Search NASA⌕ Search

SEARCH · Search NASA

Results for “Short-term prediction”

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 19 records
All sourcesNASA NTRSDOE OSTI
DOE OSTI2026

Predictive Model for Starlink Maritime Performance Using Multi-Horizon RandomForest

Low Earth orbit (LEO) satellite systems have become a crucial enabler of broadband access for maritime industries, where traditional networks are unavailable. However, the high mobility of LEO constellations and constantly changing weather conditions result in unpredictable link fluctuations, limiting the ability of maritime platforms to plan bandwidth usage proactively. To the best of our knowledge, no prior work has developed a short-term predictive model for maritime LEO connectivity using real experimental field measurements. This paper proposes a data-driven forecasting model that predicts future downlink throughput using multi-horizon RandomForest regression. The model is trained using real experimental coastal measurement data incorporating recent throughput history, network-layer indicators, and environmental variables. The proposed approach reduces mean absolute error by approximately 31% compared to a persistence baseline for 15-minute horizons. It maintains a measurable improvement at 30 minutes, despite increased stochasticity. These findings confirm that proactive bandwidth awareness is feasible on maritime platforms and can effectively support operational decisions such as adaptive streaming, routing, and resource scheduling. The performance gap between forecasting horizons also highlights the need for expanded offshore datasets to improve prediction robustness under harsher maritime environments.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2026

Predictive Modeling and Operational Monitoring of Starlink Leo Satellite Network Performance in Maritime Environments

This thesis investigates short-term performance prediction for maritime LEO operational planning and application performance cannot anticipate available bandwidth or communication delay, which complicates variation alter signal conditions over short time scales. As a result, maritime users often fluctuations in link quality. In addition, Frequent satellite handoffs and Doppler-induced rapid satellite movement and changing atmospheric conditions cause substantial unavailable. Despite their availability, reliable operation at sea remains difficult because broadband connectivity in maritime regions where terrestrial infrastructure in

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2026

Inundation and Sediment Supply Predict Annual but Not Centennial Carbon Accumulation in Tidal Wetlands Across Land‐Use Types

Despite growing interest in the contributions of tidal wetlands to natural climate solutions, data remain scarce on how land use affects their carbon accumulation rates (CAR). Additionally, environmental factors driving the large observed variability in CAR among sites are poorly understood. To address these knowledge gaps, we measured short-term (∼1 year) and long-term (∼100 years) CAR using feldspar marker horizons, 210 Pb profiles, and surface elevation tables from 39 sites in seven estuaries in Oregon and Washington, USA. Sites varied in wetland type (tidal marsh, tidal swamp, nontidal pasture), land-use history (reference, restored, and disturbed), and salinity (fresh to polyhaline). Across both timescales, CAR was lowest in disturbed pastures and highest in restored marshes, reflecting patterns in sediment accretion rates. Short-term CAR exceeded long-term CAR by approximately 50% on average and was only weakly correlated with long-term CAR, with differences among hydrogeomorphic setting. Short-term CAR was well predicted by summer inundation frequency and relative sediment load, together explaining 60% of variance, whereas long-term CAR was poorly predicted by contemporary environmental conditions. These findings highlight the importance of aligning predictor and response timescales when modeling blue carbon dynamics, and reinforce the climate mitigation potential of tidal wetland restoration.

land use and land cover change↗
DOE OSTI2026

Deep Learning Reconstruction of Daily Soil CO 2 Efflux Reveals Biogeochemical Insights and Reduces Annual Estimate Uncertainty Despite Limited Daily Predictability

Soil CO 2 efflux is commonly measured monthly or seasonally, leaving daily dynamics poorly resolved and contributing to global estimation uncertainty. We trained a single Long Short-Term Memory (LSTM) model to predict daily soil CO 2 efflux across 82 globally distributed sites in COSORE, with 0.2%–46.9% daily data coverage from 2003 to 2020. Despite using far fewer sites than are typically used to train a single deep learning model, with observations biased toward temperate mesic sites, the LSTM model performed well at approximately one-third of sites, reconstructed nearly 2 decades of daily efflux, and outperformed commonly used approaches for estimating daily efflux when applied to the same data set. Performance was weakest at pronounced peaks and troughs and at non-temperate sites with <1.5 years of observations and irregular data patterns. Nevertheless, annual efflux from reconstructed daily data had <40% error even at underperforming sites, substantially improving estimates derived from monthly and seasonal sampling (maximum errors of 95% and 136%, respectively). Temperature sensitivity (Q 10 ) estimated from reconstructed daily predictions closely matched estimates from daily observations, whereas Q 10 values derived from monthly or seasonal observations deviated substantially, suggesting that coarse temporal sampling may contribute to uncertainty in reported Q 10 values. Consistent daily reconstructions further enabled trend analyses for well-performing, predominantly temperate sites and showed increasing soil CO 2 efflux at most sites from 2003 to 2020, with more variable summer trends. Despite limitations, these results demonstrate the potential of LSTM models to reconstruct daily soil CO 2 efflux and reduce estimation uncertainties from sparse observations.

Smykalov, Valerie [Pennsylvania State University, ↗
DOE OSTI2026

L-VISP: LSTM Visualization for Interpretable Symptom Prediction in Patient Cohorts

Symptom modelling in head and neck cancer is challenged by the complexity of heterogeneous patient data, leading to an interest in deep learning approaches. Although Long Short-Term Memory Networks (LSTMs) have shown great results in patient risk prediction, their low interpretability requires data modellers to collaborate with clinical experts to validate the results. We present L-VISP, a human–machine solution that uses visual analytics for LSTM modelling in clinical research. L-VISP uses custom visual encodings to make multiple LSTM variants interpretable, supporting a full range of analysis, from understanding model operations and evaluating performance to interpreting results in a clinical context. We evaluate L-VISP with data modellers and a clinical oncologist and present the takeaways from this multidisciplinary collaboration.

LSTM modeling↗
DOE OSTI2026

Uncertainty guided online ensemble for non-stationary data streams in fusion science

Machine Learning (ML) is poised to play a pivotal role in the development and operation of next-generation fusion devices. Fusion data shows non-stationary behavior with distribution drifts, resulted by both experimental evolution and machine wear-and-tear. ML models assume stationary distribution and fail to maintain performance when encountered with such non-stationary data streams. Online learning techniques have been leveraged in other domains, however it has been largely unexplored for fusion applications. In this paper, we investigate online learning for continuous adaptation to drifting data streams in the prediction of Toroidal Field (TF) coils deflection at the DIII-D fusion facility. We further address the short-term performance degradation inherent to standard online learning, which arises because ground truth is unavailable at prediction time. To mitigate this issue, we propose an uncertainty-guided online ensemble framework. The method leverages the Deep Gaussian Process Approximation (DGPA) for calibrated uncertainty estimation and uses these uncertainty measures to guide a meta-algorithm that aggregates predictions from learners trained over different historical horizons. Our results show that online learning reduces prediction error by 80% compared to a static model. The online ensemble and the proposed uncertainty-guided ensemble further reduce error by approximately 6%, and 10% respectively, relative to standard single-model online learning, while also providing calibrated uncertainty estimates to support operational decision-making.

AI↗
NASA NTRS2026

Machine Learning for Predicting Team Functioning in HERA Missions

Team functioning is integral to success in future long term space exploration missions. Proactively detecting declines in team functioning can mitigate conflict and ensure mission success. This project developed a speech-based artificial intelligence (AI) system that unobtrusively predicts degradation in team functioning, including performance and cohesion, in the Human Exploration Research Analog (HERA) Campaigns 4 and 5. The AI system conducted automated analysis of the prosodic (tone of voice) and linguistic (language content) components of speech, modeling interpersonal dynamics at both the turn-taking and day-wide levels. We investigated team functioning via observing structured interactions (i.e., multi-mission space exploration vehicle-extra vehicular activity [MMSEV-EVA], team interaction battery [TIB]) and unstructured interactions before the MMSEV-EVA task. We developed machine learning models to predict team functioning (objective task accuracy, self reported team efficacy and self reported team cohesion) by analyzing OpenSmile acoustic features, linguistic descriptors extracted via the linguistic inquiry and word count (LIWC) dictionary, and semantic embeddings. In the TIB, static models using logistic regression and random forests were not able to predict task accuracy, but predicted team efficacy and cohesion during both the decision making and relational tasks to a moderate level (60-70%). Majority voting on the individual turns to predict day long team efficacy further increased accuracies (70-80%). Finally, long short-term memory (LSTM) models showed the best performance across all variables (80-91%), including task performance. In the MMSEV-EVA, static models achieved an accuracy of 60% with majority voting, which increased to 80% through the incorporation of mission day as a variable, accounting for the learning effect. A key finding across both tasks was the "team-dependent" nature of these interactions; models achieved much higher accuracy when trained on prior days of the same team's data rather than attempting to generalize across entirely different teams, with even 1-2 days of prior data per team achieving 5-15% improvement over team-independent models. In addition, the incorporation of pre-task data from the same team also improves model performance, e.g., incorporating data from the decision-making task of the TIB, which preceded the relational task, improved the prediction of team efficacy and cohesion during the latter. We compared model performance when trained on machine-generated data compared to data that had been further corrected by human annotators. Overall, models trained on human-corrected data exhibited a modest improvement in performance, particularly when acoustic features were used. We found no significant correlation between word error rate (WER) and model accuracy (r(55) = -0.08, p = 0.51), but model’s accuracy was significantly higher for medium/high quality transcription (0.74 (SD = 0.48)) compared to the low-quality group (0.64 (SD = 0.36)) (t(63)=2.82, p = 0.006). Based on these, several design recommendation emerge, that could inform Standards at NASA. Models predicting team functioning should incorporate at least one to two days of historical interaction data, include brief pre-task discussions, and explicitly model temporal learning effects, especially for longer operational tasks. Minimum quality standards for automated speech-processing pipelines are needed, given the performance gains observed with manually corrected acoustic data. Finally, systems should leverage both acoustic features and language embeddings in complementary ways, with modality choices and fusion strategies tailored to mission context, task demands, and data quality requirements.

Shrivatsa Mishra↗
DOE OSTI2026

Assessing shellfish water exposure to fecal bacteria pollution in Salish Sea: three-dimensional modeling and implications for monitoring

Fecal bacteria (FB) contamination poses significant risks to shellfish safety and management in coastal and estuarine waters. Despite extensive pollution identification and correction efforts, FB contamination in shellfish-growing areas persists in the Salish Sea, highlighting the need to identify overlooked sources and better understand FB transport from riverine and shoreline inputs to shellfish beds. To address this, a high-resolution three-dimensional hydrodynamic model coupled with FB kinetics was developed and applied to a case study site in Salish Sea—Portage Bay—to simulate freshwater plume circulation, flushing dynamics, and bacterial transport. Daily FB loading from the major freshwater inflow—Nooksack River was generated by both linear interpolation and integrating a machine learning approach (XGBoost), trained on historical hydrological and meteorological data. The model successfully reproduced both the magnitude and seasonal variation of FB concentrations in Portage Bay for the year of 2021, demonstrating that simplified FB kinetics with first-order decay due to mortality was effective in this dynamic coastal environment with short flushing time. Model results identified the Nooksack River as the dominant far-field FB source, while scenario simulations showed that near-field coastal stormwater outfalls elevated local FB levels following rainfall, particularly under low-flow conditions. The XGBoost prediction provided comparable or superior accuracy to linear interpolation, particularly during periods of missing observational data, by capturing short-term variability and event-driven loading more effectively. Integrating data-driven riverine FB inputs with mechanistic coastal numerical modeling provides a robust framework for operational forecasting of shellfish bed exposure risk and supports adaptive monitoring and management of shellfish growing areas in the Salish Sea and similar coastal systems.

Salish Sea↗
DOE OSTI2026

Short‐Term Hourly Weather Forecasting Using PredRNN With Image Preprocessing

Global weather forecast models are vital tools with numerous applications, including public safety, agriculture, and transportation. Recent advancements in artificial intelligence (AI) and deep learning (DL) have shown the potential to enhance weather forecasting accuracy and speed. In this study, we developed a short-term hourly weather forecast framework with a wavelet transform function for data preprocessing and a spatiotemporal DL model, PredRNN, for predicting five surface atmospheric variables, including wind speed and direction, mean sea level pressure (MSLP), temperature, and precipitation. The framework demonstrated promising results. It produces global forecasts at 0.25° (∼25 km) with a 1-day lead time RMSE of 1.8 m/s for wind components, 180 Pa for MSLP, and 1.8 K for temperature. Although our model does not surpass state-of-the-art AI weather forecast models across all metrics, it outperforms these models in precipitation forecasting and wind prediction at short lead times and achieves comparable accuracy for MSLP. Its native hourly forecasting capability, together with training on widely accessible GPU hardware, contributes meaningfully to the advancement of accessible DL weather forecasting methods. Our work highlights the importance of integrating temporal components and data transformation techniques to improve the predictability and accuracy of weather forecasts.

