Systematic Literature Review on the Application of Mathematics, Statistics, and Computer Science in Wildfire Analysis

Wildfires pose a significant threat to ecosystems, human settlements, and air quality, making accurate prediction and analysis crucial for disaster mitigation. Traditional statistical methods often struggle with the vast and complex nature of wildfire data, necessitating advanced mathematical, statistical, and computational approaches. This study presents a systematic literature review of wildfire analysis techniques, focusing on trends from 2000 to 2025. By analyzing 6,498 articles using the PRISMA framework, we identify the most widely applied methods, such as correlation, regression, classification, clustering, and artificial neural networks, while highlighting underutilized yet promising techniques such as copula, fuzzy inference, image recognition, quantile mapping, and empirical orthogonal function (EOF). The findings reveal an increasing shift toward interdisciplinary, data-driven approaches, with a significant increase in high-impact publications over the last decade. We emphasize the need for further exploration of advanced methodologies to enhance wildfire prediction models and improve decision-making in fire-prone regions. This review bridges computational innovations with environmental challenges, this study provides a roadmap for future research in wildfire analysis and management.