A Transfer Learning Based Deep Learning Method for Mesoscale Convective Cloud Segmentation
Keywords:
Deep learning, Kalpana-1 infrared images, Mesoscale Convective Systems, Transfer learningAbstract
Risky weather events associated with Mesoscale Convective Systems (MCS) may end in considerable financial losses and occasionally even fatalities. Owing to the unpredictability of climate scenarios, little is known about the dynamics behind the development and deepening of MCS. Satellite images of MCS Clouds (MCSC) reveal a range of topologies, from open to closed, yet study on MCSC activities remains severely constrained. Through the use of high-resolution mathematical models of the atmosphere and the analysis of remote sensing imagery, high cloud-top temperature gradients, specific spatial shapes of temperature patterns, and other aspects of MCSCs can be investigated. In this study, deep learning (DL) methods are used to segment MCSC images using a transfer learning (TL) strategy. VGG-16 has been improved in the present work by fusing encoder-decoder architecture and taking cues from UNet architecture. The design that is generated is called ENDE-VGG. The proposed approach enables the collection of more pertinent data over a wider region. Images based on the Brightness Temperature in the infrared (K1-IR) channel by the Indian geostationary satellite Kalpana-1 are used in the present research. The TL technique produced a Dice coefficient of 0.935 on the validation data set, an intersection of union (IoU) of 0.875 on the K1-IR data set, and a mean IoU of 0.93. Additionally, using the test data, it obtained a 0.933 Dice coefficient and 0.875 IoU. ENDE-VGG performed better than the most sophisticated cloud image segmentation methods when using IoU as the loss function, based on numerous research studies.
Downloads
References
V. M. Kattsov, E. M. Akentieva, O. A. Anisimov, M. Y. Bardin, S. A. Zhuravlev, A. A. Kiselev, M. V. Klyueva, P. I. Konstantinov, V. N. Korotkov, and Kostyanoy, A. G., “Third assessment report on climate change and its consequences on the territory of the Russian federation general summary,” Roshydromet Science-Intensive Technologies: St. Petersburg, Russia, 2022.
A. Chernokulsky, A. Eliseev, F. Kozlov, N. Korshunova, M. Kurgansky, I. Mokhov, V. Semenov, N. Shvets’, A. Shikhov, and Y. I. Yarinich, “Atmospheric severe convective events in Russia: changes observed from different data,” Russ. Meteorol. Hydrol, vol. 47, pp. 343–354, Aug. 22, 2022.
E. P. Meredith, V. A. Semenov, D. Maraun, W. Park, and A. V. Chernokulsky, “Crucial role of Black Sea warming in amplifying the 2012 Krymsk precipitation extreme,” Nat. Geosci. vol. 8, pp. 615–619, Jul. 13, 2015.
A. Chernokulsky, M. Kurgansky, I. Mokhov, A. Shikhov, I. Azhigov, E. Selezneva, D. Zakharchenko, B. Antonescu, and T. Kuhne, “Tornadoes in northern Eurasia: From the middle age to the information era,” Weather Rev. vol. 148, pp. 3081–3110, Jul. 08, 2020.
A. Chernokulsky, A. Shikhov, A. Bykov, and I. Azhigov, “Satellite- based study and numerical forecasting of two tornado outbreaks in the Ural region in June 2017,” Atmosphere. vol. 11, pp. 1146, Oct. 22, 2020.
A. Chernokulsky, M. Kurgansky, I. Mokhov, A. Shikhov, I. Azhigov, E. Selezneva, D. Zakharchenko, B. Antonescu, and T. Kuhne, “Tornadoes in the Russian regions,” Russ. Meteorol. Hydrol. vol. 46, pp. 69–82, Feb. 2021.
T. Lister, and J. Masters, “Moscow Storm Kills 16,” Injures nearly 170-CNN. Available online: https://edition.cnn.com/2017/05/30/europe/moscow-storm/index.html (accessed on 11 November 2023).
A. Chernokulsky, A. Shikhov, A. Bykov, N. Kalinin, M. Kurgansky, B. Sherstyukov, and Y. Yarinich, “Diagnosis and modelling of two destructive derecho events in European Russia in the summer of 2010,” Atmos. Res. vol. 267, pp. 105928, Apr. 2022.
