Rescene: band-limited stochastic forcing turns a frozen neural weather operator into a climate emulator

• URL: http://arxiv.org/abs/2608.09971v1
• Date: Thu, 30 Jul 2026 09:42:39 GMT
• Title: Rescene: band-limited stochastic forcing turns a frozen neural weather operator into a climate emulator
• Abstract summary: We present Rescene, a wrapper around a frozen 1.5 degree, 6-hourly vision-transformer operator.<n>It blends the forecast toward a lead-aware day-of-year climatology and a generative head (0.06 M) that adds a spectrally shaped perturbation at every step.<n>The performance evaluation demonstrates that the deterministic wrapper alone is stable for decades but collapses daily variability to 40% of ERA5.
• Score: 3.993449663756884
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Over the past few years, the rapid development of machine learning (ML) models for weather forecasting has produced deterministic models whose medium-range skill matches or exceeds that of the European Centre for Medium-Range Weather Forecasts (ECMWF)'s high-resolution forecast (HRES). However, when these models are integrated freely beyond the horizon they were trained for, they blow up, drift, or lose their seasonal cycle, and retraining them for stability is expensive. We therefore ask what can be recovered from a strictly frozen backbone. We present Rescene, a 0.4 M-parameter wrapper around a frozen 1.5 degree, 6-hourly vision-transformer operator, developed using ERA5 reanalysis data and comprising a deterministic "slow clock" (0.33 M) that blends the forecast toward a lead-aware day-of-year climatology and a generative head (0.06 M) that adds a spectrally shaped stochastic perturbation at every step. The performance evaluation demonstrates that the deterministic wrapper alone is stable for decades but collapses daily variability to 40% of ERA5. Adding the generative head restores 126% (Z500) and 130% (MSLP) of the observed daily variability with pattern correlations of 0.89 and 0.92, recovers 82% of the observed blocking frequency, keeps the ensemble calibrated (spread-skill ratio 0.78-0.97 from day 7 to day 90), and integrates for 100 years with no detectable drift (+0.008 +/- 0.014 K per century). Moreover, because the perturbation is band-limited to total wavenumber $k \le 20$, the small scales are never forced, yet realistic $k \ge 20$ power is sustained: a direct decomposition of the 6-hourly energy budget shows that the frozen operator supplies 28 times more energy than the perturbation at $k \ge 40$, with a fractional growth rate 247 times larger at the grid scale than at planetary scales.

