SEARCH · Search NASA
Results for “data fusion, modeling”
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.
GeoThermalCloud: Cloud Fusion of Big Data and Multi-Physics Models using Machine Learning for Discovery, Exploration, and Development of Hidden Geothermal Resources
The primary goals of this project are identifying hidden geothermal resources in the USA and designing profitable enhanced geothermal systems (EGS). Many non-obvious processes and parameters could characterize geothermal resources and could control the ultimate energy potential of geothermal fields. Diverse datasets (e.g., geology, geochemistry, geophysics, satellite, airborne geophysics) are available to help characterize geothermal resources, but this data is sparse and multi-scale that has hindered attempts to leverage the datasets for geothermal exploration and profitable EGS design. Recent advancements in machine learning (ML) give promise to overcome these issues. Modern ML methods and tools can (1) analyze large datasets, (2) assimilate model ensembles that include a multitude of inputs and outputs, (3) process sparse datasets, (4) perform transfer learning between sites with different data quality, (5) extract hidden geothermal signatures from field and simulation data, (6) label geothermal resources and processes, (7) identify highvalue data acquisition targets, and (8) guide geothermal exploration and production by selecting optimal exploration, production, and drilling strategies.
Cloud Fusion of Big Data and Multi-Physics Models using Machine Learning for Discovery, Exploration, and Development of Hidden Geothermal Resources
The primary goals of this project are identifying hidden geothermal resources in the USA and designing profitable enhanced geothermal systems (EGS). Many non-obvious processes and parameters could characterize geothermal resources and could control the ultimate energy potential of geothermal fields. Diverse datasets (e.g., geology, geochemistry, geophysics, satellite, airborne geophysics) are available to help characterize geothermal resources, but this data is sparse and multi-scale. This has hindered attempts to leverage the datasets for geothermal exploration and profitable EGS design. Recent advancements in machine learning (ML) give promise to overcome these issues. Modern ML methods and tools can (1) analyze large datasets, (2) assimilate model ensembles that include a multitude of inputs and outputs, (3) process sparse datasets, (4) perform transfer learning between sites with different data quality, (5) extract hidden geothermal signatures from field and simulation data, (6) label geothermal resources and processes, (7) identify high-value data acquisition targets, and (8) guide geothermal exploration and production by selecting optimal exploration, production, and drilling strategies. In this work, we implement ML-based geothermal exploration and an enhanced geothermal systems (EGS) design tool to achieve the above goals. Our exploration tool is GeoThermalCloud (GTC) EGS design tool is GeoDT-ML. GTC (github.com/SmartTensors/GeoThermalCloud.jl) utilizes a LANL unsupervised ML platform called SmartTensors (https://tensors.lanl.gov/) to automate data analyses and interpretations by extracting hidden signatures to identify geothermal prospects. It enables the identification of critical measurements needed to identify geothermal resource signatures. GeoDT-ML (github.com/SmartTensors/GeoThermalCloud.jl/tree/master/) adds coupling to GeoDT (https://github.com/GeoDesignTool/GeoDT.git) for stochastic EGS design optimization and performance prediction. GeoDT-ML leverages recent advances in deep learning and high-performance computing. Contributors to this effort include LANL, PNNL, Google, Stanford, and Julia Computing.
GeoThermalCloud: Cloud Fusion of Big Data and Multi-Physics Models using Machine Learning for Discovery, Exploration, and Development of Hidden Geothermal Resources
The primary goals of this project are exploring hidden geothermal resources in the U.S.A. and designing profitable enhanced geothermal systems (EGS). Many processes and parameters control geothermal exploration and energy production from geothermal fields. Diverse datasets (e.g., geology, geochemistry, geophysics, satellite, airborne geophysics) are available to help characterize subsurface geothermal conditions. Sparse and multi-scale characteristics of these datasets prohibit properly leveraging these datasets for geothermal exploration and profitable EGS design. Recent advancements in machine learning (ML) promise to resolve these issues. The tremendous challenges and risks of geothermal exploration and production bring the demand for novel ML methods and tools that can (1) analyze large field datasets, (2) assimilate model simulations (large inputs and outputs), (3) process sparse datasets, (4) perform transfer learning (between sites with different exploratory levels), (5) extract hidden geothermal signatures in the field and simulation data, (6) label geothermal resources and processes, (7) identify high-value data acquisition targets, and (8) guide geothermal exploration and production by selecting optimal exploration, production, and drilling strategies. To address these necessities, ML-based geothermal resources exploration and enhanced geothermal systems (EGS) design tools have been developed. The exploration tool is called GeoThermalCloud and EGS design tool is called GeoDT-ML. GeoThermalCloud (https://github.com/SmartTensors/GeoThermalCloud.jl) utilizes a LANL unsupervised ML platform called SmartTensors (https://tensors.lanl.gov/) to automate data analyses and interpretations by extracting hidden signatures to identify geothermal prospects. Also, it enables the identification of critical measurements needed to identify geothermal resource signatures. Alternatively, GeoDT-ML (https://github.com/SmartTensors/GeoThermalCloud.jl/tree/master/EGS) is an ML-based alternative to GeoDT (https://github.com/GeoDesignTool/GeoDT.git), a fast, simplified multi-physics solver to evaluate EGS project designs in uncertain geologic systems. GeoDT-ML leverages recent advances in deep learning and high-performance computing. It is a faster and simpler version of GeoDT. To make this project a success, we used capabilities of LANL, PNNL, Google, Stanford, and Julia Computing. We analyzed eight datasets of the U.S.A. using GeothermalCloud and demonstrated potential highly prospective geothermal resources and identified key factors defining highly prospective sites. The first data set includes 44 locations in southwest New Mexico and 18 geological, hydrogeological, geophysical, geothermal, geochemical attributes. We defined low- and medium-temperature hydrothermal systems and discovered a new highly prospective site. The second data set analyzed 18 shallow water chemistry attributes at 14,342 locations in the Great Basin. It demarcated modestly, moderately, and highly prospective sites including key attributes for each type of prospectivity. The third data set analyzed Utah FORGE data including satellite (InSAR), geophysical (gravity, seismic), geochemical, and geothermal attributes. Here, we performed prospectivity analysis to identify future drilling locations using geological, geochemical, and geophysical attributes. Maps of temperature at depth and heat flow are constructed based on the available data. Prospectivity maps were generated, and drilling locations were proposed for future geothermal field exploration. The fourth data set analyzed 21 attributes at 120 locations in Tularosa Basin, New Mexico; data comes from past play fairway analyses in this region. ML analyses identified geothermal signatures associated with modestly, moderately, and highly hydrothermal systems. We also defined dominant attributes and spatial distribution of the geothermal signatures. The fifth, sixth, seventh, and eighth datasets include Tohatchi Springs, New Mexico, Hawaii, Brady site, Nevada, and EGS Collab, respectively. Moreover, we coupled GeothermalCloud and magnetotellurics data to pinpoint drilling locations for developing geothermal projects in the Tularosa Basin, New Mexico. GeothermalCloud found potential prospective locations for geothermal resources near White Sands Missile Range and McGregor Range at Fort Bliss. Magnetotellurics data determined the potential depth (~1800m) of geothermal prospects at McGregor Range based on apparent resistivity structures/layers in the subsurface. The McGregor Range consists of three resistivity layers and two resistivity structures. Magnetotellurics data also helps identify that the western portion of the McGregor Range has thick and low-resistivity earth materials. The low resistivity to the west is most likely for a fault system. Assuming temperature is consistent with a geothermal reservoir, the west-central part of the McGregor Range has the highest geothermal potential because of the increase in porosity and associated permeability attributed to the interpreted fault system. Also, we devised a coupling strategy between a process model and GeothermalCloud to characterize hydrogeological conditions and geothermal conditions, respectively. The process model characterizes hydrogeological and geothermal conditions on highly prospective geothermal sites provided by GeothermalCloud. We developed a physics-informed neural network (PINN) version of the Burns equation that can be easily coupled with GeothermalCloud. Furthermore, we performed an optimal design decision maximizing the economic value of an EGS power plant. This study optimized the range of well spacing between injection and production wells maximizing net present value in dollars (NPV). For this task, we