Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “hybrid learning”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 577 records · Page 32
All sourcesNASA NTRSDOE OSTI
DOE OSTI2023

Modular machine learning-based elastoplasticity: Generalization in the context of limited data

The development of highly accurate constitutive models for materials that undergo path-dependent processes continues to be a complex challenge in computational solid mechanics. Challenges arise both in considering the appropriate model assumptions and from the viewpoint of data availability, verification, and validation. Recently, data-driven modeling approaches have been proposed that aim to establish stress-evolution laws that avoid user-chosen functional forms by relying on machine learning representations and algorithms. However, these approaches not only require a significant amount of data but also need data that probes the full stress space with a variety of complex loading paths. Furthermore, they rarely enforce all necessary thermodynamic principles as hard constraints. Hence, they are in particular not suitable for low-data or limited-data regimes, where the first arises from the cost of obtaining the data and the latter from the experimental limitations of obtaining labeled data, which is commonly the case in engineering applications. In this work, we discuss a hybrid framework that can work on a variable amount of data by relying on the modularity of the elastoplasticity formulation where each component of the model can be chosen to be either a classical phenomenological or a data-driven model depending on the amount of available information and the complexity of the response. The method is tested on synthetic uniaxial data coming from simulations as well as cyclic experimental data for structural materials. The discovered material models are found to not only interpolate well but also allow for accurate extrapolation in a thermodynamically consistent manner far outside the domain of the training data. This ability to extrapolate from limited data was the main reason for the early and continued success of phenomenological models and the main shortcoming in machine learning-enabled constitutive modeling approaches. Training aspects and details of the implementation of these models into Finite Element simulations are discussed and analyzed.

42 ENGINEERING↗
DOE OSTI2025

Data Quality Monitoring for the Hadron Calorimeters Using Transfer Learning for Anomaly Detection

The proliferation of sensors brings an immense volume of spatio-temporal (ST) data in many domains, including monitoring, diagnostics, and prognostics applications. Data curation is a time-consuming process for a large volume of data, making it challenging and expensive to deploy data analytics platforms in new environments. Transfer learning (TL) mechanisms promise to mitigate data sparsity and model complexity by utilizing pre-trained models for a new task. Despite the triumph of TL in fields like computer vision and natural language processing, efforts on complex ST models for anomaly detection (AD) applications are limited. In this study, we present the potential of TL within the context of high-dimensional ST AD with a hybrid autoencoder architecture, incorporating convolutional, graph, and recurrent neural networks. Motivated by the need for improved model accuracy and robustness, particularly in scenarios with limited training data on systems with thousands of sensors, this research investigates the transferability of models trained on different sections of the Hadron Calorimeter of the Compact Muon Solenoid experiment at CERN. The key contributions of the study include exploring TL’s potential and limitations within the context of encoder and decoder networks, revealing insights into model initialization and training configurations that enhance performance while substantially reducing trainable parameters and mitigating data contamination effects.

47 OTHER INSTRUMENTATION↗
DOE OSTI2026

Deep Learning enabled spectral energy conversion for in situ exposure measurements

A detector-specific deep learning (DL) approach is presented for spectra-to-exposure conversion using large-format sodium iodide (NaI(Tl)) detectors deployed for in situ environmental radiation measurements in emergency response scenarios. Accurate determination of exposure from NaI spectra is challenging due to poor energy resolution, partial energy absorption, and the strong sensitivity of traditionally deployed analytical conversion methods to calibrated source geometry and pre-deployment assumptions. Here, to address these limitations, a multi-layer perceptron model was trained on a hybrid in situ /Monte Carlo dataset constructed to span a broad range of photon energies, spatial extents, and realistic deployment variability, representative of general in situ emergency response conditions. The DL model was evaluated against commonly fielded analytical approaches under matched simulation conditions, including a single-factor method, a G-function method, and a modeled pressurized ion chamber (PIC) baseline. This study was intentionally computational in scope to enable controlled, like-for-like comparisons between conversion techniques while minimizing confounding real-world variability. Comparison to the modeled PIC provides contextual benchmarking and is not intended as a field inter-comparison with deployed instruments. Across the evaluated 20 keV to 3 MeV energy range, the DL approach consistently exhibited higher accuracy and reduced variance relative to the analytical methods against a deterministically calculated exposure. This may indicate improved robustness to spectral complexity without reliance on source-, geometric-, or spectral region-specific optimization. While results do not represent real-world validation, the presented work demonstrates that deep learning may effectively learn the nonlinear detector response-to-exposure relationship for asymmetric NaI(Tl) detectors and offers a promising pathway for improving in situ exposure estimation using spectroscopic systems already integrated into initial real-time emergency response operations.

