Search

Over the last three decades, ensemble forecasts have become an integral part of forecasting the weather. They provide users with more complete information than single forecasts as they permit to estimate the probability of weather events by representing the sources of uncertainties and accounting for the day-to-day variability of error growth in the atmosphere. This paper presents a novel approach to obtain a weather forecast model for ensemble forecasting with machine-learning. AIFS-CRPS is a variant of the Artificial Intelligence Forecasting System (AIFS) developed at ECMWF. Its loss function is based on a proper score, the Continuous Ranked Probability Score (CRPS). For the loss, the almost fair CRPS is introduced because it approximately removes the bias in the score due to finite ensemble size yet avoids a degeneracy of the fair CRPS. The trained model is stochastic and can generate as many exchangeable members as desired and computationally feasible in inference. For medium-range forecasts AIFS-CRPS outperforms the physics-based Integrated Forecasting System (IFS) ensemble for the majority of variables and lead times. For subseasonal forecasts, AIFS-CRPS outperforms the IFS ensemble before calibration and is competitive with the IFS ensemble when forecasts are evaluated as anomalies to remove the influence of model biases.

Data-driven machine learning models for weather forecasting have made transformational progress in the last 1-2 years, with state-of-the-art ones now outperforming the best physics-based models for a wide range of skill scores. Given the strong links between weather and climate modelling, this raises the question whether machine learning models could also revolutionize climate science, for example by informing mitigation and adaptation to climate change or to generate larger ensembles for more robust uncertainty estimates. Here, we show that current state-of-the-art machine learning models trained for weather forecasting in present-day climate produce skillful forecasts across different climate states corresponding to pre-industrial, present-day, and future 2.9K warmer climates. This indicates that the dynamics shaping the weather on short timescales may not differ fundamentally in a changing climate. It also demonstrates out-of-distribution generalization capabilities of the machine learning models that are a critical prerequisite for climate applications. Nonetheless, two of the models show a global-mean cold bias in the forecasts for the future warmer climate state, i.e. they drift towards the colder present-day climate they have been trained for. A similar result is obtained for the pre-industrial case where two out of three models show a warming. We discuss possible remedies for these biases and analyze their spatial distribution, revealing complex warming and cooling patterns that are partly related to missing ocean-sea ice and land surface information in the training data. Despite these current limitations, our results suggest that data-driven machine learning models will provide powerful tools for climate science and transform established approaches by complementing conventional physics-based models., Comment: 14 pages, 4 figures

Machine learning-based weather forecasting models have quickly emerged as a promising methodology for accurate medium-range global weather forecasting. Here, we introduce the Artificial Intelligence Forecasting System (AIFS), a data driven forecast model developed by the European Centre for Medium-Range Weather Forecasts (ECMWF). AIFS is based on a graph neural network (GNN) encoder and decoder, and a sliding window transformer processor, and is trained on ECMWF's ERA5 re-analysis and ECMWF's operational numerical weather prediction (NWP) analyses. It has a flexible and modular design and supports several levels of parallelism to enable training on high-resolution input data. AIFS forecast skill is assessed by comparing its forecasts to NWP analyses and direct observational data. We show that AIFS produces highly skilled forecasts for upper-air variables, surface weather parameters and tropical cyclone tracks. AIFS is run four times daily alongside ECMWF's physics-based NWP model and forecasts are available to the public under ECMWF's open data policy.

