Browse > Article
http://dx.doi.org/10.7780/kjrs.2020.36.5.3.4

Multi-task Learning Based Tropical Cyclone Intensity Monitoring and Forecasting through Fusion of Geostationary Satellite Data and Numerical Forecasting Model Output  

Lee, Juhyun (Department of Urban and Environmental Engineering, Ulsan National Institute of Science and Technology)
Yoo, Cheolhee (Department of Urban and Environmental Engineering, Ulsan National Institute of Science and Technology)
Im, Jungho (Department of Urban and Environmental Engineering, Ulsan National Institute of Science and Technology)
Shin, Yeji (Department of Urban and Environmental Engineering, Ulsan National Institute of Science and Technology)
Cho, Dongjin (Department of Urban and Environmental Engineering, Ulsan National Institute of Science and Technology)
Publication Information
Korean Journal of Remote Sensing / v.36, no.5_3, 2020 , pp. 1037-1051 More about this Journal
Abstract
The accurate monitoring and forecasting of the intensity of tropical cyclones (TCs) are able to effectively reduce the overall costs of disaster management. In this study, we proposed a multi-task learning (MTL) based deep learning model for real-time TC intensity estimation and forecasting with the lead time of 6-12 hours following the event, based on the fusion of geostationary satellite images and numerical forecast model output. A total of 142 TCs which developed in the Northwest Pacific from 2011 to 2016 were used in this study. The Communications system, the Ocean and Meteorological Satellite (COMS) Meteorological Imager (MI) data were used to extract the images of typhoons, and the Climate Forecast System version 2 (CFSv2) provided by the National Center of Environmental Prediction (NCEP) was employed to extract air and ocean forecasting data. This study suggested two schemes with different input variables to the MTL models. Scheme 1 used only satellite-based input data while scheme 2 used both satellite images and numerical forecast modeling. As a result of real-time TC intensity estimation, Both schemes exhibited similar performance. For TC intensity forecasting with the lead time of 6 and 12 hours, scheme 2 improved the performance by 13% and 16%, respectively, in terms of the root mean squared error (RMSE) when compared to scheme 1. Relative root mean squared errors(rRMSE) for most intensity levels were lessthan 30%. The lower mean absolute error (MAE) and RMSE were found for the lower intensity levels of TCs. In the test results of the typhoon HALONG in 2014, scheme 1 tended to overestimate the intensity by about 20 kts at the early development stage. Scheme 2 slightly reduced the error, resulting in an overestimation by about 5 kts. The MTL models reduced the computational cost about 300% when compared to the single-tasking model, which suggested the feasibility of the rapid production of TC intensity forecasts.
Keywords
Tropical cyclone; Intensity forecasting; Multi-task learning; Convolutional Neural Networks; Geostationary satellite; Numerical forecasting model;
Citations & Related Records
Times Cited By KSCI : 2  (Citation Analysis)
연도 인용수 순위
1 Chaudhuri, S., D. Dutta, S. Goswami, and A. Middey, 2013. Intensity forecast of tropical cyclones over North Indian Ocean using multilayer perceptron model: skill and performance verification, Natural Hazards, 65(1): 97-113.   DOI
2 Chung, C. Y., H. K. Lee, H. J. Ahn, M. H. Ahn, and S. N. Oh, 2006. Developing the cloud detection algorithm for COMS Meteorolgical Data Processing System, Korean Journal of Remote Sensing, 22(5): 367-372 (in Korean with English abstract).   DOI
3 Combinido, J. S., J. R. Mendoza, and J. Aborot, 2018. A convolutional neural network approach for estimating tropical cyclone intensity using satellite-based infrared images, Proc. of 2018 24th International Conference on Pattern Recognition (ICPR), IEEE, Beijing, China, Aug. 20-24, pp.1474-1480.
4 Dvorak, V. F., 1975. Tropical cyclone intensity analysis and forecasting from satellite imagery, Monthly Weather Review, 103(5): 420-430.   DOI
5 Feng, B., 2005. A neural network regression model for tropical cyclone forecast, Proc. of 2005 International Conference on Machine Learning and Cybernetics, IEEE, Guangzhou, China, Aug. 18-21, pp.4122-4128.
6 Grossman, M., and M. Zaiki, 2009. Reconstructing typhoons in Japan in the 1880s from documentary records, Weather, 64(12): 315-322.   DOI
7 Guo, Y., J. Cai, B. Jiang, and J. Zheng, 2018. Cnnbased real-time dense face reconstruction with inverse-rendered photo-realistic face images, IEEE Transactions on Pattern Analysis and Machine Intelligence, 41(6): 1294-1307.   DOI
8 Ham, Y.-G., J.-H. Kim, and J.-J. Luo, 2019. Deep learning for multi-year ENSO forecasts, Nature, 573(7775): 568-572.   DOI
9 Han, H., S. Lee, J. Im, M. Kim, M.-I. Lee, M. H. Ahn, and S.-R. Chung, 2015. Detection of convective initiation using Meteorological Imager onboard Communication, Ocean, and Meteorological Satellite based on machine learning approaches, Remote Sensing, 7(7): 9184-9204.   DOI
10 Hoegh-Guldberg, O., D. Jacob, M. Bindi, S. Brown, I. Camilloni, A. Diedhiou, R. Djalante, K. Ebi, F. Engelbrecht, and J. Guiot, 2018. Impacts of 1.5 C global warming on natural and human systems, Global warming of 1.5$^{\circ}C$. An IPCC Special Report, http://hdl.handle.net/10138/311749, Accessed on Sep. 25, 2020.
11 Huang, X., Z. Guan, L. He, Y. Huang, and H. Zhao, 2016. A PNN prediction scheme for local tropical cyclone intensity over the South China Sea, Natural Hazards, 81(2): 1249-1267.   DOI
12 Liu, X., Y. Lu, G. Zhu, Y. Lei, L. Zheng, H. Qin, C. Tang, G. Ellison, R. McCormack, and Q. Ji, 2013. The diagnostic accuracy of pleural effusion and plasma samples versus tumour tissue for detection of EGFR mutation in patients with advanced non-small cell lung cancer: comparison of methodologies, Journal of Clinical Pathology, 66(12): 1065-1069.   DOI
13 Kayalibay, B., G. Jensen, and P. van der Smagt, 2017. CNN-based segmentation of medical imaging data, arXiv preprint arXiv:1701.03056, Accessed on Sep. 25, 2020.
14 Kim, Y., G.-H. Kwak, K.-D. Lee, S.-I. Na, C.-W. Park, and N.-W. Park, 2018. Performance evaluation of machine learning and deep learning algorithms in crop classification: Impact of hyper-parameters and training sample size, Korean Journal of Remote Sensing, 34(5): 811-827 (in Korean with English abstract).   DOI
15 Lee, J., J. Im, D.-H. Cha, H. Park, and S. Sim, 2020. Tropical cyclone intensity estimation using multidimensional convolutional neural networks from geostationary satellite data, Remote Sensing, 12(1): 108.
16 Mendelsohn, R., K. Emanuel, S. Chonabayashi, and L. Bakkensen, 2012. The impact of climate change on global tropical cyclone damage, Nature Climate Change, 2(3): 205-209.   DOI
17 Menzel, W. P., and J. F. Purdom, 1994. Introducing GOES-I: The first of a new generation of geostationary operational environmental satellites, Bulletin of the American Meteorological Society, 75(5): 757-782.   DOI
18 Pradhan, R., R. S. Aygun, M. Maskey, R. Ramachandran, and D. J. Cecil, 2017. Tropical cyclone intensity estimation using a deep convolutional neural network, IEEE Transactions on Image Processing, 27(2): 692-702.   DOI
19 Nwe, T. L., T. H. Dat, and B. Ma, 2017. Convolutional neural network with multi-task learning scheme for acoustic scene classification, Proc. of 2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), IEEE, Kuala Lumpur, Malaysia, Dec.12-15, pp.1347-1350.
20 Olander, T. L., and C. S. Velden, 2007. The advanced Dvorak technique: Continued development of an objective scheme to estimate tropical cyclone intensity using geostationary infrared satellite imagery, Weather and Forecasting, 22(2): 287-298.   DOI
21 Qiu, Z., T. Yao, and T. Mei, 2017. Learning spatiotemporal representation with pseudo-3d residual networks, Proc. of the IEEE International Conference on Computer Vision, Venice, Italy, Oct. 22-29, pp. 5533-5541.
22 Ritchie, E. A., K. M. Wood, O. G. Rodreiguez-Herrera, M. F. Pineros, and J. S. Tyo, 2014. Satellitederived tropical cyclone intensity in the North Pacific Ocean using the deviation-angle variance technique, Weather and Forecasting, 29(3): 505-516.   DOI
23 Ruder, S., 2017. An overview of multi-task learning in deep neural networks, arXiv preprint arXiv:1706.05098, Accessed on Sep. 25, 2020.
24 Schmetz, J., S. Tjemkes, M. Gube, and L. Van de Berg, 1997. Monitoring deep convection and convective overshooting with METEOSAT, Advances in Space Research, 19(3): 433-441.   DOI
25 Sim, S., J. Im, S. Park, H. Park, M. H. Ahn, and P.-w. Chan, 2018. Icing detection over East Asia from geostationary satellite data using machine learning approaches, Remote Sensing, 10(4): 631.   DOI
26 Yoo, C., D. Han, J. Im, and B. Bechtel, 2019. Comparison between convolutional neural networks and random forest for local climate zone classification in mega urban areas using Landsat images, ISPRS Journal of Photogrammetry and Remote Sensing, 157: 155-170.   DOI
27 Song, A., and Y. Kim, 2017. Deep learning-based hyperspectral image classification with application to environmental geographic information systems, Korean Journal of Remote Sensing, 33(6-2): 1061-1073 (in Korean with English abstract).   DOI
28 Velden, C. S., C. M. Hayden, S. J. W. Nieman, W. Paul Menzel, S. Wanzong, and J. S. Goerss, 1997. Upper-tropospheric winds derived from geostationary satellite water vapor observations, Bulletin of the American Meteorological Society, 78(2): 173-196.   DOI