A. V. Chernokulsky, A. N. Shikhov, I. O. Azhigov, N. A. Eroshkina, D. P. Korenev, A. V. Bykov, N. A. Kalinin, M. V. Kurgansky, Y. B. Pavlyukov, and A. A. Sprygin, “Squalls and tornadoes over the European territory of Russia on May 15, 2021: diagnosis and modeling,” Russ. Meteorol. Hydrol. Vol. 47, pp. 867–881, Nov. 2022.
R. Houze, W. Schmid, R. Fovell, and H. Schiesser, “Hailstorms in Switzerland: left movers, right movers, and false hooks,” Mon. Weather Rev. Vol. 121, pp. 3345–3370, Dec. 01, 1993.
A. G. Laing, and J. Michael Fritsch, “The global population of mesoscale convective complexes,” Q. J. R. Meteorol. Soc. vol. 123, pp. 389–405, Jan. 1997.
R. A. Maddox, “Mesoscale convective complexes,” Bull. Am. Meteorol. Soc. vol. 61, 11, pp. 1374–1387, Nov. 1980.
I. Orlanski, “A rational subdivision of scales for atmospheric processes,” Bull. Am. Meteorol. Soc. vol. 56, 5, pp. 527–530, May 1975.
S. M. Cheeks, S. Fueglistaler, and S. T. Garner, “A Satellite-based climatology of Central and Southeastern U.S. mesoscale convective systems,” Weather Rev. vol. 148, pp. 2607–2621, Jun. 2020.
Z. Feng, L. R. Leung, N. Liu, J. Wang, R. A. Houze, J. Li, J. C. Hardin, D. Chen, and J. Guo, “A global high-resolution mesoscale convective system database using satellite-derived cloud tops, surface precipitation, and tracking,” J. Geophys. Res. Atmos. Vol. 126, e2020JD034202, Apr. 27, 2021.
D. Chen, J. Guo, D. Yao, Y. Lin, C. Zhao, M. Min, H. Xu, L. Liu, X. Huang, and T. Chen, “Mesoscale convective systems in the Asian monsoon region from advanced Himawari imager: Algorithms and preliminary results,” J. Geophys. Res. Atmos. vol. 124, 4, pp. 2210–2234, Feb. 27, 2019.
X. Yang, J. Fei, X. Huang, X. Cheng, L.M.V. Carvalho, and H. He, “Characteristics of mesoscale convective systems over China and its vicinity using geostationary satellite FY2,” J. Clim. vol. 28, pp. 4890–4907, Jun. 15, 2015.
C. Klein, D. Belusiˇ c, and C.M. Taylor, “Wavelet scale analysis of ´ mesoscale convective systems for detecting deep convection from infrared imagery,” J. Geophys. Res. Atmos. vol. 123, pp. 3035–3050, Mar. 27, 2018.
K. Bedka, J. Brunner, R. Dworak, W. Feltz, J. Otkin, and T. Greenwald, “Objective satellite-based detection of overshooting tops using infrared window channel brightness temperature gradients,” J. Appl. Meteorol. Climatol. vol. 49, pp. 181–202, Feb. 01, 2010.
M. Setvak, D. T. Lindsey, P. Novak, P. K. Wang, M. Radov ´ a, J. Kerkmann, L. Grasso, S. H. Su, R. M. Rabin, and J. Sˇˇtastka, “Satellite- observed cold-ring-shaped features atop deep convective clouds,” Atmos. Res. vol. 97, pp. 80–96, Jul. 2010.
J. C. Brunner, S. A. Ackerman, A. S. Bachmeier, and R. M. Rabin, “A quantitative analysis of the enhanced-v feature in relation to severe weather,” Weather Forecast. vol. 22, pp. 853–872, Aug. 01, 2007.
K. Bedka, E.M. Murillo, C.R. Homeyer, B. Scarino, and H. Mersiovsky, “The above-anvil cirrus plume: an important severe weather indicator in visible and infrared satellite imagery,” Weather Forecast. vol. 33, pp. 1159–1181, Oct. 01, 2018.