used the GeoDT to simulate the Utah FORGE EGS development cycle from the initial well design to the end of production. Next, we accomplished another crucial task, which is predicting permeability of geothermal reservoirs. Predicting permeability of geothermal reservoirs is a non-trivial task because of huge computational runtime of simulation and lack of measurements. To avoid these limitations, we used easy-to-measure chemical concentrations in the subsurface as measurement data and convolutional neural network based ML model of a high-fidelity model. Next, we predicted permeability using Markov chain Monte Carlo simulation. We found that Markov chain Monte Carlo simulation predicts permeability with a high certainty if the prediction zone in the simulation area has chemical concentration data. Finally, we analyzed the DOE funded INGENIOUS and GeoDAWN projects data. For discovering hidden geothermal systems in the Great Basin, the INGENIOUS project accumulated old data, collected new data, and released them in 2022. The dataset includes a total of 24 geological, geophysical, and geochemical attributes. Data resolution and scale significantly vary prohibiting an appropriate usage. To avoid such limitations, we brought all data in the same resolution and scale by applying the inverse distance weighting interpolation technique for predicting data in unsampled locations. Subsequently, we analyzed LiDAR data of the GeoDAWN project. We received data in tiles format. The DOE’s overarching goal is to use ML on LiDAR data for finding favorable geological structures (e.g., step up faults in Brady, Nevada). To serve the purpose, we need to label favorable geologic structures that correspond to LiDAR data. We wrote an algorithm to label the LiDAR data with the favorable geologic structures.
Multisource Data Fusion Outage Location in Distribution Systems via Probabilistic Graphical Models
Efficient outage location is critical to enhancing the resilience of power distribution systems. However, accurate outage location requires combining massive evidence received from diverse data sources, including smart meter (SM) last gasp signals, customer trouble calls, social media messages, weather data, vegetation information, and physical parameters of the network. This is a computationally complex task due to the high dimensionality of data in distribution grids. In this paper, we propose a multi-source data fusion approach to locate outage events in partially observable distribution systems using Bayesian networks (BNs). A novel aspect of the proposed approach is that it takes multi-source evidence and the complex structure of distribution systems into account using a probabilistic graphical method. Our method can radically reduce the computational complexity of outage location inference in high-dimensional spaces. The graphical structure of the proposed BN is established based on the network’s topology and the causal relationship between random variables, such as the states of branches/customers and evidence. Utilizing this graphical model, accurate outage locations are obtained by leveraging a Gibbs sampling (GS) method, to infer the probabilities of de-energization for all branches. Compared with commonly-used exact inference methods that have exponential complexity in the size of the BN, GS quantifies the target conditional probability distributions in a timely manner. As a result, a case study of several real-world distribution systems is presented to validate the proposed method.
Fusion of Surface Ceilometer Data and Satellite Cloud Retrievals in 2D Mesh Interpolating Model with Clustering
For accurate cloud ceiling information, a data fusion approach is proposed that utilizes satellite data to extend surface station information to much wider areas. Cloud base height (CBH) retrieved from satellite observations provides for much larger spatial coverage and higher resolution. The direct comparison of GOES-16 CBH with surface station ceiling yields a local bias that has to be corrected for in the initial GOES-16 cloud base information. This sparsely sampled bias correction presents an irregular 2D mesh of control points, which is then interpolated by constructing a continuous smooth field using polyharmonic splines. The influence of remote stations is restricted by grouping the control points into clusters depending on an effective distance. This cluster-based approach allows for constructing separate spline surfaces corresponding to physically different clouds. The obtained continuous bias correction function is then applied to the entire GOES-16 pixel level CBH except for areas far away from surface stations in data sparse regions such as offshore. The described method is currently being tested using daytime-only observations over the central and eastern United States. Overall, this approach has potential to provide more accurate, high spatial resolution cloud ceiling information for the aviation community.
Visualization of the operational space of edge-localized modes through low-dimensional embedding of probability distributions
Information visualization aimed at facilitating human perception is an important tool for the interpretation of experiments on the basis of complex multidimensional data characterizing the operational space of fusion devices. This work describes a method for visualizing the operational space on a two-dimensional map and applies it to the discrimination of type I and type III edge-localized modes (ELMs) from a series of carbon-wall ELMy discharges at JET. The approach accounts for stochastic uncertainties that play an important role in fusion data sets, by modeling measurements with probability distributions in a metric space. The method is aimed at contributing to physical understanding of ELMs as well as their control. Furthermore, it is a general method that can be applied to the modeling of various other plasma phenomena as well.
