Accurate estimation of Remaining Useful Life (RUL) and State of Health (SOH) is essential for Prognostics and Health Management (PHM) across a wide range of industrial applications. We propose a novel framework -- Reinforced Graph-Based Physics-Informed Neural Networks Enhanced with Dynamic Weights (RGPD) -- that combines physics-based supervision with advanced spatio-temporal learning. Graph Convolutional Recurrent Networks (GCRNs) embed graph-convolutional filters within recurrent units to capture how node representations evolve over time. Graph Attention Convolution (GATConv) leverages a self-attention mechanism to compute learnable, edge-wise attention coefficients, dynamically weighting neighbor contributions for adaptive spatial aggregation. A Soft Actor-Critic (SAC) module is positioned between the Temporal Attention Unit (TAU) and GCRN to further improve the spatio-temporal learning. This module improves attention and prediction accuracy by dynamically scaling hidden representations to minimize noise and highlight informative features. To identify the most relevant physical constraints in each area, Q-learning agents dynamically assign weights to physics-informed loss terms, improving generalization across real-time industrial systems and reducing the need for manual tuning. In both RUL and SOH estimation tasks, the proposed method consistently outperforms state-of-the-art models, demonstrating strong robustness and predictive accuracy across varied degradation patterns across three diverse industrial benchmark datasets.

EPT -2 delivers substantial improvements over its predecessor, EPT -1.5, and sets a new state of the art in predicting energy-relevant variables-including 10m and 100m wind speed, 2m temperature, and surface solar radiation-across the full 0-240h forecast horizon. It consistently outperforms leading AI weather models such as Microsoft Aurora, as well as the operational numerical forecast system IFS HRES from the European Centre for Medium-Range Weather Forecasts (ECMWF). In parallel, we introduce a perturbation-based ensemble model of EPT -2 for probabilistic forecasting, called EPT -2e. Remarkably, EPT -2e significantly surpasses the ECMWF ENS mean-long considered the gold standard for medium-to long-range forecasting-while operating at a fraction of the computational cost. EPT models, as well as third-party forecasts, are accessible via the app.jua.ai

Artificial intelligence (AI) systems often interact with multiple agents. The regulation of such AI systems often requires that {\em a priori\/} guarantees of fairness and robustness be satisfied. With stochastic models of agents' responses to the outputs of AI systems, such {\em a priori\/} guarantees require non-trivial reasoning about the corresponding stochastic systems. Here, we present an open-source PyTorch-based toolkit for the use of stochastic control techniques in modelling interconnections of AI systems and properties of their repeated uses. It models robustness and fairness desiderata in a closed-loop fashion, and provides {\em a priori\/} guarantees for these interconnections. The PyTorch-based toolkit removes much of the complexity associated with the provision of fairness guarantees for closed-loop models of multi-agent systems.

Artificial intelligence (AI) has made remarkable progress in recent years, yet its rapid expansion brings overlooked environmental and ethical challenges. This review explores four critical areas where AI's impact extends beyond performance: energy consumption, electronic waste (e-waste), inequality in compute access, and the hidden energy burden of cybersecurity systems. Drawing from recent studies and institutional reports, the paper highlights systemic issues such as high emissions from model training, rising hardware turnover, global infrastructure disparities, and the energy demands of securing AI. By connecting these concerns, the review contributes to Responsible AI discourse by identifying key research gaps and advocating for sustainable, transparent, and equitable development practices. Ultimately, it argues that AI's progress must align with ethical responsibility and environmental stewardship to ensure a more inclusive and sustainable technological future.

With the exponential growth of smart devices connected to wireless networks, data production is increasing rapidly, requiring machine learning (ML) techniques to unlock its value. However, the centralized ML paradigm raises concerns over communication overhead and privacy. Federated learning (FL) offers an alternative at the network edge, but practical deployment in wireless networks remains challenging. This paper proposes a lightweight FL (LTFL) framework integrating wireless transmission power control, model pruning, and gradient quantization. We derive a closed-form expression of the FL convergence gap, considering transmission error, model pruning error, and gradient quantization error. Based on these insights, we formulate an optimization problem to minimize the convergence gap while meeting delay and energy constraints. To solve the non-convex problem efficiently, we derive closed-form solutions for the optimal model pruning ratio and gradient quantization level, and employ Bayesian optimization for transmission power control. Extensive experiments on real-world datasets show that LTFL outperforms state-of-the-art schemes.

This paper proposes a neural stochastic optimization method for efficiently solving the two-stage stochastic unit commitment (2S-SUC) problem under high-dimensional uncertainty scenarios. The proposed method approximates the second-stage recourse problem using a deep neural network trained to map commitment decisions and uncertainty features to recourse costs. The trained network is subsequently embedded into the first-stage UC problem as a mixed-integer linear program (MILP), allowing for explicit enforcement of operational constraints while preserving the key uncertainty characteristics. A scenario-embedding network is employed to enable dimensionality reduction and feature aggregation across arbitrary scenario sets, serving as a data-driven scenario reduction mechanism. Numerical experiments on IEEE 5-bus, 30-bus, and 118-bus systems demonstrate that the proposed neural two-stage stochastic optimization method achieves solutions with an optimality gap of less than 1%, while enabling orders-of-magnitude speedup compared to conventional MILP solvers and decomposition-based methods. Moreover, the model's size remains constant regardless of the number of scenarios, offering significant scalability for large-scale stochastic unit commitment problems.