61 RADIATION PROTECTION AND DOSIMETRY↗
DOE OSTI2025

Correlated dynamic disorder, octahedral tilts, and acoustic phonon softening in CsSnBr 3 and CsPbBr 3

Metal halide perovskites (MHPs) have emerged as highly promising materials for optoelectronic applications, with all-inorganic MHPs presenting enhanced stability compared to their hybrid counterparts. Here, in this study, we investigate the atomic dynamics and structural fluctuations in single crystals of CsSnBr⁢ 3 and CsPbBr⁢ 3 through systematic inelastic neutron scattering (INS) measurements as a function of temperature. Our experiments are compared with first-principle simulations, augmented with large-scale molecular dynamics modeling, based on machine-learned neural network potentials. Through both INS and simulations, we find quasi-elastic diffuse rods in reciprocal space in both compounds, originating from fluctuating planar domains featuring correlated tilts of Br octahedron. The diffuse rods exhibit a slow, overdamped dynamic process, modulated across 𝑸 space, reflecting the strong lattice anharmonicity of the inorganic framework. We do not find evidence for dynamic off-centering of the Sn 2+ ions besides phonon vibrations at the center of the Br octahedron. These results offer valuable insights into the unusual anharmonic atomic dynamics and intricate correlated structural distortions in MHPs, which will be critical for rationalizing and further tailoring their thermal and optoelectronic properties.

36 MATERIALS SCIENCE↗
DOE OSTI2025

Accelerating phase field simulations through a hybrid adaptive Fourier neural operator with U-net backbone

Prolonged contact between a corrosive liquid and metal alloys can cause progressive dealloying. For one such process as liquid-metal dealloying (LMD), phase field models have been developed to understand the mechanisms leading to complex morphologies. However, the LMD governing equations in these models often involve coupled non-linear partial differential equations (PDE), which are challenging to solve numerically. In particular, numerical stiffness in the PDEs requires an extremely refined time step size (on the order of 10 -12 s or smaller). This computational bottleneck is especially problematic when running LMD simulation until a late time horizon is required. This motivates the development of surrogate models capable of leaping forward in time, by skipping several consecutive time steps at-once. In this paper, we propose a U-shaped adaptive Fourier neural operator (U-AFNO), a machine learning (ML) based model inspired by recent advances in neural operator learning. U-AFNO employs U-Nets for extracting and reconstructing local features within the physical fields, and passes the latent space through a vision transformer (ViT) implemented in the Fourier space (AFNO). We use U-AFNOs to learn the dynamics of mapping the field at a current time step into a later time step. We also identify global quantities of interest (QoI) describing the corrosion process (e.g., the deformation of the liquid-metal interface, lost metal, etc.) and show that our proposed U-AFNO model is able to accurately predict the field dynamics, in spite of the chaotic nature of LMD. Most notably, our model reproduces the key microstructure statistics and QoIs with a level of accuracy on par with the high-fidelity numerical solver, while achieving a significant 11, 200 × speed-up on a high-resolution grid when comparing the computational expense per time step. Finally, we also investigate the opportunity of using hybrid simulations, in which we alternate forward leaps in time using the U-AFNO with high-fidelity time stepping. We demonstrate that while advantageous for some surrogate model design choices, our proposed U-AFNO model in fully auto-regressive settings consistently outperforms hybrid schemes.

