Spatiotemporal dynamics of Bacillus anthracis under climate change: a machine learning approach

This study examines the spatiotemporal dynamics of <i>Bacillus anthracis</i>, the causative agent of anthrax, under climate change scenarios using advanced machine learning techniques. Climate change is increasingly recognized as a critical factor influencing the distribution and transmission dynamics of infectious diseases, particularly those reliant on environmental reservoirs. Our research employs Maximum Entropy (Maxent) modeling to forecast the current global distribution of <i>B. anthracis</i> based on climatic factors and to predict future habitat suitability under various Coupled Model Intercomparison Project Phase 5 (CMIP5) scenarios (RCP-2.6 and RCP-8.5) for the 2050's and 2070's. We identify high-risk areas where climate change may enhance the suitability for <i>B. anthracis</i>, emphasizing the need for proactive monitoring and early-warning systems. The findings indicate potential shifts in anthrax-endemic zones, with new regions becoming conducive to the establishment of <i>B. anthracis</i> due to the changing climate. Our results demonstrate the applicability of machine learning in predicting disease risk, providing a framework for public health preparedness in light of evolving environmental challenges. These insights are critical for developing targeted surveillance strategies and mitigating the introduction of zoonotic diseases in a warming environment.