Related papers

• RynnValue: Scaling Robotic Value Foundation Models with Temporal Distance [84.26294415726723]
  General-purpose reward models are increasingly the bottleneck for scaling robot learning.<n>We introduce RynnValue, an open-source value foundation model for robotic manipulation.<n>RynnValue scales to over 7,000 hours and roughly 3M instruction-conditioned clips without preference or progress annotations.
  arXiv  Detail & Related papers  (2026-08-10T17:09:37Z)
• Do AI weather models miss extremes? [3.3270769893417707]
  First-generation AI weather models are often reported to underperform at extremes.<n>We verify eleven physical and AI forecast systems against European synoptic, solar, and rain-gauge stations over ten months.<n>Among these systems, AI models do not show a uniform relative-skill deficit in the tails.
  arXiv  Detail & Related papers  (2026-07-31T14:18:43Z)
• Cycle-Consistent and Uncertainty-Aware Neural Surrogates for Tokamak Edge Plasmas [0.040071856451118486]
  Boundary and divertor plasma govern how a tokamak exhausts power and particles.<n>Machine-learning surrogates offer a fast alternative, yet most are forward-only.<n>We introduce a cycle-consistent neural surrogate for edge plasmas.
  arXiv  Detail & Related papers  (2026-07-23T15:06:57Z)
• TSSM: Triaxial State Space Model for Global Station Weather Forecasting with Temporal-Variable-Historical Modeling [74.915718648935]
  Existing methods show limited accuracy gains and struggle with extreme events and error accumulation.<n>We propose a novel Triaxial State Space Model (TSSM) with a history-enhanced Temporal-VariableHistorical paradigm.<n>TSSM stacks historical samples into period-aligned batches, where forecasting is causally supported by historical and current observations.
  arXiv  Detail & Related papers  (2026-07-14T07:36:19Z)
• EO-WM: A Physically Informed World Model for Probabilistic Earth Observation Forecasting [50.31500063307306]
  We introduce EO-WM, a video diffusion transformer for multispectral Earth Observation forecasting.<n> EO-WM incorporates a physically informed conditioning framework that represents meteorological forcing through a climatological baseline, weather anomalies, and cumulative physical stress signals.<n>Experiments show that EO-WM reduces the error in predicted Normalized Difference Vegetation Index (NDVI) decline amplitude by a relative 5.63% and improves directional hit rate by a relative 7.80%.
  arXiv  Detail & Related papers  (2026-06-25T16:53:30Z)
• Short-Term Electricity Demand Forecasting for New England Using a Hybrid Transformer-XGBoost Framework with Weather, Calendar, and COVID-19 Indicators [0.0]
  This paper presents a hybrid framework combining a Transformer encoder for temporal feature extraction with gradient-boosted decision trees (XGBoost) for daily electricity demand forecasting across New England.<n>The framework integrates meteorological observations from six cities spanning all six New England states, calendar and holiday effects, autoregressive demand lags, and COVID-19 epidemiological variables.
  arXiv  Detail & Related papers  (2026-06-18T20:15:39Z)
• Time series Foundation Models based on Physics-Informed Synthetic Histories for Cold-Start Photovoltaic Forecasting [45.753923525593045]
  The evaluation spans $440$ PV sites across four datasets and diverse climate regimes.<n>Performance is largely insensitive to the synthetic-history source, indicating that accuracy is driven more by the availability of plausible temporal context than by the specific generator.
  arXiv  Detail & Related papers  (2026-06-05T17:05:19Z)
• Residual Corrective Diffusion Modeling for Km-scale Atmospheric Downscaling [58.456404022536425]
  State of the art for physical hazard prediction from weather and climate requires expensive km-scale numerical simulations driven by coarser resolution global inputs. Here, a generative diffusion architecture is explored for downscaling such global inputs to km-scale, as a cost-effective machine learning alternative. The model is trained to predict 2km data from a regional weather model over Taiwan, conditioned on a 25km global reanalysis.
  arXiv  Detail & Related papers  (2023-09-24T19:57:22Z)
• Long-term drought prediction using deep neural networks based on geospatial weather data [75.38539438000072]
  High-quality drought forecasting up to a year in advance is critical for agriculture planning and insurance. We tackle drought data by introducing an end-to-end approach that adopts a systematic end-to-end approach. Key findings are the exceptional performance of a Transformer model, EarthFormer, in making accurate short-term (up to six months) forecasts.
  arXiv  Detail & Related papers  (2023-09-12T13:28:06Z)
• A generalised multi-factor deep learning electricity load forecasting model for wildfire-prone areas [0.0]
  This paper proposes a generalised and robust multi-factor Gated Recurrent Unit (GRU) based Deep Learning (DL) model to forecast electricity load in distribution networks during wildfire seasons. Compared to the regular use of instantaneous temperature, the Mean Absolute Percentage Error (MAPE) is decreased by 30.73%. The proposed method achieves an average forecast MAPE of around 3%, giving a potential annual energy saving of AU$80.46 million for the state of Victoria.
  arXiv  Detail & Related papers  (2023-04-21T00:42:24Z)
• FengWu: Pushing the Skillful Global Medium-range Weather Forecast beyond 10 Days Lead [93.67314652898547]
  We present FengWu, an advanced data-driven global medium-range weather forecast system based on Artificial Intelligence (AI) FengWu is able to accurately reproduce the atmospheric dynamics and predict the future land and atmosphere states at 37 vertical levels on a 0.25deg latitude-longitude resolution. The results suggest that FengWu can significantly improve the forecast skill and extend the skillful global medium-range weather forecast out to 10.75 days lead.
  arXiv  Detail & Related papers  (2023-04-06T09:16:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.