Efficient Reconstruction of Resonant Cavity Fields from Sparse Sensor Data
Explore the source record for details and available documents.
SEARCH · Engineering Papers
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.
Explore the source record for details and available documents.
Explore the source record for details and available documents.
Abstract not provided.
Abstract not provided.
As new loads such as rooftop photovoltaics, electric vehicles and other distributed energy resources become commonplace on the distribution grid, the stress on already aging assets begins to escalate. This increased loading and changing dynamics can exacerbate failure rates. While traditional monitoring efforts focus on transmission and generation assets, utilities are now beginning to pay close attention to distribution assets in order to increase reliability indices and reduce cost from unexpected outages. This research develops low-cost and scalable methods to monitoring the health of a critical distribution grid asset: the service transformer. Existing methods in literature are either invasive and thus difficult to implement or require the device to be tested offline in an expensive lab setting. Data from the ubiquitous smart meter as well as a novel Bluetooth based transformer monitor are leveraged to automatically notify the utility of deteriorating or damaged transformers. Voltage, temperature, and vibration are some of the signals measured and analyzed by the proposed algorithms to predict transformer failures. Furthermore, these algorithms are designed to keep the implementation and processing costs low by taking advantage of edge computing where possible.
Explore the source record for details and available documents.
Powerpoint presentation for project update.
Explore the source record for details and available documents.
This presentation is for the paper INL/CON-22-65800
Explore the source record for details and available documents.
Sensor data proving the technical and economic feasibility of utilizing the available unused heat to generate additional electric power from a binary power plant from the low-temperature brine at the Dixie Valley Geothermal Power Plant. Monthly data for Jan 2013 - October 7 2013
Sensor (or Data) fusion is the process of integrating multiple data sources to produce more consistent, accurate and comprehensive information than is provided by a single data source. Sensor fusion may also be used to combine multiple signals from a single modality to improve the performance of a particular inspection technique. Industrial nondestructive testing may utilize multiple sensors to acquire inspection data depending upon the object under inspection and the anticipated types of defects that can be identified. Sensor fusion can be performed at various levels of signal abstraction with each having its strengths and weaknesses. A multimodal data fusion strategy first proposed by Heideklang and Shokouhi that combines spatially scattered detection locations to improve detection performance of surface-breaking and near-surface cracks in ferromagnetic metals is shown using a surface inspection example and is then extended for volumetric inspections. Utilizing data acquired from an Olympus Omniscan MX2 from both phased array eddy current and ultrasound probes on test phantoms, single and multilevel fusion techniques are employed to integrate signals from the two modalities. Preliminary results demonstrate how confidence in defect identification and interpretation benefit from sensor fusion techniques. Lastly, techniques for integrating data into radiographic and volumetric imagery from computed tomography are described and results are presented.
This dataset supports a broader study examining the drivers of temporal variability in sediment respiration rates in the Yakima River Basin. The dataset provides periodic (weekly or biweekly) in situ hydrological and water chemistry sensor data, handheld sensor water chemistry data, general environmental context photos, and field metadata collected at six sites within multiple rivers in the Yakima River Basin in Washington, USA. In addition to the sensor data, there are plots of continuous in situ sensor data and R scripts used to generate the plots. Related sample-based water chemistry data are published separately at https://data.ess-dive.lbl.gov/datasets/doi:10.15485/1898912.The data package was originally published in September 2022. It was updated in June 2025 (v2; modified files). See the change history section in the readme for more details. For details on how to navigate data packages generated by this project, see https://data.ess-dive.lbl.gov/portals/PNNLRiverCorridorSFA/About. This dataset is comprised of one main data folder containing two sensor-specific subfolders, and one photographs folder. The main data folder includes file-level metadata (flmd), data dictionary (dd), installation methods, field metadata, handheld sensor data, field data collection protocols, international generic sample number (IGSN) mapping file, and a readme file. Each sensor subfolder (BarotrollAtm and MantaRiverData) contains a subfolder containing sensor timeseries data and plots. The BarotrollAtm Data subfolder contains In Situ Rugged BaroTROLL sensor pressure and air temperature data. The MantaRiverData subfolder contains Eureka Manta+ 35B multisonde temperature, specific conductance, and turbidity. The FieldPhotos folder contains environmental context photographs and videos. All files are .csv, .pdf, .R, .jpg, .jpeg, .heic, .mov, or .mp4.
