PRRS Outbreak Prediction via Deep Switching Auto-Regressive Factorization Modeling

TL;DR

This paper introduces a deep generative model that predicts PRRS virus outbreaks in swine farms by capturing complex spatio-temporal infection dynamics, achieving accurate forecasts with low error.

Contribution

The paper presents a novel hierarchical factorized deep generative model for high-dimensional epidemic time series prediction in livestock, integrating intra- and inter-farm transmission data.

Findings

Achieved average NRMSE of 2.5% in outbreak prediction

Successfully modeled intra- and inter-farm transmission dynamics

Demonstrated effective epidemic forecasting in swine industry

Abstract

We propose an epidemic analysis framework for the outbreak prediction in the livestock industry, focusing on the study of the most costly and viral infectious disease in the swine industry -- the PRRS virus. Using this framework, we can predict the PRRS outbreak in all farms of a swine production system by capturing the spatio-temporal dynamics of infection transmission based on the intra-farm pig-level virus transmission dynamics, and inter-farm pig shipment network. We simulate a PRRS infection epidemic based on the shipment network and the SEIR epidemic model using the statistics extracted from real data provided by the swine industry. We develop a hierarchical factorized deep generative model that approximates high dimensional data by a product between time-dependent weights and spatially dependent low dimensional factors to perform per farm time series prediction. The prediction results demonstrate the ability of the model in forecasting the virus spread progression with average error of NRMSE = 2.5\%.