Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “network performance evaluation”

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 1,585 records · Page 88
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

Using spatio-temporal graph neural networks to estimate fleet-wide photovoltaic performance degradation patterns

Accurate estimation of photovoltaic (PV) system performance is crucial for determining its feasibility as a power generation technology and financial asset. PV-based energy solutions offer a viable alternative to traditional energy resources due to their superior Levelized Cost of Energy (LCOE). A significant challenge in assessing the LCOE of PV systems lies in understanding the Performance Loss Rate (PLR) for large fleets of PV systems. Estimating the PLR of PV systems becomes increasingly important in the rapidly growing PV industry. Precise PLR estimation benefits PV users by providing real-time monitoring of PV module performance, while explainable PLR estimation assists PV manufacturers in studying and enhancing the performance of their products. However, traditional PLR estimation methods based on statistical models have notable drawbacks. Firstly, they require user knowledge and decision-making. Secondly, they fail to leverage spatial coherence for fleet-level analysis. Additionally, these methods inherently assume the linearity of degradation, which is not representative of real world degradation. To overcome these challenges, we propose a novel graph deep learning-based decomposition method called the Spatio-Temporal Graph Neural Network for fleet-level PLR estimation (PV-stGNN-PLR). PV-stGNN-PLR decomposes the power timeseries data into aging and fluctuation components, utilizing the aging component to estimate PLR. PV-stGNN-PLR exploits spatial and temporal coherence to derive PLR estimation for all systems in a fleet and imposes flatness and smoothness regularization in loss function to ensure the successful disentanglement between aging and fluctuation. We have evaluated PV-stGNN-PLR on three simulated PV datasets consisting of 100 inverters from 5 sites. Experimental results show that PV-stGNN-PLR obtains a reduction of 33.9% and 35.1% on average in Mean Absolute Percent Error (MAPE) and Euclidean Distance (ED) in PLR degradation pattern estimation compared to the state-of-the-art PLR estimation methods.

14 SOLAR ENERGY↗
NASA NTRSDate not supplied

Statistical Classification of Biosignature Information using Multiple Instrument Observations

The accurate identification of biosignatures (indications of life) from data taken from remote or in situ planetary exploration is one of the most important challenges in astrobiology, the interdisciplinary field examining habitability and the potential for extraterrestrial life. This study employs machine learning algorithms to optimize the identification of biosignatures, with an emphasis on those which are agnostic to a specific biochemical basis. We exploit the wealth of terrestrial data available from biogenic and abiogenic systems to enhance efficient feature prioritization. Our dataset, pulled from public databases and laboratory recorded measurements, includes elemental abundance, isotopic fractionation, and VNIR/Raman spectra The data curation process included standardization for detection limits and ranges. Subsequent feature extraction yielded detailed inputs for machine learning, including combinations of elemental content, isotopic ratios, and parameters of spectral peaks and troughs. Feature significance was evaluated across diverse machine learning methodologies, such as k-nearest neighbors, logistic regression, Random Forest, support vector machines, and Gaussian Naïve Bayes, along with a combined voting classifier. We utilized Receiver Operating Characteristic Area Under the Curve (ROC AUC) across 2,000 50% test-train splits as a robust metric of model performance. Results revealed a promising ROC AUC of 0.853 for the combined voting classifier. Removing elemental abundance data notably reduced model accuracy (13% decrease in AUC), highlighting its critical role in biosignature detection. Several other individual data features exhibited significance within their respective data types, offering additional granularity. This research fortifies the relevance of machine learning to astrobiology, potentially enhancing life detection missions by allowing algorithmic prioritization of high-interest samples for further investigation. Future work will refine data standardization, expand the dataset to include more terrestrial systems, and incorporate convolutional neural networks for spectral feature extraction. The potential for public data sharing is also under exploration, reinforcing our commitment to collective scientific advancement.

