{"type":"ScholarlyArticle","title":"Self-Supervised Vision for Climate Downscaling","authors":[{"name":"Karandeep Singh","slug":"karandeep-singh","given":"Karandeep","family":"Singh","affiliation":"Data Science Group , IBS , South Korea"},{"name":"Chaeyoon Jeong","slug":"chaeyoon-jeong","given":"Chaeyoon","family":"Jeong","affiliation":"School of Computing , KAIST , South Korea; Data Science Group , IBS , South Korea"},{"name":"Naufal Shidqi","slug":"naufal-shidqi","given":"Naufal","family":"Shidqi","affiliation":"School of Computing , KAIST , South Korea; Data Science Group , IBS , South Korea"},{"name":"Sungwon Park","slug":"sungwon-park","given":"Sungwon","family":"Park","affiliation":"School of Computing , KAIST , South Korea; Data Science Group , IBS , South Korea"},{"name":"Arjun Nellikkattil","slug":"arjun-nellikkattil","given":"Arjun","family":"Nellikkattil","affiliation":"Center for Climate Physics , IBS , South Korea; Department of Climate System , PNU , South Korea"},{"name":"Elke Zeller","slug":"elke-zeller","given":"Elke","family":"Zeller","affiliation":"Center for Climate Physics , IBS , South Korea; Department of Climate System , PNU , South Korea"},{"name":"Meeyoung Cha","slug":"meeyoung-cha","given":"Meeyoung","family":"Cha","affiliation":"Data Science Group , IBS , South Korea; School of Computing , KAIST , South Korea; MPI-SP , Germany"}],"abstract":"Climate change is one of the most critical challenges that our planet is facing today. Rising global temperatures are already affecting Earth's weather and climate patterns with an increased frequency of unpredictable and extreme events. Future projections for climate change research are based on computer models like Earth System Models (ESMs). Climate simulations typically run on a coarser grid due to the high computational resources required, and then undergo a lighter downscaling process to obtain data on a finer grid. This work presents a self-supervised deep learning model that does not require high resolution ground truth data for downscaling. This is realized by leveraging salient distribution patterns and the hidden dependencies between weather variables for an individual data point at runtime. We propose three climate-specific components that well represent the patterns of underlying weather variables and learn intricate inter-variable dependencies. Extensive evaluation with 2x, 3x, and 4x scaling factors demonstrates that our model obtains 8% to 47% performance gain over existing baselines while greatly reducing the overall runtime. The improved performance and no dependence on high resolution ground truth data make our method a valuable tool for future climate research.","doi":"10.24963/ijcai.2024/825","url":"https://ijcai.org/proceedings/2024/825","pdf":"https://ijcai.org/proceedings/2024/0825.pdf","markdown":"https://ijcai.org/proceedings/2024/825.md","bibtex":"https://ijcai.org/proceedings/2024/bibtex/825","volume":{"slug":"2024","title":"Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2024","url":"https://ijcai.org/proceedings/2024/","year":2024,"location":"Jeju, Korea","dates":"3-9 August 2024","editors":"Kate Larson","isbn":"978-1-956792-04-1","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2024"},"section":"AI for Good","track":"AI for Good","number":825,"pages":{"first":7456,"last":7464},"keywords":["Multidisciplinary Topics and Applications: General","Computer Vision: General","Machine Learning: General"],"videos":[],"references":[{"position":1,"raw":"[Assaf Shocher, 2018] Michal Irani Assaf Shocher, Na- dav Cohen. \"zero-shot\" super-resolution using deep in- ternal learning. In proc. of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2018.","title":"zero-shot\" super-resolution using deep internal learning","authors":"Michal Irani, Assaf Shocher, Nadav Cohen","year":"2018","venue":"proc. of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Baño-Medina et al., 2020] Jorge Baño-Medina, Rodrigo Manzanas, and José Manuel Gutiérrez. Configuration and intercomparison of deep learning neural models for sta- tistical downscaling. Geoscientific Model Development, 13(4):2109-2124, 2020.","title":"Jorge Baño-Medina, Rodrigo Manzanas, and José Manuel Gutiérrez. Configuration and intercomparison of deep learning neural models for statistical