Papers › Self-Attentive Ensemble Transformer: Representing Ensemble Interactions in Neural...

Self-Attentive Ensemble Transformer: Representing Ensemble Interactions in Neural Networks for Earth System Models

21 Jun 2021arXiv:2106.13924archive 2025-07-28

Tobias Sebastian Finn

Ensemble data from Earth system models has to be calibrated and post-processed. I propose a novel member-by-member post-processing approach with neural networks. I bridge ideas from ensemble data assimilation with self-attention, resulting into the self-attentive ensemble transformer. Here, interactions between ensemble members are represented as additive and dynamic self-attentive part. As proof-of-concept, I regress global ECMWF ensemble forecasts to 2-metre-temperature fields from the ERA5 reanalysis. I demonstrate that the ensemble transformer can calibrate the ensemble spread and extract additional information from the ensemble. As it is a member-by-member approach, the ensemble transformer directly outputs multivariate and spatially-coherent ensemble members. Therefore, self-attention and the transformer technique can be a missing piece for a non-parametric post-processing of ensemble data with neural networks.

PaperPDFCodeCode Syntology ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2106.13924")

Code

Syntology Ran 14 of 21 code samples harvested from 3 repositories linked to this paper; 7 have no recorded run. Of those that ran: 1 ran · violated contract; 3 ran · our draft was wrong; 1 ran · fixture could not drive it; 9 ran with no contract checked.

By repository: official repository: 8 samples from 1 repository, 6 ran; community (archive-listed): 13 samples from 2 repositories, 8 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

tobifinn/ensemble_transformer officialmentioned in papermentioned on GitHubpytorch report
spcl/ens10 mentioned on GitHubpytorch report
uantwerpm4s/pp_eupp mentioned on GitHubpytorch 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

21 samples harvested; 14 ran; 0 honoured the contract we drafted; 7 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · violated contract
3ran · our draft was wrong
1ran · fixture could not drive it
9ran
7unverified

Licence: 0 of the 21 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 3 repositories linked to this paper, official or community; each sample names its own and says which. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

EnsConv2d tobifinn/ensemble_transformer/ens_transformer/models/transformer_net.py official repository ran MIT (permissive) · ad34619b242f6a9d · report
EnsembleWrapper tobifinn/ensemble_transformer/ens_transformer/models/transformer_net.py official repository ran MIT (permissive) · 3750e194b65c613a · report
WeightedScore tobifinn/ensemble_transformer/ens_transformer/models/transformer_net.py official repository ran MIT (permissive) · e4801729382540d8 · report
crps_loss tobifinn/ensemble_transformer/ens_transformer/models/transformer_net.py official repository ran · fixture could not drive it fingerprinted MIT (permissive) · 023f04ffe4196204 · report
ens_to_batch tobifinn/ensemble_transformer/ens_transformer/models/transformer_net.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · 6789383a70b5c542 · report
split_batch_ens tobifinn/ensemble_transformer/ens_transformer/models/transformer_net.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · 74fe55c52a7b6a5b · report
BaseNet tobifinn/ensemble_transformer/ens_transformer/models/transformer_net.py official repository unverified MIT (permissive) · 24e7e6a6819ae729 · report
TransformerNet tobifinn/ensemble_transformer/ens_transformer/models/transformer_net.py official repository unverified MIT (permissive) · de833e6644ba1743 · report
MLPBlock uantwerpm4s/pp_eupp/Transformer.py community (archive-listed) ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · bbd2919773fe3e55 · report
SelfAttentionModule spcl/ens10/baselines/models/tformer.py community (archive-listed) ran Apache-2.0 (permissive) · 26d1810bc409110b · report
SoftmaxWeights spcl/ens10/baselines/models/tformer.py community (archive-listed) ran Apache-2.0 (permissive) · 58af3fed01b7382e · report
StackedTransformer uantwerpm4s/pp_eupp/Transformer.py community (archive-listed) ran · metamorphic tier: deterministic MIT (permissive) · 8334b746497b2f6a · report
TransformerBlock uantwerpm4s/pp_eupp/Transformer.py community (archive-listed) ran · metamorphic tier: deterministic MIT (permissive) · b8f30b82390a6db8 · report
branch_layer spcl/ens10/baselines/models/tformer.py community (archive-listed) ran Apache-2.0 (permissive) · f52b211eaf1367c3 · report
scaled_dot_product_attention_custom uantwerpm4s/pp_eupp/Transformer.py community (archive-listed) ran · violated contract fingerprinted MIT (permissive) · 6f8ebcbf0a2d1a10 · report
split_mean_perts spcl/ens10/baselines/models/tformer.py community (archive-listed) ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · fcab1db5e55829f5 · report
EnsAttention uantwerpm4s/pp_eupp/Transformer.py community (archive-listed) unverified MIT (permissive) · fb7b244cd8a8a820 · report
Reweighter spcl/ens10/baselines/models/tformer.py community (archive-listed) unverified Apache-2.0 (permissive) · 904c66e4297f4d17 · report
StateReweighter spcl/ens10/baselines/models/tformer.py community (archive-listed) unverified Apache-2.0 (permissive) · 0a79f2e78656549c · report
TransformerNet spcl/ens10/baselines/models/tformer.py community (archive-listed) unverified Apache-2.0 (permissive) · a94febc2f5a68109 · report
WeightEstimator spcl/ens10/baselines/models/tformer.py community (archive-listed) unverified Apache-2.0 (permissive) · fb91c28f159e549c · 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