In this work, we present a coordinate-based Recurrent Neural Networks (RNN) for error correction on the Numerical Weather Prediction (NWP) model. We show that the output errors on NWP have spatial and temporal properties, which is collinear with meteorological data. The correction model reflects these characteristics by encompassing the latitude and longitude coordinates as direct inputs to RNN. Examined with the NWP data in Korea, the proposed RNN-based correction reduces the humidity prediction errors by 4.8% and 4.2% compared to the predictions without correction and with simple linear correction, respectively. The overall result highlights the promise of our approach.
|Title of host publication||International Conference on Electronics, Information and Communication, ICEIC 2018|
|Publisher||Institute of Electrical and Electronics Engineers Inc.|
|Number of pages||3|
|Publication status||Published - 2018 Apr 2|
|Event||17th International Conference on Electronics, Information and Communication, ICEIC 2018 - Honolulu, United States|
Duration: 2018 Jan 24 → 2018 Jan 27
|Name||International Conference on Electronics, Information and Communication, ICEIC 2018|
|Other||17th International Conference on Electronics, Information and Communication, ICEIC 2018|
|Period||18/1/24 → 18/1/27|
Bibliographical noteFunding Information:
This work was supported by the National Research Foundation of Korea grant (NRF-2016R1D1A1B03931077, NRF-2017R1C1B2002850) as well as a grant from Korea Meteorological Administration.
© 2018 Institute of Electronics and Information Engineers.
- Meteorological data
- error correction
- numerical weather prediction model
- recurrent neural network
ASJC Scopus subject areas
- Information Systems
- Computer Networks and Communications
- Computer Science Applications
- Signal Processing
- Electrical and Electronic Engineering