High temperature gas sensors have been highly demanded for combustion process optimization and toxic emissions control, which usually suffer from poor selectivity. In order to solve this selectivity issue and identify unknown reducing gas species (CO, CH 4 , and CH 8 ) and concentrations, a high temperature resistive sensor array data set was built in this study based on 5 reported sensors. As each sensor showed specific responses towards different types of reducing gas with certain concentrations, based on which calibration curves were fitted, providing benchmark sensor array response database, then Bayesian inference framework was utilized to process the sensor array data and build a sample selection program to simultaneously identify gas species and concentration, by formulating proper likelihood between input measured sensor array response pattern of an unknown gas and each sampled sensor array response pattern in benchmark database. This algorithm shows good robustness which can accurately identify gas species and predict gas concentration with a small error of less than 10% based on limited amount of experiment data. These features indicate that Bayesian probabilistic approach is a simple and efficient way to process sensor array data, which can significantly reduce the required computational overhead and training data.
This dataset supports a broader study examining the drivers of temporal variability in sediment respiration rates in the Yakima River Basin. The dataset provides periodic (bi-weekly or monthly) in situ hydrological and water chemistry sensor data, handheld sensor water chemistry data, general environmental context photos, and field metadata collected at six sites across the Yakima River Basin in Washington, USA. Sample and sensor data from previous years (2021-2022) can be found at https://data.ess-dive.lbl.gov/datasets/doi:10.15485/1898912 and https://data.ess-dive.lbl.gov/datasets/doi:10.15485/1892054, respectively. Related sample data from 2022-2024 are available at https://data.ess-dive.lbl.gov/datasets/doi:10.15485/2562910. For details on how to navigate data packages generated by this project, see https://data.ess-dive.lbl.gov/portals/PNNLRiverCorridorSFA/About. In addition to a readme, this data package also includes a file-level metadata (FLMD) file that describes each file and a data dictionary (DD) that describes all column/row headers and variable definitions This dataset contains a folder of environmental context photographs and videos and (1) file-level metadata; (2) data dictionary; (3) readme; (4) field metadata; (5) field protocols; (6) international generic sample number (IGSN) mapping file; (7) handheld sensor data; and (8) two sensor subfolders. Each sensor subfolder (BarotrollAtm and MantaRiverData) contains a subfolder containing sensor time series data and plots. The BarotrollAtm Data subfolder contains In Situ Rugged BaroTROLL sensor pressure and air temperature data. The MantaRiverData subfolder contains Eureka Manta+ 35B multisonde temperature, specific conductance, and chlorophyll A. All files are .csv, .pdf, .jpg, .jpeg, .mp4, .png, or .mov.
