizing these analyze seasonal spatial trends shedding light impact change phenomenon. We influence various features using eXplainable Artificial Intelligence (XAI) frameworks. findings highlight differences between wildfires. Moreover, demonstrate that, even over short time span decade, changes have steadily increased This distinction underscores imperative need dedicated predictive weather indices specifically each type wildfire.

Language: Английский

---

Machine Learning-Based Wildfire Susceptibility Mapping: A Gis-Integrated Predictive Framework

Published: Jan. 1, 2025

Language: Английский

---

A Comprehensive Review of Empirical and Dynamic Wildfire Simulators and Machine Learning Techniques used for the Prediction of Wildfire in Australia

Technology Knowledge and Learning, Journal Year: 2025, Volume and Issue: unknown

Published: April 2, 2025

Language: Английский

---

Advanced 3D abrasion mapping in sediment bypass tunnels using XGBoost: A high-dimensional approach to predictive modeling

Expert Systems with Applications, Journal Year: 2025, Volume and Issue: unknown, P. 127686 - 127686

Published: April 1, 2025

Language: Английский

---