{"doi":"10.1029/2022ms003593","title":"Deep Learning Regional Climate Model Emulators: A Comparison of Two Downscaling Training Frameworks","abstract":"<jats:title>Abstract</jats:title><jats:p>Regional climate models (RCMs) have a high computational cost due to their higher spatial resolution compared to global climate models (GCMs). Therefore, various downscaling approaches have been developed as a surrogate for the dynamical downscaling of GCMs. This study assesses the potential of using a cost‐efficient machine learning alternative to dynamical downscaling by using the example case study of emulating surface mass balance (SMB) over the Antarctic Peninsula. More specifically, we determine the impact of the training framework by comparing two training scenarios: (a) a perfect and (b) an imperfect model framework. In the perfect model framework, the RCM‐emulator learns only the downscaling function; therefore, it was trained with upscaled RCM (UPRCM) features at GCM resolution. This emulator accurately reproduced SMB when evaluated on UPRCM, but its predictions on GCM data conserved RCM‐GCM inconsistencies and led to underestimation. In the imperfect model framework, the RCM‐emulator was trained with GCM features and downscaled the GCM while exposed to RCM‐GCM inconsistencies. This emulator predicted SMB close to the truth, showing it learned the underlying inconsistencies and dynamics. Our results suggest that a deep learning RCM‐emulator can learn the proper GCM to RCM downscaling function while working directly with GCM data. Furthermore, the RCM‐emulator presents a significant computational gain compared to an RCM simulation. We conclude that machine learning emulators can be applied to produce fast and fine‐scaled predictions of RCM simulations from GCM data.</jats:p>","journal":"Journal of Advances in Modeling Earth Systems","year":2023,"id":25918,"datarank":1.2060086283655618,"base_score":3.8066624897703196,"endowment":3.8066624897703196,"self_citation_contribution":0.5709993734655481,"citation_network_contribution":0.6350092549000137,"self_endowment_contribution":0.5709993734655481,"citer_contribution":0.6350092549000137,"corpus_percentile":null,"corpus_rank":null,"citation_count":44,"citer_count":39,"citers_with_citation_signal":24,"citers_with_endowment":24,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":null,"is_data_producer":false,"deposit_databanks":null,"is_oa":false,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":null,"fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":151279,"name":"Sophie de Roda Husman","orcid":"0000-0001-8830-9894","position":1,"is_corresponding":false},{"id":151280,"name":"Stef Lhermitte","orcid":"0000-0002-1622-0177","position":2,"is_corresponding":false},{"id":151278,"name":"Marijn van der Meer","orcid":"0000-0002-7604-4494","position":0,"is_corresponding":false}],"reference_count":0,"raw_metadata":{"has_enrichment":true,"base_score":3.8066624897703196,"endowment":3.8066624897703196,"datacite_reuse_total":0,"file_count":0,"downloads":0,"views":0,"has_version_chain":false,"is_dataset":false,"is_oa":false,"pmid":"18998881","pmcid":null,"openalex_id":"https://openalex.org/W4379739870","authors":[],"funders":[{"funder_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek","grant_id":"OCENW.GROOT.2019.091","title":"State and fate of Antarctica’s gatekeepers: a HIgh Resolution approach for Ice ShElf instability (HiRISE)"}],"total_grants":1,"fwci":6.6095,"citation_percentile":0.97582119,"influential_citations":2,"citation_trend":[{"year":2023,"count":2},{"year":2024,"count":18},{"year":2025,"count":16},{"year":2026,"count":8}],"oa_status":"gold","license":"cc-by","oa_locations":[{"url":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2022MS003593","host_type":"journal"},{"url":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2022MS003593","host_type":"GOLD"},{"url":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1029/2022MS003593","host_type":"publisher"},{"url":"https://agupubs.onlinelibrary.wiley.com/doi/pdf/10.1029/2022MS003593","host_type":"publisher"},{"url":"https://doi.org/10.1029/2022ms003593","host_type":"journal"},{"url":"https://lirias.kuleuven.be/handle/20.500.12942/721339","host_type":"repository"},{"url":"https://www.dora.lib4ri.ch/wsl/islandora/object/wsl%3A35455","host_type":"repository"},{"url":"https://lirias.kuleuven.be/retrieve/02af9b20-7642-45b8-806b-8f33bbc1b998","host_type":"repository"},{"url":"https://doi.org/10.22541/essoar.167214210.02213149/v1","host_type":""},{"url":"https://dx.doi.org/10.3929/ethz-b-000617206","host_type":""},{"url":"http://hdl.handle.net/20.500.11850/617206","host_type":""}],"fields_of_study":["Climate variability and models","Cryospheric studies and observations","Meteorological Phenomena and Simulations","Environmental Science","Computer Science"],"mesh_terms":[],"keywords":["Downscaling","GCM transcription factors","Computer science","Climate model","Climatology","Environmental science","General Circulation Model","Climate change","Geology","Science & Technology","EARTH SYSTEM MODEL","SURFACE MASS-BALANCE","machine learning; RCM-emulator; GCM downscaling; Antarctica","ERRORS","machine learning","PRECIPITATION","GCM downscaling","Physical Sciences","Meteorology & Atmospheric Sciences","RCM-emulator","Antarctica","CMIP5","3704 Geoinformatics","0401 Atmospheric Sciences","3701 Atmospheric sciences","MELT"],"sdg_mappings":[{"sdg_number":13,"sdg_label":"13. Climate action"},{"sdg_number":0,"sdg_label":"Climate action"}],"linked_datasets":[],"clinical_trials":[],"software_tools":[],"database_accessions":[],"source":"live","citation_network_status":"fetched"},"created_at":"2026-06-08T09:30:03.826885Z","pmid":null,"pmcid":null,"fwci":null,"citation_percentile":null,"influential_citations":0,"oa_status":null,"license":null,"views":0,"total_file_size_bytes":0,"version_count":0,"fair_f":null,"fair_a":null,"fair_i":null,"fair_r":null,"fair_zscore":null,"fair_rationale":null,"fair_model":null,"fair_agent_version":null,"fair_fulltext_source":null,"fair_has_llm":null,"fair_computed_at":null,"clinical_trials":[],"software_tools":[],"db_accessions":[],"linked_datasets":[],"topics":[]}