A survey of published research, from the Essentia Memoria newsroom. It lists real papers, each looked up at its DOI registry; the game has not repeated their results.
Research survey
What AI research has found: weather and climate
Happened: · Published:
10 published works on weather and climate, each looked up at its DOI registry before it was listed here, with what each one reports in plain words.
Watch
Explanatory visualisation, drawn from the record's numbers. It is not footage of the event: nobody filmed it.
Listen
Transcript
News from the Essentia Memoria game universe. What AI research has found: weather and climate. 10 published works on weather and climate, each looked up at its DOI registry before it was listed here, with what each one reports in plain words. This survey lists what each paper reports. The game has not repeated these results. A search finds papers that match its words, so a listed paper may use AI only in part. The search is limited to the fifty most-cited matches, so the newest results may be missing until they are cited. This report was written from the world record by a fixed template. The full story and its source records are on essentiamemoria.com.
The question
Can a model trained on past weather forecast the coming days as well as physics-based forecasts?
Claims, and where each one comes from
- Where this research lives in the game (a place the world grammar builds)observatory → laboratory
Game simulation · Set in code
src/lib/world-grammar/place-grammar.ts · resolvePurpose('observatory') - Published works in this survey, each resolved at its DOI registry10
Real-world knowledge · Source [1] [2] [3] [4] [5] [6] [7] [8] [9] [10]
- GraphCast learned from decades of reanalysis data to forecast global weather up to ten days ahead.Lam 2023
Real-world knowledge · Source [1]
- Can deep learning beat numerical weather prediction?Schultz 2021
Real-world knowledge · Source [2]
- Accurate medium-range global weather forecasting with 3D neural networksBi 2023
Real-world knowledge · Source [3]
- Neural Networks for Postprocessing Ensemble Weather ForecastsRasp 2018
Real-world knowledge · Source [4]
- Challenges and design choices for global weather and climate models based on machine learningDueben 2018
Real-world knowledge · Source [5]
- Temporal convolutional neural (TCN) network for an effective weather forecasting using time-series data from the local weather stationHewage 2020
Real-world knowledge · Source [6]
- SmaAt-UNet: Precipitation nowcasting using a small attention-UNet architectureTrebing 2021
Real-world knowledge · Source [7]
- Comparison of machine learning methods for photovoltaic power forecasting based on numerical weather predictionMarkovics 2022
Real-world knowledge · Source [8]
- Probabilistic weather forecasting with machine learningPrice 2024
Real-world knowledge · Source [9]
- Deep learning to represent subgrid processes in climate modelsRasp 2018
Real-world knowledge · Source [10]
References, checked at their registry
[1] Lam (2023). Learning skillful medium-range global weather forecasting. Science. doi:10.1126/science.adi2336
Verified: the work exists and matches · checked at Crossref on Oct 28, 2026, 10:35 PM UTC · the registry holds “Learning skillful medium-range global weather forecasting” (2023)
[2] Schultz (2021). Can deep learning beat numerical weather prediction?. Philosophical Transactions of the Royal Society A Mathematical Physical and Engineering Sciences. doi:10.1098/rsta.2020.0097
Verified: the work exists and matches · checked at Crossref on Oct 28, 2026, 10:35 PM UTC · the registry holds “Can deep learning beat numerical weather prediction?” (2021)
[3] Bi (2023). Accurate medium-range global weather forecasting with 3D neural networks. Nature. doi:10.1038/s41586-023-06185-3
Verified: the work exists and matches · checked at Crossref on Oct 28, 2026, 10:35 PM UTC · the registry holds “Accurate medium-range global weather forecasting with 3D neural networks” (2023)
[4] Rasp (2018). Neural Networks for Postprocessing Ensemble Weather Forecasts. Monthly Weather Review. doi:10.1175/mwr-d-18-0187.1
Verified: the work exists and matches · checked at Crossref on Oct 28, 2026, 10:35 PM UTC · the registry holds “Neural Networks for Postprocessing Ensemble Weather Forecasts” (2018)
[5] Dueben (2018). Challenges and design choices for global weather and climate models based on machine learning. Geoscientific model development. doi:10.5194/gmd-11-3999-2018
