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.
Repository containing all the data necessary to reproduce the paper "Inorganic synthesis-structure maps in zeolites with machine learning and crystallographic distances". This content includes: raw data for all results in the article; figures appearing in the main paper; and Jupyter notebooks and scripts containing the code for analyzing/reproducing the results.
The Deep Lynx Machine Learning (ML) Adapter is a generic adapter that programmatically runs the ML as continuous data is received. Then, Jupyter Notebooks can be customized according to the project for pre-processing the data, building the machine learning models, prediction analysis of incoming data using an existing model, and forecasting anomalies / failures of the physical asset.
This is a repository with the tools developed for predicting energy produced at Open-Source Reservoir (OSR). It includes both simulation data for OSR, as well as Jupyter notebooks for training and evaluating prediction models. OSR was constructed based on the data from Brady Hot Springs reservoir (Nevada, USA) but has a number of sufficiently modified characteristics and does not disclose any sensitive data.
This package contains the code for the paper Combining Deep Learning with Physics Based Features in Explosion-Earthquake Discrimination published at Geophysical Research Letters. There are two Jupyter notebooks, one for building and training the two-branch model, and the other is visualizing the deep learning branch using GradCAM.
The labquake_future_prediction code is a collection of python modules and scripts that serves as supporting information for the article “Predicting future laboratory fault friction through deep learning” for publication in the journal of “Geophysical Research Letters”. It is designed to predict laboratory fault slips in the immediate future by scanning continuous acoustic emission (AE) waveforms recorded in laboratory biaxial shear experiments. The predictions are made with a deep learning model based on convolutional encoder-decoder (CED) models and the Transformer model primarily developed for Natural Language Processing (NLP). The deep learning model is trained with the tensorflow package using publicly available laboratory data sets in standard binary file format in numpy. The utility functions for reading data files, configuring model hyperparameters, constructing the CED and Transformer models, training and testing of the models are defined in python module files. The workflow of training the models for labquake future predictions and the multiple GPU’s rapid model hyperparameter optimization as described in the journal article, are demonstrated in accompanying python script files and Jupyter notebooks.
We would like to disclose two scripts, written in Jupyter notebook, in which we implement the "Blackout Diffusion Process" described in the manuscript "Blackout Diffusion: Generative Diffusion Models in Discrete-State Spaces" (LA-UR-23-20509), to be submitted to the International Conference of Machine Learning (ICML). The abstract of the manuscript is append below. == Typical generative diffusion models rely on a Gaussian diffusion process for training the backward transformations, which can then be used generate samples from Gaussian noise. However, real world data often takes place in discrete-state spaces, which occur in many scientific applications. Here, we develop a theoretical formulation for arbitrary discrete-state Markov processes in the forward diffusion process. We relate the theory to the existing continuous-state Gaussian diffusion and identify the corresponding reverse-time stochastic process and score function in the continuous-time setting, and the reverse-time mapping in the discrete-time setting. As an example of this framework, we introduce "Blackout Diffusion", which learns to produce samples from an empty image instead of from noise. Numerical experiments on the CIFAR-10 dataset confirm the feasibility of generative diffusion modeling in a discrete space. Generalizing from specific (Gaussian) forward processes to a more general framework also sheds light on how to interpret generative diffusion models and their mathematical structure, which we comment on.
The bifacial_radiance software contains a series of Python wrapper functions to make working with RADIANCE easier, particularly for the PV researcher interested in bifacial PV performance. For more information, check out our documentation, Tutorials in the form of Jupyter Notebooks, or refer to our Wiki and Issues page. Installation https://youtu.be/4A9GocfHKyM This video shows how to install the bifacial_radiance software and all associated software needed. More info on the Wiki. Instructions are also shown below. For detailed instructions of how to install bifacial_radiance, you can also refer to the installation guide. A GUI has been added in version 3.0. The GUI reads/writes all input parameters necessary to run a simulation, and runs the specified simulation by calling the correct functions with the specified parameters. So no need to use a journal or a script! But you still need to install following the procedure below.
This software is a suite of Python files and Jupyter notebooks supporting the calculation of cost and financial parameters for the Annual Technology Baseline (ATB) electricity data, including capital expenditures, levelized cost of energy, and debt fractions using the ATB input data.
The Open Energy Data Initiative (OEDI) provides a number of tools to enable the use of the open data published through this initiative. The source is largely written in Python, including Jupyter notebooks. The Open Energy Data Initiative (OEDI) is a partnership between the National Renewable Energy Laboratory (NREL), the U.S. Department of Energy (DOE), Amazon, Microsoft, and Google to provide universal access to big data in the cloud. At the heart of OEDI is a centralized repository of high-value energy research datasets aggregated from DOE Program Offices, National Laboratories and other collaborators.
This repository contains example implementations of phase-field codes primarily for educational purposes. These codes demonstrate how a simple phase-field models can be implemented as an introduction for researchers new to the area (students, new staff, collaborators from different domains, etc.). The computer code includes highly documented Jupyter notebooks that implement phase-field models and analyze the results.
