One of the most significant challenges in research related to nutritional epidemiology is the achievement of high accuracy and validity of dietary data to establish an adequate link between dietary exposure and health outcomes. Recently, the emergence of artificial intelligence (AI) in various fields has filled this gap with advanced statistical models and techniques for nutrient and food analysis. We aimed to systematically review available evidence regarding the validity and accuracy of AI-based dietary intake assessment methods (AI-DIA). In accordance with PRISMA guidelines, an exhaustive search of the EMBASE, PubMed, Scopus and Web of Science databases was conducted to identify relevant publications from their inception to 1 December 2024. Thirteen studies that met the inclusion criteria were included in this analysis. Of the studies identified, 61·5 % were conducted in preclinical settings. Likewise, 46·2 % used AI techniques based on deep learning and 15·3 % on machine learning. Correlation coefficients of over 0·7 were reported in six articles concerning the estimation of calories between the AI and traditional assessment methods. Similarly, six studies obtained a correlation above 0·7 for macronutrients. In the case of micronutrients, four studies achieved the correlation mentioned above. A moderate risk of bias was observed in 61·5 % (n 8) of the articles analysed, with confounding bias being the most frequently observed. AI-DIA methods are promising, reliable and valid alternatives for nutrient and food estimations. However, more research comparing different populations is needed, as well as larger sample sizes, to ensure the validity of the experimental designs.

Photovoltaic (PV) energy grows rapidly and is crucial for the decarbonization of electric systems. However, centralized registries recording the technical characteristics of rooftop PV systems are often missing, making it difficult to monitor this growth accurately. The lack of monitoring could threaten the integration of PV energy into the grid. To avoid this situation, remote sensing of rooftop PV systems using deep learning has emerged as a promising solution. However, existing techniques are not reliable enough to be used by public authorities or transmission system operators (TSOs) to construct up-to-date statistics on the rooftop PV fleet. The lack of reliability comes from deep learning models being sensitive to distribution shifts. This work comprehensively evaluates distribution shifts’ effects on the classification accuracy of deep learning models trained to detect rooftop PV panels on overhead imagery. We construct a benchmark to isolate the sources of distribution shifts and introduce a novel methodology that leverages explainable artificial intelligence (XAI) and decomposition of the input image and model’s decision regarding scales to understand how distribution shifts affect deep learning models. Finally, based on our analysis, we introduce a data augmentation technique designed to improve the robustness of deep learning classifiers under varying acquisition conditions. Our proposed approach outperforms competing methods and can close the gap with more demanding unsupervised domain adaptation methods. We discuss practical recommendations for mapping PV systems using overhead imagery and deep learning models.

Many pension plans and private retirement products contain annuity factors, converting the funds at some future time into lifelong income. In general model settings like, for example, the Li-Lee mortality model, analytical values for the annuity factors are not available and one has to rely on numerical techniques. Their computation typically requires nested simulations as they depend on the interest rate level and the mortality tables at the time of retirement. We exploit the flexibility and efficiency of feed-forward neural networks (NNs) to value the annuity factors at the time of retirement. In a numerical study, we compare our deep learning approach to (least-squares) Monte-Carlo, which can be represented as a special case of the NN.

The dynamic model of the distributed propulsion vehicle faces significant challenges due to several factors. The primary difficulties arise from the strong coupling between multiple power units and aerodynamic rudder surfaces, the interaction between thrust and vehicle dynamics, and the complexity of the aerodynamic model, which includes high-dimensional and high-order variables. To address these challenges, wind tunnel tests are conducted to analyse the aerodynamic characteristics and identify variables affecting the aerodynamic coefficients. Subsequently, a deep neural network is employed to investigate the influence of the power system and aerodynamic rudder on the aerodynamic coefficients. Based on these findings, a multi-dynamic coupled aerodynamic model is developed. Furthermore, a control-oriented nonlinear dynamics model for the distributed propulsion vehicle is established, and a flight controller is designed. Finally, closed-loop simulations for the climb, descent and turn phases are performed, validating the effectiveness of the established model.

