ECMWF short-term prediction accuracy improvement by deep learning.

Journal: Scientific reports
Published Date:

Abstract

This paper aims to describe and evaluate the proposed calibration model based on a neural network for post-processing of two essential meteorological parameters, namely near-surface air temperature (2 m) and 24 h accumulated precipitation. The main idea behind this work is to improve short-term (up to 3 days) forecasts delivered by a global numerical weather prediction (NWP) model called ECMWF (European Centre for Medium-Range Weather Forecasts). In comparison to the existing local weather models that typically provide weather forecasts for limited geographic areas (e.g., within one country but they are more accurate), ECMWF offers a prediction of the weather phenomena across the world. Another significant benefit of this global NWP model includes the fact, that by using it in several well-known online applications, forecasts are freely available while local models outputs are often paid. Our proposed ECMWF-enhancing model uses a combination of raw ECMWF data and additional input parameters we have identified as useful for ECMWF error estimation and its subsequent correction. The ground truth data used for the training phase of our model consists of real observations from weather stations located in 10 cities across two European countries. The results obtained from cross-validation indicate that our parametric model outperforms the accuracy of a standard ECMWF prediction and gets closer to the forecast precision of the local NWP models.

Authors

  • Jaroslav Frnda
    Department of Quantitative Methods and Economic Informatics, Faculty of Operation and Economics of Transport and Communications, University of Zilina, 01026, Zilina, Slovakia. jaroslav.frnda@fpedas.uniza.sk.
  • Marek Durica
    Department of Quantitative Methods and Economic Informatics, Faculty of Operation and Economics of Transport and Communications, University of Zilina, 01026, Zilina, Slovakia.
  • Jan Rozhon
    Department of Telecommunications, Faculty of Electrical Engineering and Computer Science, VSB Technical University of Ostrava, 70833, Ostrava-Poruba, Czech Republic.
  • Maria Vojtekova
    Department of Quantitative Methods and Economic Informatics, Faculty of Operation and Economics of Transport and Communications, University of Zilina, 01026, Zilina, Slovakia.
  • Jan Nedoma
    Department of Telecommunications, Faculty of Electrical Engineering and Computer Science, VSB Technical University of Ostrava, 70833, Ostrava-Poruba, Czech Republic.
  • Radek Martinek
    Department of Cybernetics and Biomedical Engineering, Faculty of Electrical Engineering and Computer Science, VSB-Technical University of Ostrava, 700 30 Ostrava, Czech Republic.