Artificial intelligence (AI), based on deep-learning algorithm using high-quality reanalysis datasets, is showing enormous potential for weather forecasting. In this context, the European Centre for Medium-Range Weather Forecasts (ECMWF) is developing a new forecasting system based on AI. Verification results of deterministic forecast for now are promising. However, the realism of weather forecasts based on AI is often questioned. Here, different types of realism are identified and we discuss, in particular, the relationship between structural realism and predictability of weather events. Furthermore, a statistical analysis of deterministic forecasts based on AI points to a realism/performance dilemma that a probabilistic approach should help to solve. -- L'intelligence artificielle (IA) bouleverse aujourd'hui le monde de la pr\'evision m\'et\'eorologique avec l'utilisation d'algorithmes d'apprentissage profond nourris par des champs de r\'eanalyses. Dans ce contexte, le Centre Europ\'een pour les Pr\'evisions M\'et\'eorologiques \`a Moyen Terme (CEPMMT) a d\'ecid\'e de d\'evelopper un nouveau syst\`eme de pr\'evisions resposant sur l'IA. Ces pr\'evisions, pour le moment de type d\'eterministe, montrent des r\'esultats prometteurs. Toutefois, le r\'ealisme de ce type de pr\'evisions reposant sur l'IA est souvent questionn\'e. Ici, nous identifions diff\'erents types de r\'ealisme et interrogeons notamment le rapport entre r\'ealisme structurel et pr\'evisibilit\'e des \'ev\^enements m\'et\'eorologiques. Une analyse statistique de pr\'evisions d\'eterministes reposant sur l'IA laisse apparaitre un dilemme r\'ealisme/performance qu'une approche probabiliste devrait aider \`a r\'esoudre., Comment: 8 pages, in French

Complex ocean systems such as the Antarctic Circumpolar Current play key roles in the climate, and current models predict shifts in their strength and area under climate change. However, the physical processes underlying these changes are not well understood, in part due to the difficulty of characterizing and tracking changes in ocean physics in complex models. Using the Antarctic Circumpolar Current as a case study, we extend the method Tracking global Heating with Ocean Regimes (THOR) to a mesoscale eddy permitting climate model and identify regions of the ocean characterized by similar physics, called dynamical regimes, using readily accessible fields from climate models. To this end, we cluster grid cells into dynamical regimes and train an ensemble of neural networks, allowing uncertainty quantification, to predict these regimes and track them under climate change. Finally, we leverage this new knowledge to elucidate the dynamical drivers of the identified regime shifts as noted by the neural network using the 'explainability' methods SHAP and Layer-wise Relevance Propagation. A region undergoing a profound shift is where the Antarctic Circumpolar Current intersects the Pacific-Antarctic Ridge, an area important for carbon draw-down and fisheries. In this region, THOR specifically reveals a shift in dynamical regime under climate change driven by changes in wind stress and interactions with bathymetry. Using this knowledge to guide further exploration, we find that as the Antarctic Circumpolar Current shifts north under intensifying wind stress, the dominant dynamical role of bathymetry weakens and the flow intensifies., Comment: 14 pages, 11 figures, NeurIPS 2023 Workshop: Tackling Climate Change with Machine Learning

Data-driven modeling based on machine learning (ML) is showing enormous potential for weather forecasting. Rapid progress has been made with impressive results for some applications. The uptake of ML methods could be a game-changer for the incremental progress in traditional numerical weather prediction (NWP) known as the 'quiet revolution' of weather forecasting. The computational cost of running a forecast with standard NWP systems greatly hinders the improvements that can be made from increasing model resolution and ensemble sizes. An emerging new generation of ML models, developed using high-quality reanalysis datasets like ERA5 for training, allow forecasts that require much lower computational costs and that are highly-competitive in terms of accuracy. Here, we compare for the first time ML-generated forecasts with standard NWP-based forecasts in an operational-like context, initialized from the same initial conditions. Focusing on deterministic forecasts, we apply common forecast verification tools to assess to what extent a data-driven forecast produced with one of the recently developed ML models (PanguWeather) matches the quality and attributes of a forecast from one of the leading global NWP systems (the ECMWF IFS). The results are very promising, with comparable skill for both global metrics and extreme events, when verified against both the operational analysis and synoptic observations. Increasing forecast smoothness and bias drift with forecast lead time are identified as current drawbacks of ML-based forecasts. A new NWP paradigm is emerging relying on inference from ML models and state-of-the-art analysis and reanalysis datasets for forecast initialization and model training.