downscaling","authors":"Baño-Medina","year":"2020","venue":"Geoscientific Model Development","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Chou et al., 2021] Christopher Chou, Junho Park, and Eric Chou. Generating high-resolution climate change projec- tions using super-resolution convolutional LSTM neural networks. In proc. of the International Conference on Ad- vanced Computational Intelligence (ICACI), pages 293- 298. IEEE, 2021.","title":"Generating high-resolution climate change projections using super-resolution convolutional LSTM neural networks","authors":"Christopher Chou, Junho Park, Eric Chou","year":"2021","venue":"proc. of the International Conference on Advanced Computational Intelligence (ICACI)","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Chu et al., 2020] Jung-Eun Chu, Sun-Seon Lee, Axel Tim- mermann, Christian Wengel, Malte F Stuecker, and Ryohei Yamaguchi. Reduced tropical cyclone densities and ocean effects due to anthropogenic greenhouse warming. Science Advances, 6(51):eabd5109, 2020.","title":"Reduced tropical cyclone densities and ocean effects due to anthropogenic greenhouse warming","authors":"Jung-Eun Chu, Sun-Seon Lee, Axel Timmermann, Christian Wengel, Malte F Stuecker, Ryohei Yamaguchi","year":"2020","venue":"Science Advances","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Cornillère et al., 2019] Victor Cornillère, Abdelaziz Djelouah, Yifan Wang, Olga Sorkine-Hornung, and Christopher Schroers. Blind image super-resolution with spatially variant degradations. ACM Transactions on Graphics (TOG), 38:1 -13, 2019.","title":"Blind image super-resolution with spatially variant degradations","authors":"Abdelaziz Victor Cornillère, Yifan Djelouah, Olga Wang, Christopher Sorkine-Hornung, Schroers","year":"2019","venue":"ACM Transactions on Graphics (TOG)","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Dong et al., 2014] Chao Dong, Chen Change Loy, Kaiming He, and Xiaoou Tang. Learning a deep convolutional net- work for image super-resolution. In David Fleet, Tomas Pajdla, Bernt Schiele, and Tinne Tuytelaars, editors, Com- puter Vision -ECCV 2014, pages 184-199, Cham, 2014. Springer International Publishing.","title":"Learning a deep convolutional network for image super-resolution","authors":"Chao Dong, Chen Change Loy, Kaiming He, Xiaoou Tang","year":"2014","venue":"Computer Vision -ECCV 2014","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Ducournau and Fablet, 2016] Aurelien Ducournau and Ro- nan Fablet. Deep learning for ocean remote sensing: an application of convolutional neural networks for super- resolution on satellite-derived sst data. In proc. of the IAPR Workshop on Pattern Recogniton in Remote Sensing (PRRS), pages 1-6, 2016.","title":"Aurelien Ducournau and Ronan Fablet. Deep learning for ocean remote sensing: an application of convolutional neural networks for superresolution on satellite-derived sst data","authors":"Fablet Ducournau","year":"2016","venue":"proc. of the IAPR Workshop on Pattern Recogniton in Remote Sensing (PRRS)","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Finn et al., 2017] Chelsea Finn, Pieter Abbeel, and Sergey Levine. Model-agnostic meta-learning for fast adaptation of deep networks. In proc. of the International Conference on Machine Learning (ICML), pages 1126-1135. PMLR, 2017. Glasner et al., 2009] Daniel Glasner, Shai Bagon, and Michal Irani. Super-resolution from a single image. In proc. of the IEEE International Conference on Computer Vision (ICCV), pages 349-356, 2009.","title":"Model-agnostic meta-learning for fast adaptation of deep networks","authors":"Finn","year":"2009","venue":"proc. of the International Conference on Machine Learning (ICML)","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Groenke et al., 2020] Brian Groenke, Luke Madaus, and Claire Monteleoni. Climalign: Unsupervised statistical downscaling of climate variables via normalizing flows. In proc. of the International Conference on Climate Informat- ics, pages 60-66, 2020.","title":"Climalign: Unsupervised statistical downscaling of climate variables via normalizing flows","authors":"Brian Groenke, Luke Madaus, Claire Monteleoni","year":"2020","venue":"proc. of the International Conference on Climate Informatics","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[H.