{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,2]],"date-time":"2026-03-02T10:24:35Z","timestamp":1772447075346,"version":"3.50.1"},"reference-count":47,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2024,6,12]],"date-time":"2024-06-12T00:00:00Z","timestamp":1718150400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,6,12]],"date-time":"2024-06-12T00:00:00Z","timestamp":1718150400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100006206","name":"Biological and Environmental Research","doi-asserted-by":"publisher","award":["DE-SC0023044"],"award-info":[{"award-number":["DE-SC0023044"]}],"id":[{"id":"10.13039\/100006206","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Earth Sci Inform"],"published-print":{"date-parts":[[2024,8]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Climate projections at fine spatial resolutions are required to conduct accurate risk assessment for critical infrastructure and design adaptation planning. Generating these projections using advanced Earth system models (ESM) requires significant computational resources. To address this issue, various statistical downscaling techniques have been introduced to generate fine-resolution data from coarse-resolution simulations. In this study, we evaluate and compare five deep learning-based downscaling techniques, namely, super-resolution convolutional neural networks, fast super-resolution convolutional neural network ESM, efficient sub-pixel convolutional neural network, enhanced deep residual network (EDRN), and super-resolution generative adversarial network (SRGAN). These techniques are applied to a dataset generated by the Energy Exascale Earth System Model (E3SM), focusing on key surface variables such as surface temperature, shortwave heat flux, and longwave heat flux. Models are trained and validated using paired fine-resolution (0.25<jats:inline-formula><jats:alternatives><jats:tex-math>$$^{\\circ }$$<\/jats:tex-math><mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\">\n                  <mml:msup>\n                    <mml:mrow\/>\n                    <mml:mo>\u2218<\/mml:mo>\n                  <\/mml:msup>\n                <\/mml:math><\/jats:alternatives><\/jats:inline-formula>) and coarse-resolution (1<jats:inline-formula><jats:alternatives><jats:tex-math>$$^{\\circ }$$<\/jats:tex-math><mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\">\n                  <mml:msup>\n                    <mml:mrow\/>\n                    <mml:mo>\u2218<\/mml:mo>\n                  <\/mml:msup>\n                <\/mml:math><\/jats:alternatives><\/jats:inline-formula>) monthly data obtained from a 9-year simulation. Next, blind testing is performed using monthly data obtained from two different years outside of the training and validation set. To evaluate the efficiency of each technique, different statistical metrics are used, including mean squared error (MSE), peak signal-to-noise ratio (PSNR), structural similarity index measure (SSIM), and learned perceptual image patch similarity (LPIPS). The results show that EDRN outperforms other algorithms in terms of PSNR, SSIM, and MSE, but struggles to capture fine-scale features in the data. In contrast, SRGAN, a generative model that uses perceptual loss, excels in capturing fine details at boundaries and internal structures, resulting in lower LPIPS than other methods.