Statistical↗
NASA NTRS2021

Evaluation of SO2, SO4(2−) and an Updated SO2 Dry Deposition Parameterization in the United Kingdom Earth System Model

In this study we evaluate simulated surface SO2 and sulphate (SO4(2-)) concentrations from the United Kingdom Earth System Model (UKESM1) against observations from ground based measurement networks in the USA and Europe for the period 1987 to 2014. We find that UKESM1 captures the historical trend for decreasing concentrations of atmospheric SO2 and SO4(2-) in both Europe and the USA over the period 1987 to 2014. However, in the polluted regions of the eastern USA and Europe, UKESM1 over-predicts surface SO2 concentrations by a factor of 3, while under-predicting surface SO4(2-) concentrations by 25-35%. In the cleaner western USA, the model over-predicts both surface SO2 and SO4(2-) concentrations by a factor of 12 and 1.5 respectively. We find that UKESM1’s bias in surface SO2 and SO4(2-) concentrations is variable according to region and season. We also evaluate UKESM1 against total column SO2 from the Ozone Monitoring Instrument (OMI) using an updated data product. This comparison provides information about the model’s global performance, finding that UKESM1 over predicts total column SO2 over much of the globe, including the large source regions of India, China, the USA and Europe as well as over outflow regions. Finally, we assess the impact of a more realistic treatment of the model’s SO2 dry deposition parameterization. This change increases SO2 dry deposition to the land and ocean surfaces, thus reducing the atmospheric loading of SO2 and SO(sup 2-)(sub 4). In comparison with the ground-based and satellite observations, we find that the modified parameterization reduces the models over prediction of surface SO2 concentrations and total column SO2. Relative to the ground-based observations the simulated surface SO4(2-) concentrations are also reduced, while the simulated SO2 dry deposition fluxes increase.

SO2↗
DOE OSTI2022

Microstructure analysis of laser beam weldments performed on neutron-irradiated 304L steel containing 3 and 8 appm helium

We report that AISI 304 L austenitic stainless steel is one of the major structural materials used in light water reactors (LWRs). In the future, 304 L components may require repair, and several welding techniques have been proposed as candidates. In this study, laser beam welding using the low-energy contribution approach was performed in ~2016 on neutron-irradiated AISI 304 L steel with nominal values of 3 and 8 appm helium (He). The goal was to investigate the impact of helium on the irradiated material weldability and evaluate helium-associated damage. The weld and heat-affected zone (HAZ) microstructure was studied using scanning electron microscopy, electron backscatter diffraction, and transmission electron microscopy (TEM). Analysis of the weldment cross-sections did not reveal severe cracking. Still, evidence of incipient helium-associated damage was observed in the HAZ, manifesting as degraded grain boundaries (GBs) “decorated” by pore chains and mostly small (i.e., ≤ 25-30 µm) scattered cracks. The largest observed crack was ~50 µm in length. Helium-associated damage was localized within ~200-300 µm of the weld pool boundary, and the fraction of the compromised GBs, as a rule, was below ~9-11% of the total GB network. TEM analysis showed significant annealing of the radiation-induced defects at distances up to ~300 µm from the weld pool boundary. Inside the HAZ, the cavities (likely, helium bubbles) tended to form at GBs and inclusions, such as manganese sulfide precipitates in the grain interior. Crystallography analysis of the HAZ damage showed that random high-angle boundaries were most susceptible to helium-associated damage. In contrast, low-angle random boundaries and twin boundaries appeared to be strongly resistant to degradation from the combined effects of helium and welding.

36 MATERIALS SCIENCE↗
DOE OSTI2023

Deep generative models for vehicle speed trajectories

Generating realistic vehicle speed trajectories is a crucial component in evaluating vehicle fuel economy and in predictive control of self-driving cars. Traditional generative models rely on Markov chain methods and can produce accurate synthetic trajectories but are subject to the curse of dimensionality. They do not allow to include conditional input variables into the generation process. In this paper, we show how extensions to deep generative models allow accurate and scalable generation. Proposed architectures involve recurrent and feed-forward layers and are trained using adversarial techniques. Our models are shown to perform well on generating vehicle trajectories using a model trained on GPS data from Chicago metropolitan area.

