This paper presents a comprehensive systematic review of generative models (GANs, VAEs, DMs, and LLMs) used to synthesize various medical data types, including imaging (dermoscopic, mammographic, ultrasound, CT, MRI, and X-ray), text, time-series, and tabular data (EHR). Unlike previous narrowly focused reviews, our study encompasses a broad array of medical data modalities and explores various generative models. Our search strategy queries databases such as Scopus, PubMed, and ArXiv, focusing on recent works from January 2021 to November 2023, excluding reviews and perspectives. This period emphasizes recent advancements beyond GANs, which have been extensively covered previously. The survey reveals insights from three key aspects: (1) Synthesis applications and purpose of synthesis, (2) generation techniques, and (3) evaluation methods. It highlights clinically valid synthesis applications, demonstrating the potential of synthetic data to tackle diverse clinical requirements. While conditional models incorporating class labels, segmentation masks and image translations are prevalent, there is a gap in utilizing prior clinical knowledge and patient-specific context, suggesting a need for more personalized synthesis approaches and emphasizing the importance of tailoring generative approaches to the unique characteristics of medical data. Additionally, there is a significant gap in using synthetic data beyond augmentation, such as for validation and evaluation of downstream medical AI models. The survey uncovers that the lack of standardized evaluation methodologies tailored to medical images is a barrier to clinical application, underscoring the need for in-depth evaluation approaches, benchmarking, and comparative studies to promote openness and collaboration.

Lithium-ion batteries are widely used in transportation, energy storage, and consumer electronics, driving the need for reliable battery management systems (BMS) for state estimation and control. The Single Particle Model (SPM) balances computational efficiency and accuracy but faces challenges in parameter estimation due to numerous parameters. Current SPM models using parabolic approximation introduce intermediate variables and hard to do parameter grouping. This study presents a control-oriented SPM reformulation that employs parameter grouping and parabolic approximation to simplify model parameters while using average and surface lithium-ion concentrations as model output. By parameter grouping, the original 17 parameters were reduced to 9 grouped parameters. The reformulated model achieves a reduced-order ordinary differential equation form while maintaining mathematical accuracy equivalent to the pre-grouped discretized SPM. Through Sobol sensitivity analysis under various current profiles, the grouped parameters were reduced from 9 to 6 highly sensitive parameters. Results demonstrate that estimating these 6 parameters achieves comparable practical accuracy to estimating all 9 parameters, with faster convergence. This control-oriented SPM enhances BMS applications by facilitating state estimation and control while reducing parameter estimation requirements.

State estimation allows to monitor power networks, exploiting field measurements to derive the most likely grid state. In the literature, measurement errors are usually assumed to follow zero-mean Gaussian distributions; however, it has been shown that this assumption often does not hold. One such example is when considering pseudo-measurements. In distribution networks, a significant amount of pseudo-measurements might be necessary, due to the scarcity of real-time measurements. In this paper, a state estimator is presented which allows to model measurement uncertainty with any continuous distribution, without approximations. This becomes possible by writing state estimation as a general maximum-likelihood estimation-based constrained optimization problem. To realistically describe distribution networks, three-phase unbalanced power flow equations are used. Results are presented that illustrate the differences in accuracy and computational effort between different uncertainty modeling methods, for the IEEE European Low Voltage Test Feeder.

In the remote sensing community, Land Use Land Cover (LULC) classification with satellite imagery is a main focus of current research activities. Accurate and appropriate LULC classification, however, continues to be a challenging task. In this paper, we evaluate the performance of multi-temporal (monthly time series) compared to mono-temporal (single time step) satellite images for multi-label classification using supervised learning on the RapidAI4EO dataset. As a first step, we trained our CNN model on images at a single time step for multi-label classification, i.e. mono-temporal. We incorporated time-series images using a LSTM model to assess whether or not multi-temporal signals from satellites improves CLC classification. The results demonstrate an improvement of approximately 0.89% in classifying satellite imagery on 15 classes using a multi-temporal approach on monthly time series images compared to the mono-temporal approach. Using features from multi-temporal or mono-temporal images, this work is a step towards an efficient change detection and land monitoring approach.

