Convolution Neural Network Based Algorithm for Estimating the Intensity of Tropical Cyclone from Infrared Satellite Images
Keywords:
Unsupervised Machine Learning, Convolution Neural Network (Cnn), Satellite Imagery, Tropical Cyclones, Intensity PredictionAbstract
The Comprehensive Intention Of The Present Study Is To Develop A Convolution Neural Network (Cnn) Based Prediction Model To Estimate The Intensity Of Tropical Cyclone From The Infrared Satellite Imagery. The Proposed Methodology Is A Two Phase Unsupervised Machine Learning Algorithm. The First Phase Is A Data Acquisition Part That Extracts Data From The Hursat - B1 And Hurdat2 Satellites And Merges Them. The Second Phase Involves Converting The Image Matrix Into Convolved Matrix Which Is Then Passed Through A Rectified Linear Unit Layer To Extract The Important Information From The Images. Finally The Information Are Passed Through A Fully Connected Layer Comprising Of Number Of Neurons That Are Connected To The Previous Layer. In The Proposed Model, Rms prop Optimizer Is Used to Get the Optimized Configuration. At Last, The Proposed Model Is Validated With Pictures Of 10 Different Tropical Cyclones And The Mean Absolute Error And Root Mean Square Error Computed Is 8.42 Knots And 11.14 Knots Respectively Which Is Well Within The Acceptable Range.
References
Pradhan, R., Aygun, R. S., Maskey, M., Ramachandran, R., & Cecil, D. J. (2017). Tropical Cyclone Intensity Estimation Using A Deep Convolutional Neural Network. Ieee Transactions On Image Processing, 27(2), 692-702.
Dvorak, V. F. (1973). A Technique For The Analysis And Forecasting Of Tropical Cyclone Intensities From Satellite Pictures.
Knaff, J. A., Brown, D. P., Courtney, J., Gallina, G. M., &Beven, J. L. (2010). An Evaluation Of Dvorak Technique–Based Tropical Cyclone Intensity Estimates. Weather And Forecasting, 25(5), 1362-1379.
Maskey, M., Ramachandran, R., Ramasubramanian, M., Gurung, I., Freitag, B., Kaulfus, A., Bollinger, D., Cecil, D.& Miller, J. (2020). Deepti: Deep-Learning-Based Tropical Cyclone Intensity Estimation System. Ieee Journal Of Selected Topics In Applied Earth Observations And Remote Sensing, 13, 4271-4281.
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). Imagenet Classification With Deep Convolutional Neural Networks. Advances In Neural Information Processing Systems, 25, 1097-1105.
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., ... &Rabinovich, A. (2015). Going Deeper With Convolutions. In Proceedings Of The Ieee Conference On Computer Vision And Pattern Recognition (Pp. 1-9).
Szegedy, C., Reed, S., Erhan, D., Anguelov, D., &Ioffe, S. (2014). Scalable, High-Quality Object Detection. Arxiv Preprint Arxiv:1412.1441.
Szegedy, C., Toshev, A., & Erhan, D. (2013). Deep Neural Networks For Object Detection.
Wang, L., Lu, H., Ruan, X., & Yang, M. H. (2015). Deep Networks For Saliency Detection Via Local Estimation And Global Search. In Proceedings Of The Ieee Conference On Computer Vision And Pattern Recognition (Pp. 3183-3192).
Wimmers, A., Velden, C., &Cossuth, J. H. (2019). Using Deep Learning To Estimate Tropical Cyclone Intensity From Satellite Passive Microwave Imagery. Monthly Weather Review, 147(6), 2261-2282.
Lee, J., Im, J., Cha, D. H., Park, H., & Sim, S. (2020). Tropical Cyclone Intensity Estimation Using Multi-Dimensional Convolutional Neural Networks From Geostationary Satellite Data. Remote Sensing, 12(1), 108.
Giffard-Roisin, S., Yang, M., Charpiat, G., Kumlerbonfanti, C., Kégl, B., &Monteleoni, C. (2020). Tropical Cyclone Track Forecasting Using Fused Deep Learning From Aligned Reanalysis Data. Frontiers In Big Data, 3, 1.
Mudigonda, M., Kim, S., Mahesh, A., Kahou, S., Kashinath, K., Williams, D., ... & Prabhat, M. (2017). Segmenting And Tracking Extreme Climate Events Using Neural Networks. In Deep Learning For Physical Sciences (Dlps) Workshop, Held With Nips Conference.
Gao, S., Zhao, P., Pan, B., Li, Y., Zhou, M., Xu, J., ... & Shi, Z. (2018). A Nowcasting Model For The Prediction Of Typhoon Tracks Based On A Long Short Term Memory Neural Network. Acta Oceanologicasinica, 37(5), 8-12.
Kim, S., Kim, H., Lee, J., Yoon, S., Kahou, S. E., Kashinath, K., & Prabhat, M. (2019, January). Deep-Hurricane-Tracker: Tracking And Forecasting Extreme Climate Events. In 2019 Ieee Winter Conference On Applications Of Computer Vision (Wacv) (Pp. 1761-1769). Ieee.