Search NASA⌕ Search

SEARCH · Search NASA

Results for “Benchmark dataset”

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

Slater transition methods for core-level electron binding energies

Methods for computing core-level ionization energies using self-consistent field (SCF) calculations are evaluated and benchmarked. These include a “full core hole” (or “ΔSCF”) approach that fully accounts for orbital relaxation upon ionization, but also methods based on Slater’s transition concept in which the binding energy is estimated from an orbital energy level that is obtained from a fractional-occupancy SCF calculation. A generalization that uses two different fractional-occupancy SCF calculations is also considered. The best of the Slater-type methods afford mean errors of 0.3–0.4 eV with respect to experiment for a dataset of K-shell ionization energies, a level of accuracy that is competitive with more expensive many-body techniques. An empirical shifting procedure with one adjustable parameter reduces the average error below 0.2 eV. Here, this shifted Slater transition method is a simple and practical way to compute core-level binding energies using only initial-state Kohn–Sham eigenvalues. It requires no more computational effort than ΔSCF and may be especially useful for simulating transient x-ray experiments where core-level spectroscopy is used to probe an excited electronic state, for which the ΔSCF approach requires a tedious state-by-state calculation of the spectrum. As an example, we use Slater-type methods to model x-ray emission spectroscopy.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2024

Acoustic sensing and autoencoder approach for abnormal gas detection in a spent nuclear fuel canister mock-up

Currently, spent nuclear fuel (SNF) from commercial nuclear power plants is stored in stainless-steel canisters for interim dry storage. To provide an inert environment, these canisters are backfilled with helium after vacuum drying. However, the helium environment may be contaminated during extended storage because of the material degradation. For example, the heavier fission gas xenon may be released from the fuel rods into the canister cavity should the fuel cladding be breached. Other gases such as air and water vapor may also be present as a result of leakage caused by chloride-induced stress corrosion cracking on the canister walls or by insufficient vacuum drying. Therefore, monitoring the gas composition can provide critical information about the health of SNF canisters. In this study, noninvasive testing was conducted on a 2/3-scaled SNF canister mock-up using acoustic sensing. Ultrasonic transducers were placed on the exterior surface of the canister to probe the gas composition. A dataset was collected by sealing the canister mock-up and introducing up to 1.53% argon or 1.29% air into the helium background gas. Three methods were used to detect changes in the gas composition: the time-of-flight (TOF) method, the differential method, and the autoencoder method. Results showed that the TOF method had sufficient resolution to detect abnormal gas concentrations of less than 1.0%. The differential method demonstrated a periodic in-phase and out-of-phase behavior between the benchmark (i.e., pure helium) and abnormal (i.e., with argon or air) state signals. The variational autoencoder (VAE) and the Wasserstein autoencoder (WAE) were trained on the benchmark data and were applied directly to the abnormal state data. It was found that both the unsupervised VAE and the WAE were able to distinguish the benchmark and abnormal states of the canister mock-up based on the reconstruction error.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗
DOE OSTI2022

Data for: Patel et al. Carbon flux estimates are sensitive to data source: A comparison of field and lab temperature sensitivity data

