Explore the vast range of titles available.

The data‐driven approaches for medium‐range weather forecasting are recently shown to be extraordinarily promising for ensemble forecasting due to their fast inference speed compared to the traditional numerical weather prediction models. However, their forecast accuracy can hardly match the state‐of‐the‐art operational ECMWF Integrated Forecasting System (IFS) model. Previous data‐driven approaches perform ensemble forecasting using some simple perturbation methods, like the initial condition perturbation and the Monte Carlo dropout. However, their ensemble performance is often limited arguably by the sub‐optimal ways of applying perturbation. We propose a Swin Transformer‐based Variational Recurrent Neural Network (SwinVRNN), which is a stochastic weather forecasting model combining a SwinRNN predictor with a perturbation module. SwinRNN is designed as a Swin Transformer‐based recurrent neural network, which predicts the future states deterministically. Furthermore, to model the stochasticity in the prediction, we design a perturbation module following the Variational Auto‐Encoder paradigm to learn the multivariate Gaussian distributions of a time‐variant stochastic latent variable from the data. Ensemble forecasting can be easily performed by perturbing the model features leveraging the noise sampled from the learned distribution. We also compare four categories of perturbation methods for ensemble forecasting, that is, fixed distribution perturbation, learned distribution perturbation, MC dropout, and multi model ensemble. Comparisons on the WeatherBench data set show that the learned distribution perturbation method using our SwinVRNN model achieves remarkably improved forecasting accuracy and reasonable ensemble spread due to the joint optimization of the two targets. More notably, SwinVRNN surpasses operational IFS on the surface variables of the 2‐m temperature and the 6‐hourly total precipitation at all lead times up to 5 days (Code is available at https://github.com/tpys/wwprediction). Plain Language Summary Ensemble forecasting plays a crucial role in numerical weather prediction (NWP), since a single deterministic model is hard to forecast the chaotic atmosphere conditions. Recent works have begun to explore the data‐driven based ensemble methods due to their rapid prediction speed over traditional NWP. We develop an efficient and effective deep learning model capable of generating large ensemble forecasts with high prediction accuracy and low prediction time cost. The predicted ensemble members have much greater and more reasonable ensemble spread, and better coverage of the ground truth, compared to the prior data‐driven methods. Moreover, our model surpasses the state‐of‐the‐art operational NWP model on the surface atmospheric variables of the 2‐m temperature and the 6‐hourly total precipitation, offering an impressive probability weather prediction baseline. Key Points A transformer‐based variational model called SwinVRNN is developed for medium‐range weather prediction The proposed SwinVRNN can effectively generate large ensemble forecasts with great prediction accuracy and reasonable ensemble spread The model sets a new state‐of‐the‐art among data‐driven models and surpasses the Integrated Forecast System on key atmospheric variables

A major challenge in structural health monitoring (SHM) is the efficient handling of big data, namely of high-dimensional datasets, when damage detection under environmental variability is being assessed. To address this issue, a novel data-driven approach to early damage detection is proposed here. The approach is based on an efficient partitioning of the dataset, gathering the sensor recordings, and on classical multidimensional scaling (CMDS). The partitioning procedure aims at moving towards a low-dimensional feature space; the CMDS algorithm is instead exploited to set the coordinates in the mentioned low-dimensional space, and define damage indices through norms of the said coordinates. The proposed approach is shown to efficiently and robustly address the challenges linked to high-dimensional datasets and environmental variability. Results related to two large-scale test cases are reported: the ASCE structure, and the Z24 bridge. A high sensitivity to damage and a limited (if any) number of false alarms and false detections are reported, testifying the efficacy of the proposed data-driven approach.

This paper surveys the data‐driven dose prediction methods investigated for knowledge‐based planning (KBP) in the last decade. These methods were classified into two major categories—traditional KBP methods and deep‐learning (DL) methods—according to their techniques of utilizing previous knowledge. Traditional KBP methods include studies that require geometric or anatomical features to either find the best‐matched case(s) from a repository of prior treatment plans or to build dose prediction models. DL methods include studies that train neural networks to make dose predictions. A comprehensive review of each category is presented, highlighting key features, methods, and their advancements over the years. We separated the cited works according to the framework and cancer site in each category. Finally, we briefly discuss the performance of both traditional KBP methods and DL methods, then discuss future trends of both data‐driven KBP methods to dose prediction.