Statistical post-processing of global ensemble weather forecasts is revisited by leveraging recent developments in machine learning. Verification of past forecasts is exploited to learn systematic deficiencies of numerical weather predictions in order to boost post-processed forecast performance. Here, we introduce PoET, a post-processing approach based on hierarchical transformers. PoET has 2 major characteristics: 1) the post-processing is applied directly to the ensemble members rather than to a predictive distribution or a functional of it, and 2) the method is ensemble-size agnostic in the sense that the number of ensemble members in training and inference mode can differ. The PoET output is a set of calibrated members that has the same size as the original ensemble but with improved reliability. Performance assessments show that PoET can bring up to 20% improvement in skill globally for 2m temperature and 2% for precipitation forecasts and outperforms the simpler statistical member-by-member method, used here as a competitive benchmark. PoET is also applied to the ENS10 benchmark dataset for ensemble post-processing and provides better results when compared to other deep learning solutions that are evaluated for most parameters. Furthermore, because each ensemble member is calibrated separately, downstream applications should directly benefit from the improvement made on the ensemble forecast with post-processing.

Wind farm modelling has been an area of rapidly increasing interest with numerous analytical as well as computational-based approaches developed to extend the margins of wind farm efficiency and maximise power production. In this work, we present the novel ML framework WakeNet, which can reproduce generalised 2D turbine wake velocity fields at hub-height over a wide range of yaw angles, wind speeds and turbulence intensities (TIs), with a mean accuracy of 99.8% compared to the solution calculated using the state-of-the-art wind farm modelling software FLORIS. As the generation of sufficient high-fidelity data for network training purposes can be cost-prohibitive, the utility of multi-fidelity transfer learning has also been investigated. Specifically, a network pre-trained on the low-fidelity Gaussian wake model is fine-tuned in order to obtain accurate wake results for the mid-fidelity Curl wake model. The robustness and overall performance of WakeNet on various wake steering control and layout optimisation scenarios has been validated through power-gain heatmaps, obtaining at least 90% of the power gained through optimisation performed with FLORIS directly. We also demonstrate that when utilising the Curl model, WakeNet is able to provide similar power gains to FLORIS, two orders of magnitude faster (e.g. 10 minutes vs 36 hours per optimisation case). The wake evaluation time of wakeNet when trained on a high-fidelity CFD dataset is expected to be similar, thus further increasing computational time gains. These promising results show that generalised wake modelling with ML tools can be accurate enough to contribute towards active yaw and layout optimisation, while producing realistic optimised configurations at a fraction of the computational cost, hence making it feasible to perform real-time active yaw control as well as robust optimisation under uncertainty., Comment: 16 Pages, 18 Figures, 3 Tables

Wind energy resource assessment typically requires numerical models, but such models are too computationally intensive to consider multi-year timescales. Increasingly, unsupervised machine learning techniques are used to identify a small number of representative weather patterns to simulate long-term behaviour. Here we develop a novel wind energy workflow that for the first time combines weather patterns derived from unsupervised clustering techniques with numerical weather prediction models (here WRF) to obtain efficient and accurate long-term predictions of power and downstream wakes from an entire wind farm. We use ERA5 reanalysis data clustering not only on low altitude pressure but also, for the first time, on the more relevant variable of wind velocity. We also compare the use of large-scale and local-scale domains for clustering. A WRF simulation is run at each of the cluster centres and the results are aggregated using a novel post-processing technique. By applying our workflow to two different regions, we show that our long-term predictions agree with those from a year of WRF simulations but require less than 2% of the computational time. The most accurate results are obtained when clustering on wind velocity. Moreover, clustering over the Europe-wide domain is sufficient for predicting wind farm power output, but downstream wake predictions benefit from the use of smaller domains. Finally, we show that these downstream wakes can affect the local weather patterns. Our approach facilitates multi-year predictions of power output and downstream farm wakes, by providing a fast, accurate and flexible methodology that is applicable to any global region. Moreover, these accurate long-term predictions of downstream wakes provide the first tool to help mitigate the effects of wind energy loss downstream of wind farms, since they can be used to determine optimum wind farm locations., Comment: 18 pages, 18 figures