This dataset contains data and code used for the paper "Carbon flux estimates are sensitive to data source: A comparison of field and lab temperature sensitivity data" [DOI COMING SOON]A large literature exists on mechanisms driving soil production of the greenhouse gases CO2 and CH4. Measurements of these gases’ fluxes are often performed using closed-chamber incubations in the laboratory or in situ, i.e., in the field. Although it is common knowledge that measurements obtained through field studies vs. laboratory incubations can diverge because of the vastly different conditions of these environments, few studies have systematically examined these patterns. It is crucial to understand the magnitude and reasons for any differences, as these data are used to parametrize and benchmark ecosystem- to global-scale models, which are then susceptible to the biases of the source data. Here, we specifically examine how greenhouse gas measurements may be influenced by whether the measurement/incubation was conducted in the field vs. laboratory, focusing on CO2 and CH4 measurements. We use Q10 of greenhouse gas flux (temperature sensitivity) for our analyses, because of the ubiquity of this metric in biological and Earth system sciences and its importance to many modeling frameworks. We predicted that laboratory measurements would be less variable, but also less representative of true field conditions. However, there was greater variability in the Q10 values calculated from lab-based measurements of CO2 fluxes, because lab experiments explore extremes rarely seen in situ, and reflect the physical and chemical disturbances occurring during sampling, transport, and incubation. Overall, respiration Q10 values were significantly greater in laboratory incubations (mean = 4.19) than field measurements (mean = 3.05), with strong influences of incubation temperature and climate region/biome. However, this was in part because field measurements typically represent total respiration (Rs), whereas lab incubations typically represent heterotrophic respiration (Rh), making direct comparisons difficult to interpret. Focusing only on Rh-derived Q10, these values showed almost identical distributions across laboratory (n = 1110) and field (n = 581) experiments, providing strong support for using the former as an experimental proxy for the latter, although we caution that geographic biases in the extant data make this conclusion tentative. Due to a smaller sample size of CH4 Q10 data, we were unable to perform a comparable robust analysis, but we expect similar interactions with soil temperature, moisture, and environmental/climatic variables. Our results here suggest the need for more concerted efforts to document and standardize these data, including sample and site metadata. This dataset contains a compressed (.zip) archive of the data and R scripts used for this manuscript. The dataset includes files in .csv format, which can be accessed and processed using MS Excel or R. This archive can also be accessed on GitHub at https://github.com/kaizadp/field_lab_q10 (DOI: 10.5281/zenodo.7106554).

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2025

The Importance of Being Adaptable: An Exploration of the Power and Limitations of Domain Adaptation for Simulation-Based Inference with Galaxy Clusters

The application of deep machine learning methods in astronomy has exploded in the last decade, with new models showing remarkably improved performance on benchmark tasks. Not nearly enough attention is given to understanding the models' robustness, especially when the test data are systematically different from the training data, or "out of domain." Domain shift poses a significant challenge for simulation-based inference, where models are trained on simulated data but applied to real observational data. In this paper, we explore domain shift and test domain adaptation methods for a specific scientific case: simulation-based inference for estimating galaxy cluster masses from X-ray profiles. We build datasets to mimic simulation-based inference: a training set from the Magneticum simulation, a scatter-augmented training set to capture uncertainties in scaling relations, and a test set derived from the IllustrisTNG simulation. We demonstrate that the Test Set is out of domain in subtle ways that would be difficult to detect without careful analysis. We apply three deep learning methods: a standard neural network (NN), a neural network trained on the scatter-augmented input catalogs, and a Deep Reconstruction-Regression Network (DRRN), a semi-supervised deep model engineered to address domain shift. Although the NN improves results by 17% in the Training Data, it performs 40% worse on the out-of-domain Test Set. Surprisingly, the Scatter-Augmented Neural Network (SANN) performs similarly. While the DRRN is successful in mapping the training and Test Data onto the same latent space, it consistently underperforms compared to a straightforward Yx scaling relation. These results serve as a warning that simulation-based inference must be handled with extreme care, as subtle differences between training simulations and observational data can lead to unforeseen biases creeping into the results.

