A novel tropical cyclone (TC) size estimation model (TC-SEM) in the western North Pacific was developed based on a convolutional neural network (CNN) using geostationary satellite infrared (IR) images. The proposed TC-SEM was tested using three CNN schemes: a single-task regression model that separately estimated the radius of maximum wind (RMW) and the radius of 34 kt wind (R34) of the TC, a multi-task regression model that estimated the RMW and R34 simultaneously, and a multi-task regression model using best-track TC intensity information. For model training, validation, and testing, 29,730, 2505, and 11,624 geostationary satellite images of the region around the center of the TC, respectively, were used, each containing four IR bands: short-wavelength IR (3.7 µm), water vapor (6.7 µm), IR1 (10.8 µm), and IR2 (12.0 µm). The results showed that the multi-task model performed better than the single-task model due to knowledge sharing and its ability to solve multiple interrelated tasks simultaneously. The inclusion of TC intensity information in the multi-task model further improved the performance of the RMW and R34 estimations, with correlations (mean absolute errors) of 0.95 (2.05 nmi) and 0.93 (9.77 nmi), respectively, which represent significant improvements over the performance of existing linear regression statistical methods. The results suggested that this CNN model using geostationary satellite images may be a powerful tool for estimating TC sizes in operational TC forecasts.

Baek, Y.-H. and Moon, I.-J., 2019. Estimation of satellite-based upper-ocean temperature profile in the western North Pacific and its application to tropical cyclone intensity predictions. In: Jung, H.-S.; Lee, S.; Ryu, J.-H., and Cui, T. (eds.), Advances in Remote Sensing and Geoscience Information Systems of Coastal Environments. Journal of Coastal Research, Special Issue, No. 90, pp. 261-266. Coconut Creek (Florida), ISSN 0749-0208.Satellite measurements have limitations in obtaining information below sea surface, because they assess only the ocean surface. However, combining the satellite-measured sea surface temperature and heights with a large number of ARGO and reanalysis profiles allows estimating upper-ocean temperature profiles (UTPs) below the surface. In this study, a satellite-based UTP estimation algorithm was developed using a massive data set of 128,136 ARGO profiles and ocean reanalysis data collected over 17 years (2000–2016). The algorithm has the advantage of producing UPTs in all tropical cyclone (TC)-passing areas in the western North Pacific (WNP) without missed points. The verification results revealed that the estimated UTPs and TC-intensity-related predictors, such as depth-averaged temperatures up to 80 m and 100 m, isothermal depths at 20 °C and 26 °C, ocean heat content, and maximum potential intensity, overall are in good agreement with the observations, although there still exists a relatively large error in the higher latitudes (north of 40°N) and the Kuroshio extension area where spatial and temporal variations are large. Based on the relationships between the TC intensity change and the predictors obtained for WNP TCs during 2004–2014, this study finally provides a guideline for predicting satellite-based TC intensity using estimated predictors.