We present a robust data-driven control scheme for an unknown linear system model with bounded process and measurement noise. Instead of depending on a system model in traditional predictive control, a controller utilizing data-driven reachable regions is proposed. The data-driven reachable regions are based on a matrix zonotope recursion and are computed based on only noisy input-output data of a trajectory of the system. We assume that measurement and process noise are contained in bounded sets. While we assume knowledge of these bounds, no knowledge about the statistical properties of the noise is assumed. In the noise-free case, we prove that the presented purely data-driven control scheme results in an equivalent closed-loop behavior to a nominal model predictive control scheme. In the case of measurement and process noise, our proposed scheme guarantees robust constraint satisfaction, which is essential in safety-critical applications. Numerical experiments show the effectiveness of the proposed data-driven controller in comparison to model-based control schemes.

Maximising the power production of wind farms is vital to meet the growing demand for wind energy and reduce its cost. Wake effects, resulting from the aerodynamic interactions between turbines in a wind farm, significantly impact farm efficiency, leading to substantial annual power losses. Wake steering, an influential control strategy, involves mitigating wake effects by strategically yaw misaligning upstream turbines to deflect their wakes. Conventional wake steering approaches typically rely on physics‐based analytical wake models with their parameters often calibrated using higher fidelity data. However, these approaches determine a fixed set of parameters prior to conducting wake steering, neglecting each parameter's dependency on yaw misalignment (i.e. the optimisation variables) exhibited throughout the optimisation process, potentially affecting its accuracy. To address this limitation, this paper introduces a novel data‐driven parameter tuning approach that integrates higher fidelity power measurements using Gaussian processes to continuously adapt parameters in lower fidelity wake models based on the current farm's yaw configuration. The effectiveness of the proposed approach is demonstrated on a 5×5 $$ 5\\times 5 $$wind farm and a layout corresponding to the Horns Rev wind farm, where various wind directions are investigated. The results reveal that the approach can enable a lower fidelity model to capture more complex physics, thereby improving its accuracy in wake steering optimisation, while maintaining robustness and computational efficiency. This method holds promise for real‐time control applications and can be extended to other control strategies and closed‐loop frameworks.

The linear parameter-varying (LPV) model is widely used in aero engine control system design. The conventional local modeling method is inaccurate and inefficient in the full flying envelope. Hence, a novel online data-driven LPV modeling method based on the online sequential extreme learning machine (OS-ELM) with an additional multiplying layer (MLOS-ELM) was proposed. An extra multiplying layer was inserted between the hidden layer and the output layer, where the hidden layer outputs were multiplied by the input variables and state variables of the LPV model. Additionally, the input layer was set to the LPV model’s scheduling parameter. With the multiplying layer added, the state space equation matrices of the LPV model could be easily calculated using online gathered data. Simulation results showed that the outputs of the MLOS-ELM matched that of the component level model of a turbo-shaft engine precisely. The maximum approximation error was less than 0.18%. The predictive outputs of the proposed online data-driven LPV model after five samples also matched that of the component level model well, and the maximum predictive error within a large flight envelope was less than 1.1% with measurement noise considered. Thus, the efficiency and accuracy of the proposed method were validated.

The conventional numerical solvers for partial differential equations encounter a formidable challenge, as their computational efficiency and accuracy are heavily contingent on grid size. Recently, machine learning (ML) has exhibited substantial promise in addressing partial differential equations. Nevertheless, substantial hurdles persist in practical applications. In this work, we endeavor to establish a deep learning framework founded on the Fourier neural operator (FNO) for resolving the intricacies of simulating real landslide dynamic processes. Our findings demonstrate that the current FNO approach adeptly replicates landslide dynamic processes and boasts exceptional computational efficiency. Additionally, it is noteworthy that this data‐driven ML methodology can seamlessly incorporate data from other experimental sources or numerical simulation techniques. Consequently, this work underscores the significant potential of utilizing ML methodologies to supplant conventional numerical simulation methods. Plain Language Summary There are great challenges involved in leveraging machine learning methods to learn realistic physical dynamic processes. When it comes to the real landslide movement across intricate terrains, it is meaningful to validate the capacities of machine learning in tackling the complicated problem. This study aims to propose an innovative solution of modeling of landslide dynamic processes from a machine learning perspective. Here, we introduce a data‐driven framework based on Fourier neural operator to predict the dynamic behavior of actual landslides. Following an exhaustive assessment, the superior performance of our suggested model in real landslide situations and its versatility in adapting to landslides across various geographical regions have been confirmed. This study explores a new approach to modeling landslide dynamic processes and highlights the great potential of data‐driven approaches to address dynamic process challenges present in real physical world. Key Points The data‐driven deep learning method based on FNO can achieve fast prediction of real landslide accumulation process The proposed data‐driven method for predicting landslide dynamic processes can be extended to new areas after transfer learning We provide numerical datasets of landslide dynamics, which can serve as the foundational resources for ML‐based landslide forecasting tasks