Sensor-agnostic photogrammetric image registration with applications to population modeling
Photogrammetric registration of airborne and spaceborne imagery is a crucial prerequisite to many data fusion tasks. While embedded sensor models provide a rough geolocation estimate, these metadata may be incomplete or imprecise. Manual solutions are appropriate for small-scale projects, but for rapid streams of cross-modal, multi-sensor, multi-temporal imagery with varying metadata standards, an automated approach is required. We present a high-performance image registration workflow to address this need. This paper outlines the core development concepts and demonstrates its utility with respect to the 2016 data fusion contest imagery. In particular, Iris ultra-HD video is georeferenced to the Earth surface via registration to DEIMOS-2 imagery, which serves as a trusted control source. Geolocation provides opportunity to augment the video with spatial context, stereo-derived disparity, spectral sensitivity, change detection, and numerous ancillary geospatial layers. We conclude by leveraging these derivative data layers towards one such fusion application: population distribution modeling.
Evaluating Direct and Indirect Influence on EV Charging Stations Across the US
The adoption of new technology for electric vehicles (EV) and mobility applications can bring underappreciated vulnerabilities to the power grid. One area of potential fraud and adversarial influence is through the business ecosystem of startups that own and deploy EV technology. Yet, there are no models or analyses that map the network of organizations and people that have direct and indirect influence over technologies currently deployed in the grid. To fill this gap, we develop a multilayer network model to measure direct and indirect influence on EV charging stations. First, we create and adversarial socio-technical network (ASTN) model via a data fusion pipeline for different US regions of interest (ROI). Then, we develop an integrated ASTN for Chicago, Los Angeles, New York, and Philadelphia. We rank EV charging companies direct influence within each geographic region as well as indirect influence via social network analysis. While some companies have strong direct and indirect influence (i.e., ChargePoint) others show a mismatch between their influence over charging stations and their position within the social network. For example, Tesla has strong direct influence on stations and weak indirect influence over competitors. In contrast, 7Charge has weak direct influence over stations, but strong indirect influence over competitors.
Energy dependence of incomplete fusion processes in the {sup 16}O+{sup 181}Ta system: Measurement and analysis of forward-recoil-range distributions at E{sub lab}<=7 MeV/nucleon
To study the energy dependence of incomplete fusion processes, the recoil range distributions for the reactions {sup 181}Ta({sup 16}O,xn), {sup 181}Ta({sup 16}O,pxn), {sup 181}Ta({sup 16}O,alphan), {sup 181}Ta({sup 16}O,alpha2n), {sup 181}Ta({sup 16}O,alpha3n), and {sup 181}Ta({sup 16}O,2alpha3n) have been measured at approx =81-, 90-, and 96 MeV beam energies. The disentanglement of the complete and incomplete fusion processes have been done in terms of full and partial linear momentum transfer from the projectile to the target nucleus. The measurements have been done using recoil catcher technique. The experimentally measured forward recoil range distributions have been interpreted in terms of breakup fusion model. Detailed analysis of the data indicates that incomplete fusion processes have significant contribution at energies as low as approx =5 MeV/nucleon and their contribution is found to increase with energy.
Improving Data and Prediction Quality of High-Throughput Perovskite Synthesis with Model Fusion
Combinatorial fusion analysis (CFA) is an approach for combining multiple scoring systems using the rank-score characteristic function and cognitive diversity measure. One example is to combine diverse machine learning models to achieve better prediction quality. In this work, we apply CFA to the synthesis of metal halide perovskites containing organic ammonium cations via inverse temperature crystallization. Using a data set generated by high-throughput experimentation, four individual models (support vector machines, random forests, weighted logistic classifier, and gradient boosted trees) were developed. We characterize each of these scoring systems and explore 66 possible combinations of the models. When measured by the precision on predicting crystal formation, the majority of the combination models improves the individual model results. The best combination models outperform the best individual models by 3.9 percentage points in precision. In addition to improving prediction quality, we demonstrate how the fusion models can be used to identify mislabeled input data and address issues of data quality. In particular, we identify example cases where all single models and all fusion models do not give the correct prediction. Experimental replication of these syntheses reveals that these compositions are sensitive to modest temperature variations across the different locations of the heating element that can hinder or enhance the crystallization process. In summary, we demonstrate that model fusion using CFA can not only identify a previously unconsidered influence on reaction outcome but also be used as a form of quality control for high-throughput experimentation.