36 MATERIALS SCIENCE↗
DOE OSTI2022

Physics makes the difference: Bayesian optimization and active learning via augmented Gaussian process

Abstract Both experimental and computational methods for the exploration of structure, functionality, and properties of materials often necessitate the search across broad parameter spaces to discover optimal experimental conditions and regions of interest in the image space or parameter space of computational models. The direct grid search of the parameter space tends to be extremely time-consuming, leading to the development of strategies balancing exploration of unknown parameter spaces and exploitation towards required performance metrics. However, classical Bayesian optimization (BO) strategies based on the Gaussian process (GP) do not readily allow for the incorporation of the known physical behaviors or past knowledge. Here we explore a hybrid optimization/exploration algorithm created by augmenting the standard GP with a structured probabilistic model of the expected system’s behavior. This approach balances the flexibility of the non-parametric GP approach with a rigid structure of physical knowledge encoded into the parametric model. The fully Bayesian treatment of the latter allows additional control over the optimization via the selection of priors for the model parameters. The method is demonstrated for a noisy version of a standard univariate test function used to evaluate optimization algorithms and further extended to physical lattice models. This methodology is expected to be universally suitable for injecting prior knowledge in the form of physical models and past data in the BO framework.

42 ENGINEERING↗
DOE OSTI2024

Neuromorphic intermediate representation: A unified instruction set for interoperable brain-inspired computing

Abstract Spiking neural networks and neuromorphic hardware platforms that simulate neuronal dynamics are getting wide attention and are being applied to many relevant problems using Machine Learning. Despite a well-established mathematical foundation for neural dynamics, there exists numerous software and hardware solutions and stacks whose variability makes it difficult to reproduce findings. Here, we establish a common reference frame for computations in digital neuromorphic systems, titled Neuromorphic Intermediate Representation (NIR). NIR defines a set of computational and composable model primitives as hybrid systems combining continuous-time dynamics and discrete events. By abstracting away assumptions around discretization and hardware constraints, NIR faithfully captures the computational model, while bridging differences between the evaluated implementation and the underlying mathematical formalism. NIR supports an unprecedented number of neuromorphic systems, which we demonstrate by reproducing three spiking neural network models of different complexity across 7 neuromorphic simulators and 4 digital hardware platforms. NIR decouples the development of neuromorphic hardware and software, enabling interoperability between platforms and improving accessibility to multiple neuromorphic technologies. We believe that NIR is a key next step in brain-inspired hardware-software co-evolution, enabling research towards the implementation of energy efficient computational principles of nervous systems. NIR is available atneuroir.org

Science & Technology - Other Topics↗
DOE OSTI2021

Machine learning accelerated turbulence modeling of transient flashing jets

We report modeling the sudden depressurization of superheated liquids through nozzles is a challenge because the pressure drop causes rapid flash boiling of the liquid. The resulting jet usually demonstrates a wide range of structures, including ligaments and droplets, due to both mechanical and thermodynamic effects. As the simulation comprises increasingly numerous phenomena, the computational cost begins to increase. One way to moderate the additional cost is to use machine learning surrogacy for specific elements of the calculation. This study presents a machine learning-assisted computational fluid dynamics approach for simulating the atomization of flashing liquids accounting for distinct stages, from primary atomization to secondary breakup to small droplets using the Σ - Y model coupled with the homogeneous relaxation model. Notably, the models for thermodynamic non-equilibrium (HRM) and Σ - Y are coupled, for the first time, with a deep neural network that simulates the turbulence quantities, which are then used in the prediction of superheated liquid jet atomization. The data-driven component of this method is used for turbulence modeling, avoiding the solution of the two-equation turbulence model typically used for Reynolds-averaged Navier-Stokes simulations for these problems. Both the accuracy and speed of the hybrid approach are evaluated, demonstrating adequate accuracy and at least 25% faster computational fluid dynamics simulations than the traditional approach. This acceleration suggests that perhaps additional components of the calculation could be replaced for even further benefit. Published under an exclusive license by AIP Publishing.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2021

Physics-Informed Learning for Predictive Multi-Scale Modeling of Water Cycle and Extreme Events

Climate and earth system models have limited skill in predicting water cycle and associated extremes such as intense rain- and wind-producing storms and resulting hazards across all timescales. Water cycle predictions are inherently limited by the predictability of the chaotic system, but large potential for improving predictions remains untapped due to limited use of data-model integration to improve predictive modeling. This white paper proposes a hybrid data-physics paradigm based on physics-informed neural networks (PINNs) to improve the Energy Exascale Earth System Model (E3SM). In particular, we aim to predict and quantify uncertainties of water cycle processes and low probability high impact events.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2024

Learning From User Behavior: A Survey-Assist Algorithm for Longitudinal Mobility Data Collection

