A Novel Spatial Reaction-Diffusion Framework with Machine Learning-Enhanced Climate Parameters and a Weighted Spatial Risk Index for Optimal Budget-Constrained Resource Allocation in Vector Control Under Climate Change

Climate change is fundamentally reshaping the spatiotemporal dynamics of vector-borne diseases, challenging conventional control strategies. This study presents a novel methodological framework that integrates spatial reaction–diffusion modeling with machine learning–enhanced climate parameterization and a weighted spatial risk index to optimize budget-constrained vector control. The framework simulates vector population dynamics over heterogeneous spatial domains while dynamically adjusting climate-sensitive parameters using data-driven models. A weighted spatial risk index aggregates vector density, climate suitability, and exposure indicators, guiding spatial prioritization of interventions. Resource allocation is formulated as a constrained optimization problem, aiming to minimize cumulative risk under explicit budgetary limits. Numerical simulations demonstrate that climate-responsive parameters generate complex, shifting high-risk zones, accurately capturing nonlinear environmental influences on vector dynamics. Optimized interventions consistently outperform uniform strategies, efficiently concentrating resources in emerging high-risk areas and achieving significant risk reduction within budget constraints. The results highlight the synergistic benefits of combining mechanistic modeling, machine learning, and optimization, providing robust, adaptive, and interpretable decision-support tools for public health management. This approach offers a scalable and generalizable methodology for spatially explicit control of vector-borne diseases under evolving climatic conditions.