Physics-Informed Neural Networks (PINNs) have gained attention for solving partial differential equations, including the scattered Helmholtz equation, due to their flexibility and mesh-free formulation. However, their performance suffers from low-frequency bias, particularly in high-frequency wavefield simulations, limiting convergence speed and accuracy. To address this, we propose a novel and simplified PINN framework that incorporates explicit, trainable Gabor basis functions to efficiently capture the localized and oscillatory nature of wavefields. Unlike previous Gabor-based PINNs that rely on multiplicative filters or auxiliary networks to learn Gabor parameters, our approach redefines the network's task as learning a nonlinear mapping from input coordinates to a custom Gabor coordinate system, where a Gabor function captures the dominant oscillatory behavior of the wavefield. This formulation absorbs the effect of two Gabor parameters into the learned mapping, reducing computational complexity and eliminating the need for manual tuning of hyperparameters. We also present an efficient formulation for incorporating a Perfectly Matched Layer (PML) into the training by deriving real-valued loss components and introducing an analytical expression for the background wavefield. Numerical experiments on various velocity models show that our Gabor-PINN achieves faster convergence, higher accuracy, and greater robustness to architectural design and initialization compared to both traditional PINNs and prior Gabor-based methods. The improvement lies not in adding architectural complexity-as is common in enhanced PINNs-but in absorbing this complexity into the learned coordinate transformation, making the method both simpler and more effective. Our implementation is publicly available to support reproducibility and future research.

Robots come in various forms and have different characteristics that may shape the interaction with them. In human-human interactions, height is a characteristic that shapes human dynamics, with taller people typically perceived as more persuasive. In this work, we aspired to evaluate if the same impact replicates in a human-robot interaction and specifically with a highly non-humanoid robotic object. The robot was designed with modules that could be easily added or removed, allowing us to change its height without altering other design features. To test the impact of the robot’s height, we evaluated participants’ compliance with its request to volunteer to perform a tedious task. In the experiment, participants performed a cognitive task on a computer, which was framed as the main experiment. When done, they were informed that the experiment was completed. While waiting to receive their credits, the robotic object, designed as a mobile robotic service table, entered the room, carrying a tablet that invited participants to complete a 300-question questionnaire voluntarily. We compared participants’ compliance in two conditions: A Short robot composed of two modules and 95cm in height and a Tall robot consisting of three modules and 132cm in height. Our findings revealed higher compliance with the Short robot’s request, demonstrating an opposite pattern to human dynamics. We conclude that while height has a substantial social impact on human-robot interactions, it follows a unique pattern of influence. Our findings suggest that designers cannot simply adopt and implement elements from human social dynamics to robots without testing them first.

Transformers are crucial for reliable and efficient power system operations, particularly in supporting the integration of renewable energy . Effective monitoring of transformer health is critical to maintain grid stability and performance. Thermal insulation ageing is a key transformer failure mode, which is generally tracked by monitoring the hotspot temperature (HST). However, HST measurement is complex, costly, and often estimated from indirect measurements. Existing HST models focus on space-agnostic thermal models, providing worst-case HST estimates. This article introduces a spatio-temporal model for transformer winding temperature and ageing estimation, which leverages physics-based partial differential equations (PDEs) with data-driven Neural Networks (NN) in a Physics Informed Neural Networks (PINNs) configuration to improve prediction accuracy and acquire spatio-temporal resolution. The computational accuracy of the PINN model is improved through the implementation of the Residual-Based Attention (PINN-RBA) scheme that accelerates the PINN model convergence. The PINN-RBA model is benchmarked against self-adaptive attention schemes and classical vanilla PINN configurations. For the first time, PINN based oil temperature predictions are used to estimate spatio-temporal transformer winding temperature values, validated through PDE numerical solution and fiber optic sensor measurements. Furthermore, the spatio-temporal transformer ageing model is inferred, which supports transformer health management decision-making. Results are validated with a distribution transformer operating on a floating photovoltaic power plant.

