In scientific applications, predictive modeling is often of limited use without accurate uncertainty quantification (UQ) to indicate when a model may be extrapolating or when more data needs to be collected. Bayesian Neural Networks (BNNs) produce predictive uncertainty by propagating uncertainty in neural network (NN) weights and offer the promise of obtaining not only an accurate predictive model but also accurate UQ. However, in practice, obtaining accurate UQ with BNNs is difficult due in part to the approximations used for practical model training and in part to the need to choose a suitable set of hyperparameters; these hyperparameters outnumber those needed for traditional NNs and often have opaque effects on the results. We aim to shed light on the effects of hyperparameter choices for BNNs by performing a global sensitivity analysis of BNN performance under varying hyperparameter settings. Our results indicate that many of the hyperparameters interact with each other to affect both predictive accuracy and UQ. For improved usage of BNNs in real-world applications, we suggest that global sensitivity analysis, or related methods such as Bayesian optimization, should be used to aid in dimensionality reduction and selection of hyperparameters to ensure accurate UQ in BNNs.

Phase-field models of liquid metal dealloying (LMD) can resolve rich microstructural dynamics but become intractable for large domains or long time horizons. We present a conditionally parameterized, fully convolutional U-Net surrogate that generalizes far beyond its training window in both space and time. The design integrates convolutional self-attention and physics-aware padding, while parameter conditioning enables variable time-step skipping and adaptation to diverse alloy systems. Although trained only on short, small-scale simulations, the surrogate exploits the translational invariance of convolutions to extend predictions to much longer horizons than traditional solvers. It accurately reproduces key LMD physics, with relative errors typically under 5% within the training regime and below 10% when extrapolating to larger domains and later times. The method accelerates computations by up to 16,000 times, cutting weeks of simulation down to seconds, and marks an early step toward scalable, high-fidelity extrapolation of LMD phase-field models.

In this work, we develop machine learning (ML) based strategies to predict resources (costs) required for massively parallel chemistry computations, such as coupled-cluster methods, to guide application users before they commit to running expensive experiments on a supercomputer. By predicting application execution time, we determine the optimal runtime parameter values such as number of nodes and tile sizes. Two key questions of interest to users are addressed. The first is the shortest-time question, where the user is interested in knowing the parameter configurations (number of nodes and tile sizes) to achieve the shortest execution time for a given problem size and a target supercomputer. The second is the cheapest-run question in which the user is interested in minimizing resource usage, i.e., finding the number of nodes and tile size that minimizes the number of node-hours for a given problem size. We evaluate a rich family of ML models and strategies, developed based on the collections of runtime parameter values for the CCSD (Coupled Cluster with Singles and Doubles) application executed on the Department of Energy (DOE) Frontier and Aurora supercomputers. Our experiments show that when predicting the total execution time of a CCSD iteration, a Gradient Boosting (GB) ML model achieves a Mean Absolute Percentage Error (MAPE) of 0.023 and 0.073 for Aurora and Frontier, respectively. In the case where it is expensive to run experiments just to collect data points, we show that active learning can achieve a MAPE of about 0.2 with just around 450 experiments collected from Aurora and Frontier.

--Adaptive scheduling is crucial for ensuring the reliability and safety of time-triggered systems (TTS) in dynamic operational environments. Scheduling frameworks face significant challenges, including message collisions, locked loops from incorrect precedence handling, and the generation of incomplete or invalid schedules, which can compromise system safety and performance. T o address these challenges, this paper presents a novel reconstruction framework designed to dynamically validate and assemble schedules. The proposed reconstruction models operate by systematically transforming AI-generated or heuristically derived scheduling priorities into fully executable schedules, ensuring adherence to critical system constraints such as precedence rules and collision-free communication. It incorporates robust safety checks, efficient allocation algorithms, and recovery mechanisms to handle unexpected context events, including hardware failures and mode transitions. Comprehensive experiments were conducted across multiple performance profiles, including makespan minimisation, workload balancing, and energy efficiency, to validate the operational effectiveness of the reconstruction models. Results demonstrate that the proposed framework significantly enhances system adaptability, operational integrity, and runtime performance while maintaining computational efficiency. Overall, this work contributes a practical and scalable solution to the problem of safe schedule generation in safety-critical TTS, enabling reliable and flexible real-time scheduling even under highly dynamic and uncertain operational conditions. Safety-critical time-triggered systems (TTS) are commonly used in areas like automotive, aviation, industrial automation, and medical devices, where operations must be predictable and reliable. These systems rely on carefully designed schedules that specify exact times for tasks to run and messages to be sent, ensuring deterministic behavior. However, real-world situations can introduce unexpected events such as hardware failures, variations in task execution times (slack), or changes in operational modes. As a result, these systems must adapt quickly and effectively to maintain safety and performance [1] [2]. Metascheduling is a widely adopted solution to provide adaptability in time-triggered systems. Unlike traditional static scheduling, metascheduling involves creating multiple pre-computed schedules designed to handle different anticipated scenarios such as hardware failures, task execution slacks, or mode transitions.