Neural networks are increasingly being used in a variety of settings to predict wind direction and speed, two of the most important factors for estimating the potential power output of a wind farm. However, these predictions are arguably of limited value because classical neural networks lack the ability to express uncertainty. Here we instead consider the use of Bayesian Neural Networks (BNNs), for which the weights, biases and outputs are distributions rather than deterministic point values. This allows for the evaluation of both epistemic and aleatoric uncertainty and leads to well-calibrated uncertainty predictions of both wind speed and power. Here we consider the application of BNNs to the problem of offshore wind resource prediction for renewable energy applications. For our dataset, we use observations recorded at the FINO1 research platform in the North Sea and our predictors are ocean data such as water temperature and current direction. The probabilistic forecast predicted by the BNN adds considerable value to the results and, in particular, informs the user of the network's ability to make predictions of out-of-sample datapoints. We use this property of BNNs to conclude that the accuracy and uncertainty of the wind speed and direction predictions made by our network are unaffected by the construction of the nearby Alpha Ventus wind farm. Hence, at this site, networks trained on pre-farm ocean data can be used to accurately predict wind field information from ocean data after the wind farm has been constructed., Comment: 8 pages, 6 figures

The trustworthiness of neural networks is often challenged because they lack the ability to express uncertainty and explain their skill. This can be problematic given the increasing use of neural networks in high stakes decision-making such as in climate change applications. We address both issues by successfully implementing a Bayesian Neural Network (BNN), where parameters are distributions rather than deterministic, and applying novel implementations of explainable AI (XAI) techniques. The uncertainty analysis from the BNN provides a comprehensive overview of the prediction more suited to practitioners' needs than predictions from a classical neural network. Using a BNN means we can calculate the entropy (i.e. uncertainty) of the predictions and determine if the probability of an outcome is statistically significant. To enhance trustworthiness, we also spatially apply the two XAI techniques of Layer-wise Relevance Propagation (LRP) and SHapley Additive exPlanation (SHAP) values. These XAI methods reveal the extent to which the BNN is suitable and/or trustworthy. Using two techniques gives a more holistic view of BNN skill and its uncertainty, as LRP considers neural network parameters, whereas SHAP considers changes to outputs. We verify these techniques using comparison with intuition from physical theory. The differences in explanation identify potential areas where new physical theory guided studies are needed., Comment: 25 pages, 11 figures

The success of deep learning techniques over the last decades has opened up a new avenue of research for weather forecasting. Here, we take the novel approach of using a neural network to predict full probability density functions at each point in space and time rather than a single output value, thus producing a probabilistic weather forecast. This enables the calculation of both uncertainty and skill metrics for the neural network predictions, and overcomes the common difficulty of inferring uncertainty from these predictions. This approach is data-driven and the neural network is trained on the WeatherBench dataset (processed ERA5 data) to forecast geopotential and temperature 3 and 5 days ahead. Data exploration leads to the identification of the most important input variables, which are also found to agree with physical reasoning, thereby validating our approach. In order to increase computational efficiency further, each neural network is trained on a small subset of these variables. The outputs are then combined through a stacked neural network, the first time such a technique has been applied to weather data. Our approach is found to be more accurate than some numerical weather prediction models and as accurate as more complex alternative neural networks, with the added benefit of providing key probabilistic information necessary for making informed weather forecasts., Comment: 21 pages, 14 figures, Github repository: https://github.com/mc4117/ResNet_Weather, Submitted to Quarterly Journal of the Royal Meteorological Society