Seismic data often contain gaps due to various obstacles in the investigated area and recording instrument failures. Deep-learning techniques offer promising solutions for reconstructing missing data parts by utilizing existing data. Nonetheless, self-supervised methods frequently struggle with capturing under-represented features such as weaker events, crossing dips, and higher frequencies. To address these challenges, we propose a novel ensemble deep model (EDM) along with a tailored self-supervised training approach for reconstructing seismic data with consecutive missing traces. Our model comprises two branches of U-nets, each fed from distinct data transformation modules aimed at amplifying under-represented features and promoting diversity among learners. Our loss function minimizes relative errors at the outputs of individual branches and the entire model, ensuring accurate reconstruction of various features while maintaining overall data integrity. Additionally, we employ masking while training to enhance sample diversity and memory efficiency. Applications on two benchmark synthetic datasets and two real datasets demonstrate improved accuracy compared to a conventional U-net, successfully reconstructing weak events, diffractions, higher frequencies, and reflections covered by groundroll. Despite these advancements, our method does incur three times the training cost compared to a simple U-net.

Deep learning (DL) inversion of induction logging measurements is used in well geosteering for real-time imaging of the distribution of subsurface electrical conductivity. We develop a DL inversion workflow to solve 2.5-D inverse problems arising in well geosteering. The inversion workflow employs three DL modules: a “look-around” fault detection module and two inversion modules for reconstructing anisotropic resistivity models in the presence or absence of fault planes, respectively. Our DL approach is capable of detecting and quantifying arbitrary dipping fault planes in real time. We compare inversion performance considering only short logging-while-drilling (LWD) measurements versus using both short LWD and deep-sensing measurements. The latter measurements provide enhanced depth-of-investigation while minimizing uncertainty. We also obtain improved results when using multidimensional inversion, especially nearby fault planes. This study verifies the applicability of real-time 2.5-D DL inversion across arbitrary faulted formations for well geosteering.

Seismic studies exhibit gaps in the recorded data due to surface obstacles. To fill in the gaps with self-supervised deep learning, the network learns to predict different events from the recorded parts of data and then applies it to reconstruct the missing parts of the same dataset. We propose two improvements to the task: a rearrangement of the data, and a new deep-learning approach. We rearrange the traces of a 2D acquisition line as 3D data cubes, sorting the traces by the source and receiver coordinates. This 3D representation offers more information about the structure of the seismic events and allows a coherent reconstruction of them. However, learning the structure of events in 3D cubes is more complicated than in 2D images while the size of the training dataset is limited. Thus, we propose a specific architecture and training strategy to take advantage of 3D data samples, while benefiting from the simplicity of 2D reconstructions. Our proposed multidirectional convolutional neural network has two parallel branches trained to perform 2D reconstructions along the vertical and horizontal directions and a small 3D part that combines their results. We use our method to reconstruct data gaps resulting from several missing shots in a benchmark synthetic and a real land dataset. Compared to a conventional 3D U-net, our network learns to reconstruct the events more accurately. Compared to 2D U-nets, our method avoids the discontinuities that arise from the 2D reconstruction of each trace of the missing shot gathers.

We study three-dimensional isogeometric analysis (IGA) and the solution of the resulting system of linear equations via a direct solver. IGA uses highly continuous $C^{p-1}$Cp-1 basis functions, which provide multiple benefits in terms of stability and convergence properties. However, smooth basis significantly deteriorate the direct solver performance and its parallel scalability. As a partial remedy for this, refined Isogeometric Analysis (rIGA) method improves the sequential execution of direct solvers. The refinement strategy enriches traditional highly-continuous $C^{p-1}$Cp-1 IGA spaces by introducing low-continuity $C^0$C0-hyperplanes along the boundaries of certain pre-defined macro-elements. In this work, we propose a solution strategy for rIGA for parallel distributed memory machines and compare the computational costs of solving rIGA versus IGA discretizations. We verify our estimates with parallel numerical experiments. Results show that the weak parallel scalability of the direct solver improves approximately by a factor of $p^2$p2 when considering rIGA discretizations rather than highly-continuous IGA spaces.

