{"type":"ScholarlyArticle","title":"Generating High Resolution Climate Change Projections through Single Image Super-Resolution: An Abridged Version","authors":[{"name":"Thomas Vandal","slug":"thomas-vandal","given":"Thomas","family":"Vandal","affiliation":"Northeastern University , Civil and Environmental Engineering"},{"name":"Evan Kodra","slug":"evan-kodra","given":"Evan","family":"Kodra","affiliation":"risQ Inc."},{"name":"Sangram Ganguly","slug":"sangram-ganguly","given":"Sangram","family":"Ganguly","affiliation":"NASA Ames Research Center; Bay Area Environmental Research Institute"},{"name":"Andrew Michaelis","slug":"andrew-michaelis","given":"Andrew","family":"Michaelis","affiliation":"University Corporation , Monterey Bay"},{"name":"Ramakrishna Nemani","slug":"ramakrishna-nemani","given":"Ramakrishna","family":"Nemani","affiliation":"NASA Ames Research Center; NASA Advanced Supercomputing Division"},{"name":"Auroop R Ganguly","slug":"auroop-r-ganguly","given":"Auroop R","family":"Ganguly","affiliation":"Northeastern University , Civil and Environmental Engineering; risQ Inc."}],"abstract":"The impacts of climate change are felt by most critical systems, such as infrastructure, ecological systems, and power-plants. However, contemporary Earth System Models (ESM) are run at spatial resolutions too coarse for assessing effects this localized. Local scale projections can be obtained using statistical downscaling, a technique which uses historical climate observations to learn a low-resolution to high-resolution mapping. The spatio-temporal nature of the climate system motivates the adaptation of super-resolution image processing techniques to statistical downscaling. In our work, we present DeepSD, a generalized stacked super resolution convolutional neural network (SRCNN) framework with multi-scale input channels for statistical downscaling of climate variables. A comparison of DeepSD to four state-of-the-art methods downscaling daily precipitation from 1 degree (~100km) to 1/8 degrees (~12.5km) over the Continental United States. Furthermore, a framework using the NASA Earth Exchange (NEX) platform is discussed for downscaling more than 20 ESM models with multiple emission scenarios.","doi":"10.24963/ijcai.2018/759","url":"https://ijcai.org/proceedings/2018/759","pdf":"https://ijcai.org/proceedings/2018/0759.pdf","markdown":"https://ijcai.org/proceedings/2018/759.md","bibtex":"https://ijcai.org/proceedings/2018/bibtex/759","volume":{"slug":"2018","title":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2018","url":"https://ijcai.org/proceedings/2018/","year":2018,"location":"Stockholm","dates":"13-19 July 2018","editors":"Jérôme Lang","isbn":"978-0-9992411-2-7","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2018"},"section":"Sister Conferences Best Papers","track":"Best Sister Conferences","number":759,"pages":{"first":5389,"last":5393},"keywords":["Multidisciplinary Topics and Applications: Multidisciplinary Topics and Applications","Machine Learning: Deep Learning"],"videos":[],"references":[{"position":1,"raw":"[Abadi et al., 2016] Martın Abadi, Ashish Agarwal, Paul Barham, Eugene Brevdo, Zhifeng Chen, Craig Citro, Greg S Corrado, Andy Davis, Jeffrey Dean, Matthieu Devin, et al. Tensorflow: Large-scale machine learn- ing on heterogeneous distributed systems. arXiv preprint arXiv:1603.04467, 2016.","title":"Tensorflow: Large-scale machine learning on heterogeneous distributed systems","authors":"Abadi","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Cannon, 2011] Alex J Cannon. Quantile regression neu- ral networks: Implementation in r and application to precipitation downscaling. Computers & geosciences, 37(9):1277-1284, 2011.","title":"Quantile regression neural networks: Implementation in r and application to precipitation downscaling","authors":"Alex J Cannon","year":"2011","venue":"Computers & geosciences","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Daly et al., 2008] Christopher Daly, Michael Halbleib, Joseph I Smith, Wayne P Gibson, Matthew K Doggett, George H Taylor, Jan Curtis, and Phillip P Pasteris. Phys- iographically sensitive mapping of climatological