Temporal Analysis of Infectious Diseases

Infectious diseases have presented unprece-dented challenges worldwide, highlighting the critical need for accurate and timely forecasting of infection rates to guide public health interventions. From sophisticated mathematical models to data-driven machine learning techniques, researchers have been striving to enhance the accuracy and robustness of predictive models. Additionally, the integration of real-time data streams, such as mobility patterns, has further enriched the predictive capabilities of these models. In this paper, we propose a novel approach to predict infectious disease rates using Next-Generation Reservoir Computing (NGRC), Leveraging the temporal dynamics of high-dimensional reservoir states, NGRC offers a flexible and efficient framework for modeling complex nonlinear dynamics, making it well-suited for capturing the intricate spread of infectious diseases. We employ an NGRC model trained on data generated from a modified SEIRS compartmental model, which provides insights into the underlying epidemiological dy-namics. Initial evaluations demonstrate the model's efficacy in accurately forecasting infection trends for the first few weeks. Moving forward, we aim to enhance the model's per-formance by incorporating real-world data obtained from recorded infection rates. By iteratively refining the model's training dataset, we anticipate improving its predictive capabilities and ensuring its effectiveness in forecasting infectious disease dynamics over extended time frames.