We propose a novel image-dehazing technique based on the minimization of two energy functionals and a fusion scheme to combine the output of both optimizations. The proposed fusion-based variational image-dehazing (FVID) method is a spatially varying image enhancement process that first minimizes a previously proposed variational formulation that maximizes contrast and saturation on the hazy input. The iterates produced by this minimization are kept, and a second energy that shrinks faster intensity values of well-contrasted regions is minimized, allowing to generate a set of difference-of-saturation (DiffSat) maps by observing the shrinking rate. The iterates produced in the first minimization are then fused with these DiffSat maps to produce a haze-free version of the degraded input. The FVID method does not rely on a physical model from which to estimate a depth map, nor it needs a training stage on a database of human-labeled examples. Experimental results on a wide set of hazy images demonstrate that FVID better preserves the image structure on nearby regions that are less affected by fog, and it is successfully compared with other current methods in the task of removing haze degradation from faraway regions.

This paper focuses on the application of hp hierarchic genetic strategy ( hp –HGS) for solution of a challenging problem, the inversion of 3D direct current (DC) resistivity logging measurements. The problem under consideration has been formulated as the global optimization one, for which the objective function (misfit between computed and reference data) exhibits multiple minima. In this paper, we consider the extension of the hp –HGS strategy, namely we couple the hp –HGS algorithm with a gradient based optimization method for a local search. Forward simulations are performed with a self-adaptive hp finite element method, hp –FEM. The computational cost of misfit evaluation by hp –FEM depends strongly on the assumed accuracy. This accuracy is adapted to the tree of populations generated by the hp –HGS algorithm, which makes the global phase significantly cheaper. Moreover, tree structure of demes as well as branch reduction and conditional sprouting mechanism reduces the number of expensive local searches up to the number of minima to be recognized. The common (direct and inverse) accuracy control, crucial for the hp –HGS efficiency, has been motivated by precise mathematical considerations. Numerical results demonstrate the suitability of the proposed method for the inversion of 3D DC resistivity logging measurements.

Images obtained under adverse weather conditions, such as haze or fog, typically exhibit low contrast and faded colors, which may severely limit the visibility within the scene. Unveiling the image structure under the haze layer and recovering vivid colors out of a single image remains a challenging task, since the degradation is depth-dependent and conventional methods are unable to overcome this problem. In this work, we extend a well-known perception-inspired variational framework for single image dehazing. Two main improvements are proposed. First, we replace the value used by the framework for the gray-world hypothesis by an estimation of the mean of the clean image. Second, we add a set of new terms to the energy functional for maximizing the interchannel contrast. Experimental results show that the proposed enhanced variational image dehazing (EVID) method outperforms other state-of-the-art methods both qualitatively and quantitatively. In particular, when the illuminant is uneven, our EVID method is the only one that recovers realistic colors, avoiding the appearance of strong chromatic artifacts.

Through-casing resistivity (TCR) measurement instruments such as Cased Hole Formation Resistivity are extensively used for the dynamic monitoring of oil reservoirs during the production phase in oil wells to evaluate the residual oil distribution. However, two shortcomings still exist in the common TCR model based on single-injection electrodes: The real value of steel-casing resistance is difficult to acquire, and the effect from mechanical tolerances of electrode scale is unpredictable. This paper proposes an innovative model based on double-injection electrodes. In this new model, all the required variables can be measured simultaneously; furthermore, a compensating arithmetic method is employed to obtain the real casing resistance. Self-adaptive goal-orientedhp-finite-element simulations have been performed to prove that the influence of mechanical tolerances of electrode scale can be reduced effectively. Therefore, the TCR measurement accuracy is highly improved.

The authors simulate multifrequency through-casing resistivity tool measurements operating at different frequencies in a borehole environment for the assessment of rock-formation properties. Rock formations are assumed to exhibit axial symmetry around the axis of a vertical borehole. The simulations are performed with a goal-oriented hp-adaptive finite-element method that delivers exponential convergence rates in terms of the quantity of interest (for example, the second vertical difference of the electric potential) against the CPU time. Numerical results confirm the efficiency and accuracy of the method, allowing for high-accuracy and reliable simulations of borehole logging measurements in the presence of highly conductive steel casing. The study of different tool configurations shows the advantages of using calibrated instruments with toroid antennas located on the borehole wall. The agreement between the numerical and analytical results, when the latter is available, is quantified. Errors on the simulations are consistently below 0.1%.