<\/jats:p>","DOI":"10.1007\/s12145-024-01357-9","type":"journal-article","created":{"date-parts":[[2024,6,12]],"date-time":"2024-06-12T11:01:48Z","timestamp":1718190108000},"page":"3511-3528","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["ESM data downscaling: a comparison of super-resolution deep learning models"],"prefix":"10.1007","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1161-3289","authenticated-orcid":false,"given":"Nikhil M.","family":"Pawar","sequence":"first","affiliation":[]},{"given":"Ramin","family":"Soltanmohammadi","sequence":"additional","affiliation":[]},{"given":"Seyed Kourosh","family":"Mahjour","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6543-1691","authenticated-orcid":false,"given":"Salah A.","family":"Faroughi","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,6,12]]},"reference":[{"key":"1357_CR1","doi-asserted-by":"crossref","unstructured":"B\u00fcrger G (1996) Expanded downscaling for generating local weather scenarios. Clim Res 7:111\u2013128","DOI":"10.3354\/cr007111"},{"key":"1357_CR2","doi-asserted-by":"crossref","unstructured":"B\u00fcrger G, Chen Y (2005) Regression-based downscaling of spatial variability for hydrologic applications. J Hydrol 311:299\u2013317","DOI":"10.1016\/j.jhydrol.2005.01.025"},{"key":"1357_CR3","doi-asserted-by":"crossref","unstructured":"Cannon AJ (2011) Quantile regression neural networks: implementation in r and application to precipitation downscaling. Comput & Geosci 37:1277\u20131284","DOI":"10.1016\/j.cageo.2010.07.005"},{"key":"1357_CR4","doi-asserted-by":"crossref","unstructured":"Cheng Y, Wang D, Zhou P, Zhang T (2018) Model compression and acceleration for deep neural networks: the principles, progress, and challenges. IEEE Signal Process Mag 35:126\u2013136","DOI":"10.1109\/MSP.2017.2765695"},{"key":"1357_CR5","doi-asserted-by":"crossref","unstructured":"Choudhary T, Mishra V, Goswami A, Sarangapani J (2020) A comprehensive survey on model compression and acceleration. Artif Intell Rev 53:5113\u20135155","DOI":"10.1007\/s10462-020-09816-7"},{"key":"1357_CR6","doi-asserted-by":"crossref","unstructured":"Davarpanah A, Babaie H, Dhakal N (2023) Semantic modeling of climate change impacts on the implementation of the un sustainable development goals related to poverty, hunger, water, and energy. Earth Sci Inform 16:929\u2013943","DOI":"10.1007\/s12145-023-00941-9"},{"key":"1357_CR7","doi-asserted-by":"crossref","unstructured":"Deng X (2018) Enhancing image quality via style transfer for single image super-resolution. IEEE Signal Process Lett 25:571\u2013575","DOI":"10.1109\/LSP.2018.2805809"},{"key":"1357_CR8","doi-asserted-by":"crossref","unstructured":"Ding B, Qian H, Zhou J, (2018) Activation functions and their characteristics in deep neural networks. In: 2018 Chinese control and decision conference (CCDC), IEEE, pp 1836\u20131841","DOI":"10.1109\/CCDC.2018.8407425"},{"key":"1357_CR9","doi-asserted-by":"publisher","unstructured":"Dong C, Loy CC, He K, Tang X (2014) Learning a deep convolutional network for image super-resolution. In: European conference on computer vision, Springer, pp 184\u2013199. https:\/\/doi.org\/10.1007\/978-3-319-10593-2_13","DOI":"10.1007\/978-3-319-10593-2_13"},{"key":"1357_CR10","doi-asserted-by":"publisher","unstructured":"Dosselmann R, Yang XD (2011) A comprehensive assessment of the structural similarity index. Signal, Image and Video Processing 5:81\u201391. https:\/\/doi.org\/10.1007\/s11760-009-0144-1","DOI":"10.1007\/s11760-009-0144-1"},{"key":"1357_CR11","unstructured":"Dupont E, Goli\u0144ski A, Alizadeh M, Teh YW, Doucet A (2021) Coin: compression with implicit neural representations. arXiv:2103.03123"},{"key":"1357_CR12","doi-asserted-by":"publisher","unstructured":"E3SM\u00a0Project D (2018) Energy exascale earth system model v1.0. [Computer Software]. https:\/\/doi.org\/10.11578\/E3SM\/dc.20180418.36","DOI":"10.11578\/E3SM\/dc.20180418.36"},{"key":"1357_CR13","doi-asserted-by":"crossref","unstructured":"Faroughi