GPS-based travel surveys are widely used in mobility studies to gather crucial qualitative data, like purpose, transportation mode and replaced mode. However, survey response still poses a burden to users, especially in long-term mobility studies, leading to response fatigue. We explore a survey-assist strategy to ease this burden by a novel, user-level modeling approach that leverages past responses from each user to predict responses for new trips, without relying on external data sources like GIS data. We investigate three main algorithms for predicting responses: (i) clustering trips and extrapolating responses for similar trips, (ii) using random forest classification, and (iii) clustering that uses a hybrid algorithm to determine spatial structure, which is then fed as input to a classic random forest classifier. The clustering approach can flexibly predict responses for even complex qualitative survey questions; it achieved F-scores of 65%. The random forest pipeline uses architecture that restricts it to predicting three predetermined survey questions: trip purpose, mode, and replaced mode. However, it achieved F-scores of 78%. While the survey-assist approach has been implemented by several proprietary systems, to our knowledge, this is the first exploration in the academic literature. It follows that this is also the first rigorous evaluation of multiple algorithms that can implement the approach. The evaluation uses a large scale, publicly available, longitudinal dataset consisting of ~ 92k trips from 235 users over a period of roughly one and a half years. With this approach, travel surveys can be pre-filled with the predicted responses for each trip, thus streamlining the survey process for users. Combined with an active learning system that requests user input on low-confidence predictions, models can be updated and improved over time to better support the long-term collection of longitudinal qualitative data.

clustering↗
DOE OSTI2026

Instabilities and phase transitions in architected metamaterials: a gradient-enhanced continuum approach

Architected metamaterials such as foams and lattices exhibit a wide range of properties governed by microstructural instabilities and emerging phase transitions. Their macroscopic response–including energy dissipation during impact, large recoverable deformations, morphing between configurations, and auxetic behavior–remains difficult to capture with conventional continuum models, which often rely on discrete approaches that limit scalability. In this work, we propose a nonlocal continuum formulation that captures both stable and unstable responses of elastic architected metamaterials. The framework extends anisotropic hyperelasticity by introducing nonlocal variables and internal length scales reflective of microstructural features. Local polyconvex free-energy models are systematically augmented with two families of non-(poly)convex energies, enabling both metastable and bistable responses. Implementation in a finite element framework enables solution using a hybrid monolithic–staggered strategy. Simulations capture densification fronts, forward and reverse transitions, hysteresis loops, imperfection sensitivity, and globally coordinated auxetic modes. Overall, this framework provides a robust foundation for accelerated modeling of instability-driven phenomena in architected metamaterials, while enabling extensions to anisotropic, dissipative, and active systems as well as integration with data-driven and machine learning approaches.

42 ENGINEERING↗
NASA NTRS2006

Techniques for Embedding Instrumentation in Pressure Vessel Test Articles

Many interesting structural and thermal events occur in materials that are housed within a surrounding pressure vessel. In order to measure the environment during these events and explore their causes instrumentation must be installed on or in the material. Transducers can be selected that are small enough to be embedded within the test material but these instruments must interface with an external system in order to apply excitation voltages and output the desired data. The methods for installing the instrumentation and creating an interface are complicated when the material is located in a case or housing containing high pressures and hot gases. Installation techniques for overcoming some of these difficulties were developed while testing a series of small-scale solid propellant and hybrid rocket motors at Marshall Space Flight Center. These techniques have potential applications in other test articles where data are acquired from materials that require containment due to the severe environment encountered during the test process. This severe environment could include high pressure, hot gases, or ionized atmospheres. The development of these techniques, problems encountered, and the lessons learned from the ongoing testing process are summarized.

