Statistical Post-Processing for Gridded Temperature Prediction Using Encoder-Decoder-Based Deep Convolutional Neural Networks

TL;DR

This paper introduces an encoder-decoder deep convolutional neural network to improve gridded temperature predictions, effectively correcting biases and errors in operational weather guidance models for the Kanto region in Japan.

Contribution

The study presents a novel neural network approach for post-processing temperature forecasts, enhancing accuracy over traditional Kalman filter methods.

Findings

Significant improvement in temperature prediction accuracy.

Effective correction of front position errors and extreme temperature biases.

Enhanced operational weather guidance performance.

Abstract

The Japan Meteorological Agency operates gridded temperature guidance to predict two-dimensional snowfall amounts and precipitation types, e.g., rain and snow, because surface temperature is one of the key elements to predict them. Operational temperature guidance is based on the Kalman filter, which uses temperature observation and numerical weather prediction (NWP) outputs only around observation sites. Correcting a temperature field when NWP models incorrectly predict a front's location or when observed temperatures are extremely cold or hot has been challenging. In this study, an encoder-decoder-based convolutional neural network has been proposed to predict gridded temperatures at the surface around the Kanto region in Japan. Verification results showed that the proposed model greatly improves the operational guidance and can correct NWP model biases, such as a positional error of fronts and extreme temperatures.