Deep-Learning-Based Precipitation Nowcasting with Ground Weather Station Data and Radar Data

TL;DR

This paper introduces ASOC, a novel attentive method that enhances deep-learning precipitation nowcasting models by effectively integrating ground weather station data, leading to improved prediction accuracy for heavy and light rainfall events.

Contribution

The paper proposes ASOC, a new attention-based approach that effectively incorporates ground weather station data into existing image-based models for better precipitation nowcasting.

Findings

Improved average CSI by 5.7% for heavy and light rainfall predictions.

Effective integration of ground station data enhances model performance.

Applicable to existing models without architectural changes.

Abstract

Recently, many deep-learning techniques have been applied to various weather-related prediction tasks, including precipitation nowcasting (i.e., predicting precipitation levels and locations in the near future). Most existing deep-learning-based approaches for precipitation nowcasting, however, consider only radar and/or satellite images as inputs, and meteorological observations collected from ground weather stations, which are sparsely located, are relatively unexplored. In this paper, we propose ASOC, a novel attentive method for effectively exploiting ground-based meteorological observations from multiple weather stations. ASOC is designed to capture temporal dynamics of the observations and also contextual relationships between them. ASOC is easily combined with existing image-based precipitation nowcasting models without changing their architectures. We show that such a combination improves the average critical success index (CSI) of predicting heavy (at least 10 mm/hr) and light (at least 1 mm/hr) rainfall events at 1-6 hr lead times by 5.7%, compared to the original image-based model, using the radar images and ground-based observations around South Korea collected from 2014 to 2020.