This study introduces an innovative deep learning method for intelligent healthcare emotion analysis, specifically targeting the recognition of pain based on facial expressions. The suggested approach combines cloud-based mobile applications, utilising separate front-end and back-end elements to optimise data processing. The main contributions consist of a Smart Automated System (SASys) that integrates statistical and deep learning methods to extract features, thereby guaranteeing both resilience and efficiency. Image preprocessing encompasses the tasks of detecting faces and normalising them, which is crucial for extracting features with high accuracy. The comparison of statistical feature representation using Histogram of Oriented Gradients and Local Binary Pattern, along with machine learning classifiers, against an enhanced deep learning-based approach with an integrated multi-tasking feature known as multi-task convolutional neural network, demonstrates encouraging outcomes that support the superiority of the convolutional neural network architecture. Statistical and deep learning-based classification scores, when combined, greatly enhance the system’s overall performance. The results of the experiments prove that the method is effective, outperforming traditional classifiers and exhibiting comparable accuracy to cutting-edge healthcare SASys.

Particle diffusometry (PD) is a technique of measuring the diffusion coefficient of a fluid sample by seeding it with tracer particles and observing their motion under a microscope. In microfluidic set-ups, the observed particles are often defocused and their motion is affected by factors such as fluid flow, which leads to high errors for conventional and deep learning-based PD (DPD) algorithms. This work improves the performance of DPD models by updating their architecture, avoiding temporal averaging in the input, and exploring the impact of various choices during training. These models provide state-of-the-art performance for generalised datasets regardless of particle shapes, concentration, flow or image noise and are called DPD-v2. These models provide a mean absolute error of 0.09$\mu$m2s−1 for Gaussian particles and 0.07$\mu$m2s−1 for defocused particles, which is 2x–4x lower errors as compared with the two following best methods. The performance of DPD-v2 models increases with crop size and the use of multiple stacks of images. The outputs of the DPD-v2 models were compared against the outputs from conventional algorithms on Gaussianised experimental no flow datasets, which provided < 0.5$\mu$m2s−1 mean absolute difference. Hence, the DPD-v2 models can be used in real-world scenarios.

Among various deep learning-based SLAM systems, many exhibit low accuracy and inadequate generalization on non-training datasets. The deficiency in generalization ability can result in significant errors within SLAM systems during real-world applications, particularly in environments that diverge markedly from those represented in the training set. This paper presents a methodology to enhance the generalization capabilities of deep learning SLAM systems. It leverages their superior performance in feature extraction and introduces Exponential Moving Average (EMA) and Bayes online learning to improve generalization and localization accuracy in varied scenarios. Experimental validation, utilizing Absolute Trajectory Error (ATE) metrics on the dataset, has been conducted. The results demonstrate that this method effectively reduces errors by $20\%$ on the EuRoC dataset and by $35\%$ on the TUM dataset, respectively.

Achieving net-zero carbon emissions by 2050 necessitates the integration of substantial wind power capacity into national power grids. However, the inherent variability and uncertainty of wind energy present significant challenges for grid operators, particularly in maintaining system stability and balance. Accurate short-term forecasting of wind power is therefore essential. This article introduces an innovative framework for regional wind power forecasting over short-term horizons (1–6 h), employing a novel Automated Deep Learning regression framework called WindDragon. Specifically designed to process wind speed maps, WindDragon automatically creates Deep Learning models leveraging Numerical Weather Prediction (NWP) data to deliver state-of-the-art wind power forecasts. We conduct extensive evaluations on data from France for the year 2020, benchmarking WindDragon against a diverse set of baselines, including both deep learning and traditional methods. The results demonstrate that WindDragon achieves substantial improvements in forecast accuracy over the considered baselines, highlighting its potential for enhancing grid reliability in the face of increased wind power integration.

Natural language processing (NLP) has significantly advanced our ability to model and interact with human language through technology. However, these advancements have disproportionately benefited high-resource languages with abundant data for training complex models. Low-resource languages, often spoken by smaller or marginalized communities, need help realizing the full potential of NLP applications. The primary challenges in developing NLP applications for low-resource languages stem from the need for large, well-annotated datasets, standardized tools, and linguistic resources. This scarcity of resources hinders the performance of data-driven approaches that have excelled in high-resource settings. Further, low-resource languages frequently exhibit complex grammatical structures, diverse vocabularies, and unique social contexts, which pose additional challenges for standard NLP techniques. Innovative strategies are emerging to address these challenges. Researchers are actively collecting and curating datasets, even utilizing community engagement platforms to expand data resources. Transfer learning, where models pre-trained on high-resource languages are adapted to low-resource settings, has shown significant promise. Multilingual models like Multilingual Bidirectional Encoder Representations from Transformers (mBERT) and Cross Lingual Models (XLM-R), trained on vast quantities of multilingual data, offer a powerful avenue for cross-lingual knowledge transfer. Additionally, researchers are exploring integrating multimodal approaches, combining textual data with images, audio, or video, to enhance NLP performance in low-resource language scenarios. This survey covers applications like part-of-speech tagging, morphological analysis, sentiment analysis, hate speech detection, dependency parsing, language identification, discourse annotation guidelines, question answering, machine translation, information retrieval, and predictive authoring for augmentative and alternative communication systems. The review also highlights machine learning approaches, deep learning approaches, Transformers, and cross-lingual transfer learning as practical techniques. Developing practical NLP applications for low-resource languages is crucial for preserving linguistic diversity, fostering inclusion within the digital world, and expanding our understanding of human language. While challenges remain, the strategies outlined in this survey demonstrate the ongoing progress and highlight the potential for NLP to empower communities that speak low-resource languages and contribute to a more equitable landscape within language technology.