Verified: the work exists and matches · checked at Crossref on Oct 28, 2026, 10:35 PM UTC · the registry holds “Challenges and design choices for global weather and climate models based on machine learning” (2018)
[6] Hewage (2020). Temporal convolutional neural (TCN) network for an effective weather forecasting using time-series data from the local weather station. Soft Computing. doi:10.1007/s00500-020-04954-0
Verified: the work exists and matches · checked at Crossref on Oct 28, 2026, 10:35 PM UTC · the registry holds “Temporal convolutional neural (TCN) network for an effective weather forecasting using time-series data from the local weather station” (2020)
[7] Trebing (2021). SmaAt-UNet: Precipitation nowcasting using a small attention-UNet architecture. Pattern Recognition Letters. doi:10.1016/j.patrec.2021.01.036
Verified: the work exists and matches · checked at Crossref on Oct 28, 2026, 10:35 PM UTC · the registry holds “SmaAt-UNet: Precipitation nowcasting using a small attention-UNet architecture” (2021)
[8] Markovics (2022). Comparison of machine learning methods for photovoltaic power forecasting based on numerical weather prediction. Renewable and Sustainable Energy Reviews. doi:10.1016/j.rser.2022.112364
Verified: the work exists and matches · checked at Crossref on Oct 28, 2026, 10:35 PM UTC · the registry holds “Comparison of machine learning methods for photovoltaic power forecasting based on numerical weather prediction” (2022)
[9] Price (2024). Probabilistic weather forecasting with machine learning. Nature. doi:10.1038/s41586-024-08252-9
Verified: the work exists and matches · checked at Crossref on Oct 28, 2026, 10:35 PM UTC · the registry holds “Probabilistic weather forecasting with machine learning” (2025)
[10] Rasp (2018). Deep learning to represent subgrid processes in climate models. Proceedings of the National Academy of Sciences. doi:10.1073/pnas.1810286115
Verified: the work exists and matches · checked at Crossref on Oct 28, 2026, 10:35 PM UTC · the registry holds “Deep learning to represent subgrid processes in climate models” (2018)
Review
Not peer reviewed. No human scientist has reviewed this survey. Its template and landmark summaries were written with an AI assistant (Claude); the papers it lists are real and each was checked at its registry, so anyone can follow the links and read them.
- Each listed DOI was resolved, and its title, year and first author matched the listing.
- Each work the search found is held by Crossref, a registry independent of the search.
- Each number in the headline and summary is accounted for by a listed claim.
- Not shown: 2 candidate work(s) whose registry record did not confirm them (10.48550/arxiv.1506.04214 verified (not in Crossref); 10.48550/arxiv.1706.03458 verified (not in Crossref)).
Code version: fa127b6f988c
What the record does not say
This survey lists what each paper reports; the game has not repeated these results. A search finds papers that match its words, so a listed paper may use AI only in part. The search is limited to the fifty most-cited matches, so the newest results may be missing until they are cited.
How this was written
Landmark works named by the desk, then the most-cited works with a DOI that OpenAlex returns when titles and abstracts are searched for ("weather forecasting" OR "weather forecast" OR "weather prediction" OR "numerical weather prediction" OR "precipitation nowcasting" OR "climate model") AND ("machine learning" OR "deep learning" OR "neural network" OR "neural networks" OR "artificial intelligence" OR convolutional OR "reinforcement learning" OR "language model" OR transformer); a hit is kept only if its own title names the field and its title or abstract names an AI method, as whole words, and the hits that name the most of these words in their title come first. Each candidate was looked up at Crossref (OpenAlex as second resolver) and its title, year and first author compared; a work the search found is shown only when Crossref holds it. Landmark summaries were written by the desk; the other works are listed by their own titles.
Source records: code:src/lib/world-grammar/place-grammar.ts#resolvePurpose · doi:10.1126/science.adi2336 · doi:10.1098/rsta.2020.0097 · doi:10.1038/s41586-023-06185-3 · doi:10.1175/mwr-d-18-0187.1 · doi:10.5194/gmd-11-3999-2018 · doi:10.1007/s00500-020-04954-0 · doi:10.1016/j.patrec.2021.01.036 · doi:10.1016/j.rser.2022.112364 · doi:10.1038/s41586-024-08252-9 · doi:10.1073/pnas.1810286115