A GNN-boosted reinforcement learning framework for maintenance optimization in multi-dependency manufacturing system

A generalized framework for design optimization of UHPC structures at both material and structural levels

A spatio-temporal graph convolutional networks framework for urban fire risk management and resource optimization

• A universal framework (UPCM-EQF) is developed for PCM performance quantification. • Climate-responsive metrics integrate thermal comfort and energy efficiency. • Suitability Ratio (SR) and Enhanced Suitability Index (ESI) are introduced. • Empirical relations enable simulation-free PCM evaluation across climates. • Framework validated using FEM simulations and real-world climate data. Phase Change Materials (PCMs) are widely recognized for reducing HVAC energy loads and enhancing indoor comfort, yet their effectiveness remains highly climate-dependent and difficult to generalize. This study introduces the Universal PCM Effectiveness Quantification Framework (UPCM-EQF), a unified, climate-responsive methodology that integrates heat transfer principles, thermal comfort indices (PMV/PPD), and adaptive climate metrics. Novel metrics, including the Suitability Ratio (SR) and the Enhanced Suitability Index (ESI), are developed to quantify dual-season PCM performance. In addition, empirical relations are derived to estimate energy savings, comfort improvements, and payback periods, enabling practical design-stage decision-making. Validated through finite element simulations and multi-climate case studies, UPCM-EQF demonstrates predictive accuracy across tropical, temperate, and continental climates. It thus provides a universal, scalable, and simulation-free tool to support PCM integration for energy efficiency and thermal comfort.

Development of a deep learning-based framework for operational optimisation of municipal solid waste incinerators

• Optimal treatment strategies for epidemics under explicit and endogenous budgets. • Health authority minimizes infection and costs via dynamic treatment allocation. • Quadratic and blow-up cost structures yield different epidemic and spending paths. • Extension: drug pricing modeled as a Stackelberg game with strategic responses. • Policy insights stress coordinated budget design and outcome-based pricing. Effective epidemic control policies must balance public health objectives with economic constraints, especially when deploying high-cost curative treatments for infectious diseases. This study develops an optimal control framework for a Health Authority (HA), embedded in a controlled SIR epidemic model, to minimize the societal and economic burden of infection under budget constraints. We analyze two institutional cost specifications: a quadratic cost with an explicit budget constraint and a blow-up cost with endogenous constraint enforcement. Numerical simulations calibrated to the case of hepatitis C in France illustrate how cost structures, budget design, and the health authority’s preference over the final state of the epidemic jointly influence treatment intensity, infection dynamics, and long-term health outcomes. As an extension, we incorporate a Stackelberg differential game in which a Pharmaceutical Company (PC) strategically sets the drug price, anticipating the HA’s optimal treatment response. We show that the PC’s valuation of residual infection decisively shapes price trajectories and public health outcomes. The analysis suggests that effective policies should integrate coherent budget planning, outcome-sensitive pricing schemes, and regulatory incentives to align private behavior with long-term public health objectives.

Adaptive optimization of combined steam and CO2 reforming for hydrogen production from variable biogas feed.

