Predicting Avian Influenza Outbreaks: Machine Learning and Neural Network approaches to anomalous mortality detection.

Avian Influenza (AI) represents a critical global challenge due to its rapid spread and severe consequences for both animal and public health. In Italy, recurring outbreaks of highly pathogenic avian influenza (HPAI) have led to significant economic losses in the poultry industry, highlighting the urgent need for effective monitoring and prevention strategies. Current surveillance systems primarily rely on retrospective analysis and reactive interventions, limiting the ability to predict outbreaks in a timely manner. This study aims to bridge this gap by leveraging Machine Learning (ML) and Neural Networks (NN) models to predict AI outbreaks based on epidemiological, environmental, and biosecurity data. A series of ML models, including One-Class SVM, Isolation Forest, Random Forest, XGBoost, and Neural Networks, were trained to identify anomalous mortality patterns potentially indicative of AI outbreak that can be considered as first step for enhancing early detection capabilities. Furthermore, this research proposes a structured framework for an integrated system that could be deployed in a real-time fashion to support veterinary authorities and farm operators in taking timely preventive actions.