B. Czernecki, M. Taszarek, M. Marosz, M. Połrolniczak, L. Kolendow´icz, A. Wyszogrodzki, and J. Szturc, “Application of machine learning to large hail prediction—The importance of radar reflectivity, lightning occurrence and convective parameters derived from ERA5,” Atmos. Res. vol. 227, pp. 249–262, Oct. 01, 2019.
A.M. Haberlie, and W.S. Ashley, “Radar-based climatology of mesoscale convective systems in the United States,” J. Clim. vol. 32, pp. 1591–1606, Mar. 01, 2019.
A. Surowiecki, and M. Taszarek, “A 10-year radar-based climatology of mesoscale convective system archetypes and derechos in Poland,” Weather Rev. vol. 148, pp. 3471–3488, Jul. 30, 2020.
L. Nisi, O. Martius, A. Hering, M. Kunz, and U. Germann, “Spatial and temporal distribution of hailstorms in the Alpine region: A longterm, high resolution, radar-based analysis,” Q. J. R. Meteorol. Soc. vol. 142, pp. 1590–1604, Apr. 2016.
J. L. Cintineo, T. M. Smith, V. Lakshmanan, H. E. Brooks, and K. L. Ortega, “An objective high-resolution hail climatology of the contiguous United States,” Weather Forecast. vol. 27, pp. 1235–1248, Oct. 01, 2012.
M. A. Krinitskiy, and A. V. Sinitsyn, “Adaptive algorithm for cloud cover estimation from all-sky images over the sea.” Oceanology. vol. 56, pp. 315–319, Jul. 14, 2016.
M. Krinitskiy, M. Aleksandrova, P. Verezemskaya, S. Gulev, A. Sinitsyn, N. Kovaleva, and A. Gavrikov, “On the generalization ability of data-driven models in the problem of total cloud cover retrieval,” Remote Sens. vol. 13, pp. 326, Jan. 19, 2021.
Y. Liu, E. Racah, Prabhat, J. Correa, A. Khosrowshahi, D. Lavers, K. Kunkel, M. Wehner, and W. Collins, “Application of deep convolutional neural networks for detecting extreme weather in climate datasets” arXiv 2016, arXiv:1605.01156.
A. Rupe, K. Kashinath, N. Kumar, V. Lee, J. P. Prabhat, and Crutchfield, “Towards unsupervised segmentation of extreme weather events” arXiv 2019, arXiv:1909.07520.
G. Muszynski, K. Kashinath, V. Kurlin, M. Wehner, and Prabhat, “Topological data analysis and machine learning for recognizing atmospheric river patterns in large climate datasets,” Methods Assess. Model. vol. 12, pp. 613–628, Feb. 07, 2019.
D. Matsuoka, M. Nakano, D. Sugiyama, and S. Uchida, “Deep learning approach for detecting tropical cyclones and their precursors in the simulation by a cloud-resolving global nonhydrostatic atmospheric model,” Prog. Earth Planet. Sci. vol. 5, pp. 80, Dec. 19, 2018.
S. Pang, P. Xie, D. Xu, F. Meng, X. Tao, B. Li, Y. Li, and T. Song, “NDFTC: A new detection framework of tropical cyclones from meteorological satellite images with deep transfer learning,” Remote Sens. vol. 13, 9, pp. 1860, May. 10, 2021.
Prabhat, K. Kashinath, M. Mudigonda, S. Kim, L. Kapp-Schwoerer, A. Graubner, E. Karaismailoglu, L. von Kleist, T. Kurth, and A. Greiner, “ClimateNet: An expert-labeled open dataset and deep learning architecture for enabling high-precision analyses of extreme weather,” Geosci. Model Dev. vol. 14, pp. 107–124, Jan. 08, 2021.
D. Huang, Y. Du, Q. He, W. Song, and A. Liotta, “DeepEddy: A simple deep architecture for mesoscale oceanic eddy detection in SAR images,” in Proc. ICNSC, Calabria, Italy, 16–18 May 2017, pp. 673–678.