Forest Aboveground Biomass Density (AGBD) estimation supports forest carbon accounting and informs carbon monitoring, reporting, and verification. Despite the demonstrated potential of airborne light detection and ranging (lidar) and satellite imagery, accurate AGBD estimation in disturbance-prone, mixed forests remains challenging. To better understand the applicability of these data in disturbance-prone forests, we sought to determine an optimal modeling framework for AGBD estimation. We utilized 70 PlanetScope (3 m), 34 airborne lidar, and 3 ancillary predictors (elevation, slope, and aspect) with field-estimated AGBD across 5 sites in the southeastern United States (US) with different kinds of wind disturbance (tornado, hurricane, straight-line wind): Bankhead, Mountain Longleaf, Oakmulgee, Weeks Bay, and Flagg Mountain. We evaluated: (1) five established variable selection methods; (a) all predictors, (b) top 5 predictors from Random Forest (RF), (c) top 10 predictors from RF, (d) Least Absolute Shrinkage and Selection Operator (lasso), and (e) Recursive Feature Elimination (RFE), and (2) compared 2 modeling algorithms; (a)RF and (b) Bayesian-based Gaussian Process Regression (GPR) for AGBD estimation. Results show that lasso and RF-based variable selection methods outperformed RFE, while GPR outperformed RF. Model accuracy (R 2 = 0.29–0.73; Root Mean Squared Error (RMSE) = 16.29–75.14 Mg/ha) was highest in the undisturbed (Bankhead) and lowest in the wind-disturbance-prone site (Oakmulgee). Findings demonstrate that AGBD estimation is more reliable in undisturbed landscapes, while such frameworks may be inadequate in disturbance-prone, dynamic landscapes. Our study offers optimal modeling frameworks for disturbance-prone mixed forests and advances the synergistic use of lidar and PlanetScope for AGBD estimation. • Built site-specific AGBD frameworks for disturbance-prone sites, fusing airborne lidar and PlanetScope (20 m). • Model accuracies are highest in undisturbed southeastern US forests, and lowest in disturbed forests. • RF-based and lasso feature selection outperformed RFE across sites.

A self-learning refined model and tracking for near space hypersonic vehicle by space-based radar

Facile synthesis of micro and nano sized iron based metal organic frameworks for optimization of effective metronidazole removal

Expanding the cloud: An integrated optimization framework for distributed infrastructure scaling under uncertainty

Experimental and FEM investigation of dynamic and static recrystallization with grain growth in SCM440 steel during hot compression

Toward trustworthy decision-making for wing-diesel hybrid ship’s navigation: A collaborative energy efficiency optimization framework via an Adversarial Robust Reinforcement Learning with Transformer approach

Resilient RoRo fleet scheduling for mixed EV and ICEV transport demand: An optimization framework for EV dedicated service strategy

An explainable artificial intelligence prediction and optimization framework for catalyst layer in proton exchange membrane fuel cell

Multi-objective optimization of nozzle-switching strategy for power regulation in Pelton turbine

CSG-DOF:A Class Structure-Guided Discriminative Optimization Framework for few-shot object detection

Energy-aware trajectory and resource management for NOMA-enabled MEC in UAV-based airborne maneuvering networks: A PPO-driven approach

Management of the part-load operation of a heat pump-based low enthalpy district heating and cooling network in a university campus with photovoltaic generation

High-temperature superconducting (HTS) spherical tokamaks face stringent space constraints, particularly at the inboard side, where excessive toroidal field (TF) coil inner-leg thickness limits space for other components like the central solenoid (CS) and shielding. To resolve this conflict, this study develops a genetic algorithm (GA) framework to optimize TF coil contours, minimizing their inner-leg thickness. Rigorous enforcement of TF coil safety constraints—electromagnetic, thermal, and mechanical—and plasma performance requirements is maintained throughout. Integrated rapid semi-analytical models evaluate key parameters during optimization: magnetic fields, quench temperature rise, and Tresca stress. Applied to the Compact Tokamak Based Repetitive Fusion Reactor-1 (CTRFR-1) HTS spherical tokamak, the GA optimization reduced TF coil inner leg thickness by 18 mm. This space reclamation enables a 26% increase in CS flux generation capacity at a engineering current density of 100 A/mm<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup>. Crucially, finite element analysis (FEA) validated that critical thresholds were maintained: toroidal field ripple below 1%, peak loading factor (J/Jc) below 0.6, maximum quench temperature under 150 K, and peak von Mises stress under 600 MPa. This approach successfully resolves the space-performance conflict in spherical tokamaks, achieving significant CS enhancement while fully preserving TF operational safety and plasma performance. The work establishes an efficient multiphysics optimization framework for designing next-generation spherical tokamaks that fully leverage HTS capabilities within their unique geometry.