Tran, Hoang [Pacific Northwest National Laboratory↗
DOE OSTI2026

Xanthos-Lake Model Source Code

This repository contains the source code for Xanthos-Lake, a lake-modeling extension of the Xanthos framework that introduces a coupled lake component comprising the Xanthos-Lake Snow and Ice Model (xLSIM) and the Xanthos-Lake Water Balance Model (xLWBM). xLSIM is a basin-aware machine-learning model for lake snow, ice, and thermal conditions. It predicts monthly lake ice thickness, snow depth, snow-cover fraction, mixing-layer temperature, and lake ice fraction from meteorological forcing and lake surface-area information. It uses sequence-based deep-learning architectures, including Transformer and hybrid Long Short-Term Memory–Transformer (LSTM–Transformer) models, together with seasonal encoding, multi-lake learning, physical masking, and basin-level cryospheric and non-cryospheric classification. The training workflow uses Ray for scalable execution and includes optional Ray Tune hyperparameter optimization. Model predictions, observations, diagnostics, and feature-importance outputs are written in NetCDF. xLWBM is the water-balance component of the new lake framework. It simulates monthly lake storage, surface area, evaporation, inflow, outflow, and lake–groundwater exchange. It combines physical water-balance equations with calibrated bathymetric relationships, weir-based outlet flow, modified Penman open-water evaporation, groundwater head relaxation, Penman–Monteith snow and ice sublimation, and snow, ice, and thermal conditions supplied by xLSIM. The model calibrates lake parameters against satellite-derived surface-area data, using evaporation-based calibration where surface-area data are unavailable, and supports small, medium, and large lake classes. For large lakes, xLWBM is integrated with the managed-routing workflow so that lake storage and outflow interact directly with downstream river routing and reservoir operations. Together, xLSIM and xLWBM provide Xanthos with a coupled lake-modeling capability. xLSIM supplies the snow, ice, and thermal conditions that affect lake evaporation and snow- and ice-related water exchanges, while xLWBM translates those conditions into dynamic lake storage, surface area, evaporation, and discharge. In return, xLWBM supplies evolving lake surface area to xLSIM. This coupling enables Xanthos to represent lakes as active hydrologic components within basin-scale water-availability and routing simulations.

Machine Learning↗
DOE OSTI2026

Knowledge-guided graph machine learning for spatially distributed prediction of daily discharge and nitrogen export dynamics

Spatially distributed prediction of streamflow and nitrogen export dynamics is essential for precision management of agricultural watersheds. While temporal deep learning models such as Long Short-Term Memory (LSTM) have shown strong performance at basin scales, their ability to generalize spatially is limited by insufficient representation of spatial dependencies and flow paths, particularly under data-scarce conditions. To address this gap, we propose HydroGraphNet, a knowledge-guided graph machine learning framework that integrates process-based knowledge and explicit spatial learning into temporal modeling. This framework incorporates directed graph topology to encode watershed connectivity and upstream inflows, with mass balance constraints to improve physical consistency. To enhance generalization in sparsely monitored regions, HydroGraphNet is pretrained on synthetic data generated by the SWAT+ (Soil and Water Assessment Tool Plus) model. We evaluated HydroGraphNet in the Upper Sangamon River Basin (44 HUC-12 subwatersheds, 2001–2020) against two LSTM baselines: a lumped basin-level model and a distributed variant. When benchmarked on SWAT+ simulations in pretraining, HydroGraphNet improved test NSEs by 8.9% (discharge) and 13.7% (NO₃–N load) in temporal extrapolation, and by 27.1% and 34.7% in spatial extrapolation, relative to the Lumped LSTM baseline. After fine-tuning with USGS monitoring data, the model achieved mean test NSE (KGE) scores of 0.768 (0.861) for discharge and 0.626 (0.664) for NO₃–N load, substantially outperforming baselines. Attribution analysis further highlighted the importance of upstream inflow representation and graph-based spatial learning in capturing cross-subwatershed dependencies. The model also reproduced seasonal hydrological and biogeochemical patterns consistent with known processes, demonstrating its robustness and process fidelity for spatially distributed prediction. Altogether, HydroGraphNet advances the integration of physical knowledge and spatially explicit learning in hydrological modeling, offering a generalizable framework for distributed modeling to support spatially targeted water quality management in data-scarce watersheds.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2026

Using Explainable Artificial Intelligence to Predict Perovskite Solar Cell Electrical Metastability from Operando Photoluminescence Images in Accelerated Stress Testing

