SEARCH · Engineering Papers
Results for “Learning”
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.
Lessons learned and best practices derived from environmental monitoring at a large-scale CO2 injection project
Not Available
A novel machine learning and deep learning semi-supervised approach for automatic detection of InSAR-based deformation hotspots
Not Available
Learning constitutive relations from indirect observations using deep neural networks
Not provided.
Prediction of yield surface of single crystal copper from discrete dislocation dynamics and geometric learning
Not provided.
Stochastic gradient based extreme learning machines for stable online learning of advanced combustion engines
Not Available
Estimating regional effects of climate change and altered land use on biosphere carbon fluxes using distributed time delay neural networks with Bayesian regularized learning
Not Available
Methodology and performance comparison of statistical learning pulse shape classifiers as demonstrated with organic liquid scintillator [Performance comparison of statistical learning pulse shape classifiers]
In this study, we present novel methods for automated pulse shape discrimination. The classifiers are trained using simple radionuclide sources and do not require ground truth labeling. We test their performance using labels derived from time of flight experiments and present the results in terms of energy-dependent Receiver Operating Characteristic (ROC) curves. In addition, we also train and test standard pulse shape discrimination methods on the same data for comparison. We find multiple methods that can yield similar false neutron and true neutron rates at 24 keVee as tail-to-total or Gatti’s optimal linear filter yield at 54 keVee.
Evaluation of ASR in concrete using acoustic emission and deep learning
Not provided.
Lessons for machine learning from the analysis of porosity-permeability transforms for carbonate reservoirs
Not provided.
What can we learn from in-soil imaging of a live plant: X-ray Computed Tomography and 3D numerical simulation of root-soil system
Plant roots play a critical role in plant-soil-microbe interactions that occur in the rhizosphere, as well as processes with important implications to farming, forest management and climate change. X-ray computed tomography (XCT) has been proven to be an effective tool for non-invasive root imaging and analysis. A combination of XCT, open-source software, and our own code was used to noninvasively image a prairie dropseed (Sporobolus heterolepis) specimen, segment the root data to obtain a 3D image of the root structure at 31µm resolution, and extract quantitative information (root volume and surface area) from the 3D data, respectively. Based on the mesh generated from the root structure, computational fluid dynamics (CFD) simulations were applied to numerically investigate the root-soil-groundwater system. The plant root conductivity, soil hydraulic conductivity and transpiration rate were shown to control the groundwater distribution. The flow variability and soil water distributions under different scenarios were investigated. Parameterizations were evaluated to show their impacts on the average conductivity. The pore-scale modeling approach provides realistic simulations of rhizosphere flow processes and provides useful information that can be linked to upscaled models.
Identifying flow defects in amorphous alloys using machine learning outlier detection methods
Not provided.
Opening the Black Box: Interpretable Machine Learning for Geneticists
Not provided.