Open AccessPerformance comparison of solar radiation forecasting between WRF and LSTM in Gifu, Japan
Author(s) -
Jose Manuel Soares de Araujo
Publication year - 2020
Publication title -
environmental research communications
Language(s) - English
Resource type - Journals
ISSN - 2515-7620
DOI - 10.1088/2515-7620/ab7366
Subject(s) - weather research and forecasting model , mean squared error , meteorology , mesoscale meteorology , environmental science , metric (unit) , computer science , climatology , algorithm , geography , mathematics , statistics , geology , engineering , operations management
Three months comparison of hourly solar radiation forecasting from 1st January to 31st March 2017 between Weather Research and Forecasting (WRF) mesoscale model and Long short-term memory (LSTM) algorithm is presented in this study. One-way grid nesting technique of the WRF model is applied for the simulation with a six-hourly input dataset downloaded from the National Oceanic and Atmospheric Administration - National Operational Model Archive and Distribution System (NOMADS) website. Three years’data of solar radiation from 1st January 2014 to 31st December 2016 are used as input data for Long Short Term Memory (LSTM) algorithm to simulate solar radiation. The results show the root mean square error of the LSTM algorithm is 310 W m −2 higher compared to 210 W m −2 from the WRF model. The MBE and the nMBE of the WRF model are obtained positive value 96 W m −2 and 9% compared to −101 W m −2 and −9% of LSTM for 2160 h prediction. Meanwhile, the performance error percentage of WRF is 19% lower compared to 28% of LSTM for the nRMSE error metric. Although this study found that the WRF model performed better and lower error compared to the LSTM algorithm, however, it also recommends the LSTM algorithm configuration can be used for long-term prediction.