The increased deployment of intermittent renewable energy generators opens up opportunities for grid-connected energy storage. Batteries offer significant flexibility but are relatively expensive at present. Battery lifetime is a key factor in the business case, and it depends on usage, but most techno-economic analyses do not account for this. For the first time, this paper quantifies the annual benefits of grid-connected batteries including realistic physical dynamics and nonlinear electrochemical degradation. Three lithium-ion battery models of increasing realism are formulated, and the predicted degradation of each is compared with a large-scale experimental degradation data set (Mat4Bat). A respective improvement in RMS capacity prediction error from 11\% to 5\% is found by increasing the model accuracy. The three models are then used within an optimal control algorithm to perform price arbitrage over one year, including degradation. Results show that the revenue can be increased substantially while degradation can be reduced by using more realistic models. The estimated best case profit using a sophisticated model is a 175% improvement compared with the simplest model. This illustrates that using a simplistic battery model in a techno-economic assessment of grid-connected batteries might substantially underestimate the business case and lead to erroneous conclusions.

When we are primarily interested in solving several problems jointly with a given prescribed high performance accuracy for each target application, then Foundation Models should for most cases be used rather than problem-specific models. We focus on the specific Computer Vision application of Foundation Models for Earth Observation (EO) and geospatial AI. These models can solve important problems we are tackling, including for example land cover classification, crop type mapping, flood segmentation, building density estimation, and road regression segmentation. In this paper, we show that for a limited number of labelled data, Foundation Models achieve improved performance compared to problem-specific models. In this work, we also present our proposed evaluation benchmark for Foundation Models for EO. Benchmarking the generalization performance of Foundation Models is important as it has become difficult to standardize a fair comparison across the many different models that have been proposed recently. We present the results using our evaluation benchmark for EO Foundation Models and show that Foundation Models are label efficient in the downstream tasks and help us solve problems we are tackling in EO and remote sensing.

State-of-the-art Model Predictive Control (MPC) applications for building heating adopt either a deterministic controller together with a nonlinear model or a linearized model with a stochastic MPC controller. However, deterministic MPC only considers one single realization of the disturbances and its performance strongly depends on the quality of the forecast of the disturbances, which can lead to low performance. In fact, inadequate building energy management can lead to high energy costs and CO$_2$ emissions. On the other hand, a linearized model can fail to capture some dynamics and behavior of the building under control. In this article, we combine a stochastic scenario-based MPC (SBMPC) controller together with a nonlinear Modelica model that is able to provide a richer building description and to capture the dynamics of the building more accurately than linear models. The adopted SBMPC controller considers multiple realizations of the external disturbances obtained through a statistically accurate model, so as to consider different possible disturbance evolutions and to robustify the control action. To this purpose, we present a scenario generation method for building temperature control that can be applied to several exogenous perturbations, e.g.\ solar irradiance, outside temperature, and that satisfies several important stastistical properties, in contrast with simpler and less accurate methods adopted in the literature. We show the benefits of our proposed approach through several simulations in which we compare our method against the standard ones from the literature, for several combinations of a trade-off parameter between comfort and energy cost. We show how our SBMPC controller approach outperforms the standard controllers available in the literature.

Although unprecedented sensitivity and specificity values are reported, recent glaucoma detection deep learning models lack in decision transparency. Here, we propose a methodology that advances explainable deep learning in the field of glaucoma detection and vertical cup-disc ratio (VCDR), an important risk factor. We trained and evaluated deep learning models using fundus images that underwent a certain cropping policy. We defined the crop radius as a percentage of image size, centered on the optic nerve head (ONH), with an equidistant spaced range from 10%-60% (ONH crop policy). The inverse of the cropping mask was also applied (periphery crop policy). Trained models using original images resulted in an area under the curve (AUC) of 0.94 [95% CI: 0.92-0.96] for glaucoma detection, and a coefficient of determination (R^2) equal to 77% [95% CI: 0.77-0.79] for VCDR estimation. Models that were trained on images with absence of the ONH are still able to obtain significant performance (0.88 [95% CI: 0.85-0.90] AUC for glaucoma detection and 37% [95% CI: 0.35-0.40] R^2 score for VCDR estimation in the most extreme setup of 60% ONH crop). Our findings provide the first irrefutable evidence that deep learning can detect glaucoma from fundus image regions outside the ONH.