Sensor fusion IV: Control paradigms and data structures; Proceedings of the Meeting, Boston, MA, Nov. 12-15, 1991
Various papers on control paradigms and data structures in sensor fusion are presented. The general topics addressed include: decision models and computational methods, sensor modeling and data representation, active sensing strategies, geometric planning and visualization, task-driven sensing, motion analysis, models motivated biology and psychology, decentralized detection and distributed decision, data fusion architectures, robust estimation of shapes and features, application and implementation. Some of the individual subjects considered are: the Firefly experiment on neural networks for distributed sensor data fusion, manifold traversing as a model for learning control of autonomous robots, choice of coordinate systems for multiple sensor fusion, continuous motion using task-directed stereo vision, interactive and cooperative sensing and control for advanced teleoperation, knowledge-based imaging for terrain analysis, physical and digital simulations for IVA robotics.
Assessing methods in fusion and fitting for time series construction in remote sensing-based earth observations
This study evaluates the comparative performance of spatiotemporal fusion and time-series fitting methods for constructing high-spatiotemporal-resolution remote sensing time-series data. Due to in-class similarity of fusion methods and fitting methods, we employ the Fit-FC (Fitting, spatial Filtering, and residual Compensation) model as a representative fusion method and the linear harmonic fitting model as a representative fitting method. Both Fit-FC and the linear harmonic fitting are widely used for high-spatiotemporal-resolution time-series data construction, and we modify the original Fit-FC model to enable automatic time-series fusion. To ensure data representativeness, we use 3 years (2019–2021) of Harmonized Landsat and Sentinel-2 surface reflectance datasets and Terra MCD43A4 products. Eight experimental regions are selected worldwide to guarantee generalization of the comparative performance between fusion and fitting methods, covering diverse land-use types (cropland, developed land, forest, and grassland) and varying climatological conditions. Time-series of NDVI and surface reflectance are analyzed under both actual observations and simulated data-missing scenarios. The constructed time-series data reveals that (1) the modified Fit-FC and linear harmonic fitting model achieve excellent performance in constructing high-resolution time-series images; (2) the fusion method outperforms the fitting method in constructing time-series of NDVI and surface reflectance images in cropland-, forest-, and grassland-dominated regions; (3) both methods achieve comparable performance in developed-dominated regions; (4) the fusion method is more robust to missing data, and better captures abrupt phenological transitions under conditions of continuous missing data; (5) the fitting method is computationally more efficient, making it suitable for large-scale time-series image reconstruction. This study provides valuable insights for selecting optimal strategies to generate high-resolution time-series images across diverse application scenarios and lays a foundation for extensions to other vegetation indices or land surface variables.
Fusion of Multiple Models for Improving Gross Primary Production Estimation With Eddy Covariance Data Based on Machine Learning
Abstract Terrestrial gross primary production (GPP) represents the magnitude of CO 2 uptake through vegetation photosynthesis, and is a key variable for carbon cycles between the biosphere and atmosphere. Light use efficiency (LUE) models have been widely used to estimate GPP for its physiological mechanisms and availability of data acquisition and implementation, yet each individual GPP model has exhibited large uncertainties due to input errors and model structure, and further studies of systematic validation, comparison, and fusion of those models with eddy covariance (EC) site data across diverse ecosystem types are still needed in order to further improve GPP estimation. We here compared and fused five GPP models (VPM, EC‐LUE, GOL‐PEM, CHJ, and C‐Fix) across eight ecosystems based on FLUXNET2015 data set using the ensemble methods of Bayesian Model Averaging (BMA), Support Vector Machine (SVM), and Random Forest (RF) separately. Our results showed that for individual models, EC‐LUE gave a better performance to capture interannual variability of GPP than other models, followed by VPM and GLO‐PEM, while CHJ and C‐Fix were more limited in their estimation performance. We found RF and SVM were superior to BMA on merging individual models at various plant functional types (PFTs) and at the scale of individual sites. On the basis of individual models, the fusion methods of BMA, SVM, and RF were examined by a five‐fold cross validation for each ecosystem type, and each method successfully improved the average accuracy of estimation by 8%, 18%, and 19%, respectively.