33 ADVANCED PROPULSION SYSTEMS↗
NASA NTRSDate not supplied

SimUAM: A Comprehensive Microsimulation Toolchain to Evaluate the Impact of Urban Air Mobility in Metropolitan Areas

Over the past several years, Urban Air Mobility (UAM) has galvanized enthusiasm from investors and researchers, marrying expertise in aircraft design, transportation, logistics, artificial intelligence, battery chemistry, and broader policymaking. However, two significant questions remain unexplored: (1) What is the value of UAM in a region’s transportation network?, and (2) How can UAM be effectively deployed to realize and maximize this value to all stakeholders, including riders and local economies? To adequately understand the value proposition of UAM for metropolitan areas, we develop a holistic multi-modal toolchain, SimUAM, to model and simulate UAM and its impacts on travel behavior. This toolchain has several components: (1) MANTA: A fast, high-fidelity regional-scale traffic microsimulator, (2) VertiSim: A granular, discrete-event vertiport and pedestrian, (3) 3: A high-fidelity, trajectory-based aerial microsimulation. SimUAM, rooted in granular, GPU-based microsimulation, models millions of trips and their exact movements in the street network and in the air, producing interpretable and actionable performance metrics for UAM designs and deployments. The modularity, extensibility, and speed of the platform will allow for rapid scenario planning and sensitivity analysis, effectively acting as a detailed performance assessment tool. As a result, stakeholders in UAM can understand the impacts of critical infrastructure, and subsequently define policies, requirements, and investments needed to support UAM as a viable transportation mode.

Urban air mobility↗
DOE OSTI2025

Energy metric prediction for double insertion mutants via the RoseNet deep learning framework

Studying the structural and functional implications of protein mutations is an important task in computational biology and bioinformatics. We leverage our previously proposed RoseNet neural network architecture to predict energy metrics of proteins with double amino acid insertions or deletions (InDels). We train models on previously generated benchmark datasets containing the exhaustive double InDel mutations for three proteins, as well as an additional three proteins for which ∼145k random mutants, each with two InDels, have been generated. We expand on our previous work by evaluating three additional proteins and analyzing domain features that impact the prediction capabilities of RoseNet. These features include InDels into secondary structures and the solvent accessible surface area (SASA) scores of the residues. We uncover further evidence to support that RoseNet has a higher proficiency of generalizing to unseen residue combinations than unseen insertion positions. We also observe that RoseNet produces higher-quality predictions when inserting into a β-sheet over an α-helix. Additionally, when the insertions fall in an area of high SASA, RoseNet often displays better performance than inserting into areas of low SASA.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2025

FedCSpc: A Cross-Silo Federated Learning System With Error-Bounded Lossy Parameter Compression

Cross-Silo federated learning is widely used for scaling deep neural network (DNN) training over data silos from different locations worldwide while guaranteeing data privacy. Communication has been identified as the main bottleneck when training large-scale models due to large-volume model parameters and gradient transmission across public networks with limited bandwidth. Most previous works focus on gradient compression, while limited work tries to compress parameters that can not be ignored and extremely affect communication performance during the training. Here, to bridge this gap, we propose FedCSpc: an efficient cross-silo federated learning system with an XAI-driven adaptive parameter compression strategy for large-scale model training. Our work substantially differs from existing gradient compression techniques due to the distinct data features of gradient and parameter. The key contributions of this paper are fourfold. (1) Our designed FedCSpc proposes to compress the parameter during the training using the state-of-the-art error-bounded lossy compressor – SZ3. (2) We develop an adaptive compression error bound adjustment algorithm to guarantee the model accuracy effectively. (3) We exploit an efficient approach to utilize the idle CPU resources of clients to compress the parameters. (4) We perform a comprehensive evaluation with a wide range of models and benchmarks on a GPU cluster with 65 GPUs. Results show that FedCSpc can achieve the same model accuracy as FedAvg while reducing the data volume of parameters and gradients in communication by up to 7.39× and 288×, respectively. With 32 clients on a 4 Gb size model, FedCSpc significantly outperforms FedAvg in wall-clock time in the emulated WAN environment (at the bandwidth of 1 Gbps or lower without loss of generality).