Cornelius, Michael↗
DOE OSTI2026

Subseasonal Forecasting and MJO Teleconnections in Machine Learning Weather Prediction Models

Abstract In recent years, machine‐learning (ML) models trained on reanalysis data have rivaled physics‐based forecast models in terms of performance skill for global weather forecasting. With increased rollout stability, the question of how these models perform for subseasonal to seasonal (S2S, week 3–8) forecasting has emerged. In this study we run a large set of subseasonal hindcasts over 2004–2023 to evaluate two ML weather forecast models at the S2S time scale, SFNO‐HENS (Nvidia, fully ML) and NeuralGCM (Google Research, hybrid). Corresponding hindcasts from the European Centre for Medium‐Range Weather Forecasts (ECMWF) are used as a baseline for comparison to a physics‐based model. Because our focus is on predicting moisture transport over the Western United States between October and March, we evaluate the models' prediction skill for the Madden‐Julian Oscillation (MJO) and its associated teleconnections in the North Pacific. We find that both ML models are competitive with the ECWMF model, with comparable skill in predicting the North Pacific large‐scale circulation and the MJO at week 3 and beyond. Even though overall the mid‐latitude subseasonal prediction skill remains low, the ML models exhibit interesting behavior such as a realistic propagation of the MJO across the Maritime Continent and realistic teleconnections. A SFNO‐HENS sensitivity experiment with altered initial conditions in the tropics demonstrates the stability of the model, and it illustrates the capability of ML models to represent important physical processes of the atmosphere at the S2S time scale. Plain Language Summary Predicting weather patterns and precipitation a few weeks in advance (subseasonal time scale) is of great interest for stakeholders such as water managers in the Southwest United States (US), where arid conditions prevail. Subseasonal forecasts from traditional weather forecast models exhibit low skill in the region, limiting their applicability. Here we examine whether the recent breakthrough in weather forecasting made with machine learning/artificial intelligence models can translate to improved subseasonal forecasts. Recently‐developed machine learning models exhibit comparable skill to a state‐of‐the‐art physics‐based model for predicting weather patterns in the North Pacific/North America region, and associated moisture transport. The same applies to their skill in predicting the tropical pattern, the Madden‐Julian Oscillation, and its important remote perturbations over the midlatitude East Pacific and Southwest US. Additionally, a perturbation experiment carried out with one of the machine learning models illustrates their ability to not only predict the evolution of atmospheric fields, but also to learn and represent physical processes such as tropics‐extratropics Rossby wave propagation. Key Points Two machine learning weather forecast models exhibit state‐of‐the‐art prediction skill at the subseasonal time scale in the Pacific sector The models equal ECWMF in terms of Madden‐Julian oscillation (MJO) prediction skill, and they accurately predict the MJO propagation and associated teleconnections The two machine‐learning models represent key physical processes for subseasonal prediction, despite being trained for weather forecasting

Peings, Yannick↗
DOE OSTI2024

Improving the Concrete Crack Detection Process via a Hybrid Visual Transformer Algorithm

Inspections of concrete bridges across the United States represent a significant commitment of resources, given their biannual mandate for many structures. With a notable number of aging bridges, there is an imperative need to enhance the efficiency of these inspections. This study harnessed the power of computer vision to streamline the inspection process. Our experiment examined the efficacy of a state-of-the-art Visual Transformer (ViT) model combined with distinct image enhancement detector algorithms. We benchmarked against a deep learning Convolutional Neural Network (CNN) model. These models were applied to over 20,000 high-quality images from the Concrete Images for Classification dataset. Traditional crack detection methods often fall short due to their heavy reliance on time and resources. This research pioneers bridge inspection by integrating ViT with diverse image enhancement detectors, significantly improving concrete crack detection accuracy. Notably, a custom-built CNN achieves over 99% accuracy with substantially lower training time than ViT, making it an efficient solution for enhancing safety and resource conservation in infrastructure management. These advancements enhance safety by enabling reliable detection and timely maintenance, but they also align with Industry 4.0 objectives, automating manual inspections, reducing costs, and advancing technological integration in public infrastructure management.

42 ENGINEERING↗
DOE OSTI2022

HIDES (Hybrid Intrusion Detection for Energy Systems) [SWR-19-65]

Hybrid Intrusion Detection for Energy Systems (HIDES) is a conglomerate detector that incorporates three major components: (1) Signature-based detection that involves information technology (IT) related anomaly detection rules, (2) Behavior-based detection that utilizes specially crafted rulesets for detecting abnormal behavior regarding the power system's supervisory control and data acquisition (SCADA) communication streams, and (3) Learning-based detection that combines SCADA communication with phasor measurements to identify otherwise non-detectible attack vectors. The software itself interconnects intrusion detection engine (IDE) enabling communications between the generated OT and IT alerts with phasor measurements for the learning-based detection system. The resulting detection system can detect a wide array of IT, OT, and physical attacks in a real-time setting.