Ntampaka, Michelle [Baltimore, Space Telescope Sci↗
DOE OSTI2022

Dataset from: Improved multispecies Dougherty collisions

The Dougherty model Fokker-Planck operator is extended to describe nonlinear full-f collisions between multiple species in plasmas. Simple relations for cross-species primitive moments are developed which obey conservation laws, and reproduce familiar velocity and temperature relaxation rates. This treatment of multispecies Dougherty collisions, valid for arbitrary mass ratios, avoids unphysical temperatures and satisfies the H-theorem unlike an analogous Bhatnagar-Gross-Krook operator. Formulas for both a Cartesian velocity-space and a gyroaveraged operator are provided for use in Vlasov as well as long-wavelength gyrokinetic models. We present an algorithm for the discontinuous Galerkin discretization of this operator, and provide results from relaxation and Landau damping benchmarks.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2022

Effects of Chlorine Capture and a Proposed Density Law on the Reactivity of Plutonium Solution Systems

During fissionable material processing, all normal and credible abnormal conditions must remain safely subcritical. Nuclear Criticality Safety (NCS) uses a number of methods to determine subcriticality, one of which is the use of neutron transport codes such as MCNP6. In order to create models for use with MCNP6, both the geometry and materials in fissionable material processes must be known, or assumptions must be made and quantified for the impact to bias. One of the systems with a significant amount of bias due to material modeling assumptions is in the area of aqueous plutonium processing. These solutions are typically plutonium nitrate solutions or plutonium chloride solutions, which are modeled as fictitious plutonium metal-water mixtures because little is known about the actual density of the solution and there is no current predictive capability approved for use at Los Alamos National Laboratory (LANL) for modeling them. This research is currently underway to fill the gap and develop an algorithm for use with MCNP6 to model the density of plutonium chloride solutions. The method is to be validated with experimental data for density, and also validated with critical experiments using MCNP6. Note that the Chlorine Worth Study (CWS) was performed in December 2021 to help bridge the gap in chlorine data for critical experiments, and is currently awaiting International Criticality Safety Benchmark Evaluation Project (ICSBEP) review. This study was performed by LANL at the National Criticality Experiments Research Center (NCERC) at the Nevada National Security Site (NNSS). Additional information regarding this experiment may currently be found in LA-UR- 22-29180. Additionally, the Chemistry-Actinide Analytical Chemistry (C-AAC) at LANL has performed a number of solution density measurements for PuCl 3 -HC 1 -H 2 O, allowing for such data be used to create a semi-empirical density via the Pitzer method. The published dataset for the measurements is documented in LA-UR-22-25454. This method has already been tested successfully for aqueous plutonium nitrate solutions in SCALE. Current solution density measurements exist of plutonium concentrations of 0-~142g/L, all at 2M HC1, at temperatures 20-40°C. Additional data was taken for HC1-corrected density values, which essentially mimics the data for a pure PuCl x -water solution. The calculations in this report aim to support the current research by demonstrating the difference in system reactivity for the current modeling method when compared to the new proposed modeling with a density law implementation, which is being written as a Python tool to be used with MCNP6.

38 RADIATION CHEMISTRY, RADIOCHEMISTRY, AND NUCLEA↗
NASA NTRSDate not supplied

Laser Beam Welding Benchmark Experiments Performed in Reduced Gravity and Vacuum

Laser beam welding (LBW) is affected by the extreme temperatures, reduced pressure, and reduced gravity present in space environments. Gravity and pressure especially influence its melt pool and solidification dynamics. A compact, modular vacuum chamber adaptable to flight platforms from parabolic to orbital currently hosts an experiment to investigate the combined influence of reduced gravity and pressure on LBW. A swappable cartridge contains a rotating platen on which customizable workpieces can be welded under vacuum, greatly increasing experimental throughput. Instrumentation includes weld and thermal cameras observing the process, thermocouples placed on workpieces, accelerometers, and vacuum sensors. Experimental data gathered during the welding process will be combined with post-flight nondestructive evaluation, metallography, and mechanical testing to provide validation datasets for computational modeling. Phase I of this effort involves a parabolic flight campaign in low gravity while an anticipated Phase II would proceed to in-space demonstration to access extended duration microgravity.

in-space welding↗
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 OSTI2023

Comparing simulated demand flexibility against actual performance in commercial office buildings