SZ3↗
DOE OSTI2023

Assessment of Cloud-Based Applications Enabling a Scalable Risk-Informed Predictive Maintenance Strategy Across the Nuclear Fleet

The current light water reactor fleet uses time-based or failure-based maintenance strategies to achieve high-capacity factors. But to make nuclear more competitive in the energy market, these reactors could utilize emerging technologies in terms of artificial intelligence (AI) and cloud computing to enable a cost-effective, predictive maintenance strategy. This report examines the feasibility of cloud computing for the nuclear industry’s needs in terms of the cloud’s computing capabilities, feasibility, and regulatory concerns. The technical viability of cloud computing was analyzed using one year worth of data from a boiling water reactor’s safety relief valve. Models were hosted on a local desktop, Idaho National Laboratory’s high-performance computer, and Microsoft Azure. Data was loaded, processed, and two types of models were trained in an A/B fashion. Based on the speed at which these actions were completed, it was used to determined that cloud computing has adequate computing resources. Additionally, the computing power can scale with the demanded load. To enable cloud computing in the existing fleet, additional sensors, networks, and other requirements must be implemented to ensure a smooth transition from current maintenance strategies. However, there is a benefit as the plant no longer needs manage their own servers, software, cybersecurity, and IT support staff. Many of these features can be offloaded on to the cloud provider. A comprehensive analysis was completed that showed the current annual cost of operating is more expensive than using cloud computing resources. Lastly, the regulatory framework does not explicitly address AI or autonomous control. Currently, the NRC and other regulatory bodies are evaluating providing guidance to address gaps rather than new regulations to address the use of AI and ML. But since many of the AI applications are focused on non-safety related applications, such as balance-of-plant components, they will likely have little or no regulatory restrictions or necessary approvals. Demonstrating how AI can improve maintenance and operation of these non-safety related systems seems like the likely path forward for implementing AI and cloud computing resources inside nuclear power plants (NPPs).

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2024

Peer-to-peer communication control for resilient operations of networked cyberphysical systems

This report includes two main accomplishments of the peer-to-peer communication control for resilient operation of networked microgrids project in FY24, which include a scheme for cyberattack-aware coordination of networked microgrids for supporting voltages of bulk power systems and a scheme for price signal-based operations of EV-rich networked microgrids with mixed ownership. First, the cyberattack-aware scheme enables networked microgrids to distributedly determine the amount of reactive power injection to support the voltage of bulk power system (BPS) in a fair manner. In this scheme, a risk-informed algorithm is presented to generate the peer-to- peer (P2P) communication graph with minimal risk of attack on communication links. To deal with cyberattacks on MG controllers, the resilient consensus algorithm (CA) is utilized for MG controllers to robustly estimate the total reactive power headroom, from which the MGs can accurately provide the needed amount of reactive power injection for supporting the voltage of BPS. The CA implementation and performance within the P2P communication framework are demonstrated on the IEEE 39-bus system with 6 microgrids contained in the distribution feeder under different cyberattack scenarios. Second, the price-based scheme enables the usage of the real-time price signal for the operations of electric vehicle (EV)-rich networked-microgrids with mixed ownership, in which not all the microgrids can communicate with the distribution system operator (DSO). In this scheme, a max consensus is introduced to enable the real-time price signal to be propagated from the DSO to all the microgrids, from which each microgrid controller will manage the DERs to balance the load demand and the power injection from the EV charging stations within its microgrid. Numerical results over one day with 288 slots of 5-minute intervals on the modified 123-node test feeder including 3 microgrids with high penetration of EV are presented to evaluate how the price signal affects the operations of networked microgrids under different charging strategies of the EV charging stations. The result indicates that our proposed EVCS (dis)charging strategy, which leverages the flexibility of EVs to support the grid through discharging during peak demand, proves to be a cost-effective solution that reduces operational costs while improving the social welfare of EV charging.

