{"database":"biostudies-literature","file_versions":[],"scores":null,"additional":{"omics_type":["Unknown"],"volume":["15(1)"],"submitter":["Grundner A"],"funding":["Deutsches Zentrum für Luft- und Raumfahrt e.V. (DLR)"],"pubmed_abstract":["Cloud-related parameterizations remain a leading source of uncertainty in climate projections. Although machine learning holds promise for Earth system models (ESMs), many data-driven parameterizations lack interpretability, physical consistency, and smooth integration into ESMs. Here, a two-step method is presented to improve a climate model with data-driven parameterizations. First, we incorporate a physically consistent cloud cover parameterization-derived from storm-resolving simulations via symbolic regression, preserving interpretability while enhancing accuracy-into the ICON global atmospheric model. Second, we apply the gradient-free Nelder-Mead optimizer to automatically recalibrate the hybrid model against Earth observations, tuning in nested stages (2-, 7-, 30- and 365-day runs) to ensure stability and tractability. The tuned hybrid model substantially reduces long-standing biases in cloud cover-particularly over the Southern Ocean (by 75%) and subtropical stratocumulus regions (by 44%)-and remains robust under +4K surface warming. These results demonstrate that interpretable machine-learned parameterizations, paired with practical tuning, can efficiently and transparently strengthen ESM fidelity."],"journal":["Scientific reports"],"pagination":["43836"],"full_dataset_link":["https://www.ebi.ac.uk/biostudies/studies/S-EPMC12705993"],"repository":["biostudies-literature"],"pubmed_title":["Reduced cloud cover errors in a hybrid AI-climate model through equation discovery and automatic tuning."],"pmcid":["PMC12705993"],"pubmed_authors":["Schlund M","Beucler T","Savre J","Eyring V","Grundner A","Lauer A"],"additional_accession":[]},"is_claimable":false,"name":"Reduced cloud cover errors in a hybrid AI-climate model through equation discovery and automatic tuning.","description":"Cloud-related parameterizations remain a leading source of uncertainty in climate projections. Although machine learning holds promise for Earth system models (ESMs), many data-driven parameterizations lack interpretability, physical consistency, and smooth integration into ESMs. Here, a two-step method is presented to improve a climate model with data-driven parameterizations. First, we incorporate a physically consistent cloud cover parameterization-derived from storm-resolving simulations via symbolic regression, preserving interpretability while enhancing accuracy-into the ICON global atmospheric model. Second, we apply the gradient-free Nelder-Mead optimizer to automatically recalibrate the hybrid model against Earth observations, tuning in nested stages (2-, 7-, 30- and 365-day runs) to ensure stability and tractability. The tuned hybrid model substantially reduces long-standing biases in cloud cover-particularly over the Southern Ocean (by 75%) and subtropical stratocumulus regions (by 44%)-and remains robust under +4K surface warming. These results demonstrate that interpretable machine-learned parameterizations, paired with practical tuning, can efficiently and transparently strengthen ESM fidelity.","dates":{"release":"2025-01-01T00:00:00Z","publication":"2025 Dec","modification":"2026-06-07T05:03:59.189Z","creation":"2026-06-07T03:06:33.566Z"},"accession":"S-EPMC12705993","cross_references":{"pubmed":["41390512"],"doi":["10.1038/s41598-025-29155-3"]}}