Accelerating Domain-aware Deep Learning Models with Distributed Training

TL;DR

This paper introduces a distributed deep learning model tailored for geo-spatiotemporal data, integrating domain knowledge to enhance prediction accuracy and computational efficiency, demonstrated through flood prediction in hydrology.

Contribution

The paper presents a novel distributed domain-aware spatiotemporal network combining domain-specific modules with multi-scale CNN and recurrent blocks for improved performance.

Findings

Achieved up to 4.1x speedup in flood prediction

Increased prediction accuracy up to 93%

Overall 12.6x speedup and 16% performance improvement

Abstract

Recent advances in data-generating techniques led to an explosive growth of geo-spatiotemporal data. In domains such as hydrology, ecology, and transportation, interpreting the complex underlying patterns of spatiotemporal interactions with the help of deep learning techniques hence becomes the need of the hour. However, applying deep learning techniques without domain-specific knowledge tends to provide sub-optimal prediction performance. Secondly, training such models on large-scale data requires extensive computational resources. To eliminate these challenges, we present a novel distributed domain-aware spatiotemporal network that utilizes domain-specific knowledge with improved model performance. Our network consists of a pixel-contribution block, a distributed multiheaded multichannel convolutional (CNN) spatial block, and a recurrent temporal block. We choose flood prediction in hydrology as a use case to test our proposed method. From our analysis, the network effectively predicts high peaks in discharge measurements at watershed outlets with up to 4.1x speedup and increased prediction performance of up to 93\%. Our approach achieved a 12.6x overall speedup and increased the mean prediction performance by 16\%. We perform extensive experiments on a dataset of 23 watersheds in a northern state of the U.S. and present our findings.