This paper proposes a paradigm shift in the numerical simulation approach to predict rain erosion damage on wind turbine blades, given the blade geometry, its coating material, and the atmospheric conditions (wind and rain) expected at the installation site. Contrary to what has been done so far, numerical simulations (flow field and particle tracking) are used not to study a specific (wind and rain) operating condition but to build a large database of possible operating conditions of the blade section. A machine learning algorithm, trained on this database, defines a prediction module that gives the feature of the impact pattern over the 2‐D section, given the wind and rain flow. The advantage of this approach is that the prediction becomes much faster than using the standard simulations; thus, the study of a large set of variable operating conditions becomes possible. The module, coupled with an erosion model, is used to compute the erosion damage of the blade working on specific installation site. In this way, the variations of the flow conditions due to dynamic effects such as variable wind, wind turbulence, and turbine control can be also considered in the erosion computation. Here, we describe the method, the database creation, and the development of the prediction tool. Then, the method is applied to predict the erosion damage on a blade section of a reference wind turbine, after one year of operation in a rainy onshore site. Results are in good agreement with on field observations, showing the potential of the approach.

Data plays a central role in data‐driven methods, but is not often the subject of focus in investigations of machine learning algorithms as applied to Earth System Modeling related problems. Here we consider the problem of eddy‐mean interaction in rotating stratified turbulence in the presence of lateral boundaries, where it is known that rotational components of the eddy flux plays no direct role in the sub‐grid forcing onto the mean state variables, and its presence is expected to affect the performance of the trained machine learning models. While an often utilized choice in the literature is to train a model from the divergence of the eddy fluxes, here we provide theoretical arguments and numerical evidence that learning from the eddy fluxes with the rotational component appropriately filtered out, achieved in this work by means of an object called the eddy force function, results in models with comparable or better skill, but substantially reduced sensitivity to the presence of small‐scale features. We argue that while the choice of data choice and/or quality may not be critical if we simply want a model to have predictive skill, it is highly desirable and perhaps even necessary if we want to leverage data‐driven methods to aid in discovering unknown or hidden physical processes within the data itself. Plain Language Summary Data‐driven methods are increasingly being utilized in various problems relating to the numerical modeling of the Earth system. While there are many investigations focusing on the machine learning algorithms or the problems themselves, there have been relative few investigations into the impact of data choice or quality, given the central role of data. We consider here the impact of the choice of data for a particular problem relevant to ocean modeling, that of eddy‐mean interaction, where it is known that the training data generically contains a component that plays no role in the eddy‐mean interaction, and its presence in the training phase is expected to degrade the model performance. We provide arguments and evidence that one choice is preferable over a more standard choice utilized in related research. While the choice of data choice and/or quality may not be critical if we simply want a data‐driven model to be skillful, we argue it is highly desirable, possibly even a necessity, if we want to leverage data‐driven methods as a means to aid in discovery of unknown or hidden physical processes within the data itself. Key Points Investigated the dependence of convolution neural networks on the choice of training data for geostrophic turbulence Models are trained on eddy fluxes with rotational component filtered out by means of an eddy force function Resulting models as accurate but less sensitive to small‐scale features than models trained on divergence of eddy fluxes

In the field of material informatics, artificial neural networks (ANNs) contribute to the investigation of the processing‐structure‐properties‐performance relationship of materials. This inspires us to leverage the capabilities of ANNs to decode properties of hydrogels, thereby customizing these active materials for sensors or actuators. In the current work, we introduce an approach to predict discrete swelling states of temperature‐responsive hydrogels, especially PNIPAAm, based on their synthesis parameters, utilizing ANN models. To build the database, we analyze literature on temperature‐responsive hydrogels and compile essential synthesis parameters. The corresponding data points related to these synthesis parameters are then extracted. We propose different variants of ANN models and compare their accuracy on the acquired dataset. The selected model can predict the swelling states of hydrogel samples within the test dataset with relative prediction error of 0.11. This approach is applied to predict the expected properties. Subsequently, the hydrogels can be synthesized, and their properties can be experimentally verified. Our approach can be extended to other types of hydrogels and in the prediction of additional properties. The identified synthesis parameters serve as a valuable foundation for the expansion of the database with further literature resources. An enriched database will enhance the performance of the data‐driven model, thereby improving its predictive capabilities. Artificial neural networks (ANNs) can be used to model the processing‐structure‐property‐performance (PSPP) relationship of hydrogels. The current article is focused on regression model A, which predicts the swelling properties of hydrogels, directly based on the synthesis parameters, thus leapfrogging the inner structure description. Based on our model, the research of the PSPP relationship can be completed in the future to predict the influence of synthesis parameters towards the performance of an active–passive system that includes hydrogels.