TY - GEN
T1 - Coordinate-RNN for error correction on numerical weather prediction
AU - Yu, Chanjong
AU - Ahn, Heewoong
AU - Seok, Junhee
N1 - Funding 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.
Publisher Copyright:
© 2018 Institute of Electronics and Information Engineers.
PY - 2018/4/2
Y1 - 2018/4/2
N2 - 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.
AB - 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.
KW - Meteorological data
KW - coordinates
KW - error correction
KW - numerical weather prediction model
KW - recurrent neural network
UR - http://www.scopus.com/inward/record.url?scp=85048537190&partnerID=8YFLogxK
U2 - 10.23919/ELINFOCOM.2018.8330699
DO - 10.23919/ELINFOCOM.2018.8330699
M3 - Conference contribution
AN - SCOPUS:85048537190
T3 - International Conference on Electronics, Information and Communication, ICEIC 2018
SP - 1
EP - 3
BT - International Conference on Electronics, Information and Communication, ICEIC 2018
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 17th International Conference on Electronics, Information and Communication, ICEIC 2018
Y2 - 24 January 2018 through 27 January 2018
ER -