Metal halide perovskite (MHP) solar cells exhibit a metastable response to bias governed by coupled ionic–electronic processes, complicating the conventional reciprocity relation between luminescence intensity and device open-circuit voltage (V oc ). This limits the use of luminescence as a diagnostic for device screening or accelerated stress testing, motivating new approaches that can interpret photoluminescence (PL) signals under nonequilibrium conditions. From the artificial intelligence perspective, we develop an explainable deep learning framework that integrates convolutional neural networks (CNN), long short-term memory (LSTM) layers, and an attention mechanism to learn spatiotemporal features from operando photoluminescence PL image sequences. The model achieves a mean absolute error of ±0.027 V in predicting open-circuit voltage transients and reduces extreme-tail errors by up to 78% compared to physics-based reciprocity calculations. Gradient-weighted Class Activation Mapping (Grad-CAM) provides interpretability by highlighting physically meaningful regions such as electrode edges and emergent defect features. From the engineering application perspective, this framework enables accurate, contactless prediction of device V oc and identification of degradation-relevant features during accelerated aging of perovskite solar cells. This approach demonstrates how explainable AI can enhance operando diagnostics and reliability analysis in photovoltaic devices under nonequilibrium conditions.

14 SOLAR ENERGY↗
DOE OSTI2026

Gaps and ways forward in atmospheric blocking and extreme weather research

Atmospheric blocking often results in significant weather extremes, such as heatwaves, droughts, cold spells, and floods in mid-latitude regions. However, the physical processes behind blocking and its response to climate change are not well understood, which undermines predictions and decision-making for climate mitigation and adaptation. As a phenomenon with a timescale at the interface of weather and climate, blocking interacts with various elements of the climate system and connects short-term weather events to long-term climate extremes. Understanding atmospheric blocking is crucial, given that climate change may impact its frequency, duration, and geographic distribution. This perspective discusses new experimental approaches to improve our understanding of this important subject.

Wang, Lei [Purdue University, West Lafayette, IN (↗
DOE OSTI2026

Imputation of urban environmental sensor data using gated attention bidirectional long short-term memory (GA-BiLSTM): methods, performance, and implications

Urban environmental monitoring networks frequently encounter significant data gaps due to sensor malfunctions, environmental disturbances, and communication failures. Reliable approaches to address these gaps are essential for ensuring the continuity and quality of environmental data streams. In this study, we developed a gated attention bidirectional long short-term memory (GA-BiLSTM) model to impute missing data in a dense urban monitoring network. Using observations from the CROCUS network in Chicago, we evaluated GA-BiLSTM against widely used approaches (XGBoost and K-nearest neighbors) under scenarios of both short-term intermittent gaps and prolonged outages. GA-BiLSTM consistently outperformed comparative methods, particularly during extended outages of up to ten days, demonstrating its ability to capture spatiotemporal dependencies across sensor nodes. Beyond performance metrics, feature importance and spatial network analyses highlighted the unexpected but critical predictive role of peripheral rural nodes, underlining their strategic value for maintaining robust urban monitoring systems. These results emphasize that advanced imputation methods can substantially improve the reliability of environmental monitoring networks and support more resilient data infrastructures for urban sustainability.

Data imputation↗
DOE OSTI2026

Field Evaluation of Do-It-Yourself Air Filtration Solutions for Evaporative Coolers to Reduce Ambient Particle Infiltration in Homes in Wildfire-Affected Communities

Evaporative coolers (ECs) introduce outdoor air pollutants indoors when operating. This study evaluates the potential of do-it-yourself (DIY) air filtration solutions for ECs to cost-effectively reduce the infiltration of ambient fine particulate matter (PM2.5) in homes with ECs using measurements in 48 homes in wildfire-affected agricultural communities in California. All homes received one portable air cleaner (PAC); 25 homes also received DIY filters (mostly MERV 13) attached to their ECs. PurpleAir monitors measured indoor and outdoor PM2.5 concentrations. PAC operation was monitored in all of the homes. EC usage was monitored in some homes and predicted using relative humidity dynamics in all homes. Conditional analyses between EC likely on and off conditions were used to evaluate the impacts of DIY EC filters on ambient PM2.5 infiltration, including during several wildfire-affected days. Median levels of ambient PM2.5 infiltration increased ∼36-42% in homes with only PAC interventions when ECs were likely operating compared to only ∼10-11% in homes with both PACs and DIY EC filters. Pre/postintervention comparisons in a subset of homes confirmed PM2.5 infiltration reductions. EC filter performance declined after extended use. Results suggest that short-term EC filter deployments are likely a cost-effective way to mitigate wildfire smoke infiltration inside these homes.

