Thermo-constrained physics informed neural network based optimization of mechanical performance in recycled PLA additive manufacturing

Bayesian-optimized deep neural network surrogate for orientation-driven anisotropic thermal conductivity prediction in hybrid polymer nanocomposites

Forecasting daily reference evapotranspiration under different hydrological conditions using a hybrid wavelet–Bayesian optimization–Gaussian process regression model

Bayesian-optimized, feature-augmented deep ensemble for physics-guided critical heat-flux prediction with uncertainty quantification

USEM: A Unified Model for Simultaneous Estimation of Multiple Nutrient Concentrations in Coastal Waters using Landsat 5/7/8 and Sentinel-2 imagery.

Bayesian optimized adaptive control of injection molding machines for plastic recycling material

Design of epicardial restraints for optimized passive filling of the right ventricle.

Adaptive sampling for efficient Lamb wavefield reconstruction in composite laminates with Spatial-Temporal Masked AutoEncoder.

Bayesian optimization and progressive fine-tuning pipeline for kidney CT-scan image detection

Carbon capture, utilization, and storage (CCUS) technologies are now being developed to meet the global net-zero emissions target. Due to their high surface area and high porosity, metal-organic frameworks (MOFs) are promising solid sorbent candidates for post-combustion carbon capture. Recent studies now use machine learning (ML) to accelerate the high-throughput screening of MOFs. However, most studies only rely on supervised learning to do structure-to-property predictions and offer little understanding about the MOF chemical space. In this paper, we aim to provide a more interpretable ML workflow for finding best-performing MOFs for carbon capture using manifold learning and Bayesian optimization. We posed an optimization problem whose objective is to find MOFs from the CoRE MOF 2019 database that minimize the required energy when simulated in a pressure-swing adsorber, subject to having high CO 2 purity and high CO 2 /N 2 selectivity. Different from existing literature, we introduce uniform manifold approximation and projection (UMAP) to first embed the pore geometry descriptors data in a 2-D manifold subspace, hence visualizing the MOF chemical space. We then explored the possibility of performing Bayesian optimization in the UMAP subspace to search MOFs more efficiently. Our results include a 2-D mapping of MOFs, a ranking of best MOFs, and an analysis of regions in the geometric descriptor subspace that led to best process performance. We hope that these contributions can help increase our understanding of the relationships between the material-level and process-level metrics of MOFs for carbon capture. • Explored a 2-D chemical space of MOFs by using UMAP on their geometric descriptors. • Evaluated 50 MOFs in a PSA simulation via Aspen Adsorption Suite. • Used BayesOpt on the subspace to find low-energy, high purity, and selective MOFs. • Identified narrow ranges of descriptors that lead to cost-effective carbon capture. • Best MOFs are in the UMAP neighborhoods of IFEPUG and NIKZAJ.

Thermal comfort model for exercisers that uses Machine learning with integrated Bayesian optimization and SHAP: A case study of badminton players

Bayesian optimization based machine learning for predicting tokamak energy confinement time with quantification of feature importance

Optimization of a multi-metal-coordinated in-situ saccharification system for biohydrogen production via liquid neural network–bayesian optimization: Coupling artificial intelligence with microbial community succession and predicted functions

Quantum-chemistry informed Bayesian optimization for the accelerated discovery of novel pyrazole-based energetic materials

A physics-based framework for remote sensing inversion of fluorescent dissolved organic matter: incorporating fluorescence as an inelastic source term.

MoistViT: A vision transformer model for moisture content prediction of wood chips

An improved activation function for the recognition of knee osteoarthritis severity.

This study identifies optimal, fiscally sustainable HPV vaccination strategies for China using Bayesian optimization and transmission dynamics modeling. By integrating a demographic-based HPV transmission model with a decision-analysis framework, we simulated cervical cancer burden across varying time horizons (30-100 years). Our budget impact analysis, incorporating willingness-to-pay data from a multi-center contingent valuation survey of 787 parents, reveals critical funding dynamics. We found that achieving cervical cancer elimination within 40 years necessitates a 23.97% vaccination coverage among 15-17-year-old girls using the domestic nonavalent vaccine. Conversely, a rapid 30-year elimination target requires 76.66% coverage. At current market prices, autonomous consumer demand falls short, exposing a ¥35.93 billion funding gap for the 40-year target. To mitigate these financial barriers and ensure long-term fiscal resilience, we propose a tripartite financing mechanism-allocating costs among consumers (45.90%), the government (26.19%), and medical insurance (27.91%). These algorithm-driven findings provide an actionable, evidence-based framework for optimizing multi-party health financing and accelerating cervical cancer elimination in China.

Magnetic soft millirobots enable untethered locomotion in narrow environments. However, their design remains largely intuition-driven due to complex interactions among soft-body deformation, magnetic actuation, and environmental contact. Here, we propose an uncertainty-aware, data-efficient inverse design methodology tailored for contact-rich, non-smooth environments. It integrates a physics-based Cosserat rod model with Gaussian Process-based Bayesian optimization to automate robot design for confined-space crawling. To mitigate sim-to-real discrepancies, domain randomization is incorporated by explicitly modeling contact uncertainty. Channel segmentation focusing on critical geometric bottlenecks enhances efficiency and accuracy, halving optimization time and increasing R2 by nearly an order of magnitude in a serpentine channel. Optimized robots consistently outperform arbitrarily selected baseline designs, achieving stable crawling across heterogeneous conditions without failures such as coiling or jamming. When applied to coronary artery-mimicking geometries, the optimized design reached 2.66mm/s, nearly doubling the average baseline speed of 1.42mm/s. Validation in an artery-mimicking channel with 2.5mm out-of-plane undulations further demonstrates the reliability of the optimization framework; notably, the optimized design maintained uninterrupted motion while 25% of baseline designs got stuck. This work establishes an uncertainty-aware inverse design methodology for task-driven magnetic soft millirobot design, paving the way toward automated design-to-deployment pipelines for real-world applications.

Predictive maintenance (PdM) is a critical enabler of intelligent asset management in Industry 4.0, yet many existing frameworks remain difficult to operationalize due to methodological fragmentation. Common limitations include sacrificing temporal realism and class granularity for computational expediency, decoupling labeling strategy design from model hyperparameter optimization, and insufficient support for reproducibility and deployment traceability; particularly in rare-failure regimes. To address these challenges, we propose a unified, end-to-end, and fully traceable PdM framework that jointly optimizes labeling and model parameters while enforcing strict temporal fidelity. The proposed pipeline co-optimizes the failure lookahead window (τ) and LightGBM hyperparameters within a single Bayesian optimization space using Optuna with a Tree-structured Parzen Estimator and MedianPruner, eliminating the suboptimality of fixed or decoupled labeling designs. Temporal leakage is rigorously prevented through forward-chaining cross-validation and a strictly disjoint temporal holdout evaluation. The framework is evaluated on the widely adopted Fidan synthetic dataset (876,100 samples, five classes, [Formula: see text] failure rate), achieving state-of-the-art performance with a macro-F1 score of 0.9875, balanced accuracy of 0.9915, and superior PR-AUC compared to prior benchmarks. Computational analysis and ablation studies confirm both scalability and the non-redundant contribution of key design choices. Crucially, the pipeline exports versioned, reproducible artifacts (models, preprocessors, configurations) designed to support enterprise integration pending site-specific validation. Operational impact projections (e.g., reduced downtime, fewer dispatches) are derived from analogous deployments and require field validation for quantification.