Résumé:
Dynamic systems play a crucial role in various fields, including meteorology, finance, and
technology, and are characterized by their complexity and interdependencies. Traditional
modeling and prediction methods often struggle to capture the intricate behaviors and
evolving patterns of these systems, leading to suboptimal control and prediction outcomes.
Forest fires are a prime example of dynamic systems, where interactions among meteorological conditions, fuel types, and topography result in unpredictable and nonlinear fire
spread patterns. This issue is particularly critical in regions like Algeria, where recent
forest fires have caused significant damage, underscoring the need for advanced predictive
and management tools.
This work aims to study dynamic systems and propose an intelligent and adaptive model
for dynamic forest fire prediction using Deep Neural Networks (DNN) and Cellular Automata (CA). The primary advantage of this system lies in its ability to accurately predict
fire ignition points based on meteorological and environmental data and to simulate fire
spread across various landscapes with greater precision. This dual-method approach enhances detection and simulation accuracy, reduces response times for authorities, and
improves wildfire containment and mitigation efforts