-O. Pörtner, 2022] E.S. Poloczanska K. Mintenbeck M. Tignor A. Alegría M. Craig S. Langsdorf S. Löschke V. Möller A. Okem H.-O. Pörtner, D.C. Roberts. Summary for Policymakers, pages 3-33. Cambridge University Press, Cambridge, United Kingdom and New York, NY, USA, 2022.","title":"Summary for Policymakers","authors":"E S Poloczanska, K Mintenbeck, M Tignor, A Alegría, M S Craig, S Langsdorf, V Löschke, A Möller, H.-O Okem, D C Pörtner, Roberts","year":"2022","venue":null,"doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Haris et al., 2018] Muhammad Haris, Gregory Shakhnarovich, and Norimichi Ukita. Deep back- projection networks for super-resolution. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 1664-1673, 2018.","title":"Muhammad Haris, Gregory Shakhnarovich, and Norimichi Ukita. Deep backprojection networks for super-resolution","authors":"Haris","year":"2018","venue":"Proceedings of the IEEE conference on computer vision and pattern recognition","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Hurrell et al., 2013] James W Hurrell, Marika M Holland, Peter R Gent, Steven Ghan, Jennifer E Kay, Paul J Kushner, J-F Lamarque, William G Large, D Lawrence, Keith Lind- say, et al. The community earth system model: a frame- work for collaborative research. Bulletin of the American Meteorological Society, 94(9):1339-1360, 2013.","title":"The community earth system model: a framework for collaborative research","authors":"Marika M James W Hurrell, Peter R Holland, Steven Gent, Jennifer E Ghan, Paul J Kay, J-F Kushner, William G Lamarque, D Large, Keith Lawrence, Lindsay","year":"2013","venue":"Bulletin of the American Meteorological Society","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Ji et al., 2020] Xiaozhong Ji, Yun Cao, Ying Tai, Chengjie Wang, Jilin Li, and Feiyue Huang. Real-world super- resolution via kernel estimation and noise injection. In proc. of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshop (CVPRW), pages 1914- 1923, 2020.","title":"Real-world superresolution via kernel estimation and noise injection","authors":"Xiaozhong Ji, Yun Cao, Ying Tai, Chengjie Wang, Jilin Li, Feiyue Huang","year":"2020","venue":"proc. of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshop (CVPRW)","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Kim et al., 2016] Jiwon Kim, Jung Kwon Lee, and Ky- oung Mu Lee. Accurate image super-resolution using very deep convolutional networks. In proc. of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 1646-1654, 2016.","title":"Accurate image super-resolution using very deep convolutional networks","authors":"Jiwon Kim, Jung Kwon Lee, Kyoung Mu, Lee","year":"2016","venue":"proc. of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Kumar et al., 2021] Bipin Kumar, Rajib Chattopadhyay, Manmeet Singh, Niraj Chaudhari, Karthik Kodari, and Amit Barve. Deep learning-based downscaling of sum- mer monsoon rainfall data over indian region. Theoretical and Applied Climatology, 143:1145-1156, 2021.","title":"Deep learning-based downscaling of summer monsoon rainfall data over indian region","authors":"Bipin Kumar, Rajib Chattopadhyay, Manmeet Singh, Niraj Chaudhari, Karthik Kodari, Amit Barve","year":"2021","venue":"Theoretical and Applied Climatology","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Ledig et al., 2017] Christian Ledig, Lucas Theis, Ferenc Huszar, Jose Caballero, Andrew Cunningham, Alejandro Acosta, Andrew Aitken, Alykhan Tejani, Johannes Totz, Zehan Wang, and Wenzhe Shi. Photo-realistic single image super-resolution using a generative adversarial network. In proc. of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), July 2017.","title":"Photo-realistic single image super-resolution using a generative adversarial network","authors":"Ledig","year":"2017","venue":"proc. of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Lim et al., 2017] Bee Lim, Sanghyun Son, Heewon Kim, Seungjun Nah, and Kyoung Mu Lee. Enhanced deep resid- ual networks for single image super-resolution. In proc. of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshop (CVPRW), July 2017.","title":"Enhanced deep residual networks for single image super-resolution","authors":"Lim","year":"2017","venue":"proc. of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshop (CVPRW)","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Lu et al., 2022] Zhisheng Lu, Juncheng Li, Hong Liu, Chaoyan Huang, Linlin Zhang, and Tieyong Zeng. Trans- former for single image super-resolution. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 457-466, 2022.","title":"Trans-former for single image super-resolution","authors":"Zhisheng Lu, Juncheng Li, Hong Liu, Chaoyan Huang, Linlin Zhang, Tieyong Zeng","year":"2022","venue":"Proceedings of the IEEE/CVF conference on computer vision and pattern recognition","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Misra et al., 2018] Saptarshi Misra, Sudeshna Sarkar, and Pabitra Mitra. Statistical downscaling of precipitation using long short-term memory recurrent neural networks. Theo- retical and applied climatology, 134:1179-1196, 2018.","title":"Statistical downscaling of precipitation using long short-term memory recurrent neural networks","authors":"Saptarshi Misra, Sudeshna Sarkar, Pabitra Mitra","year":"2018","venue":"Theoretical and applied climatology","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Palmer et al., 2014] TN Palmer, A Döring, and G Seregin. The real butterfly effect. Nonlinearity, 27(9):R123, 2014.","title":"The real butterfly effect","authors":"Palmer","year":"2014","venue":"Nonlinearity","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Park et al., 2022] Sungwon Park, Karandeep Singh, Arjun Nellikkattil, Elke Zeller, Tung Duong Mai, and Meeyoung Cha. Downscaling earth system models with deep learning. In proc. of the ACM International Conference on Knowl- edge Discovery and Data Mining (SIGKDD), aug 2022.","title":"Downscaling earth system models with deep learning","authors":"Sungwon Park, Karandeep Singh, Arjun Nellikkattil, Elke Zeller, Tung Duong Mai, Meeyoung Cha","year":"2022","venue":"proc. of the ACM International Conference on Knowledge Discovery and Data Mining (SIGKDD)","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Rampal et al., 2022] Neelesh Rampal, Peter B Gibson, Abha Sood, Stephen Stuart, Nicolas C Fauchereau, Chris Bran- dolino, Ben Noll, and Tristan Meyers. High-resolution downscaling with interpretable deep learning: Rainfall ex- tremes over new zealand. Weather and Climate Extremes, 38:100525, 2022.","title":"High-resolution downscaling with interpretable deep learning: Rainfall extremes over new zealand","authors":"Neelesh Rampal, Abha Peter B Gibson, Stephen Sood, Nicolas C Stuart, Chris Fauchereau, Ben Brandolino, Tristan Noll, Meyers","year":"2022","venue":"Weather and Climate Extremes","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Seneviratne et al., 2021] S.I. Seneviratne, X. Zhang, M. Ad- nan, W. Badi, C. Dereczynski, A. Di Luca, S. Ghosh, I. Iskandar, J. Kossin, S. Lewis, F. Otto, I. Pinto, M. Satoh, S.M. Vicente-Serrano, M. Wehner, and B. Zhou. Weather and Climate Extreme Events in a Changing Climate, page 1513-1766. Cambridge University Press, Cambridge, United Kingdom and New York, NY, USA, 2021.","title":"Weather and Climate Extreme Events in a Changing Climate","authors":"S I Seneviratne, X Zhang, M Adnan, W Badi, C Dereczynski, A Di Luca, S Ghosh, I Iskandar, J Kossin, S Lewis, F Otto, I Pinto, M Satoh, S M Vicente-Serrano, M Wehner, B Zhou","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Small et al., 2014] R Justin Small, Julio Bacmeister, David Bailey, Allison Baker, Stuart Bishop, Frank Bryan, Julie Caron, John Dennis, Peter Gent, Hsiao-ming Hsu, et al. A new synoptic scale resolving global climate simulation using the community earth system model. Journal of Ad- vances in Modeling Earth Systems, 6(4):1065-1094, 2014.","title":"A new synoptic scale resolving global climate simulation using the community earth system model","authors":"Justin Small, Julio Bacmeister, David Bailey, Allison Baker, Stuart Bishop, Frank Bryan, Julie Caron, John Dennis, Peter Gent, Hsiao-Ming Hsu","year":"2014","venue":"Journal of Advances in Modeling Earth Systems","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Soh et al., 2020] Jae Woong Soh, Sunwoo Cho, and Nam Ik Cho. Meta-transfer learning for zero-shot super-resolution. In proc. of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 3516-3525, 2020.","title":"Meta-transfer learning for zero-shot super-resolution","authors":"Jae Woong Soh, Sunwoo Cho, Nam Ik