Hnx-widget is a Jupyter notebook widget for visualizing hyper graphs that is intended to work in conjunction with the HyperNetX open source package developed by PNNL. It renders hyper graphs using Euler diagrams (a Venn diagram is a special type of Euler diagram). The tool contains simple interactions that allow the user to select nodes and change their appearance. It scales to small to medium sized (100 node) hyper graphs
A data annotation tool that integrates with the python Jupyter notebook environment.
Jupyter notebooks to reconstruct and visualize microCT data from ALS beamline 8.3.2. Relies on standard tomography and image processing tools (astra, tomopy, itk, scikit-image) and ipywidgets (sliders, drop down menus, etc) to make parameter selection and data visualization easy for users.
This package contains the code for the paper Evaluating Physics Informed Neural Network Performance for Seismic Discrimination Between Earthquake published at Seismological Research Letters. There are one Jupyter notebook and demo data so that the audience can run build a machine learning model with the P/S ratios as a physics loss in addition to the data driven loss.t
Siting Lab contains a collection of user-friendly tutorials and guides for working with the Siting Lab (https://data.openei.org/siting_lab) data within the context of the reV model. The python code examples demonstrate the creation and transformation of Siting Lab data into reV compliant format as well as working with the reV model inputs and outputs. Specifically, Siting Lab provides a collection of Jupyter Notebooks that serve as guides for working with data from NREL's spatial analysis portfolio. These notebooks teach users how to create and interact with reV data in order to facilitate external use of the model. The guides in this repository reference NREL's Supply Curve data as well as Siting Lab spatial data available on OEDI.
The Spallation Neutron Source (SNS) at Oak Ridge National Laboratory (ORNL) provides pulsed neutrons with energies varying from epithermal to cold. In preparation for VENUS, the neutron imaging beamline to be located at beam port 10, we have performed a series of experiments focused on wavelength-dependent radiography and computed tomography for a broad range of applications, from materials science to biological tissues.One of the time-of-flight (TOF) techniques that is of interest to the scientific community is the 2-dimensional mapping of phases and average crystalline plane orientation in samples both ex-situ and during applied stresses such as tensile loading and heating. This technique is known as Bragg edgeimaging and relies on the identification of changes of transmission values, fitting of the edge to measure its displacement, and thus identify the shift in lattice parameter due to stresses. One of the challenges of TOF imaging measurements is the amount of data and the inability to observe Bragg edge shifts in real time during an experiment. Thus, we have been focusing on creating a Python-based interface that allows fast data processing and instantaneous mapping and fitting of the Bragg edges, and their evolution through time. Python libraries and Jupyter notebooks have been implemented to facilitate decision making during an experiment. The advantage of the notebooks is the possibility to guide an experiment as they can quickly process and display Bragg edge data. These notebooks can be used independently, or can be combined in a Python Graphical User Interface (GUI) tool called iBeatles. This interface permits visualization and fitting of the Bragg edges, and ultimately back-projects the fitting results onto the radiographs to display a strain map. Assuming data collection has sufficient statistics, the strain mapping analysis can be performed on a pixel-by-pixel basis. This development is a step forward toward a better user experience at the future VENUS beamline in terms of live feedback and productivity. Analysis that used to take days of switching between different applications can now be done in minutes within the
This code is designed to predict and analyze the decay heat generated in molten salt reactors (MSRs) using a hybrid approach that combines machine learning and segmented polynomial fitting. The accurate prediction of decay heat is essential for reactor safety and the optimization of spent fuel storage. The code operates through several key components: 1) Data Architecture: It incorporates a modular data architecture that handles various MSR-specific operational parameters such as power density, humidity content, and air ingress. These parameters are sampled using Sobol sequences to ensure comprehensive coverage of operational uncertainties. 2) Machine Learning Framework: The code employs a diverse set of machine learning models, including polynomial regression, decision trees, random forests, gradient boosting, support vector regression, k-nearest neighbors, multi-layer perceptrons, and symbolic regression. These models are trained to predict decay heat over a wide temporal range, from immediate shutdown up to 10,000 years. 3) Region-Optimized Training: The temporal domain is divided into multiple regions, each modeled separately to capture distinct decay heat characteristics across different time scales. This approach significantly improves the accuracy and interpretability of predictions. 4) Segmented Polynomial Interpretation (SPI): The SPI method translates machine learning predictions into piecewise polynomial equations. These equations are physically interpretable and can be directly integrated into existing engineering workflows and safety analyses. 5) Front-End Interfaces: The code includes both a Jupyter notebook interface for research development and a Streamlit web application for operational deployment. These interfaces allow users to interactively explore decay heat predictions, adjust operational parameters, and visualize results in real-time. 6) Applications: The framework supports various applications, including safety system validation and spent fuel container optimization. It enables real-time evaluation of worst-case decay heat scenarios, informing the design of passive safety systems and optimizing container designs for long-term storage. Overall, this code provides a robust, accurate, and user-friendly tool for predicting decay heat in MSRs, enhancing reactor safety, and optimizing spent fuel management.
A simple Jupyter notebook program for fitting isothermal compression curves to pressure-versus-volume data.