Parameter estimation in electrochemical models remains a significant challenge in their application. This study investigates the impact of different operating profiles on electrochemical model parameter estimation to identify the optimal conditions. In particular, the present study is focused on Nickel Manganese Cobalt Oxide(NMC) lithium-ion batteries. Based on five fundamental current profiles (C/5, C/2, 1C, Pulse, DST), 31 combinations of conditions were generated and used for parameter estimation and validation, resulting in 961 evaluation outcomes. The Particle Swarm Optimization is employed for parameter identification in electrochemical models, specifically using the Single Particle Model (SPM). The analysis considered three dimensions: model voltage output error, parameter estimation error, and time cost. Results show that using all five profiles (C/5, C/2, 1C, Pulse, DST) minimizes voltage output error, while {C/5, C/2, Pulse, DST} minimizes parameter estimation error. The shortest time cost is achieved with {1C}. When considering both model voltage output and parameter errors, {C/5, C/2, 1C, DST} is optimal. For minimizing model voltage output error and time cost, {C/2, 1C} is best, while {1C} is ideal for parameter error and time cost. The comprehensive optimal condition is {C/5, C/2, 1C, DST}. These findings provide guidance for selecting current conditions tailored to specific needs.

In this work, the Nusselt number is examined for periodically developed heat transfer in micro- and mini-channels with arrays of offset strip fins, subject to a constant heat flux. The Nusselt number is defined on the basis of a heat transfer coefficient which represents the spatially constant macro-scale temperature difference between the fluid and solid during conjugate heat transfer. Its values are determined numerically on a single unit cell of the array for Reynolds numbers between 1 and 600. Two combinations of the Prandtl number and the thermal conductivity ratio are selected, corresponding to air and water. It is shown that the Nusselt number correlations from the literature mainly apply to air in the transitional flow regime in larger conventional channels if the wall temperature remains uniform. As a result, they do not correctly capture the observed trends for the Nusselt number in micro- and mini-channels subject to a constant heat flux. Therefore, new Nusselt number correlations, obtained through a least-squares fitting of 2282 numerical simulations, are presented for air and water. The suitability of these correlations is assessed via the Bayesian approach for parameter estimation and model validation. The correlations respect the observed asymptotic trends and limits of the Nusselt number for all the geometrical parameters of the offset strip fins. In addition, they predict a linear dependence of the Nusselt number on the Reynolds number, in good agreement with the data from this work. Nevertheless, a detailed analysis reveals a more complex scaling of the Nusselt number with the Reynolds number, closely related to the underlying flow regimes, particularly the weak and strong inertia regimes. Finally, through 62 additional simulations, the influence of the material properties on the Nusselt number is illustrated and compared to the available literature.

Lithium-ion batteries are increasingly being deployed in liberalised electricity systems, where their use is driven by economic optimisation in a specific market context. However, battery degradation depends strongly on operational profile, and this is particularly variable in energy trading applications. Here, we present results from a year-long experiment where pairs of batteries were cycled with profiles calculated by solving an economic optimisation problem for wholesale energy trading, including a physically-motivated degradation model as a constraint. The results confirm the conclusions of previous simulations and show that this approach can increase revenue by 20% whilst simultaneously decreasing degradation by 30% compared to existing methods. Analysis of the data shows that conventional approaches cannot increase the number of cycles a battery can manage over its lifetime, but the physics-based approach increases the lifetime both in terms of years and number of cycles, as well as the revenue per year, increasing the possible lifetime revenue by 70%. Finally, the results demonstrate the economic impact of model inaccuracies, showing that the physics-based model can reduce the discrepancy in the overall business case from 170% to 13%. There is potential to unlock significant extra performance using control engineering incorporating physical models of battery ageing.

