GeoPro-Net: Learning Interpretable Spatiotemporal Prediction Models through Statistically-Guided Geo-Prototyping

TL;DR

GeoPro-Net is a novel interpretable deep learning model for spatiotemporal event forecasting that uses statistical tests and prototypes to enhance interpretability without sacrificing predictive accuracy.

Contribution

The paper introduces GeoPro-Net, a new deep learning framework that inherently interprets spatiotemporal predictions through Geo-concept extraction and prototype learning.

Findings

GeoPro-Net achieves better interpretability than existing models.

It maintains competitive prediction accuracy.

The model is validated on four real-world datasets.

Abstract

The problem of forecasting spatiotemporal events such as crimes and accidents is crucial to public safety and city management. Besides accuracy, interpretability is also a key requirement for spatiotemporal forecasting models to justify the decisions. Interpretation of the spatiotemporal forecasting mechanism is, however, challenging due to the complexity of multi-source spatiotemporal features, the non-intuitive nature of spatiotemporal patterns for non-expert users, and the presence of spatial heterogeneity in the data. Currently, no existing deep learning model intrinsically interprets the complex predictive process learned from multi-source spatiotemporal features. To bridge the gap, we propose GeoPro-Net, an intrinsically interpretable spatiotemporal model for spatiotemporal event forecasting problems. GeoPro-Net introduces a novel Geo-concept convolution operation, which employs statistical tests to extract predictive patterns in the input as Geo-concepts, and condenses the Geo-concept-encoded input through interpretable channel fusion and geographic-based pooling. In addition, GeoPro-Net learns different sets of prototypes of concepts inherently, and projects them to real-world cases for interpretation. Comprehensive experiments and case studies on four real-world datasets demonstrate that GeoPro-Net provides better interpretability while still achieving competitive prediction performance compared with state-of-the-art baselines.