ArchesWeather: An efficient AI weather forecasting model at 1.5° resolution

• URL: http://arxiv.org/abs/2405.14527v2
• Date: Wed, 3 Jul 2024 12:39:58 GMT
• Title: ArchesWeather: An efficient AI weather forecasting model at 1.5° resolution
• Abstract summary: We show that the 3D local processing in Pangu-Weather is computationally sub-optimal. We design ArchesWeather, a transformer model that combines 2D attention with a column-wise attention-based feature interaction module. ArchesWeather is trained at 1.5deg resolution and 24h lead time, with a training budget of a few GPU-days and a lower inference cost than competing methods.
• Score: 12.404004942884523
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: One of the guiding principles for designing AI-based weather forecasting systems is to embed physical constraints as inductive priors in the neural network architecture. A popular prior is locality, where the atmospheric data is processed with local neural interactions, like 3D convolutions or 3D local attention windows as in Pangu-Weather. On the other hand, some works have shown great success in weather forecasting without this locality principle, at the cost of a much higher parameter count. In this paper, we show that the 3D local processing in Pangu-Weather is computationally sub-optimal. We design ArchesWeather, a transformer model that combines 2D attention with a column-wise attention-based feature interaction module, and demonstrate that this design improves forecasting skill. ArchesWeather is trained at 1.5{\deg} resolution and 24h lead time, with a training budget of a few GPU-days and a lower inference cost than competing methods. An ensemble of four of our models shows better RMSE scores than the IFS HRES and is competitive with the 1.4{\deg} 50-members NeuralGCM ensemble for one to three days ahead forecasting. Our code and models are publicly available at https://github.com/gcouairon/ArchesWeather.

