Application of an Artificial Neural Network for a Direct Estimation of Atmospheric Instability from a Next-Generation Imager

• Published in: Advances in atmospheric sciences Vol. 33; no. 2; pp. 221 - 232
• Main Authors: Lee, Su Jeong, Ahn, Myoung-Hwan, Lee, Yeonjin
• Format: Journal Article
• Language: English
• Published: Heidelberg Science Press 01.02.2016; Springer Nature B.V; Department of Atmospheric Science and Engineering, Ewha Women's University,52 Ewhayeodae-gil, Seodaemun-gu, Seoul 120-750, Republic of Korea
• Subjects: Atmosphere; Atmospheric Sciences; Correlation coefficient; Earth and Environmental Science; Earth Sciences; Geophysics/Geodesy; Meteorology; Neural networks; Scientific imaging; Weather forecasting; 下线; 服务; 迁移; Korea, Rep; artificial neural network; CAPE; geostationary imager; instability
• ISSN: 0256-1530; 1861-9533
• DOI: 10.1007/s00376-015-5084-9

Atmospheric instability information derived from satellites plays an important role in short-term weather forecasting, especially the forecasting of severe convective storms. For the next generation of weather satellites for Korea＇s multi-purpose geostationary satellite program, a new imaging instrument has been developed. Although this imaging instrument is not de- signed to perform full sounding missions and its capability is limited, its multi-spectral infrared channels provide information on vertical sounding. To take full advantage of the observation data from the much improved spatiotemporal resolution of the imager, the feasibility of an artificial neural network approach for the derivation of the atmospheric instability is investigated. The multi-layer perceptron model with a feed-forward and back-propagation training algorithm shows quite a sensitive re- sponse to the selection of the training dataset and model architecture. Through an extensive performance test with a carefully selected training dataset of 7197 independent profiles, the model architectures are selected to be 12, 5000, and 0.3 for the number of hidden nodes, number of epochs, and learning rate, respectively. The selected model gives a mean absolute error, RMSE, and correlation coefficient of 330 J kg-1, 420 J kg-1, and 0.9, respectively. The feasibility is further demonstrated via application of the model to real observation data from a similar instrument that has comparable observation channels with the planned imager.