The high penetration of distributed energy resources (DERs) in low-voltage distribution networks (LVDNs) often leads to network instability and congestion. Discovering the flexibility potential of behind- the-meter (BTM) assets offers a promising solution to these challenges, providing benefits for both prosumers and grid operators. This review focuses on the objectives and constraints associated with the operation of BTM flexibility resources in LVDNs. We propose a new classification framework for network-aware flexibility modelling that incorporates prosumer objectives, flexibility sources, and both local and grid-level constraints. This review identifies research gaps in prosumer-centric grid considerations, control strategies, flexibility preferences, and scenarios in the use of BTM resources.

Accurate state of charge (SOC) estimation is critical for ensuring the safety, reliability, and efficiency of lithium-ion batteries in electric vehicles and energy storage systems. Electrochemical models provide high fidelity for SOC estimation but introduce challenges due to parameter variations, nonlinearities, and computational complexity. To address these issues, this paper proposes an adaptive dead-zone dual sliding mode observer(SMO) based on an improved electrochemical single-particle model. The algorithm integrates a state observer for SOC estimation and a parameter observer for online parameter adaptation. A Lyapunov-derived adaptive dead-zone is introduced to ensure stability, activating parameter updates only when the terminal voltage error lies within a rigorously defined bound. The proposed method was validated under constant-current and UDDS dynamic conditions. Results demonstrate that the adaptive dead-zone dual SMO achieves superior accuracy compared with conventional dual SMO and equivalent circuit model-based EKF methods, maintaining SOC estimation errors within 0.2% under correct initialization and below 1% under a 30% initial SOC error, with rapid convergence. Computational efficiency analysis further shows that the adaptive dead-zone dual sliding mode observer reduces execution time compared with the conventional dual SMO by limiting unnecessary parameter updates, highlighting its suitability for real-time battery management applications. Moreover, robustness under battery aging was confirmed using a cycle-aging model, where the adaptive dead-zone dual SMO maintained stable SOC estimation despite parameter drift. These findings indicate that the proposed method offers a reliable, accurate, and computationally efficient solution for SOC estimation.

Developing high power density electronics requires effective and highly reliable cooling techniques with low thermal resistance and high heat removal capacity. Loop heat pipes (LHPs) are one kind of two-phase heat transfer device which can meet all these requirements. A physics-based one-dimensional numerical model has been elaborated to further develop this promising electronics cooling solution. In addition, an experimental setup using water as coolant, and which includes an LHP built with transparent materials, is used to validate the numerical model. This validation is obtained by comparing the numerical results with the temperature measurements, the two-phase flow section length in the condenser line, and an energy balance evaluation. The numerical model is then used to predict the system performance of the LHP under investigation. The results indicate that this LHP can only work in fixed conductance mode for the given operating conditions. Further, the influence of the charging mass is assessed. For low charging masses, both the natural convection cooled condenser and the compensation chamber casing can be fully utilized to dissipate the input heat, which can exceed {29.9 W} when the coolant saturation temperature is at {100 \celsius}. The operational limits for LHPs are investigated. For the current LHP under given operating conditions, the heat dissipation limit restricts the maximum input heat power, which in turn induces the activation of the heat leakage limit and the liquid-filling limit. It is shown that the condenser with higher heat dissipation capacity and lower thermal resistance will therefore enlarge the operational envelope.