Computational Intelligence Based Data Fusion Algorithm for Dynamic sEMG and Skeletal Muscle Force Modelling
In this work, an array of three surface Electrography (sEMG) sensors are used to acquired muscle extension and contraction signals for 18 healthy test subjects. The skeletal muscle force is estimated using the acquired sEMG signals and a Non-linear Wiener Hammerstein model, relating the two signals in a dynamic fashion. The model is obtained from using System Identification (SI) algorithm. The obtained force models for each sensor are fused using a proposed fuzzy logic concept with the intent to improve the force estimation accuracy and resilience to sensor failure or misalignment. For the fuzzy logic inference system, the sEMG entropy, the relative error, and the correlation of the force signals are considered for defining the membership functions. The proposed fusion algorithm yields an average of 92.49% correlation between the actual force and the overall estimated force output. In addition, the proposed fusionbased approach is implemented on a test platform. Experiments indicate an improvement in finger/hand force estimation.
Data Fusion in Wind Tunnel Testing; Combined Pressure Paint and Model Deformation Measurements (Invited)
As the benefit-to-cost ratio of advanced optical techniques for wind tunnel measurements such as Video Model Deformation (VMD), Pressure-Sensitive Paint (PSP), and others increases, these techniques are being used more and more often in large-scale production type facilities. Further benefits might be achieved if multiple optical techniques could be deployed in a wind tunnel test simultaneously. The present study discusses the problems and benefits of combining VMD and PSP systems. The desirable attributes of useful optical techniques for wind tunnels, including the ability to accommodate the myriad optical techniques available today, are discussed. The VMD and PSP techniques are briefly reviewed. Commonalties and differences between the two techniques are discussed. Recent wind tunnel experiences and problems when combining PSP and VMD are presented, as are suggestions for future developments in combined PSP and deformation measurements.
Evaluation of a data fusion approach to estimate daily PM{sub 2.5} levels in North China
PM{sub 2.5} air pollution has been a growing concern worldwide. Previous studies have conducted several techniques to estimate PM{sub 2.5} exposure spatiotemporally in China, but all these have limitations. This study was to develop a data fusion approach and compare it with kriging and Chemistry Module. Two techniques were applied to create daily spatial cover of PM{sub 2.5} in grid cells with a resolution of 10 km in North China in 2013, respectively, which was kriging with an external drift (KED) and Weather Research and Forecast Model with Chemistry Module (WRF-Chem). A data fusion technique was developed by fusing PM{sub 2.5} concentration predicted by KED and WRF-Chem, accounting for the distance from the central of grid cell to the nearest ground observations and daily spatial correlations between WRF-Chem and observations. Model performances were evaluated by comparing them with ground observations and the spatial prediction errors. KED and data fusion performed better at monitoring sites with a daily model R{sup 2} of 0.95 and 0.94, respectively and PM{sub 2.5} was overestimated by WRF-Chem (R{sup 2}=0.51). KED and data fusion performed better around the ground monitors, WRF-Chem performed relative worse with high prediction errors in the central of study domain. In our study, both KED and data fusion technique provided highly accurate PM{sub 2.5}. Current monitoring network in North China was dense enough to provide a reliable PM{sub 2.5} prediction by interpolation technique. - Highlights: • KED and data fusion model predicted daily PM{sub 2.5} with high accuracy. • WRF-Chem performed worse in PM{sub 2.5} prediction compared with KED and data fusion. • The PM{sub 2.5} monitoring network in North China was able to support reliable PM{sub 2.5} interpolation.
Knowing our Sun: data fusion for optimizing space weather forecasts
Outline: Space weather: model for predicting solar wind & polarity; Particle filtering: optimization with Monte Carlo; Simulation & observation: twin tests and real data; Back to Earth: independent work in inertial confinement fusion (ICF)