M. Krinitskiy, P. Verezemskaya, K. Grashchenkov, N. Tilinina, S. Gulev, and M. Lazzara, “Deep convolutional neural networks capabilities for binary classification of Polar mesocyclones in satellite mosaics,” Atmosphere. vol. 9, 11, pp. 426, Oct. 31, 2018.
M. Krinitskiy, P. Verezemskaya, S. Elizarov, and S. Gulev, “Machine learning methods for the detection of polar lows in satellite mosaics: Major issues and their solutions,” IOP Conf. Ser. Earth Environ. Sci. vol. 606, pp. 012025, 2020.
R. Wood, and D. L. Hartmann, “Spatial variability of liquid water path in marine low cloud: the importance of mesoscale cellular convection,” J. Clim. vol. 19, pp. 1748–1764, May. 06, 2006.
A. Muhlbauer, I. L. McCoy, and R. Wood, “Climatology of stratocumulus cloud morphologies: Microphysical properties and radiative effects,” Atmos. Chem. Phys. vol. 14, pp. 6695–6716, Jul. 03, 2014
I.L. McCoy, R. Wood, and J.K. Fletcher, “Identifying meteorological controls on open and closed mesoscale cellular convection associated with marine cold air outbreaks,” JGR Atmos. vol. 122, pp. 11678–11702, Nov. 16, 2017.
T. Yuan, H. Song, R. Wood, J. Mohrmann, K. Meyer, L. Oreopoulos, and S. Platnick, “Applying deep learning to NASA MODIS data to create a community record of marine low-cloud mesoscale morphology,” Atmos. Meas. Tech. vol. 13, 12, pp. 6989–6997, Dec. 21, 2020.
A. Vallet, and H. Sakamoto, “A multi-label convolutional neural network for automatic image annotation,” J. Inf. Process. vol. 23, 6, pp. 767–775, 2015.
A. Gufan, Y. Lehahn, E. Fredj, C. Price, R. Kurchin, and I. Koren, “Segmentation and tracking of marine cellular clouds observed by geostationary satellites,” Int. J. Remote Sens. vol. 37, pp. 1055–1068, Feb. 12, 2016.
D. Watson-Parris, S. A. Sutherland, M. W. Christensen, R. Eastman, and P. Stier, “A large-scale analysis of pockets of open cells and their radiative impact,” Geophys. Res. Lett. vol. 48, e2020GL092213, Mar. 28, 2021.
S. Prakash, C. M., and R. M. Gairola, “Large-scale precipitation estimation using Kalpana-1 IR measurements and its validation using GPCP and GPCC data,” Theoretical and applied climatology. vol. 106, pp. 283- 293, Apr. 2011.
C. Shorten, and T. M. Khoshgoftaar, “A survey on image data augmentation for deep learning,” Journal of big data, vol. 6, no. 1, pp. 1-48, 2019.
Z. Li, H. Shen, Q. Weng, Y. Zhang, P. Dou, and L. Zhang, “Cloud and cloud shadow detection for optical satellite imagery: Features, algorithms, validation, and prospects,” ISPRS Journal of Photogrammetry and Remote Sensing. vol. 188, pp. 89-108, Jun. 2022.
Y. Zhou, A. Ji, L. Zhang, and X. Xue, “Sampling-attention deep learning network with transfer learning for large-scale urban point cloud semantic segmentation,” Engineering Applications of Artificial Intelligence, vol. 117, pp. 105554, Jan. 2023.
R. Padilla, S. L. Netto, and E. A. B. da Silva, “A survey on performance metrics for object-detection algorithms,” in Proc., IWSSIP, Online, 1–3 July 2020, pp. 237–242.
M. Fawakherji, A. Youssef, D. Bloisi, A. Pretto, and D. Nardi, “Crop and weeds classification for precision agriculture using context-independent pixel-wise segmentation,” in Proc., IRC Naples, Italy, 25–27 February 2019, pp. 146–152.
L. Jiao, L. Huo, C. Hu, and P. Tang, “Refined UNet: UNet-based refinement network for cloud and shadow precise segmentation,” Remote Sensing, vol. 12, no. 12, pp. 2001, Jun. 22, 2020.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.