24 POWER TRANSMISSION AND DISTRIBUTION↗
NASA NTRS2019

NASA EOSDIS Data Usage Metrics- Insight and Assessment

NASA's Earth Science Data and Information System (ESDIS) Project collects Earth science data usage metrics on a daily basis through the ESDIS Metrics System (EMS). This includes metrics on distribution of data products, users, data volumes, and number of files, which are key parameters in evaluating system-level performance of any of the Distributed Active Archive Centers (DAACs) encompassed by NASA's Earth Observing System (EOS) Data and Information System (EOSDIS). EOSDIS data usage metrics illustrate the benefits of making NASA data openly available to the public and show a rapid growth in data distribution to a worldwide user community. In fact, each year since 2014 the EOSDIS has distributed over one billion data files of products from EOS satellite, airborne, and in situ observations. An assessment of the long-term trends of data usage metrics and user characterization provides insights into data usability.This study will focus on describing the EMS as a metrics collection tool and will provide a comprehensive analysis of EOSDIS data usage metrics over the last 10 years. This study will also characterize the product distribution metrics by various tools and services, such as Giovanni, the Open-source Project for a Network Data Access Protocol (OPeNDAP), and subsets, to address how these tools/services have extended the usage of data in the EOSDIS collection. Data usage patterns based on discipline and study area will further assist in understanding how EOSDIS data user needs have evolved over time. Results from this study will provide useful information for the DAACs that can help them improve the functionality of their tools and services as well as more efficiently allocate the resources necessary for enhanced access and availability of their data products. Knowledge of these metrics may also benefit user discovery of data in the EOSDIS collection, promote research collaboration, and stimulate new ideas from work and research conducted using specific datasets and data collections.

Kafle, Durga N.↗
NASA NTRS2022

Mars Terrain Segmentation with Less Labels

Planetary rover systems need to perform terrain segmentation to identify drivable areas as well as identify specific types of soil for sample collection. The latest Martian terrain segmentation methods rely on supervised learning which is very data hungry and difficult to train where only a small number of labeled samples are available. Moreover, the semantic classes are defined differently for different applications (e.g., rover traversal vs. geological) and as a result the network has to be trained from scratch each time, which is an inefficient use of resources. This research proposes a semi-supervised learning framework for Mars terrain segmentation where a deep segmentation network trained in an unsupervised manner on unlabeled images is transferred to the task of terrain segmentation trained on few labeled images. The network incorporates a backbone module which is trained using a contrastive loss function and an output atrous convolution module which is trained using a pixel-wise cross-entropy loss function. Evaluation results using the metric of segmentation accuracy show that the proposed method with contrastive pre-training outperforms plain supervised learning by 2%-10%. Moreover, the proposed model is able to achieve a segmentation accuracy of 91.1% using only 161 training images (1% of the original dataset) compared to 81.9% with plain supervised learning.

Wilson, Brian D↗
NASA NTRSDate not supplied

U.S. IMERG Status

The U.S. Science Team’s Integrated Multi-satellitE Retrievals for the Global Precipitation Measurement (GPM) mission (IMERG) product provides estimates of surface precipitation rate and related information on a global 0.1° half-hour grid. It is run three times at increasingly longer latency and higher information input to serve different communities. This presentation will briefly summarize the major upgrades included in Version 07. The Goddard Profiling (GPROF) algorithm (applied to passive microwave sensor data from the GPM virtual constellation) and the Combined Radar-Radiometer Algorithm (CORRA) that provide input to IMERG V07 are both improved, and the new Precipitation Estimation from Remotely Sensed Information Using Artificial Neural Networks–Dynamic Infrared Rain Rate (PDIR) algorithm is being applied to infrared data, which employs an additional, warmer infrared temperature threshold than the previous infrared scheme and a deep neural network. V07 has improved bias performance as a result of calibrations that now employ the entire swath widths of CORRA and GPROF GPM Microwave Imager precipitation estimates. As well, time continuity in precipitation features is improved as a result of changes to the Kalman filter that approximately preserve the local histogram of precipitation rates (Scheme for Histogram Adjustment with Ranked Precipitation Estimates in the Neighborhood, or SHARPEN), and that better account for differences in sensor performance. A long-standing bug in the geolocation that shifted grid values 0.1° to the east in the latitude band 70°N-S has been corrected. Other changes in V07 include a hierarchical selection among motion vector sources to address deficiencies in the precipitation propagation near orography, an update to the precipitation phase specification for improved consistency with current inputs, and a renewed effort to implement climatological gauge adjustment to the near-real-time Runs. Early evaluations of V07 IMERG show interesting behavior across the TRMM orbit boost that is highly relevant to the planned orbit boost for the GPM Core observatory.