The elephant trunk exemplifies a natural gripper where structure, actuation, and sensing are seamlessly integrated. Inspired by the distal morphology of the African elephant trunk, we present MELEGROS, a Monolithic ELEphant-inspired GRipper with Optical Sensors, emphasizing sensing as an intrinsic, co-fabricated capability. Unlike multi-material or tendon-based approaches, MELEGROS directly integrates six optical waveguide sensors and five pneumatic chambers into a pneumatically actuated lattice structure (12.5 mm cell size) using a single soft resin and one continuous 3D print. This eliminates mechanical mismatches between sensors, actuators, and body, reducing model uncertainty and enabling simulation-guided sensor design and placement. Only four iterations were required to achieve the final prototype, which features a continuous structure capable of elongation, compression, and bending while decoupling tactile and proprioceptive signals. MELEGROS (132 g) lifts more than twice its weight, performs bioinspired actions such as pinching, scooping, and reaching, and delicately grasps fragile items like grapes. The integrated optical sensors provide distinct responses to touch, bending, and chamber deformation, enabling multifunctional perception. MELEGROS demonstrates a new paradigm for soft robotics where fully embedded sensing and continuous structures inherently support versatile, bioinspired manipulation.

Atmospheric ozone is a crucial absorber of solar radiation and an important greenhouse gas. However, most climate models participating in the Coupled Model Intercomparison Project (CMIP) still lack an interactive representation of ozone due to the high computational costs of atmospheric chemistry schemes. Here, we introduce a machine learning parameterization (mloz) to interactively model daily ozone variability and trends across the troposphere and stratosphere in standard climate sensitivity simulations, including two-way interactions of ozone with the Quasi-Biennial Oscillation. We demonstrate its high fidelity on decadal timescales and its flexible use online across two different climate models -- the UK Earth System Model (UKESM) and the German ICOsahedral Nonhydrostatic (ICON) model. With atmospheric temperature profile information as the only input, mloz produces stable ozone predictions around 31 times faster than the chemistry scheme in UKESM, contributing less than 4 percent of the respective total climate model runtimes. In particular, we also demonstrate its transferability to different climate models without chemistry schemes by transferring the parameterization from UKESM to ICON. This highlights the potential for widespread adoption in CMIP-level climate models that lack interactive chemistry for future climate change assessments, particularly when focusing on climate sensitivity simulations, where ozone trends and variability are known to significantly modulate atmospheric feedback processes.

Dehazing involves removing haze or fog from images to restore clarity and improve visibility by estimating atmospheric scattering effects. While deep learning methods show promise, the lack of paired real-world training data and the resulting domain gap hinder generalization to real-world scenarios. In this context, physics-grounded learning becomes crucial; however, traditional methods based on the Atmospheric Scattering Model (ASM) often fall short in handling real-world complexities and diverse haze patterns. T o solve this problem, we propose HazeFlow, a novel ODE-based framework that reformulates ASM as an ordinary differential equation (ODE). Inspired by Rectified Flow (RF), HazeFlow learns an optimal ODE trajectory to map hazy images to clean ones, enhancing real-world de-hazing performance with only a single inference step. Additionally, we introduce a non-homogeneous haze generation method using Markov Chain Brownian Motion (MCBM) to address the scarcity of paired real-world data. By simulating realistic haze patterns through MCBM, we enhance the adaptability of HazeFlow to diverse real-world scenarios. Through extensive experiments, we demonstrate that Haze-Flow achieves state-of-the-art performance across various real-world dehazing benchmark datasets. Code is available at https://github.com/cloor/HazeFlow .

We analyze offline designs of linear quadratic regulator (LQR) strategies with uncertain disturbances. First, we consider the scenario where the exogenous variable can be estimated in a controlled environment, and subsequently, consider a more practical and challenging scenario where it is unknown in a stochastic setting. Our approach builds on the fundamental learning-based framework of adaptive dynamic programming (ADP), combined with a Lyapunov-based analytical methodology to design the algorithms and derive sample-based approximations motivated from the Markov decision process (MDP)-based approaches. For the scenario involving non-measurable disturbances, we further establish stability and convergence guarantees for the learned control gains under sample-based approximations. The overall methodology emphasizes simplicity while providing rigorous guarantees. Finally, numerical experiments focus on the intricacies and validations for the design of offline continuous-time LQR with exogenous disturbances.

The proliferation of Time Series Foundation Models (TSFMs) has significantly advanced zero-shot forecasting, enabling predictions for unseen time series without task-specific fine-tuning. Extensive research has confirmed that no single TSFM excels universally, as different models exhibit preferences for distinct temporal patterns. This diversity suggests an opportunity: how to take advantage of the complementary abilities of TSFMs. To this end, we propose ZooCast, which characterizes each model's distinct forecasting strengths. ZooCast can intelligently assemble current TSFMs into a model zoo that dynamically selects optimal models for different forecasting tasks. Our key innovation lies in the One-Embedding-Fits-All paradigm that constructs a unified representation space where each model in the zoo is represented by a single embedding, enabling efficient similarity matching for all tasks. Experiments demonstrate ZooCast's strong performance on the GIFT-Eval zero-shot forecasting benchmark while maintaining the efficiency of a single TSFM. In real-world scenarios with sequential model releases, the framework seamlessly adds new models for progressive accuracy gains with negligible overhead.