Wang, Mingyu↗
DOE OSTI2026

Estimating Flexibility Envelopes for Residential Customers From Utility Smart Meter Data: Preprint

Demand response from residential customers has significant potential to support power system operations, but accurate flexibility estimation is challenging due to the limited resolution of advanced metering infrastructure (AMI) data. Most utility AMI measurements are recorded at hourly intervals, with only a small portion at higher resolutions, and even fewer households have appliance-level energy usage data. To address this issue, this paper proposes a two-stage long short-term memory (LSTM) framework for estimating household flexibility envelopes from low-resolution AMI data. In the first stage, the heating, ventilating, and air-conditioning (HVAC) load and non-HVAC loads are estimated by using a model trained on a small set of households with appliance-level profiles. These estimated data are then used to compute the upper- and lower-flexibility bounds, which are subsequently down-sampled to lower-resolution data. In the second stage, these flexibility bounds serve as training inputs for another LSTM model, enabling direct prediction of flexibility envelopes for households with only hourly AMI data. This method is validated using Pecan Street data from two different areas, and the results demonstrate its applicability and effectiveness.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2026

Contrasting Carbon–Water–Energy Dynamics in Perennial and Annual Bioenergy Agroecosystems Using Eddy Covariance and Interpretable Machine Learning

Understanding how agroecosystems respond to environmental variability is fundamental to predicting productivity and sustainability under a changing climate. We analyzed 55 site-years of high-frequency eddy covariance observations from five agroecosystems—two perennial grasses (miscanthus and switchgrass), two annual rotation systems (maize–soybean and sorghum–soybean), and a restored native prairie—to examine ecosystem-scale carbon, water, and energy fluxes. Using an interpretable machine-learning framework with regression tree ensembles, Shapley Additive Explanations, and Accumulated Local Effects, we quantified how environmental and temporal factors regulate gross primary productivity (GPP), evapotranspiration (ET), water-use efficiency, and the Bowen ratio. Perennials exhibited stronger physiological buffering and maintained fluxes across a broader range of temperature and moisture conditions, reflecting deeper rooting and persistent canopy cover. Annuals, in contrast, showed greater short-term variability and stronger coupling to atmospheric demand, with GPP and ET declining rapidly under low humidity or soil moisture. Differences in temperature sensitivity of Bowen ratio further revealed that perennials sustained proportionally greater sensible heat flux under cool conditions, whereas annuals exhibited constrained energy exchange when evaporative demand was low. Together, these results demonstrate that crop life cycle and canopy structure are fundamental determinants of ecosystem-scale carbon–water–energy coupling. By integrating long-term flux observations with interpretable machine learning, this study identifies the environmental drivers that shape agroecosystem function and highlights how conversion from annual to perennial feedstocks can enhance climatic resilience and alter land–atmosphere energy feedbacks. These findings provide a data-driven basis for improving crop and Earth-system models and for guiding bioenergy landscape design under future climate scenarios.

Accumulated Local Effects↗
DOE OSTI2026

Physics vs structure: A systematic benchmark of learning strategies for multi-zone building thermal dynamics

Recent advances in physics-informed and data-driven machine learning promise improved thermal models for advanced building control, yet there is limited quantitative evidence on when added physics structure and architectural complexity are beneficial. Here, this work presents a systematic benchmark of five representative system identification methods for modeling multi-zone building thermal dynamics: linear state-space models, multi-layer perceptrons, neural state-space models, neural ordinary differential equations, and physically-consistent neural networks. The methods are evaluated across multiple data regimes and zone coupling strategies. Using a high-fidelity multi-zone commercial building emulator, we examine short-term and long-term prediction accuracy, computational efficiency, and ease of development. Our results reveal critical trade-offs between prediction performance, model complexity, and physical consistency. We demonstrate that decoupled, nonlinear black-box models consistently outperform coupled physics-constrained architectures in both predictive accuracy and out-of-distribution robustness in majority of the test cases for the building type considered in the study. Our findings quantify the cost of complexity in building thermal modeling and provide concrete, actionable, scenario-based guidelines for selecting model classes for control-oriented applications.

Building thermal modeling↗