A curated UK rain radar data set for training and benchmarking nowcasting models

TL;DR

This paper introduces a curated UK rain radar dataset with sequences and features for training and benchmarking nowcasting models, along with tools and a case study demonstrating its use.

Contribution

It provides a new, well-structured radar dataset with supplementary features and tools, facilitating research in radar nowcasting and machine learning applications.

Findings

Dataset enables effective training of neural networks for nowcasting

Spatial stratification improves data representativeness

Case study demonstrates practical application of the dataset

Abstract

This paper documents a data set of UK rain radar image sequences for use in statistical modeling and machine learning methods for nowcasting. The main dataset contains 1,000 randomly sampled sequences of length 20 steps (15-minute increments) of 2D radar intensity fields of dimension 40x40 (at 5km spatial resolution). Spatially stratified sampling ensures spatial homogeneity despite removal of clear-sky cases by threshold-based truncation. For each radar sequence, additional atmospheric and geographic features are made available, including date, location, mean elevation, mean wind direction and speed and prevailing storm type. New R functions to extract data from the binary "Nimrod" radar data format are provided. A case study is presented to train and evaluate a simple convolutional neural network for radar nowcasting, including self-contained R code.