Commercial building energy benchmarking has been used as a mechanism to evaluate energy use of a single building over time, relative to other similar buildings, or to simulations of a reference building conforming to various energy standards. Lack of empirical demand flexibility data and consistent flexibility metrics has limited the ability to compare demand flexibility performance with estimated demand flexibility in buildings. In this study, we collected demand response performance data for a total of 831 demand response events from 192 sites as a first step to build such a building demand flexibility dataset, and propose a standard core data schema to consolidate field data from different sources. We also performed parametric simulations of a control strategy called “global temperature adjustment” using commercial office prototype building models. We then compared the simulated demand flexibility performance against the actual data for offices with global temperature adjustment strategy implemented. During demand response events with an average outside air temperature of 34 °C (range 23 °C–42 °C), the measured demand decrease intensity of the demand flexibility metrics were 6.1 watts per square meter (W/m 2 ), 10.0 W/m 2 , 11.1 W/m 2 , 7.1 W/m 2 , and 4.7 W/m 2 for small, small–medium, medium, medium–large, and large office buildings, respectively. Compared to the measured data in medium- and large-size buildings, the simulated demand decrease intensity was 0.7 W/m 2 (17%) lower on average. The discrepancy between simulated and measured peak demand intensities fell within one standard deviation of the mean measured data. Here, the comparison results validate the credibility of simulations in capturing real building data for assessing the technical potential of building demand flexibility.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2021

Dataset of low global warming potential refrigerant refrigeration system for fault detection and diagnostics

Abstract HVAC and refrigeration system fault detection and diagnostics (FDD) has attracted extensive studies for decades; however, FDD of supermarket refrigeration systems has not gained significant attention. Supermarkets consume around 50 kWh/ft 2 of electricity annually. The biggest consumer of energy in a supermarket is its refrigeration system, which accounts for 40%–60% of its total electricity usage and is equivalent to about 2%–3% of the total energy consumed by commercial buildings in the United States. Also, the supermarket refrigeration system is one of the biggest consumers of refrigerants. Reducing refrigerant usage or using environmentally friendly alternatives can result in significant climate benefits. A challenge is the lack of publicly available data sets to benchmark the system performance and record the faulted performance. This paper identifies common faults of supermarket refrigeration systems and conducts an experimental study to collect the faulted performance data and analyze these faults. This work provides a foundation for future research on the development of FDD methods and field automated FDD implementation.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2023

CholecTriplet2021: A benchmark challenge for surgical action triplet recognition

Context-aware decision support in the operating room can foster surgical safety and efficiency by leveraging real-time feedback from surgical workflow analysis. Most existing works recognize surgical activities at a coarse-grained level, such as phases, steps or events, leaving out fine-grained interaction details about the surgical activity; yet those are needed for more helpful AI assistance in the operating room. Recognizing surgical actions as triplets of ‹ instrument, verb, target › combination delivers more comprehensive details about the activities taking place in surgical videos. This paper presents CholecTriplet2021: an endoscopic vision challenge organized at MICCAI 2021 for the recognition of surgical action triplets in laparoscopic videos. Here, the challenge granted private access to the large-scale CholecT50 dataset, which is annotated with action triplet information. In this paper, we present the challenge setup and the assessment of the state-of-the-art deep learning methods proposed by the participants during the challenge. Here, a total of 4 baseline methods from the challenge organizers and 19 new deep learning algorithms from the competing teams are presented to recognize surgical action triplets directly from surgical videos, achieving mean average precision (mAP) ranging from 4.2% to 38.1%. This study also analyzes the significance of the results obtained by the presented approaches, performs a thorough methodological comparison between them, in-depth result analysis, and proposes a novel ensemble method for enhanced recognition. Our analysis shows that surgical workflow analysis is not yet solved, and also highlights interesting directions for future research on fine-grained surgical activity recognition which is of utmost importance for the development of AI in surgery.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2026

Data from: "Towards CONUS-Wide ML-Augmented Conceptually-Interpretable Modeling of Catchment-Scale Precipitation-Storage-Runoff Dynamics"