Abstract Machine learning (ML) methods applied in scientific research often deal with interrelated features in high‐dimensional data. Reducing data noise and redundancy is needed to increase prediction accuracy and efficiency especially when dealing with data from field sensors. We explored an unsupervised learning method, the denoising autoencoder (DAE), to extract the underlying data structure from noisy raw data in the context of predicting hydrologic quantities from multiple field sensors. These sensors have intrinsic instrumental noise and occasional malfunctions that cause missing values. Our DAE neural network reconstructed meteorological sensor data containing noise and missing values to predict evapotranspiration in a mountainous watershed. The DAE reconstructed the sensor variables with a mean coefficient of determination value of 0.77 across 15 dimensions representing individual sensors. It reduced variance and bias uncertainties compared to a classical autoencoder model. The reconstruction quality varied across dimensions depending on their cross‐correlation and alignment with the underlying data structure. Uncertainties arising from the model structure were overall higher than those resulting from data corruption. We attached the DAE structure to a downstream ET‐prediction neural network in three formats and achieved reasonably accurate ET predictions . The use of the DAE notably reduced variance uncertainty in ET prediction. However, excessive variance reduction may be accompanied by an increase in bias due to the intrinsic bias‐variance tradeoff. Our method of evaluating and reducing uncertainties in aggregated data from different sources can be used to improve predictive models, process understanding, and uncertainty quantification for better water resource management. Plain Language Summary We present a machine learning method, namely the denoising autoencoder, which reduces the effects of data noise and missing values typically present in scientific data sets collected through sensor measurements. This method selects the most relevant information from noisy raw data collected by the instruments and fills in missing values. To demonstrate the effectiveness of our method, we applied it to predict evapotranspiration, a hydrologic variable that represents the water moved from the land surface to the atmosphere through a combination of evaporation and plant water use (transpiration). We also used a random sampling technique (the Monte Carlo method) to compare the uncertainty in the predictions when using the raw and noisy data versus the reconstructed data. The denoising process produced more accurate predictions of evapotranspiration with less uncertainty. Improved predictions of evapotranspiration can lead to a better understanding and accounting of water budgets. This ML approach is broadly suitable for a wide variety of applications that involve noisy sensor data with missing values. Key Points We used a denoising autoencoder (DAE) neural network to reduce noise in meteorological and soil sensor observations by on average We used Monte Carlo sampling to estimate the bias and variance of all model outputs, including uncertainty sources from data and the model We attached the DAE component to a downstream neural network to predict ET with the variance reduced by , compared to that without the DAE
This data package includes data and scripts from the manuscript “Denoising autoencoder for reconstructing sensor observation data and predicting evapotranspiration: noisy and missing values repair and uncertainty quantification”.The study addressed common challenges faced in environmental sensing and modeling, including uncertain input data, missing sensor observations, and high-dimensional datasets with interrelated but redundant variables. Point-scaled meteorological and soil sensor observations were perturbed with noises and missing values, and denoising autoencoder (DAE) neural networks were developed to reconstruct the perturbed data and further predict evapotranspiration. This study concluded that (1) the reconstruction quality of each variable depends on its cross-correlation and alignment to the underlying data structure, (2) uncertainties from the models were overall stronger than those from the data corruption, and (3) there was a tradeoff between reducing bias and reducing variance when evaluating the uncertainty of the machine learning models.This package includes:(1) Four ipython scripts (.ipynb): “DAE_train.ipynb” trains and evaluates DAE neural networks, “DAE_predict.ipynb” makes predictions from the trained DAE models, “ET_train.ipynb” trains and evaluates ET prediction neural networks, and “ET_predict.ipynb” makes predictions from trained ET models.(2) One python file (.py): “methods.py” includes all user-defined functions and python codes used in the ipython scripts.(3) A “sub_models” folder that includes five trained DAE neural networks (in pytorch format, .pt), which could be used to ingest input data before being fed to the downstream ET models in ‘ET_train.ipynb” or ‘ET_predict.ipynb’.(4) Two data files (.csv). Daily meteorological, vegetation, and soil data is in “df_data.csv”, where “df_meta.csv” contains the location and time information of “df_data.csv”. Each row (index) in “df_meta.csv” corresponds to each row in “df_data.csv”. These data files are formatted to follow the data structure requirements and be directly used in the ipython scripts, and they have been shuffled chronologically to train machine learning models. The meteorological and soil data was collected using point sensors between 2019-2023 at(4.a) Three shrub-dominated field sites in East River, Colorado (named “ph1”, “ph2” and “sg5” in “df_meta.csv”, where “ph1” and “ph2” were located at PumpHouse Hillslopes, and “sg5” was at Snodgrass Mountain meadow) and(4.b) One outdoor, mesoscale, and herbaceous-dominated experiment in Berkeley, California (named “tb” in “df_meta.csv”, short for Smartsoils Testbed at Lawrence Berkeley National Lab).- See "df_data_dd.csv" and "df_meta_dd.csv" for variable descriptions and the Methods section for additional data processing steps. See "flmd.csv" and "README.txt" for brief file descriptions.- All ipython scripts and python files are written in and require PYTHON language software.