GPM↗
DOE OSTI2022

Using Direct Numerical Simulation of Pore-Level Events to Improve Pore-Network Models for Prediction of Residual Trapping of CO2

Direct numerical simulation and pore-network modeling are common approaches to study the physics of two-phase flow through natural rocks. For assessment of the long-term performance of geological sequestration of CO 2 , it is important to model the full drainage-imbibition cycle to provide an accurate estimate of the trapped CO 2 . While direct numerical simulation using pore geometry from micro-CT rock images accurately models two-phase flow physics, it is computationally prohibitive for large rock volumes. On the other hand, pore-network modeling on networks extracted from micro-CT rock images is computationally efficient but utilizes simplified physics in idealized geometric pore elements. This study uses the lattice-Boltzmann method for direct numerical simulation of CO 2 -brine flow in idealized pore elements to develop a new set of pore-level flow models for the pore-body filling and snap-off events in pore-network modeling of imbibition. Lattice-Boltzmann simulations are conducted on typical idealized pore-network configurations, and the interface evolution and local capillary pressure are evaluated to develop modified equations of local threshold capillary pressure of pore elements as a function of shape factor and other geometrical parameters. The modified equations are then incorporated into a quasi-static pore-network flow solver. The modified model is applied on extracted pore-network of sandstone samples, and saturation of residual trapped CO 2 is computed for a drainage-imbibition cycle. The modified model yields different statistics of pore-level events compared with the original model; in particular, the occurrence of snap-off in pore-throats is reduced resulting in a more frontal displacement pattern along the main injection direction. Compared to the original model, the modified model is in closer agreement with the residual trapped CO 2 obtained from core flow experiments and direct numerical simulation.

Kohanpur, Amir H.↗
NASA NTRS2001

Accuracy Assessment of Response Surface Approximations for Supersonic Turbine Design

There is a growing trend to employ CFD tools to supply the necessary information for design optimization of fluid dynamics components/systems. Such results are prone to uncertainties due to reasons including discretization. errors, incomplete convergence of computational procedures, and errors associated with physical models such as turbulence closures. Based on this type of information, gradient-based optimization algorithms often suffer from the noisy calculations, which can seriously compromise the outcome. Similar problems arise from the experimental measurements. Global optimization techniques, such as those based on the response surface (RS) concept are becoming popular in part because they can overcome some of these barriers. However, there are also fundamental issues related to such global optimization technique such as RS. For example, in high dimensional design spaces, typically only a small number of function evaluations are available due to computational and experimental costs. On the other hand, complex features of the design variables do not allow one to model the global characteristics of the design space with simple quadratic polynomials. Consequently a main challenge is to reduce the size of the region where we fit the RS, or make it more accurate in the regions where the optimum is likely to reside. Response Surface techniques using either polynomials or and Neural Network (NN) methods offer designers alternatives to conduct design optimization. The RS technique employs statistical and numerical techniques to establish the relationship between design variables and objective/constraint functions, typically using polynomials. In this study, we aim at addressing issues related to the following questions: (1) How to identify outliers associated with a given RS representation and improve the RS model via appropriate treatments? (2) How to focus on selected design data so that RS can give better performance in regions critical to design optimization? (3) How to combine NN and polynomial techniques for improving the accuracy of the RS model?