Related papers

• Otter Weather: Skillful and Computationally Efficient Medium-Range Weather Forecasting [30.958839430506156]
  Otter Weather is a highly efficient forecasting model designed to democratise high-performance weather prediction with AI.<n>The version outperforms the best NWP baseline by 9.6% at a 24-hour lead time.<n>Otter-XL achieves a 9.7% improvement over the IFS ENS baseline.
  arXiv  Detail & Related papers  (2026-06-24T22:23:13Z)
• FourCastNet 3: A geometric approach to probabilistic machine-learning weather forecasting at scale [91.84761739154366]
  FourCastNet 3 advances global weather modeling by implementing a scalable, geometric machine learning (ML) approach to probabilistic ensemble forecasting.<n>FourCastNet 3 delivers forecasting accuracy that surpasses leading conventional ensemble models and rivals the best diffusion-based methods.<n>Its computational efficiency, medium-range probabilistic skill, spectral fidelity, and rollout stability at subseasonal timescales make it a strong candidate for improving meteorological forecasting and early warning systems through large ensemble predictions.
  arXiv  Detail & Related papers  (2025-07-16T11:22:18Z)
• WeatherMesh-3: Fast and accurate operational global weather forecasting [0.0]
  We present WeatherMesh-3 (WM-3), an operational transformer-based global weather forecasting system. WM-3 generates 14-day global forecasts at 0.25-degree resolution in 12 seconds on a single GTX 4090. This represents a >100,000-fold speedup over traditional NWP approaches.
  arXiv  Detail & Related papers  (2025-03-28T08:37:59Z)
• ArchesWeather & ArchesWeatherGen: a deterministic and generative model for efficient ML weather forecasting [11.561776315905357]
  We propose a methodology to leverage deterministic weather models in the design of probabilistic weather models. Our work also aims to democratize the use of deterministic and generative machine learning models in weather forecasting research.
  arXiv  Detail & Related papers  (2024-12-17T14:54:30Z)
• Generalizing Weather Forecast to Fine-grained Temporal Scales via Physics-AI Hybrid Modeling [55.13352174687475]
  This paper proposes a physics-AI hybrid model (i.e., WeatherGFT) which Generalizes weather forecasts to Finer-grained Temporal scales. Specifically, we employ a carefully designed PDE kernel to simulate physical evolution on a small time scale. We introduce a lead time-aware training framework to promote the generalization of the model at different lead times.
  arXiv  Detail & Related papers  (2024-05-22T16:21:02Z)
• A Practical Probabilistic Benchmark for AI Weather Models [0.7978324349017066]
  We show that two leading AI weather models, i.e. GraphCast and Pangu, are tied on the probabilistic CRPS metric. We also reveal how multiple time-step loss functions, which many data-driven weather models have employed, are counter-productive.
  arXiv  Detail & Related papers  (2024-01-27T05:53:16Z)
• Towards an end-to-end artificial intelligence driven global weather forecasting system [57.5191940978886]
  We present an AI-based data assimilation model, i.e., Adas, for global weather variables. We demonstrate that Adas can assimilate global observations to produce high-quality analysis, enabling the system operate stably for long term. We are the first to apply the methods to real-world scenarios, which is more challenging and has considerable practical application potential.
  arXiv  Detail & Related papers  (2023-12-18T09:05:28Z)
• Self-supervised Monocular Depth Estimation: Let's Talk About The Weather [2.836066255205732]
  Current, self-supervised depth estimation architectures rely on clear and sunny weather scenes to train deep neural networks. In this paper, we put forward a method that uses augmentations to remedy this problem. We present extensive testing to show that our method, Robust-Depth, achieves SotA performance on the KITTI dataset.
  arXiv  Detail & Related papers  (2023-07-17T09:50:03Z)
• Deep Learning for Day Forecasts from Sparse Observations [60.041805328514876]
  Deep neural networks offer an alternative paradigm for modeling weather conditions. MetNet-3 learns from both dense and sparse data sensors and makes predictions up to 24 hours ahead for precipitation, wind, temperature and dew point. MetNet-3 has a high temporal and spatial resolution, respectively, up to 2 minutes and 1 km as well as a low operational latency.
  arXiv  Detail & Related papers  (2023-06-06T07:07:54Z)
• WEDGE: A multi-weather autonomous driving dataset built from generative vision-language models [51.61662672912017]
  We introduce WEDGE: a synthetic dataset generated with a vision-language generative model via prompting. WEDGE consists of 3360 images in 16 extreme weather conditions manually annotated with 16513 bounding boxes. We establish baseline performance for classification and detection with 53.87% test accuracy and 45.41 mAP.
  arXiv  Detail & Related papers  (2023-05-12T14:42:47Z)
• Pangu-Weather: A 3D High-Resolution Model for Fast and Accurate Global Weather Forecast [91.9372563527801]
  We present Pangu-Weather, a deep learning based system for fast and accurate global weather forecast. For the first time, an AI-based method outperforms state-of-the-art numerical weather prediction (NWP) methods in terms of accuracy. Pangu-Weather supports a wide range of downstream forecast scenarios, including extreme weather forecast and large-member ensemble forecast in real-time.
  arXiv  Detail & Related papers  (2022-11-03T17:19:43Z)
• Physics Informed Shallow Machine Learning for Wind Speed Prediction [66.05661813632568]
  We analyze a massive dataset of wind measured from anemometers located at 10 m height in 32 locations in Italy. We train supervised learning algorithms using the past history of wind to predict its value at a future time. We find that the optimal design as well as its performance vary with the location.
  arXiv  Detail & Related papers  (2022-04-01T14:55:10Z)
• TENT: Tensorized Encoder Transformer for Temperature Forecasting [3.498371632913735]
  We introduce a new model based on the Transformer architecture for weather forecasting. We show that compared to the original transformer and 3D convolutional neural networks, the proposed TENT model can better model the underlying complex pattern of weather data. Experiments on two real-life weather datasets are performed.
  arXiv  Detail & Related papers  (2021-06-28T14:17:22Z)

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.