temper- ature and precipitation across the conterminous united states. International journal of climatology, 28(15):2031- 2064, 2008.","title":"Physiographically sensitive mapping of climatological temperature and precipitation across the conterminous united states","authors":"Christopher Daly, Michael Halbleib, I Joseph, Wayne P Smith, Matthew K Gibson, George H Doggett, Jan Taylor, Phillip P Curtis, Pasteris","year":"2008","venue":"International journal of climatology","doi":null,"url":null,"internal_url":null},{"position":4,"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 European Conference on Computer Vision, pages 184-199. Springer, 2014.","title":"Learning a deep convolutional network for image super-resolution","authors":"Chao Dong, Chen Change Loy, Kaiming He, Xiaoou Tang","year":"2014","venue":"European Conference on Computer Vision","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Gal, 2016] Yarin Gal. Uncertainty in Deep Learning. PhD thesis, Ph. D. thesis, University of Cambridge, 2016.","title":"Uncertainty in Deep Learning","authors":"Yarin Gal","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Ghosh, 2010] Subimal Ghosh. Svm-pgsl coupled approach for statistical downscaling to predict rainfall from gcm output. Journal of Geophysical Research: Atmospheres, 115(D22), 2010.","title":"Subimal Ghosh. Svm-pgsl coupled approach for statistical downscaling to predict rainfall from gcm output","authors":"Ghosh","year":"2010","venue":"Journal of Geophysical Research: Atmospheres","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Hessami et al., 2008] Masoud Hessami, Philippe Gachon, Taha BMJ Ouarda, and André St-Hilaire. Automated regression-based statistical downscaling tool. Environ- mental Modelling & Software, 23(6):813-834, 2008.","title":"Automated regression-based statistical downscaling tool","authors":"Masoud Hessami, Philippe Gachon, Bmj Taha, André Ouarda, St-Hilaire","year":"2008","venue":"Environmental Modelling & Software","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Hinton and Salakhutdinov, 2006] Geoffrey E Hinton and Ruslan R Salakhutdinov. Reducing the dimensionality of data with neural networks. Science, 313(5786):504-507, 2006.","title":"Reducing the dimensionality of data with neural networks","authors":"Geoffrey E Hinton, Ruslan R Salakhutdinov","year":"2006","venue":"Science","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Kingma and Ba, 2014] Diederik Kingma and Jimmy Ba. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980, 2014.","title":"Adam: A method for stochastic optimization","authors":"Diederik Kingma, Jimmy Ba","year":"2014","venue":null,"doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Nicholls and Cazenave, 2010] Robert J Nicholls and Anny Cazenave. Sea-level rise and its impact on coastal zones. science, 328(5985):1517-1520, 2010.","title":"Sea-level rise and its impact on coastal zones","authors":"J Robert, Anny Nicholls, Cazenave","year":"2010","venue":"science","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Pachauri et al., 2014] Rajendra K Pachauri, MR Allen, VR Barros, J Broome, W Cramer, R Christ, JA Church, L Clarke, Q Dahe, P Dasgupta, et al. Climate change 2014: Synthesis report. contribution of working groups i, ii and iii to the fifth assessment report of the intergovernmental panel on climate change. 2014.","title":"Climate change 2014: Synthesis report. contribution of working groups i, ii and iii to the fifth assessment report of the intergovernmental panel on climate change","authors":"M R Rajendra K Pachauri, Allen, J Vr Barros, W Broome, R Cramer, J A Christ, L Church, Q Clarke, Dahe, Dasgupta","year":"2014","venue":null,"doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Perkins et al., 2007] SE Perkins, AJ Pitman, NJ Holbrook, and J McAneney. Evaluation of the ar4 climate models' simulated daily maximum temperature, minimum temper- ature, and precipitation over australia using probability density functions. Journal of climate, 20(17):4356-4376, 2007.","title":"Evaluation of the ar4 climate models' simulated daily maximum temperature, minimum temperature, and precipitation over australia