A multi-scale loss formulation for learning a probabilistic model with proper score optimisation

• URL: http://arxiv.org/abs/2506.10868v1
• Date: Thu, 12 Jun 2025 16:30:18 GMT
• Title: A multi-scale loss formulation for learning a probabilistic model with proper score optimisation
• Authors: Simon Lang, Martin Leutbecher, Pedro Maciel,
• Abstract summary: Multi-scale loss is tested in AIFS-CRPS, a machine-learned weather forecasting model developed at the European Centre for Medium-Range Weather Forecasts (ECMWF)<n>The multi-scale loss better constrains small scale variability without negatively impacting forecast skill.<n>This opens up promising directions for future work in scale-aware model training.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: We assess the impact of a multi-scale loss formulation for training probabilistic machine-learned weather forecasting models. The multi-scale loss is tested in AIFS-CRPS, a machine-learned weather forecasting model developed at the European Centre for Medium-Range Weather Forecasts (ECMWF). AIFS-CRPS is trained by directly optimising the almost fair continuous ranked probability score (afCRPS). The multi-scale loss better constrains small scale variability without negatively impacting forecast skill. This opens up promising directions for future work in scale-aware model training.

Related papers

• Amortized Predictability-aware Training Framework for Time Series Forecasting and Classification [10.816479922364097]
  We propose a general Amortized Predictability-aware Training Framework (APTF) for both time series forecasting (TSF) and time series classification (TSC)<n>APTF introduces two key designs that enable the model to focus on high-predictability samples while still learning appropriately from low-predictability ones.
  arXiv  Detail & Related papers  (2026-02-18T06:59:05Z)
• Demystifying Data-Driven Probabilistic Medium-Range Weather Forecasting [63.8116386935854]
  We demonstrate that state-of-the-art probabilistic skill requires neither intricate architectural constraints nor specialized trainings.<n>We introduce a scalable framework for learning multi-scale atmospheric dynamics by combining a directly downsampled latent space with a history-conditioned local projector.<n>We find that our framework design is robust to the choice of probabilistic estimators, seamlessly supporting interpolants, diffusion models, and CRPS-based ensemble training.
  arXiv  Detail & Related papers  (2026-01-26T03:52:16Z)
• Enforcing tail calibration when training probabilistic forecast models [0.0]
  We study how the loss function used to train probabilistic forecast models can be adapted to improve the reliability of forecasts made for extreme events.<n>We demonstrate that state-of-the-art models do not issue calibrated forecasts for extreme wind speeds, and that the calibration of forecasts for extreme events can be improved by suitable adaptations to the loss function during model training.
  arXiv  Detail & Related papers  (2025-06-16T16:51:06Z)
• Skillful joint probabilistic weather forecasting from marginals [11.348323146521931]
  This paper presents FGN, a simple, scalable and flexible modeling approach which significantly outperforms the current state-of-the-art models.<n>It is trained directly to minimize the continuous rank probability score (CRPS) of per-location forecasts.<n>It produces state-of-the-art ensemble forecasts as measured by a range of deterministic and probabilistic metrics.
  arXiv  Detail & Related papers  (2025-06-12T14:50:47Z)
• Forecast-PEFT: Parameter-Efficient Fine-Tuning for Pre-trained Motion Forecasting Models [68.23649978697027]
  Forecast-PEFT is a fine-tuning strategy that freezes the majority of the model's parameters, focusing adjustments on newly introduced prompts and adapters. Our experiments show that Forecast-PEFT outperforms traditional full fine-tuning methods in motion prediction tasks. Forecast-FT further improves prediction performance, evidencing up to a 9.6% enhancement over conventional baseline methods.
  arXiv  Detail & Related papers  (2024-07-28T19:18:59Z)
• Improving probabilistic forecasts of extreme wind speeds by training statistical post-processing models with weighted scoring rules [0.0]
  Training using the threshold-weighted continuous ranked probability score (twCRPS) leads to improved extreme event performance of post-processing models.<n>We find a distribution body-tail trade-off where improved performance for probabilistic predictions of extreme events comes with worse performance for predictions of the distribution body.
  arXiv  Detail & Related papers  (2024-07-22T11:07:52Z)
• ExtremeCast: Boosting Extreme Value Prediction for Global Weather Forecast [57.6987191099507]
  We introduce Exloss, a novel loss function that performs asymmetric optimization and highlights extreme values to obtain accurate extreme weather forecast. We also introduce ExBooster, which captures the uncertainty in prediction outcomes by employing multiple random samples. Our solution can achieve state-of-the-art performance in extreme weather prediction, while maintaining the overall forecast accuracy comparable to the top medium-range forecast models.
  arXiv  Detail & Related papers  (2024-02-02T10:34:13Z)
• Pre-trained Model Guided Fine-Tuning for Zero-Shot Adversarial Robustness [52.9493817508055]
  We propose Pre-trained Model Guided Adversarial Fine-Tuning (PMG-AFT) to enhance the model's zero-shot adversarial robustness. Our approach consistently improves clean accuracy by an average of 8.72%.
  arXiv  Detail & Related papers  (2024-01-09T04:33:03Z)
• Performative Time-Series Forecasting [64.03865043422597]
  We formalize performative time-series forecasting (PeTS) from a machine-learning perspective.<n>We propose a novel approach, Feature Performative-Shifting (FPS), which leverages the concept of delayed response to anticipate distribution shifts.<n>We conduct comprehensive experiments using multiple time-series models on COVID-19 and traffic forecasting tasks.
  arXiv  Detail & Related papers  (2023-10-09T18:34:29Z)
• 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)
• Learning Sample Difficulty from Pre-trained Models for Reliable Prediction [55.77136037458667]
  We propose to utilize large-scale pre-trained models to guide downstream model training with sample difficulty-aware entropy regularization. We simultaneously improve accuracy and uncertainty calibration across challenging benchmarks.
  arXiv  Detail & Related papers  (2023-04-20T07:29:23Z)
• Evaluating Probabilistic Classifiers: The Triptych [62.997667081978825]
  We propose and study a triptych of diagnostic graphics that focus on distinct and complementary aspects of forecast performance. The reliability diagram addresses calibration, the receiver operating characteristic (ROC) curve diagnoses discrimination ability, and the Murphy diagram visualizes overall predictive performance and value.
  arXiv  Detail & Related papers  (2023-01-25T19:35:23Z)
• Machine learning for total cloud cover prediction [0.0]
  We investigate the performance of post-processing using multilayer perceptron (MLP) neural networks, gradient boosting machines (GBM) and random forest (RF) methods. Compared to the raw ensemble, all calibration methods result in a significant improvement in forecast skill. RF models provide the smallest increase in predictive performance, while POLR and GBM approaches perform best.
  arXiv  Detail & Related papers  (2020-01-16T17:13:37Z)

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.