SA, Datta P, Mahjour SK, Faroughi S (2022) Physics-informed neural networks with periodic activation functions for solute transport in heterogeneous porous media. arXiv:2212.08965","DOI":"10.3390\/math12010063"},{"key":"1357_CR14","doi-asserted-by":"crossref","unstructured":"Ghosh S (2010) Svm-pgsl coupled approach for statistical downscaling to predict rainfall from gcm output. J Geophys Res Atmos 115","DOI":"10.1029\/2009JD013548"},{"key":"1357_CR15","doi-asserted-by":"crossref","unstructured":"Harilal N, Singh M, Bhatia U (2021) Augmented convolutional lstms for generation of high-resolution climate change projections. IEEE Access 9, pp 25208\u201325218","DOI":"10.1109\/ACCESS.2021.3057500"},{"key":"1357_CR16","doi-asserted-by":"crossref","unstructured":"Hessami M, Gachon P, Ouarda TB, St-Hilaire A (2008) Automated regression-based statistical downscaling tool. Environ Model & Softw 23:813\u2013834","DOI":"10.1016\/j.envsoft.2007.10.004"},{"key":"1357_CR17","unstructured":"Hidalgo HG, Dettinger MD, Cayan DR (2008) Downscaling with constructed analogues: daily precipitation and temperature fields over the united states. California Energy Comm PIER Final Project Rep CEC-500-2007-123"},{"key":"1357_CR18","doi-asserted-by":"crossref","unstructured":"Hohenegger C, Korn P, Linardakis L, Redler R, Schnur R, Adamidis P, Bao J, Bastin S, Behravesh M, Bergemann M et\u00a0al (2023). Icon-sapphire: simulating the components of the earth system and their interactions at kilometer and subkilometer scales. Geosci Model Develop 16:779\u2013811","DOI":"10.5194\/gmd-16-779-2023"},{"key":"1357_CR19","doi-asserted-by":"crossref","unstructured":"Hurrell JW, Holland MM, Gent PR, Ghan S, Kay JE, Kushner PJ, Lamarque JF, Large WG, Lawrence D, Lindsay K et\u00a0al (2013) The community earth system model: a framework for collaborative research. Bull Am Meteorol Soc 94:1339\u20131360","DOI":"10.1175\/BAMS-D-12-00121.1"},{"key":"1357_CR20","doi-asserted-by":"crossref","unstructured":"Kharin VV, Zwiers FW, Zhang X, Hegerl GC (2007) Changes in temperature and precipitation extremes in the ipcc ensemble of global coupled model simulations. J Climate 20:1419\u20131444","DOI":"10.1175\/JCLI4066.1"},{"key":"1357_CR21","doi-asserted-by":"crossref","unstructured":"Kumar B, Atey K, Singh BB, Chattopadhyay R, Acharya N, Singh M, Nanjundiah RS, Rao SA (2023) On the modern deep learning approaches for precipitation downscaling. Earth Sci Inform 16:1459\u20131472","DOI":"10.1007\/s12145-023-00970-4"},{"key":"1357_CR22","doi-asserted-by":"crossref","unstructured":"Ledig C, Theis L, Husz\u00e1r F, Caballero J, Cunningham A, Acosta A, Aitken A, Tejani A, Totz J, Wang Z et\u00a0al (2017) Photo-realistic single image super-resolution using a generative adversarial network. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4681\u20134690","DOI":"10.1109\/CVPR.2017.19"},{"key":"1357_CR23","doi-asserted-by":"publisher","unstructured":"Li Y, Sixou B, Peyrin F (2021) A review of the deep learning methods for medical images super resolution problems. Irbm 42:120\u2013133. https:\/\/doi.org\/10.1016\/j.irbm.2020.08.004","DOI":"10.1016\/j.irbm.2020.08.004"},{"key":"1357_CR24","doi-asserted-by":"crossref","unstructured":"Lim B, Son S, Kim H, Nah S, Mu\u00a0Lee K (2017) Enhanced deep residual networks for single image super-resolution. In: Proceedings of the IEEE conference on computer vision and pattern recognition workshops, pp 136\u2013144","DOI":"10.1109\/CVPRW.2017.151"},{"key":"1357_CR25","doi-asserted-by":"crossref","unstructured":"Mahajan S, Evans KJ, Branstetter M, Anantharaj V, Leifeld JK (2015) Fidelity of precipitation extremes in high resolution global climate