This data package was generated to support the manuscript “Towards CONUS-Wide Machine Learning-Augmented Conceptually Interpretable Modeling of Catchment-Scale Precipitation-Storage-Runoff Dynamics.” It provides input files, model outputs, plotting data, scripts, notebooks, and documentation used to develop, evaluate, and reproduce Mass-Conserving Perceptron (MCP)-based hydrologic modeling experiments across 513 selected Catchment Attributes and Meteorology for Large-sample Studies in the United States (CAMELS-US) basins. The files are organized by modeling component and analysis purpose, including rainfall–runoff experiments, snow module experiments, coupled hydrologic-snow experiments, Long Short-Term Memory (LSTM) benchmark results, model skill metrics, initialization and epoch records, cell-state normalization files, Akaike Information Criterion (AIC)-based model comparison files, and data used to generate manuscript figures. Tabular files can be opened using standard spreadsheet software or Python/R data-analysis tools. Python scripts, Jupyter notebooks, and selected MATLAB scripts are included for model execution, postprocessing, plotting, and statistical analysis. Quality assurance and quality control were conducted through the source-data selection and modeling workflow. Meteorological forcing, streamflow, and static catchment attributes were derived from the CAMELS-US dataset, and snow water equivalent data were derived from the University of Arizona (UA) Snow Water Equivalent dataset. Selected basins and time periods were screened during the associated research workflow to avoid missing observations or poor-quality cases. Static geospatial features were processed primarily using Quantum Geographic Information System (QGIS) and Geospatial Data Abstraction Library (GDAL) workflows. Additional details are provided in the associated manuscript and documentation.

ESS-DIVE CSV File Formatting Guidelines Reporting ↗
NASA NTRS2020

Continuity of A Global, Satellite-Based Terrestrial Primary Productivity Dataset in the VIIRS Era Achieved With Model-Data Fusion

The NASA Terra and Aqua satellites have been successfully operating for over two decades and have far exceeded their original 5‐year design life. However, the era of NASA’s Earth Observing System (EOS) may be coming to a close as early as 2023. We conducted a comprehensive calibration and validation of the MODIS MOD17 product [1,2] and the potential for continuity of multi‐decadal ecosystem gross primary productivity (GPP) and annual net primary productivity (NPP), using data from the Visible Infrared Imaging Radiometer Suite (VIIRS) sensors aboard Suomi NPP and NOAA‐20. We combined an 18‐year record of eddy covariance flux tower measurements with hundreds of field measurements of NPP from the Oak Ridge National Laboratories Multi‐Biome collection to benchmark MODIS MOD17 Collection 6.1 (C61) and to develop the first terrestrial productivity estimates from VIIRS. Plant traits from the literature and the global TRY database [3,4] provide strong priors for identifying model parameters in a Bayesian model‐data fusion. As MODIS‐like observations are still needed for global environmental applications, the new VIIRS VNP17 product has the potential to extend these continuous estimates of global, terrestrial primary productivity beyond 2030.

K. Arthur Endsley↗
DOE OSTI2024

Benchmarking machine learning interatomic potentials via phonon anharmonicity

Abstract Machine learning approaches have recently emerged as powerful tools to probe structure-property relationships in crystals and molecules. Specifically, machine learning interatomic potentials (MLIPs) can accurately reproduce first-principles data at a cost similar to that of conventional interatomic potential approaches. While MLIPs have been extensively tested across various classes of materials and molecules, a clear characterization of the anharmonic terms encoded in the MLIPs is lacking. Here, we benchmark popular MLIPs using the anharmonic vibrational Hamiltonian of ThO 2 in the fluorite crystal structure, which was constructed from density functional theory (DFT) using our highly accurate and efficient irreducible derivative methods. The anharmonic Hamiltonian was used to generate molecular dynamics (MD) trajectories, which were used to train three classes of MLIPs: Gaussian approximation potentials, artificial neural networks (ANN), and graph neural networks (GNN). The results were assessed by directly comparing phonons and their interactions, as well as phonon linewidths, phonon lineshifts, and thermal conductivity. The models were also trained on a DFT MD dataset, demonstrating good agreement up to fifth-order for the ANN and GNN. Our analysis demonstrates that MLIPs have great potential for accurately characterizing anharmonicity in materials systems at a fraction of the cost of conventional first principles-based approaches.

