A Deep Learning Method for Real-time Bias Correction of Wind Field Forecasts in the Western North Pacific

TL;DR

This paper introduces a deep learning model that corrects systematic biases in ECMWF wind forecasts in real time, enhancing accuracy for maritime disaster prevention in the Western North Pacific.

Contribution

The study develops the MT-DETrajGRU model with a multi-task loss function for simultaneous wind speed and direction correction, demonstrating improved bias reduction over seasonal forecasts.

Findings

Biases reduced by 8-11% for wind speed and 9-14% for wind direction.

Model performs consistently under different weather conditions, including typhoons.

Real-time bias correction improves forecast reliability in the Western North Pacific.

Abstract

Forecasts by the European Centre for Medium-Range Weather Forecasts (ECMWF; EC for short) can provide a basis for the establishment of maritime-disaster warning systems, but they contain some systematic biases.The fifth-generation EC atmospheric reanalysis (ERA5) data have high accuracy, but are delayed by about 5 days. To overcome this issue, a spatiotemporal deep-learning method could be used for nonlinear mapping between EC and ERA5 data, which would improve the quality of EC wind forecast data in real time. In this study, we developed the Multi-Task-Double Encoder Trajectory Gated Recurrent Unit (MT-DETrajGRU) model, which uses an improved double-encoder forecaster architecture to model the spatiotemporal sequence of the U and V components of the wind field; we designed a multi-task learning loss function to correct wind speed and wind direction simultaneously using only one model. The study area was the western North Pacific (WNP), and real-time rolling bias corrections were made for 10-day wind-field forecasts released by the EC between December 2020 and November 2021, divided into four seasons. Compared with the original EC forecasts, after correction using the MT-DETrajGRU model the wind speed and wind direction biases in the four seasons were reduced by 8-11% and 9-14%, respectively. In addition, the proposed method modelled the data uniformly under different weather conditions. The correction performance under normal and typhoon conditions was comparable, indicating that the data-driven mode constructed here is robust and generalizable.