using probability density functions","authors":"Perkins","year":"2007","venue":"Journal of climate","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Pierce et al., 2014] David W Pierce, Daniel R Cayan, and Bridget L Thrasher. Statistical downscaling using local- ized constructed analogs (loca)*. Journal of Hydrometeo- rology, 15(6):2558-2585, 2014.","title":"Statistical downscaling using localized constructed analogs (loca)*","authors":"David W Pierce, Bridget L Daniel R Cayan, Thrasher","year":"2014","venue":"Journal of Hydrometeorology","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Salvi et al., 2015] Kaustubh Salvi, Subimal Ghosh, and Au- roop R. Ganguly. Credibility of statistical downscaling under nonstationary climate. Climate Dynamics, (May 2014), 2015.","title":"Credibility of statistical downscaling under nonstationary climate","authors":"Kaustubh Salvi, Subimal Ghosh, Auroop R Ganguly","year":"2014","venue":"Climate Dynamics","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Schiermeier, 2010] Quirin Schiermeier. The real holes in climate science. Nature News, 463(7279):284-287, 2010.","title":"The real holes in climate science","authors":"Quirin Schiermeier","year":"2010","venue":"Nature News","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Taylor et al., 2012] Karl E Taylor, Ronald J Stouffer, and Gerald A Meehl. An overview of cmip5 and the experi- ment design. Bulletin of the American Meteorological So- ciety, 93(4):485, 2012.","title":"An overview of cmip5 and the experiment design","authors":"Karl E Taylor, Ronald J Stouffer, Gerald A Meehl","year":"2012","venue":"Bulletin of the American Meteorological Society","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Trenberth, 2012] Kevin E Trenberth. Framing the way to re- late climate extremes to climate change. Climatic change, 115:283-290, 2012.","title":"Framing the way to relate climate extremes to climate change","authors":"Kevin E Trenberth","year":"2012","venue":"Climatic change","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Vandal et al., 2017a] Thomas Vandal, Evan Kodra, and Au- roop R Ganguly. Intercomparison of machine learning methods for statistical downscaling: The case of daily and extreme precipitation. arXiv preprint arXiv:1702.04018, 2017.","title":"Intercomparison of machine learning methods for statistical downscaling: The case of daily and extreme precipitation","authors":"Vandal","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Vandal et al., 2017b] Thomas Vandal, Evan Kodra, San- gram Ganguly, Andrew Michaelis, Ramakrishna Nemani, and Auroop R Ganguly. Deepsd: Generating high res- olution climate change projections through single image super-resolution. In 23rd ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2017.","title":"Deepsd: Generating high resolution climate change projections through single image super-resolution","authors":"Vandal","year":"2017","venue":"23rd ACM SIGKDD Conference on Knowledge Discovery and Data Mining","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Vandal et al., 2018] Thomas Vandal, Evan Kodra, Jennifer Dy, Sangram Ganguly, Ramakrishna Nemani, and Au- roop R Ganguly. Quantifying uncertainty in discrete- continuous and skewed data with bayesian deep learning. arXiv preprint arXiv:1802.04742, 2018.","title":"Quantifying uncertainty in discretecontinuous and skewed data with bayesian deep learning","authors":"Thomas Vandal, Evan Kodra, Jennifer Dy, Sangram Ganguly, Ramakrishna Nemani, Auroop R Ganguly","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Vincent et al., 2010] Pascal Vincent, Hugo Larochelle, Is- abelle Lajoie, Yoshua Bengio, and Pierre-Antoine Man- zagol. Stacked denoising autoencoders: Learning use- ful representations in a deep network with a local de- noising criterion. Journal of Machine Learning Research, 11(Dec):3371-3408, 2010.","title":"Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion","authors":"Pascal Vincent, Hugo Larochelle, Isabelle Lajoie, Yoshua Bengio, Pierre-Antoine Manzagol","year":"2010","venue":"Journal of Machine Learning Research","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}