Papila, Nilay↗
NASA NTRS2017

Comparison of Satellite Rainfall Estimates and Rain Gauge Measurements in Italy, and Impact on Landslide Modeling

Landslides can be triggered by intense or prolonged rainfall. Rain gauge measurements are commonly used to predict landslides even if satellite rainfall estimates are available. Recent research focuses on the comparison of satellite estimates and gauge measurements. The rain gauge data from the Italian network (collected in the system database Verifica Rischio Frana" (VRF)) are compared with the National Aeronautics and Space Administration (NASA) Tropical Rainfall Measuring Mission (TRMM) products. For the purpose, we couple point gauge and satellite rainfall estimates at individual grid cells, evaluating the correlation between gauge and satellite data in different morpho-climatological conditions. We then analyze the statistical distributions of both rainfall data types and the rainfall events derived from them. Results show that satellite data underestimates ground data, with the largest differences in mountainous areas. Power-law models, are more appropriate to correlate gauge and satellite data. The gauge and satellite-based products exhibit different statistical distributions and the rainfall events derived from them differ. In conclusion, satellite rainfall cannot be directly compared with ground data, requiring local investigation to account for specific morpho-climatological settings. Results suggest that satellite data can be used for forecasting landslides, only performing a local scaling between satellite and ground data.

landslide; satellite rainfall; TRMM; rain gauges; ↗
DOE OSTI2025

DeepAndes: A Self-Supervised Vision Foundation Model for Multispectral Remote Sensing Imagery of the Andes

By mapping sites at large scales usingremotely sensed data, archaeologists can generate unique insights into long-term demographic trends, interregional social networks, and human adaptations in the past. Remote sensing surveys complement field-based approaches, and their reach can be especially great when combined with deep learning and computer vision techniques. However, conventional supervised deep learning methods face challenges in annotating fine-grained archaeological features at scale. In addition, while recent vision foundation models have shown remarkable success in learning large-scale remote sensing data with minimal annotations, most off-the-shelf solutions are designed for RGB images rather than multispectral satellite imagery, such as the eight-band data used in our study. In this article, we introduce DeepAndes, a transformer-based vision foundation model trained on three million multispectral satellite images, specifically tailored for Andean archaeology. DeepAndes incorporates a customized DINOv2 self-supervised learning algorithm optimized for eight-band multispectral imagery, marking the first foundation model designed explicitly for the Andes region. We evaluate its image understanding performance through imbalanced image classification, image instance retrieval, and pixel-level semantic segmentation tasks. Our experiments show that DeepAndes achieves superior F1 scores, mean average precision, and Dice scores in few-shot learning scenarios, significantly outperforming models trained from scratch or pretrained on smaller datasets. This underscores the effectiveness of large-scale self-supervised pretraining in archaeological remote sensing.

Guo, Junlin [Vanderbilt Univ., Nashville, TN (Unit↗
DOE OSTI2024

Techno-Economic Simulation Results Using dGeo for EGS-Based District Heating in the Northeastern United States

This dataset presents the results of techno-economic simulations performed using the Distributed Geothermal Market Demand Model (dGeo) to evaluate the feasibility of Enhanced Geothermal Systems (EGS)-based district heating in the Northeastern United States. Developed by the National Renewable Energy Laboratory (NREL), dGeo is a geospatially resolved, bottom-up modeling framework designed to explore the deployment potential of geothermal distributed energy resources. The dataset, created as part of the Cornell EGS Ground-Truthing Project, provides census tract-level data that includes inputs and outputs such as thermal demand, road length, energy prices, geothermal system sizing, annual energy contributions from geothermal and natural gas peaking boilers, system capital costs (CAPEX), operation and maintenance costs (OPEX), and the levelized cost of heat (LCOH). Key simulation parameters include geothermal gradients, measured well depths, production temperatures, and district heating piping lengths based on S1400 neighborhood road lengths. The simulations assume a target bottom hole temperature of 80C and the development of new district heating networks in each census tract.

15 GEOTHERMAL ENERGY↗