Cho","year":"2020","venue":"proc. of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Stengel et al., 2020] Karen Stengel, Andrew Glaws, Dylan Hettinger, and Ryan N King. Adversarial super-resolution of climatological wind and solar data. Proceedings of the National Academy of Sciences, 117(29):16805-16815, 2020.","title":"Adversarial super-resolution of climatological wind and solar data","authors":"Karen Stengel, Andrew Glaws, Dylan Hettinger, Ryan N King","year":"2020","venue":"Proceedings of the National Academy of Sciences","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Sun et al., 2019] Qianru Sun, Yaoyao Liu, Tat-Seng Chua, and Bernt Schiele. Meta-transfer learning for few-shot learning. In proc. of the IEEE/CVF Conference on Com- puter Vision and Pattern Recognition (CVPR), pages 403- 412, 2019.","title":"Meta-transfer learning for few-shot learning","authors":"Sun","year":"2019","venue":"proc. of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Vandal et al., 2017] Thomas Vandal, Evan Kodra, Sangram Ganguly, Andrew Michaelis, Ramakrishna Nemani, and Auroop R. Ganguly. DeepSD. In proc. of the ACM In- ternational Conference on Knowledge Discovery and Data Mining (SIGKDD), aug 2017.","title":"proc. of the ACM International Conference on Knowledge Discovery and Data Mining (SIGKDD)","authors":"Thomas Vandal, Evan Kodra, Sangram Ganguly, Andrew Michaelis, Ramakrishna Nemani, R Auroop, Ganguly, Deepsd","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Vandal et al., 2019] Thomas Vandal, Evan Kodra, and Au- roop R Ganguly. Intercomparison of machine learning methods for statistical downscaling: the case of daily and extreme precipitation. Theoretical and Applied Climatol- ogy, 137:557-570, 2019.","title":"Intercomparison of machine learning methods for statistical downscaling: the case of daily and extreme precipitation","authors":"Thomas Vandal, Evan Kodra, Auroop R Ganguly","year":"2019","venue":"Theoretical and Applied Climatology","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Wang et al., 2021] Longguang Wang, Yingqian Wang, Xi- aoyu Dong, Qingyu Xu, Jungang Yang, Wei An, and Yulan Guo. Unsupervised degradation representation learning for blind super-resolution. In proc. of the IEEE/CVF Confer- ence on Computer Vision and Pattern Recognition (CVPR), pages 10581-10590, 2021.","title":"Unsupervised degradation representation learning for blind super-resolution","authors":"Wang","year":"2021","venue":"proc. of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Zhang et al., 2018a] Kai Zhang, Wangmeng Zuo, and Lei Zhang. Learning a single convolutional super-resolution network for multiple degradations. In proc. of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2018.","title":"Learning a single convolutional super-resolution network for multiple degradations","authors":"Zhang","year":"2018","venue":"proc. of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[Zhang et al., 2018b] Yulun Zhang, Kunpeng Li, Kai Li, Lichen Wang, Bineng Zhong, and Yun Fu. Image super- resolution using very deep residual channel attention net- works. In Proceedings of the European conference on computer vision (ECCV), pages 286-301, 2018.","title":"Image superresolution using very deep residual channel attention networks","authors":"Zhang","year":"2018","venue":"Proceedings of the European conference on computer vision (ECCV)","doi":null,"url":null,"internal_url":null},{"position":33,"raw":"[Zhang et al., 2018c] Yulun Zhang, Yapeng Tian, Yu Kong, Bineng Zhong, and Yun Fu. Residual dense network for image super-resolution. In Proceedings of the IEEE con- ference on computer vision and pattern recognition, pages 2472-2481, 2018.","title":"Residual dense network for image super-resolution","authors":"Zhang","year":"2018","venue":"Proceedings of the IEEE conference on computer vision and pattern recognition","doi":null,"url":null,"internal_url":null},{"position":34,"raw":"[Zontak and Irani, 2011] Maria Zontak and Michal Irani. In- ternal statistics of a single natural image. In proc. of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 977-984, 2011.","title":"Maria Zontak and Michal Irani. Internal statistics of a single natural image","authors":"Irani Zontak","year":"2011","venue":"proc. of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}