Papers › Interpretable multiscale Machine Learning-Based Parameterizations of Convection for ICON

Interpretable multiscale Machine Learning-Based Parameterizations of Convection for ICON

6 Nov 2023arXiv:2311.03251links table onlyarchive 2025-07-28

Helge Heuer, Mierk Schwabe, Pierre Gentine, Marco A. Giorgetta, Veronika Eyring

The archive published only this paper's code-link row. Authors, date and abstract are from arXiv's metadata (CC0), read from the Kaggle arXiv metadata snapshot of 2026-09-12 where its title matched the archive's; the title is the archive's.

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.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 16 code samples harvested from 1 repository linked to this paper: 9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 7 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 16 samples from 1 repository, 9 ran (9 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

EyringMLClimateGroup/heuer23_ml_convection_parameterization officialmentioned in paperpytorchApache-2.0Syntology: 16 samples, 9 ran (0 instrument-failed) · 7 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

16 samples harvested: 9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 7 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

9ran
7unverified

Licence: 0 of the 16 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from EyringMLClimateGroup/heuer23_ml_convection_parameterization. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: 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. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

EyringMLClimateGroup/heuer23_ml_convection_parameterization official repository 16 samples, 9 ran (0 instrument-failed) · 7 unverified
format_date_str convection_param/HelperFuncs.py ran fingerprinted Apache-2.0 (permissive) · 87d0d51f184808c6 · report fixture: signature date_str:str/0/str · returned str · level recorded 2026-09-24
get_ax_size convection_param/setup_mpl_tex.py ran Apache-2.0 (permissive) · bfe0b544d6d55843 · report fixture: signature ax:Axes/0/?, fig:Figure/0/? · returned tuple · level recorded 2026-09-24
get_cloud_tops preprocessing/CalcConvOut.py ran fingerprinted Apache-2.0 (permissive) · 0fe62d62ce151e0c · report fixture: signature ccells:ndarray/2/float · returned ndarray · level recorded 2026-09-24
get_convective convection_param/ConvParamFuncs.py ran Apache-2.0 (permissive) · fcd0eadc364c2fab · report fixture: signature w_hl:ndarray/3/float, w_fl:ndarray/3/float, ql:ndarray/3/float, qi:ndarray/3/float, a:float/0/float, b:float/0/float · returned ndarray · level recorded 2026-09-24
get_convective_thetav_buoyancy convection_param/ConvParamFuncs.py ran Apache-2.0 (permissive) · 22f784400456751d · report fixture: signature theta_v:Tensor/2/float, theta_v_bar:Tensor/2/float, w:Tensor/2/float, qc:Tensor/2/float, qi:Tensor/2/float · returned Tensor · level recorded 2026-09-24
get_pad_last_dim convection_param/NetworksTorch.py ran Apache-2.0 (permissive) · eec9b22d31bc12bc · report fixture: signature diff:int/0/int · returned function · level recorded 2026-09-24
get_sp_size convection_param/NDLHyperOpt.py ran Apache-2.0 (permissive) · 5dfee14da8654920 · report fixture: signature search_space:dict/0/? · returned int · level recorded 2026-09-24
pick_with_idx_array_dimm1 preprocessing/CalcConvOut.py ran Apache-2.0 (permissive) · 1ada3d07328d4441 · report fixture: signature vals:ndarray/3/int, idx_arr:ndarray/2/int, axis:int/0/int · returned ndarray · level recorded 2026-09-24
set_size in 5 papers convection_param/setup_mpl_tex.py ran Apache-2.0 (permissive) · a3a734e005243bf3 · report fixture: signature width:float/0/float, ratio:str/0/str, fraction:int/0/int, subplots:tuple/1/int · returned tuple · level recorded 2026-09-24
add_tke_fl convection_param/GetTrainingData.py unverified Apache-2.0 (permissive) · 7e94037fc4753b73 · report
assign_bnd_coords convection_param/HelperFuncs.py unverified Apache-2.0 (permissive) · 14532d3bea226f2f · report
get_adv_subgrid_tend convection_param/GetTrainingData.py unverified Apache-2.0 (permissive) · b436b2e594614b17 · report
get_convective_thetav_grad convection_param/ConvParamFuncs.py unverified Apache-2.0 (permissive) · cb9c7d5be829b55c · report
rename_to_standard preprocessing/CalcConvOut.py unverified Apache-2.0 (permissive) · eb756447c8536e38 · report
vert_coarse_grain_fl preprocessing/VerticalCoarseGrainingParallel.py unverified Apache-2.0 (permissive) · d89eb716d6952c6a · report
vert_coarse_grain_hl preprocessing/VerticalCoarseGrainingParallel.py unverified Apache-2.0 (permissive) · 23c5b110f5991402 · report

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections