FDN: Interpretable Spatiotemporal Forecasting with Future Decomposition Networks

Nicholas Majeske; Ariful Azad

cs.LGJun 23, 2026

FDN: Interpretable Spatiotemporal Forecasting with Future Decomposition Networks

Authors: Nicholas Majeske, Ariful Azad

Organizations: Department of Intelligent Systems Engineering, Indiana University Bloomington, USA · Department of Computer Science and Engineering, Texas A&M University, USA

Abstract

Spatiotemporal systems comprise a collection of spatially distributed yet interdependent entities each generating unique dynamic signals. Highly sophisticated methods have been proposed in recent years delivering state-of-the-art (SOTA) forecasts but few have focused on interpretability. To address this, we propose the Future Decomposition Network (FDN), a novel forecast model capable of (a) providing interpretable predictions through classification (b) revealing latent activity patterns in the target time-series and (c) delivering forecasts competitive with SOTA methods at a fraction of their memory and runtime cost. We conduct comprehensive analyses on FDN for multiple datasets from hydrologic, traffic, and energy systems, demonstrating its improved accuracy and interpretability.

Explore similar work

Information Bottleneck Learning for Faithful Time Series Forecasting Explanations
Jul 30, 2026Xu Zheng, Wei Cheng, Zhuomin Chen +3Multivariate Forecasting Load Forecasting
TSNN: A Non-parametric and Interpretable Framework for Traffic Time Series Forecasting
May 9, 2026Bowen Liu, Haijian Lai, Chan-Tong Lam +4Accurate Traffic Forecasting Multivariate Forecasting
SPaRSe-TIME: Saliency-Projected Low-Rank Temporal Modeling for Efficient and Interpretable Time Series Prediction
Apr 19, 2026K. A. ShahriarTime Series Temporal Deep Learning Framework

Jul 30, 2026 · cs.LGJ/K move · Enter open · S save

Information Bottleneck Learning for Faithful Time Series Forecasting Explanations

Xu Zheng, Wei Cheng, Zhuomin Chen, Mo Sha+2

Florida International University, Miami, FL, USA · NEC Laboratories America, Princeton, NJ, USA · University of Houston, Houston, TX, USA · Singapore Management University, Singapore

As forecasts increasingly drive decisions in fields such as energy, transportation, and healthcare, understanding the historical data behind these predictions has become as crucial as the predictions themselves. Although existing interpretable-by-design forecasters reveal their internal structures, they offer no guarantee that these structures faithfully reflect the underlying evidence driving the predictions. In contrast, while faithfulness-oriented methods explicitly verify model behavior, they are almost exclusively designed for post-hoc classification tasks. To bridge this gap, we propose IB-Forecast, an inherently interpretable multivariate time-series forecasting framework. It decomposes forecasting into a learned periodic component and a residual component computed with explainable masks over input tokens. With a budget-constrained information bottleneck, end-to-end optimization enables users to directly control explanation sparsity. With a rigorous faithfulness evaluation protocol, extensive experiments demonstrate that IB-Forecast matches the forecasting error of leading black-box models while providing faithful explanations at no additional inference cost. Furthermore, under a matched sparsity budget, these native explanations consistently surpass gradient-based, occlusion-based, and optimization-based baselines across all evaluated datasets. Ultimately, whereas the native explanations of existing interpretable forecasters exhibit poor faithfulness, IB-Forecast guarantees high explanation fidelity, requiring only 14-20% of the observations to deliver low-error predictions.

Multivariate Forecasting Load Forecasting Multivariate Time Series Forecasting Information Bottleneck Sparsity Bottlenecks

Open paper Ask about it PDF

Abstract

Explore similar work

Information Bottleneck Learning for Faithful Time Series Forecasting Explanations

TSNN: A Non-parametric and Interpretable Framework for Traffic Time Series Forecasting

SPaRSe-TIME: Saliency-Projected Low-Rank Temporal Modeling for Efficient and Interpretable Time Series Prediction