Demystifying Deep Learning in Predictive Spatio-Temporal Analytics: An Information-Theoretic Framework

by   Qi Tan, et al.

Deep learning has achieved incredible success over the past years, especially in various challenging predictive spatio-temporal analytics (PSTA) tasks, such as disease prediction, climate forecast, and traffic prediction, where intrinsic dependency relationships among data exist and generally manifest at multiple spatio-temporal scales. However, given a specific PSTA task and the corresponding dataset, how to appropriately determine the desired configuration of a deep learning model, theoretically analyze the model's learning behavior, and quantitatively characterize the model's learning capacity remains a mystery. In order to demystify the power of deep learning for PSTA, in this paper, we provide a comprehensive framework for deep learning model design and information-theoretic analysis. First, we develop and demonstrate a novel interactively- and integratively-connected deep recurrent neural network (I^2DRNN) model. I^2DRNN consists of three modules: an Input module that integrates data from heterogeneous sources; a Hidden module that captures the information at different scales while allowing the information to flow interactively between layers; and an Output module that models the integrative effects of information from various hidden layers to generate the output predictions. Second, to theoretically prove that our designed model can learn multi-scale spatio-temporal dependency in PSTA tasks, we provide an information-theoretic analysis to examine the information-based learning capacity (i-CAP) of the proposed model. Third, to validate the I^2DRNN model and confirm its i-CAP, we systematically conduct a series of experiments involving both synthetic datasets and real-world PSTA tasks. The experimental results show that the I^2DRNN model outperforms both classical and state-of-the-art models, and is able to capture meaningful multi-scale spatio-temporal dependency.


page 1

page 2

page 3

page 4


ST-UNet: A Spatio-Temporal U-Network for Graph-structured Time Series Modeling

The spatio-temporal graph learning is becoming an increasingly important...

Spatio-Temporal Graph Neural Networks for Predictive Learning in Urban Computing: A Survey

With the development of sophisticated sensors and large database technol...

Predictive Coding for Dynamic Vision : Development of Functional Hierarchy in a Multiple Spatio-Temporal Scales RNN Model

The current paper presents a novel recurrent neural network model, the p...

A Visual Analytics System for Improving Attention-based Traffic Forecasting Models

With deep learning (DL) outperforming conventional methods for different...

Mission-Aware Spatio-Temporal Deep Learning Model for UAS Instantaneous Density Prediction

The number of daily sUAS operations in uncontrolled low altitude airspac...

Mod-DeepESN: Modular Deep Echo State Network

Neuro-inspired recurrent neural network algorithms, such as echo state n...

AIST: An Interpretable Attention-based Deep Learning Model for Crime Prediction

Accuracy and interpretability are two essential properties for a crime p...

Please sign up or login with your details

Forgot password? Click here to reset