The operational reliability of large mechanical equipment is typically influenced by the functional effectiveness of key components. Consequently, prompt repair before their failure is necessary to ensure the dependability of mechanical equipment. The prognostic and health management (PHM) technology could track the system’s health state and timely detect faults. Therefore, the remaining useful life (RUL) prediction as one of the key components of PHM is rather important. Accurate RUL prediction results could be the data support for condition-based equipment maintenance plans. Also, it could increase the dependability and safety of mechanical equipment while reducing the loss of human and financial resources and meet the requirements of sustainable manufacturing in the Industry 4.0 era. However, with the widespread use of deep learning in the field of intelligent manufacturing, there is a lack of review on RUL prediction based on deep learning. In this paper, different deep learning-based RUL prediction methods for mechanical components are summarized and classified, along with their pros and cons. Then, the case study on the C-MAPSS dataset is mainly conducted and different methods are compared. And finally, the difficulties and future directions of the RUL prediction in practical scenarios are discussed.

Applications of deep learning to physical simulations such as Computational Fluid Dynamics have recently experienced a surge in interest, and their viability has been demonstrated in different domains. However, due to the highly complex, turbulent, and three-dimensional flows, they have not yet been proven usable for turbomachinery applications. Multistage axial compressors for gas turbine applications represent a remarkably challenging case, due to the high-dimensionality of the regression of the flow field from geometrical and operational variables. This paper demonstrates the development and application of a deep learning framework for predictions of the flow field and aerodynamic performance of multistage axial compressors. A physics-based dimensionality reduction approach unlocks the potential for flow-field predictions, as it re-formulates the regression problem from an unstructured to a structured one, as well as reducing the number of degrees of freedom. Compared to traditional “black-box” surrogate models, it provides explainability to the predictions of the overall performance by identifying the corresponding aerodynamic drivers. The model is applied to manufacturing and build variations, as the associated performance scatter is known to have a significant impact on $ \mathrm{C}{\mathrm{O}}_2 $ emissions, which poses a challenge of great industrial and environmental relevance. The proposed architecture is proven to achieve an accuracy comparable to that of the CFD benchmark, in real-time, for an industrially relevant application. The deployed model is readily integrated within the manufacturing and build process of gas turbines, thus providing the opportunity to analytically assess the impact on performance with actionable and explainable data.

Prediction of dynamic environmental variables in unmonitored sites remains a long-standing challenge for water resources science. The majority of the world’s freshwater resources have inadequate monitoring of critical environmental variables needed for management. Yet, the need to have widespread predictions of hydrological variables such as river flow and water quality has become increasingly urgent due to climate and land use change over the past decades, and their associated impacts on water resources. Modern machine learning methods increasingly outperform their process-based and empirical model counterparts for hydrologic time series prediction with their ability to extract information from large, diverse data sets. We review relevant state-of-the art applications of machine learning for streamflow, water quality, and other water resources prediction and discuss opportunities to improve the use of machine learning with emerging methods for incorporating watershed characteristics and process knowledge into classical, deep learning, and transfer learning methodologies. The analysis here suggests most prior efforts have been focused on deep learning frameworks built on many sites for predictions at daily time scales in the United States, but that comparisons between different classes of machine learning methods are few and inadequate. We identify several open questions for time series predictions in unmonitored sites that include incorporating dynamic inputs and site characteristics, mechanistic understanding and spatial context, and explainable AI techniques in modern machine learning frameworks.