simulations. Procedia Comput Sci 51:2178\u20132187","DOI":"10.1016\/j.procs.2015.05.492"},{"key":"1357_CR26","doi-asserted-by":"crossref","unstructured":"Mahjour SK, Liguori G, Faroughi SA (2024) Selection of representative general circulation models under climatic uncertainty for western north america. J Water and Clim Chang","DOI":"10.21203\/rs.3.rs-2698287\/v1"},{"key":"1357_CR27","doi-asserted-by":"crossref","unstructured":"Manor A, Berkovic S (2015) Bayesian inference aided analog downscaling for near-surface winds in complex terrain. Atmos Res 164:27\u201336","DOI":"10.1016\/j.atmosres.2015.04.014"},{"key":"1357_CR28","doi-asserted-by":"crossref","unstructured":"Nicholls RJ, Cazenave A (2010) Sea-level rise and its impact on coastal zones. Science 328:1517\u20131520","DOI":"10.1126\/science.1185782"},{"key":"1357_CR29","doi-asserted-by":"crossref","unstructured":"Oyama N, Ishizaki NN, Koide S, Yoshida H (2023) Deep generative model super-resolves spatially correlated multiregional climate data. Sci Rep 13:5992","DOI":"10.1038\/s41598-023-32947-0"},{"key":"1357_CR30","doi-asserted-by":"crossref","unstructured":"Park S, Singh K, Nellikkattil A, Zeller E, Mai TD, Cha M (2022) Downscaling earth system models with deep learning. In: Proceedings of the 28th ACM SIGKDD conference on knowledge discovery and data mining, pp 3733\u20133742","DOI":"10.1145\/3534678.3539031"},{"key":"1357_CR31","doi-asserted-by":"publisher","unstructured":"Passarella LS, Mahajan S, Pal A, Norman MR (2022) Reconstructing high resolution esm data through a novel fast super resolution convolutional neural network (fsrcnn). Geophys Res Lett 49:e2021GL097571. https:\/\/doi.org\/10.1029\/2021GL097571","DOI":"10.1029\/2021GL097571"},{"key":"1357_CR32","doi-asserted-by":"crossref","unstructured":"Schmidt G (2010) The real holes in climate science. Nature 463:21","DOI":"10.1038\/463284a"},{"key":"1357_CR33","doi-asserted-by":"crossref","unstructured":"Serifi A, G\u00fcnther T, Ban N (2021) Spatio-temporal downscaling of climate data using convolutional and error-predicting neural networks. Front Clim 3:656479","DOI":"10.3389\/fclim.2021.656479"},{"key":"1357_CR34","doi-asserted-by":"crossref","unstructured":"Shi W, Caballero J, Husz\u00e1r F, Totz J, Aitken AP, Bishop R, Rueckert D, Wang Z (2016) Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1874\u20131883","DOI":"10.1109\/CVPR.2016.207"},{"key":"1357_CR35","unstructured":"Sitzmann V, Martel J, Bergman A, Lindell D, Wetzstein G (2020) Implicit neural representations with periodic activation functions. Adv Neural Inform Process Syst 33:7462\u20137473"},{"key":"1357_CR36","doi-asserted-by":"crossref","unstructured":"Soltanmohammadi R, Faroughi SA (2023) A comparative analysis of super-resolution techniques for enhancing micro-ct images of carbonate rocks. Appl Comput Geosci p 100143","DOI":"10.1016\/j.acags.2023.100143"},{"key":"1357_CR37","doi-asserted-by":"crossref","unstructured":"Stengel K, Glaws A, Hettinger D, King RN (2020) Adversarial super-resolution of climatological wind and solar data. Proceedings of the national academy of sciences 117:16805\u201316815","DOI":"10.1073\/pnas.1918964117"},{"key":"1357_CR38","doi-asserted-by":"publisher","unstructured":"Talab MA, Awang S, Najim SAdM (2019) Super-low resolution face recognition using integrated efficient sub-pixel convolutional neural network (espcn) and convolutional neural network (cnn). In: 2019 IEEE international conference on automatic control and intelligent systems (I2CACIS), IEEE, pp 331\u2013335. https:\/\/doi.org\/10.1109\/I2CACIS.2019.8825083","DOI":"10.1109\/I2CACIS.2019.8825083"},{"key":"1357_CR39","doi-asserted-by":"crossref","unstructured":"Tan