{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/interpretable-multiscale-machine-learning","title":"Interpretable multiscale Machine Learning-Based Parameterizations of Convection for ICON","arxiv_id":"2311.03251","date":"2023-11-06","proceeding":null,"authors":["Helge Heuer","Mierk Schwabe","Pierre Gentine","Marco A. Giorgetta","Veronika Eyring"],"abstract":"Machine learning (ML)-based parameterizations have been developed for Earth System Models (ESMs) with the goal to better represent subgrid-scale processes or to accelerate computations. ML-based parameterizations within hybrid ESMs have successfully learned subgrid-scale processes from short high-resolution simulations. However, most studies used a particular ML method to parameterize the subgrid tendencies or fluxes originating from the compound effect of various small-scale processes (e.g., radiation, convection, gravity waves) in mostly idealized settings or from superparameterizations. Here, we use a filtering technique to explicitly separate convection from these processes in simulations with the Icosahedral Non-hydrostatic modelling framework (ICON) in a realistic setting and benchmark various ML algorithms against each other offline. We discover that an unablated U-Net, while showing the best offline performance, learns reverse causal relations between convective precipitation and subgrid fluxes. While we were able to connect the learned relations of the U-Net to physical processes this was not possible for the non-deep learning-based Gradient Boosted Trees. The ML algorithms are then coupled online to the host ICON model. Our best online performing model, an ablated U-Net excluding precipitating tracer species, indicates higher agreement for simulated precipitation extremes and mean with the high-resolution simulation compared to the traditional scheme. However, a smoothing bias is introduced both in water vapor path and mean precipitation. Online, the ablated U-Net significantly improves stability compared to the non-ablated U-Net and runs stable for the full simulation period of 180 days. Our results hint to the potential to significantly reduce systematic errors with hybrid ESMs.","url_abs":"https://arxiv.org/abs/2311.03251v5","url_pdf":"https://arxiv.org/pdf/2311.03251v5.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"links_only","authors_date_abstract":"arXiv metadata, CC0 1.0 (https://info.arxiv.org/help/license), from the Kaggle arXiv metadata snapshot of 2026-09-12"},"code_links":[{"paper_slug":"interpretable-multiscale-machine-learning","repo_url":"https://github.com/EyringMLClimateGroup/heuer23_ml_convection_parameterization","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2311.03251","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.03251"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/EyringMLClimateGroup/heuer23_ml_convection_parameterization","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":9,"unverified":7},"by_repo_kind":{"official":{"samples":16,"ran":9,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"87d0d51f184808c6","entry":"format_date_str","repo":"EyringMLClimateGroup/heuer23_ml_convection_parameterization","repo_kind":"official","path":"convection_param/HelperFuncs.py","file_url":"https://github.com/EyringMLClimateGroup/heuer23_ml_convection_parameterization/blob/HEAD/convection_param/HelperFuncs.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"87d0d51f184808c6"}},{"code_sha256_prefix":"bfe0b544d6d55843","entry":"get_ax_size","repo":"EyringMLClimateGroup/heuer23_ml_convection_parameterization","repo_kind":"official","path":"convection_param/setup_mpl_tex.py","file_url":"https://github.com/EyringMLClimateGroup/heuer23_ml_convection_parameterization/blob/HEAD/convection_param/setup_mpl_tex.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"bfe0b544d6d55843"}},{"code_sha256_prefix":"0fe62d62ce151e0c","entry":"get_cloud_tops","repo":"EyringMLClimateGroup/heuer23_ml_convection_parameterization","repo_kind":"official","path":"preprocessing/CalcConvOut.py","file_url":"https://github.com/EyringMLClimateGroup/heuer23_ml_convection_parameterization/blob/HEAD/preprocessing/CalcConvOut.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0fe62d62ce151e0c"}},{"code_sha256_prefix":"fcd0eadc364c2fab","entry":"get_convective","repo":"EyringMLClimateGroup/heuer23_ml_convection_parameterization","repo_kind":"official","path":"convection_param/ConvParamFuncs.py","file_url":"https://github.com/EyringMLClimateGroup/heuer23_ml_convection_parameterization/blob/HEAD/convection_param/ConvParamFuncs.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"fcd0eadc364c2fab"}},{"code_sha256_prefix":"22f784400456751d","entry":"get_convective_thetav_buoyancy","repo":"EyringMLClimateGroup/heuer23_ml_convection_parameterization","repo_kind":"official","path":"convection_param/ConvParamFuncs.py","file_url":"https://github.com/EyringMLClimateGroup/heuer23_ml_convection_parameterization/blob/HEAD/convection_param/ConvParamFuncs.