The identification of fishing vessel operations holds significant importance in addressing fishing industry issues, such as overfishing and illegal, unreported and unregulated fishing (IUUF). Many countries utilise data from vessel monitoring systems (VMSs) or automatic identification systems (AISs) to monitor fishing activities. These data include vessel trajectories, headings and speeds, among others. We aimed to analyse the fishing behaviours of three types of fishing gear used by vessels (trawl, purse seine and gill net) and identify the types of gear employed by the vessels. Therefore, a 1D CNN-LSTM fishing vessel operational behaviour prediction model was proposed by combining a one-dimensional convolutional (1D CNN) neural network and a long short-term memory (LSTM) neural network. The model utilises 1D CNN to extract local features from fishing vessel trajectories and employs LSTM to capture the time series information in the data, eventually classifying fishing gears. The results show that the proposed model achieves a classification accuracy of 92% in categorising fishing vessel operational trajectories. This study significantly contributes to preventing IUUF, curtailing overfishing, and enhancing fisheries management strategies.

Rapid urbanization poses several challenges, especially when faced with an uncontrolled urban development plan. Therefore, it often leads to anarchic occupation and expansion of cities, resulting in the phenomenon of urban sprawl (US). To support sustainable decision–making in urban planning and policy development, a more effective approach to addressing this issue through US simulation and prediction is essential. Despite the work published in the literature on the use of deep learning (DL) methods to simulate US indicators, almost no work has been published to assess what has already been done, the potential, the issues, and the challenges ahead. By synthesising existing research, we aim to assess the current landscape of the use of DL in modelling US. This article elucidates the complexities of US, focusing on its multifaceted challenges and implications. Through an examination of DL methodologies, we aim to highlight their effectiveness in capturing the complex spatial patterns and relationships associated with US. This work begins by demystifying US, highlighting its multifaceted challenges. In addition, the article examines the synergy between DL and conventional methods, highlighting the advantages and disadvantages. It emerges that the use of DL in the simulation and forecasting of US indicators is increasing, and its potential is very promising for guiding strategic decisions to control and mitigate this phenomenon. Of course, this is not without major challenges, both in terms of data and models and in terms of strategic city planning policies.

Wind speed at the sea surface is a key quantity for a variety of scientific applications and human activities. For its importance, many observation techniques exist, ranging from in situ to satellite observations. However, none of such techniques can capture the spatiotemporal variability of the phenomenon at the same time. Reanalysis products, obtained from data assimilation methods, represent the state-of-the-art for sea-surface wind speed monitoring but may be biased by model errors and their spatial resolution is not competitive with satellite products. In this work, we propose a scheme based on both data assimilation and deep learning concepts to process spatiotemporally heterogeneous input sources to reconstruct high-resolution time series of spatial wind speed fields. This method allows to us make the most of the complementary information conveyed by the different sea-surface information typically available in operational settings. We use synthetic wind speed data to emulate satellite images, in situ time series and reanalyzed wind fields. Starting from these pseudo-observations, we run extensive numerical simulations to assess the impact of each input source on the model reconstruction performance. We show that our proposed framework outperforms a deep learning–based inversion scheme and can successfully exploit the spatiotemporal complementary information of the different input sources. We also show that the model can learn the possible bias in reanalysis products and attenuate it in the output reconstructions.

The growing demand for global wind power production, driven by the critical need for sustainable energy sources, requires reliable estimation of wind speed vertical profiles for accurate wind power prediction and comprehensive wind turbine performance assessment. Traditional methods relying on empirical equations or similarity theory face challenges due to their restricted applicability beyond the surface layer. Although recent studies have utilized various machine learning techniques to vertically extrapolate wind speeds, they often focus on single levels and lack a holistic approach to predicting entire wind profiles. As an alternative, this study introduces a proof-of-concept methodology utilizing TabNet, an attention-based sequential deep learning model, to estimate wind speed vertical profiles from coarse-resolution meteorological features extracted from a reanalysis dataset. To ensure that the methodology is applicable across diverse datasets, Chebyshev polynomial approximation is employed to model the wind profiles. Trained on the meteorological features as inputs and the Chebyshev coefficients as targets, the TabNet more-or-less accurately predicts unseen wind profiles for different wind conditions, such as high shear, low shear/well-mixed, low-level jet, and high wind. Additionally, this methodology quantifies the correlation of wind profiles with prevailing atmospheric conditions through a systematic feature importance assessment.