Hybrid SEIR Temporal Fusion Transformer Framework with SHAP Analysis for Interpretable Pandemic Forecasting
Abstract
Forecasting pandemic spread across heterogeneous regions demands models that are both accurate and interpretable for public health action. This paper proposes a hybrid forecasting framework that integrates an SEIR epidemiological model enhanced with a Temporal Fusion Transformer (TFT) to produce interpretable multi-horizon infection forecasts. Using region-wise COVID-19 data from the Our World in Data corpus, we present a unified pipeline that integrates epidemiological indicators (susceptible, exposed, infectious, recovered), intervention signals (masking, vaccination, policies), mobility covariates, and demographic context. The SEIR component estimates latent disease dynamics and injects mechanistic priors, while the TFT learns non-linear temporal dependencies and cross-feature interactions from historical observations and known future inputs. To ensure transparency, SHAP (SHapley Additive exPlanations) is applied at both global and local levels, quantifying feature contributions and revealing region-specific drivers of surges and slowdowns. Compared with a calibrated standalone SEIR baseline, the hybrid SEIR-TFT approach provides more stable and accurate forecasts across epidemic phases, particularly under shifting intervention regimes. The framework is further operationalized through structured prediction and explanation outputs for interactive dashboards, enabling time-series, policy-impact, and geospatial analysis. By unifying mechanistic modeling, deep temporal learning, and explainable AI, this study offers a practical decision-support system for policy-sensitive pandemic forecasting.
Related
- Probabilistic Deep Learning Framework for Phase Transformation Forecasting aided by In Situ High temperature Microscopy
- From Local Atomic Motifs to Thermodynamic State: An Interpretable Physics-Informed Framework for Cu-Zr Metallic Glasses
- A digital-twin framework for forecasting treatment-day imaging with contour uncertainty in adaptive proton radiotherapy
- Continuous vision transformer-based neural operator for scalable beam propagation modeling in optical fibers
- Variational study of the magnetization plateaus in the spin-1/2 kagome Heisenberg antiferromagnet: An approach from vision transformer neural quantum states
BibTeX
@misc{abraham2026hybrid,
title = {{Hybrid SEIR Temporal Fusion Transformer Framework with SHAP Analysis for Interpretable Pandemic Forecasting}},
author = {Ashish Anton Abraham and Gopi Krishnan R and Aiswarya Anil Nair and Ajo Babu George and Kunal Agarwal},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.31673},
eprint = {2610.31673},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.31673},
note = {CC BY-NC-SA 4.0},
}
RIS
TY - UNPB
TI - Hybrid SEIR Temporal Fusion Transformer Framework with SHAP Analysis for Interpretable Pandemic Forecasting
AU - Ashish Anton Abraham
AU - Gopi Krishnan R
AU - Aiswarya Anil Nair
AU - Ajo Babu George
AU - Kunal Agarwal
PY - 2026
DA - 2026/10/01
PB - arXiv
DO - 10.48550/arxiv.2610.31673
UR - https://arxiv.org/abs/2610.31673
AB - Forecasting pandemic spread across heterogeneous regions demands models that are both accurate and interpretable for public health action. This paper proposes a hybrid forecasting framework that integrates an SEIR epidemiological model enhanced with a Temporal Fusion Transformer (TFT) to produce interpretable multi-horizon infection forecasts. Using region-wise COVID-19 data from the Our World in Data corpus, we present a unified pipeline that integrates epidemiological indicators (susceptible, exposed, infectious, recovered), intervention signals (masking, vaccination, policies), mobility covariates, and demographic context. The SEIR component estimates latent disease dynamics and injects mechanistic priors, while the TFT learns non-linear temporal dependencies and cross-feature interactions from historical observations and known future inputs. To ensure transparency, SHAP (SHapley Additive exPlanations) is applied at both global and local levels, quantifying feature contributions and revealing region-specific drivers of surges and slowdowns. Compared with a calibrated standalone SEIR baseline, the hybrid SEIR-TFT approach provides more stable and accurate forecasts across epidemic phases, particularly under shifting intervention regimes. The framework is further operationalized through structured prediction and explanation outputs for interactive dashboards, enabling time-series, policy-impact, and geospatial analysis. By unifying mechanistic modeling, deep temporal learning, and explainable AI, this study offers a practical decision-support system for policy-sensitive pandemic forecasting.
ER -