interatomic potentials↗
DOE OSTI2026

Forest aboveground biomass estimation through integration of sentinel-2 and PALSAR-2 time series: assessing models trained on GEDI and field inventory benchmarks

Accurate and spatially explicit forest Aboveground Biomass (AGB) mapping through remote sensing is critical for quantifying terrestrial carbon stocks and informing effective forest management strategies. However, AGB estimation in dense forests with complex terrain remains challenging due to satellite sensor signal saturation problem (saturation issue occurs in high biomass forests), structural complexity, and limited ground truth for calibration. This study presents a novel framework that integrates multi-temporal Sentinel-2 optical imagery, ALOS PALSAR-2 Synthetic Aperture Radar (SAR) data, and topographic variables with explainable Machine Learning to map AGB across mountainous forests within subtropical and temperate oceanic climate zones of Mexico. We evaluate the effects of temporal granularity and sensor synergy by comparing multiple temporal inputs and sensor configurations (Sentinel-2, PALSAR-2, and their fusion), and assess model performance using two reference datasets: NASA GEDI LiDAR-derived biomass and Mexico’s National Forest and Soil Inventory (INFyS). Our results showed that models trained on INFyS consistently outperformed those trained on GEDI, highlighting limitations in GEDI’s reliability in biomass estimates within this study region. Furthermore, the integration of Sentinel-2 and PALSAR-2 provided improved predictions compared to single-sensor models, particularly when combined with temporally explicit yearly statistics. The best-performing model, which was trained on INFyS data, and considered both Sentinel-2 and PALSAR-2 yearly statistics, as well as topographic variables, achieved an R2 of 0.64, RMSE of 51.10 Mg/ha, and relative RMSE (rRMSE) of 58.69%. Explainable ML analysis identified Sentinel-2 spectral indices and topographic features as key predictors, while PALSAR-2 metrics provided complementary information, partially mitigating saturation effects in high-biomass areas. Specifically, integrating both sensors substantially improved AGB estimation in high biomass forest (≥200 Mg/ha), yielding 98% gains over optical-only model, with resulting estimates exceeding GEDI L4B by 29% and ESA-CCI-BIOMASS by 174%. Terrain-stratified analysis indicated close agreement with GEDI in low-slope areas, with increasing divergence as slope steepness increased, while estimates remained consistently higher than ESA-CCI-BIOMASS across all slope classes. The proposed approach advances multi-sensor fusion and temporal feature engineering for AGB mapping using open-access satellite datasets, providing a scalable and reproducible framework for annual biomass monitoring in topographically complex mountainous forests. The resulting 25 m resolution biomass product has the potential to provide spatially detailed information for forest monitoring and may support applications in carbon accounting and forest management.