Rivera, Joshua↗
NASA NTRS2021

NASA SpaceCube Edge TPU SmallSat Card for Autonomous Operations and Onboard Science-Data Analysis

Using state-of-the-art artificial intelligence (AI)frameworks onboard spacecraft is challenging because common spacecraft processors cannot provide comparable performance to datacenters with server-grade CPUs and GPUs available for terrestrial applications and advanced deep-learning networks. This limitation makes small, lo w-p o we r AI microchip architectures, such as the Google Coral Edge Tensor Processing Unit (TPU), attractive for space missions where the application-specific design enables both high-performance and power-efficient computing for AI applications. To address these challenging considerations for space deployment, this research introduces the design and capabilities of a CubeSat-sized Edge TPU-based co-processor card, known as the SpaceCube Low-power Ed g e Artificial Intelligence Resilient Node (SC-LEARN). This design conforms to NASA’s CubeSat Card Specification (CS2) for integration into next-generation SmallSat and CubeSat systems. This paper describes the overarching architecture and design of the SC-LEARN, as well as, the supporting test card designed for rapid prototyping and evaluation. The SC-LEARN was developed with three operational modes: (1) a high-performance parallel-processing mode,(2)a fault-tolerant mode for onboard resilience, and (3) a power-saving mode with cold spares. Importantly, this research also elaborates on both training and quantization of Tensor Flow models for the SC-LEARN for use onboard with representative, open-source datasets. Lastly, we describe future research plans, including radiation-beam testing and flight demonstration.

Advanced avionics↗
DOE OSTI2023

Role of reinforcement learning for risk-based robust control of cyber-physical energy systems

Critical infrastructures such as cyber-physical energy systems (CPS-E) integrate information flow and physical operations that are vulnerable to natural and targeted failures. Safe, secure, and reliable operation and control of CPS-E is critical to ensure societal well-being and economic prosperity. Automated control is key for real-time operations and may be mathematically cast as a sequential decision-making problem under uncertainty. Emergence of data-driven techniques for decision making under uncertainty, such as reinforcement learning (RL), have led to promising advances for addressing sequential decision-making problems for risk-based robust CPS-E control. However, existing research challenges include understanding the applicability of RL methods across diverse CPS-E applications, addressing the effect of risk preferences across multiple RL methods, and development of open-source domain-aware simulation environments for RL experimentation within a CPS-E context. This article systematically analyzes the applicability of four types of RL methods (model-free, model-based, hybrid model-free and model-based, and hierarchical) for risk-based robust CPS-E control. Problem features and solution stability for the RL methods are also discussed. We demonstrate and compare the performance of multiple RL methods under different risk specifications (risk-averse, risk-neutral, and risk-seeking) through the development and application of an open-source simulation environment. Motivating numerical simulation examples include representative single-zone and multizone building control use cases. Finally, six key insights for future research and broader adoption of RL methods are identified, with specific emphasis on problem features, algorithmic explainability, and solution stability.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2025

Reinforcement Learning Control for Buildings Co-Optimizing Energy, Comfort, and Indoor Air Quality: An Annual Assessment

Efficient control of Heating, Ventilation, and Air Conditioning (HVAC) systems is crucial for optimizing energy use and maintaining indoor comfort in buildings. Traditional control methods, such as PID control, cannot handle energy use trade-offs among multiple components in the building energy system at a supervisory level. Reinforcement learning (RL) presents a promising solution, offering adaptive and data-driven control strategies that optimize performance over time. However, RL also faces several challenges, including the conflicts encountered in co-optimizing energy savings, occupant comfort, and indoor air quality, and the requirement for extensive interactions with the environment in training. We proposed a flexible simulation platform that integrates a hybrid model for RL training and designed an RL agent to control the entire central HVAC system, focusing on co-optimizing energy consumption, thermal comfort, and indoor air quality ($\text{CO}_{2}$ and PM2.5 concentrations). Finally, we evaluated the RL agent's performance over an annual cycle. Our findings indicate that the RL agent can effectively manage the HVAC system with 14.7 % energy savings annually and balance multiple objectives, which demonstrates significant potential for improving HVAC system control and sustainability in buildings.

Guo, Fangzhou↗