Multi-agent reinforcement learning faces fundamental challenges that conventional approaches have failed to overcome: exponentially growing joint action spaces, non-stationary environments where simultaneous learning creates moving targets, and partial observability that constrains coordination. Current methods remain reactive, employing stimulus-response mechanisms that fail when facing novel scenarios. We argue for a transformative paradigm shift from reactive to proactive multi-agent intelligence through generative AI-based reinforcement learning. This position advocates reconceptualizing agents not as isolated policy optimizers, but as sophisticated generative models capable of synthesizing complex multi-agent dynamics and making anticipatory decisions based on predictive understanding of future interactions. Rather than responding to immediate observations, generative-RL agents can model environment evolution, predict other agents' behaviors, generate coordinated action sequences, and engage in strategic reasoning accounting for long-term dynamics. This approach leverages pattern recognition and generation capabilities of generative AI to enable proactive decision-making, seamless coordination through enhanced communication, and dynamic adaptation to evolving scenarios. We envision this paradigm shift will unlock unprecedented possibilities for distributed intelligence, moving beyond individual optimization toward emergent collective behaviors representing genuine collaborative intelligence. The implications extend across autonomous systems, robotics, and human-AI collaboration, promising solutions to coordination challenges intractable under traditional reactive frameworks.

Proactive maintenance strategies, such as Predictive Maintenance (PdM), play an important role in the operation of Nuclear Power Plants (NPPs), particularly due to their capacity to reduce offline time by preventing unexpected shutdowns caused by component failures. In this work, we explore the use of a Convolutional Neural Network (CNN) architecture combined with a computational thermomechanical model to calculate the temperature, stress, and strain of a Pressurized Water Reactor (PWR) fuel rod during operation. This estimation relies on a limited number of temperature measurements from the cladding's outer surface. This methodology can potentially aid in developing PdM tools for nuclear reactors by enabling real-time monitoring of such systems. The training, validation, and testing datasets were generated through coupled simulations involving BISON, a finite element-based nuclear fuel performance code, and the MOOSE Thermal-Hydraulics Module (MOOSE-THM). We conducted eleven simulations, varying the peak linear heat generation rates. Of these, eight were used for training, two for validation, and one for testing. The CNN was trained for over 1,000 epochs without signs of overfitting, achieving highly accurate temperature distribution predictions. These were then used in a thermomechanical model to determine the stress and strain distribution within the fuel rod.

Achieving sustained thermonuclear fusion in tokamak reactors [1, 2] requires a precise understanding and control of burning plasma behavior, particularly under the high-power deuterium-tritium (D-T) conditions anticipated in ITER [3-5]. In these plasmas, interactions among energetic fusion alpha particles, electrons, and ions give rise to complex nonlinear processes, including collisional heating, radiative losses, impurity effects, and multi-region energy transport. These dynamics are strongly influenced by both global and local plasma parameters, such as magnetic field strength, safety factor, impurity concentration, and transport coefficients. Quantifying the sensitivity of plasma behavior to these parameters is essential for robust scenario design, performance optimization, and predictive control of fusion reactors. Previous studies [4, 6-10] have proposed various models to simulate burning plasma dynamics. However, many of these approaches rely on empirical scaling laws with limited flexibility across operational regimes. To address these challenges, NeuralPlasmaODE [11, 12] was developed as a data-informed, multi-region, multi-timescale modeling framework based on neural ordinary differential equations (Neural ODEs) [13, 14]. This framework builds upon prior nodal modeling of tokamak plasmas [10, 15-18] and has demonstrated strong performance in capturing energy transport and species interactions in both DIII-D and ITER scenarios. In this work, we extend NeuralPlasmaODE [11, 12] to conduct a comprehensive sensitivity analysis of transport and radiation effects in ITER burning plasmas.

Achieving controlled burning plasma in tokamaks requires precise regulation of external particle and energy sources to reach and maintain target core densities and temperatures. This work presents an inverse modeling approach using a multinodal plasma dynamics model based on neural ordinary differential equations (Neural ODEs). Given a desired time evolution of nodal quantities such as deuteron density or electron temperature, we compute the external source profiles, such as neutral beam injection (NBI) power, that drive the plasma toward the specified behavior. The approach is implemented within the NeuralPlasmaODE framework, which models multi-region, multi-timescale transport and incorporates physical mechanisms including radiation, auxiliary heating, and internodal energy exchange. By formulating the control task as an optimization problem, we use automatic differentiation through the Neural ODE solver to minimize the discrepancy between simulated and target trajectories. This framework transforms the forward simulation tool into a control-oriented model and provides a practical method for computing external source profiles in both current and future fusion devices.