54 ENVIRONMENTAL SCIENCES↗
NASA NTRS2022

SatNet: A Benchmark for Satellite Scheduling Optimization

Satellites provide essential services such as networking and weather tracking, and the number of near-earth and deep space satellites are expected to grow rapidly in the coming years. Communications with terrestrial ground stations is one of the critical functionalities of any space mission. Satellite scheduling is a problem that has been scientifically investigated since the 1970s. A central aspect of this problem is the need to consider resource contention and satellite visibility constraints as they require line of sight. Due to the combinatorial nature of the problem, prior solutions such as linear programs and evolutionary algorithms require extensive compute capabilities to output a feasible schedule for each scenario. Machine learning based scheduling can provide an alternative solution by training a model with historical data and generating a schedule quickly with model inference. We present SatNet, a benchmark for satellite scheduling optimization based on historical data from the NASA Deep Space Network. We propose formulation of the satellite scheduling problem as a Markov Decision Process and use reinforcement learning (RL) policies to generate schedules. The nature of constraints imposed by SatNet differ from other combinatorial optimization problems such as vehicle routing studied in prior literature. Our initial results indicate that RL is an alternative optimization approach that can generate candidate solutions of comparable quality to existing state-of-the-practice results. However, we also find that RL policies overfit to the training dataset and do not generalize well to new data, thereby necessitating continued research on reusable and generalizable agents.

Wilson, Brian↗
DOE OSTI2022

Reverse-mode differentiation in arbitrary tensor network format: with application to supervised learning.

This paper describes an efficient reverse-mode differentiation algorithm for contraction operations of tensor networks that may have arbitrary and unconventional network topologies. The approach leverages the tensor contraction tree of Evenbly and Pfeifer (2014), which provides an instruction set for the contraction sequence of a network. We show that this tree can be efficiently leveraged for differentiation of a full tensor network contraction using a recursive scheme that exploits (1) the bilinear property of contraction and (2) the property that trees have single path from root to leaves. While differentiation of tensor-tensor contraction is already possible in most automatic differentiation packages, we show that exploiting these two additional properties in the specific context of contraction sequences can improve efficiency. Following a description of the algorithm and computational complexity analysis, we investigate its utility for gradient-based supervised learning for low-rank function recovery and for fitting real-world unstructured datasets. We demonstrate improved performance over alternating least-squares optimization approaches and the capability to handle heterogeneous and arbitrary tensor network formats. When compared to alternating minimization algorithms, we find that the gradient-based approach requires a smaller oversampling ratio (number of samples compared to number model parameters) for recovery. This increased efficiency extends to fitting unstructured data of varying dimensionality and when employing a variety of tensor network formats. Here, we show improved learning using the hierarchical Tucker method over the tensor-train in high-dimensional settings on a number of benchmark problems.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Assessment of the ParFlow–CLM CONUS 1.0 integrated hydrologic model: evaluation of hyper-resolution water balance components across the contiguous United States

Abstract. Recent advancements in computational efficiency and Earth system modeling have awarded hydrologists with increasingly high-resolution models of terrestrial hydrology, which are paramount to understanding and predicting complex fluxes of moisture and energy. Continental-scale hydrologic simulations are, in particular, of interest to the hydrologic community for numerous societal, scientific, and operational benefits. The coupled hydrology–land surface model ParFlow–CLM configured over the continental United States (PFCONUS) has been employed in previous literature to study scale-dependent connections between water table depth, topography, recharge, and evapotranspiration, as well as to explore impacts of anthropogenic aquifer depletion to the water and energy balance. These studies have allowed for an unprecedented process-based understanding of the continental water cycle at high resolution. Here, we provide the most comprehensive evaluation of PFCONUS version 1.0 (PFCONUSv1) performance to date by comparing numerous modeled water balance components with thousands of in situ observations and several remote sensing products and using a range of statistical performance metrics for evaluation. PFCONUSv1 comparisons with these datasets are a promising indicator of model fidelity and ability to reproduce the continental-scale water balance at high resolution. Areas for improvement are identified, such as a positive streamflow bias at gauges in the eastern Great Plains, a shallow water table bias over many areas of the model domain, and low bias in seasonal total water storage amplitude, especially for the Ohio, Missouri, and Arkansas River basins. We discuss several potential sources for model bias and suggest that minimizing error in topographic processing and meteorological forcing would considerably improve model performance. Results here provide a benchmark and guidance for further PFCONUS model development, and they highlight the importance of concurrently evaluating all hydrologic components and fluxes to provide a multivariate, holistic validation of the complete modeled water balance.

O'Neill, Mary M. F. (ORCID:0000000221455165)↗