# Augmented data and neural networks for robust epidemic forecasting: application to COVID-19 in Italy

arXiv: https://arxiv.org/abs/2510.09192 · HTML: https://mlsanity.com/paper/2510.09192/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 43 references that are in the map.
- First posted on arXiv 10 Oct 2025.

## Builds on (most cited first, 10 of 10)

- [Numerical analysis of physics-informed neural networks and related models in physics-informed machine learning](https://mlsanity.com/paper/2402.10926/) (2024)
- [Asymptotic-Preserving Neural Networks for multiscale hyperbolic models of epidemic spread](https://mlsanity.com/paper/2206.12625/) (2022)
- [Approaching epidemiological dynamics of COVID-19 with physics-informed neural networks](https://mlsanity.com/paper/2302.08796/) (2023)
- [A Statistical-Modelling Approach to Feedforward Neural Network Model Selection](https://mlsanity.com/paper/2207.04248/) (2022)
- [A Recurrent Neural Network and Differential Equation Based Spatiotemporal Infectious Disease Model with Application to COVID-19](https://mlsanity.com/paper/2007.10929/) (2020)
- [Kinetic modelling of epidemic dynamics: social contacts, control with uncertain data, and multiscale spatial dynamics](https://mlsanity.com/paper/2110.00293/) (2021)
- [Bifidelity data-assisted neural networks in nonintrusive reduced-order modeling](https://mlsanity.com/paper/1902.00148/) (2019)
- [Control with uncertain data of socially structured compartmental epidemic models](https://mlsanity.com/paper/2004.13067/) (2020)
- [Modelling lockdown measures in epidemic outbreaks using selective socio-economic containment with uncertainty](https://mlsanity.com/paper/2106.05122/) (2021)
- [A data augmentation strategy for deep neural networks with application to epidemic modelling](https://mlsanity.com/paper/2502.21033/) (2025)

## Built on by (most cited first, 1 of 1)

- [Discovery of interaction and diffusion kernels in particle-to-mean-field multi-agent systems](https://mlsanity.com/paper/2603.15927/) (2026)

## Abstract (arXiv)

In this work, we propose a data augmentation strategy aimed at improving the training phase of neural networks and, consequently, the accuracy of their predictions. Our approach relies on generating synthetic data through a suitable compartmental model combined with the incorporation of uncertainty. The available data are then used to calibrate the model, which is further integrated with deep learning techniques to produce additional synthetic data for training. The results show that neural networks trained on these augmented datasets exhibit significantly improved predictive performance. We focus in particular on two different neural network architectures: Physics-Informed Neural Networks (PINNs) and Nonlinear Autoregressive (NAR) models. The NAR approach proves especially effective for short-term forecasting, providing accurate quantitative estimates by directly learning the dynamics from data and avoiding the additional computational cost of embedding physical constraints into the training. In contrast, PINNs yield less accurate quantitative predictions but capture the qualitative long-term behavior of the system, making them more suitable for exploring broader dynamical trends. Numerical simulations of the second phase of the COVID-19 pandemic in the Lombardy region (Italy) validate the effectiveness of the proposed approach.