Motivated by the increasing integration among electricity markets, in this paper we propose two different methods to incorporate market integration in electricity price forecasting and to improve the predictive performance. First, we propose a deep neural network that considers features from connected markets to improve the predictive accuracy in a local market. To measure the importance of these features, we propose a novel feature selection algorithm that, by using Bayesian optimization and functional analysis of variance, evaluates the effect of the features on the algorithm performance. In addition, using market integration, we propose a second model that, by simultaneously predicting prices from two markets, improves the forecasting accuracy even further. As a case study, we consider the electricity market in Belgium and the improvements in forecasting accuracy when using various French electricity features. We show that the two proposed models lead to improvements that are statistically significant. Particularly, due to market integration, the predictive accuracy is improved from 15.7% to 12.5% sMAPE (symmetric mean absolute percentage error). In addition, we show that the proposed feature selection algorithm is able to perform a correct assessment, i.e. to discard the irrelevant features.

The increasing availability of geospatial foundation models has the potential to transform remote sensing applications such as land cover classification, environmental monitoring, and change detection. Despite promising benchmark results, the deployment of these models in operational settings is challenging and rare. Standardized evaluation tasks often fail to capture real-world complexities relevant for end-user adoption such as data heterogeneity, resource constraints, and application-specific requirements. This paper presents a structured approach to integrate geospatial foundation models into operational mapping systems. Our protocol has three key steps: defining application requirements, adapting the model to domain-specific data and conducting rigorous empirical testing. Using the Presto model in a case study for crop mapping, we demonstrate that fine-tuning a pre-trained model significantly improves performance over conventional supervised methods. Our results highlight the model's strong spatial and temporal generalization capabilities. Our protocol provides a replicable blueprint for practitioners and lays the groundwork for future research to operationalize foundation models in diverse remote sensing applications. Application of the protocol to the WorldCereal global crop-mapping system showcases the framework's scalability.

We propose stochastic control policies to cope with uncertain and variable gas extractions in natural gas networks. Given historical gas extraction data, these policies are optimized to produce the real-time control inputs for nodal gas injections and for pressure regulation rates by compressors and valves. We describe the random network state as a function of control inputs, which enables a chance-constrained optimization of these policies for arbitrary network topologies. This optimization ensures the real-time gas flow feasibility and a minimal variation in the network state up to specified feasibility and variance criteria. Furthermore, the chance-constrained optimization provides the foundation of a stochastic pricing scheme for natural gas networks, which improves on a deterministic market settlement by offering the compensations to network assets for their contribution to uncertainty and variance control. We analyze the economic properties, including efficiency, revenue adequacy and cost recovery, of the proposed pricing scheme and make them conditioned on the network design.

In the presented study, a pipe penalization approach for the economic topology optimization of District Heating Networks is proposed, drawing inspiration from density-based topology optimization. For District Heating Networks, the upfront investment is a crucial factor for the rollout of this technology. Today, the pipe routing is usually designed relying on a linearization of the underlying heat transport problem. This study proposes to solve the optimal pipe routing problem as a non-linear topology optimization problem, drawing inspiration from density-based topology optimization. The optimization problem is formulated around a non-linear heat transport model and minimizes a detailed net present value representation of the heating network cost. By relaxing the combinatorial problem of pipe placement, this approach remains scalable for large-scale applications. A discrete network topology and near-discrete pipe design is achieved by using an intermediate pipe penalization strategy. For a realistic test case, the proposed algorithm achieves a discrete network topology and near-discrete pipe design that outperforms simple post-processing steps.

To address the challenges and exploit the opportunities that the decarbonization of the energy sector is bringing about, advanced distribution network management and operation strategies are being developed. Many of these require accurate network models to work effectively, including user phase connectivity. However, such information is often not available. This paper proposes a novel method to identify the phase connectivity of single- and three-phase distribution consumers using smart meter measurements. The method is based on state estimation and mixed-integer linear programming, and requires shorter measurement collection times compared to statistical and machine learning-based techniques, for the same level of accuracy. Consequently, the duration of measurement efforts/campaigns aimed at obtaining this type of information reduces, accelerating the system knowledge acquisition process and potentially reducing the campaigns' costs. A technique is illustrated that allows to solve large networks in acceptable time despite the considerable number of integer variables. Extensive computational results are presented for publicly available low voltage feeders.