C, Sun F, Kong T, Zhang W, Yang C, Liu C (2018) A survey on deep transfer learning. In: Artificial neural networks and machine learning\u2013ICANN 2018: 27th international conference on artificial neural networks, Rhodes, Greece, October 4\u20137, 2018. Proceedings, Part III 27, Springer, pp 270\u2013279","DOI":"10.1007\/978-3-030-01424-7_27"},{"key":"1357_CR40","doi-asserted-by":"crossref","unstructured":"Thrasher B, Maurer EP, McKellar C, Duffy PB (2012) Bias correcting climate model simulated daily temperature extremes with quantile mapping. Hydrol Earth Syst Sci 16, pp 3309\u20133314","DOI":"10.5194\/hess-16-3309-2012"},{"key":"1357_CR41","doi-asserted-by":"crossref","unstructured":"Trenberth KE (2012) Framing the way to relate climate extremes to climate change. Clim Chang 115:283\u2013290","DOI":"10.1007\/s10584-012-0441-5"},{"key":"1357_CR42","doi-asserted-by":"crossref","unstructured":"Vandal T, Kodra E, Ganguly S, Michaelis A, Nemani R, Ganguly AR (2017) Deepsd: generating high resolution climate change projections through single image super-resolution. In: Proceedings of the 23rd acm sigkdd international conference on knowledge discovery and data mining, pp 1663\u20131672","DOI":"10.1145\/3097983.3098004"},{"key":"1357_CR43","doi-asserted-by":"crossref","unstructured":"Venetsanou P, Anagnostopoulou C, Loukas A, Lazoglou G, Voudouris K (2019) Minimizing the uncertainties of rcms climate data by using spatio-temporal geostatistical modeling. Earth Sci Inform 12:183\u2013196","DOI":"10.1007\/s12145-018-0361-7"},{"key":"1357_CR44","doi-asserted-by":"crossref","unstructured":"Vu MT, Aribarg T, Supratid S, Raghavan SV, Liong SY (2016) Statistical downscaling rainfall using artificial neural network: significantly wetter Bangkok? Theor Appl Climatol 126:453\u2013467","DOI":"10.1007\/s00704-015-1580-1"},{"key":"1357_CR45","doi-asserted-by":"crossref","unstructured":"Zhan R, Isola P, Efros AA, Shechtman E, Wang O (2018) The unreasonable effectiveness of deep features as a perceptual metric. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 586\u2013595","DOI":"10.1109\/CVPR.2018.00068"},{"key":"1357_CR46","doi-asserted-by":"crossref","unstructured":"Zhang X, Yan X (2015) A new statistical precipitation downscaling method with bayesian model averaging: a case study in china. Clim Dyn 45:2541\u20132555","DOI":"10.1007\/s00382-015-2491-7"},{"key":"1357_CR47","doi-asserted-by":"crossref","unstructured":"Zhang Y, An M et\u00a0al (2017) Deep learning-and transfer learning-based super resolution reconstruction from single medical image. J Healthcare Eng 2017","DOI":"10.1155\/2017\/5859727"}],"container-title":["Earth Science Informatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s12145-024-01357-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s12145-024-01357-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s12145-024-01357-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,19]],"date-time":"2024-09-19T17:15:17Z","timestamp":1726766117000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s12145-024-01357-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,12]]},"references-count":47,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2024,8]]}},"alternative-id":["1357"],"URL":"https:\/\/doi.org\/10.1007\/s12145-024-01357-9","relation":{},"ISSN":["1865-0473","1865-0481"],"issn-type":[{"value":"1865-0473","type":"print"},{"value":"1865-0481","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,6,12]]},"assertion":[{"value":"20 November 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 May 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 June 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}]}}