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"22f784400456751d"}},{"code_sha256_prefix":"eec9b22d31bc12bc","entry":"get_pad_last_dim","repo":"EyringMLClimateGroup/heuer23_ml_convection_parameterization","repo_kind":"official","path":"convection_param/NetworksTorch.py","file_url":"https://github.com/EyringMLClimateGroup/heuer23_ml_convection_parameterization/blob/HEAD/convection_param/NetworksTorch.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"eec9b22d31bc12bc"}},{"code_sha256_prefix":"5dfee14da8654920","entry":"get_sp_size","repo":"EyringMLClimateGroup/heuer23_ml_convection_parameterization","repo_kind":"official","path":"convection_param/NDLHyperOpt.py","file_url":"https://github.com/EyringMLClimateGroup/heuer23_ml_convection_parameterization/blob/HEAD/convection_param/NDLHyperOpt.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5dfee14da8654920"}},{"code_sha256_prefix":"1ada3d07328d4441","entry":"pick_with_idx_array_dimm1","repo":"EyringMLClimateGroup/heuer23_ml_convection_parameterization","repo_kind":"official","path":"preprocessing/CalcConvOut.py","file_url":"https://github.com/EyringMLClimateGroup/heuer23_ml_convection_parameterization/blob/HEAD/preprocessing/CalcConvOut.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1ada3d07328d4441"}},{"code_sha256_prefix":"a3a734e005243bf3","entry":"set_size","repo":"EyringMLClimateGroup/heuer23_ml_convection_parameterization","repo_kind":"official","path":"convection_param/setup_mpl_tex.py","file_url":"https://github.com/EyringMLClimateGroup/heuer23_ml_convection_parameterization/blob/HEAD/convection_param/setup_mpl_tex.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a3a734e005243bf3"}},{"code_sha256_prefix":"7e94037fc4753b73","entry":"add_tke_fl","repo":"EyringMLClimateGroup/heuer23_ml_convection_parameterization","repo_kind":"official","path":"convection_param/GetTrainingData.py","file_url":"https://github.com/EyringMLClimateGroup/heuer23_ml_convection_parameterization/blob/HEAD/convection_param/GetTrainingData.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7e94037fc4753b73"}},{"code_sha256_prefix":"14532d3bea226f2f","entry":"assign_bnd_coords","repo":"EyringMLClimateGroup/heuer23_ml_convection_parameterization","repo_kind":"official","path":"convection_param/HelperFuncs.py","file_url":"https://github.com/EyringMLClimateGroup/heuer23_ml_convection_parameterization/blob/HEAD/convection_param/HelperFuncs.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"14532d3bea226f2f"}},{"code_sha256_prefix":"b436b2e594614b17","entry":"get_adv_subgrid_tend","repo":"EyringMLClimateGroup/heuer23_ml_convection_parameterization","repo_kind":"official","path":"convection_param/GetTrainingData.py","file_url":"https://github.com/EyringMLClimateGroup/heuer23_ml_convection_parameterization/blob/HEAD/convection_param/GetTrainingData.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b436b2e594614b17"}},{"code_sha256_prefix":"cb9c7d5be829b55c","entry":"get_convective_thetav_grad","repo":"EyringMLClimateGroup/heuer23_ml_convection_parameterization","repo_kind":"official","path":"convection_param/ConvParamFuncs.py","file_url":"https://github.com/EyringMLClimateGroup/heuer23_ml_convection_parameterization/blob/HEAD/convection_param/ConvParamFuncs.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"cb9c7d5be829b55c"}},{"code_sha256_prefix":"eb756447c8536e38","entry":"rename_to_standard","repo":"EyringMLClimateGroup/heuer23_ml_convection_parameterization","repo_kind":"official","path":"preprocessing/CalcConvOut.py","file_url":"https://github.com/EyringMLClimateGroup/heuer23_ml_convection_parameterization/blob/HEAD/preprocessing/CalcConvOut.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"eb756447c8536e38"}},{"code_sha256_prefix":"d89eb716d6952c6a","entry":"vert_coarse_grain_fl","repo":"EyringMLClimateGroup/heuer23_ml_convection_parameterization","repo_kind":"official","path":"preprocessing/VerticalCoarseGrainingParallel.py","file_url":"https://github.com/EyringMLClimateGroup/heuer23_ml_convection_parameterization/blob/HEAD/preprocessing/VerticalCoarseGrainingParallel.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d89eb716d6952c6a"}},{"code_sha256_prefix":"23c5b110f5991402","entry":"vert_coarse_grain_hl","repo":"EyringMLClimateGroup/heuer23_ml_convection_parameterization","repo_kind":"official","path":"preprocessing/VerticalCoarseGrainingParallel.py","file_url":"https://github.com/EyringMLClimateGroup/heuer23_ml_convection_parameterization/blob/HEAD/preprocessing/VerticalCoarseGrainingParallel.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"23c5b110f5991402"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}