Search NASA⌕ Search

Engineering topics

Yarbrough, John

Publications and source records attributed to Yarbrough, John.

10 records
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

An AI-Based 3D Bat Movement Tracking System at Wind Energy Facilities Using Multi-Thermal Video Cameras

The poster at the 15th Wind Wildlife Research Meeting discusses how to leverage the potential of real-time thermal-imaging methodologies in quantifying nocturnal bat activities at wind turbines, using 3D computer vision techniques within a deep learning framework. This innovation enables the automatic detection and classification of bats, birds, and insects in thermal-imaging videos captured at wind turbine sites, facilitating efficient and accurate data analysis for enhanced understanding and mitigation of bat-wind turbine interactions.

AI↗
DOE OSTI2024

WEBAT (Wind Energy with Bat AI-based Tracker) [SWR-24-121]

The WEBAT (Wind Energy with Bat AI-based Tracker) is a Python-based bat tracking software, integrating machine learning and computer vision with infrared thermal sensors to enhance the monitoring and protection of bats in proximity to wind turbines.

Ryu, Sora [National Renewable Energy Laboratory (N↗
DOE OSTI2024

Revolutionizing Waste Management: AI-Powered Real-Time Characterization for Efficient Handling of Non-Recyclable Municipal Solid Waste

According to EPA, -300 MM tons of municipal solid waste (MSW) was available in the US as of 2018. Of that total material, nearly 50% was landfilled resulting in a significant loss for the potential to convert its energy value into cost effective and sustainable biofuels. Redirecting this material away from the landfill and into conversion ready feedstock for energy generation can directly address DOE's selling price < $2.50/GGE while securing the US national energy independence [1]. However, the paramount challenges in any rational fuel conversion strategy are understanding the chemical makeup, quality and associated calorific value of the MSW. Understanding these parameters is critical in achieving any acceptable fuel conversion and requires rapid characterization followed by accurate separation technologies. Therefore, we are proposing to address the rapid characterization by building a non-invasive, rapid, and highly accurate Artificial Intelligence (AI)-enabled spectrometric/optical approach augmented with multi-sensory information for advanced characterization of domestic heterogeneous MSW. North Carolina State University (NCSU) and the National Renewable Energy Laboratory (NREL), in partnership with strong support from the Town of Cary and IBM, Inc., will closely work together to implement this ground-breaking technology for the effective characterization of MSW for sustainable and affordable production of conversion-ready feedstocks, while solving the environment issue of planetary proportions.

artificial intelligence↗
DOE OSTI2022

BFSVBF (BatFinder Smart Video BioFilter) [SWR-22-87] and Multi-class BatFinder Smart Video BioFilter Keras

Bats are notoriously difficult to study, therefore, identifying specific behavioral trends and the precise environmental conditions at the time of collision requires a monitoring solution that can reliably collect relevant data. To date, thermal infrared video surveillance has been extensively applied to study bats and has proven to be a powerful yet cumbersome tool. Current analytical approaches are time consuming because data processing data has not been fully automated. In the past, steps have been taken to record avian and bat activity in conjunction with complicated image processing techniques that separate species from other moving objects within the field of view (i.e. clouds and portions of the wind turbine). Once the videos are collected, the post-processing does not allow real time monitoring and identification, leading to a delay in both studying the behavior of these species and determining the effectiveness of any impact reduction strategy being studied. Moreover, object identification capability is lacking, thus limiting the usefulness of video data. To resolve these issues, we are using open source computer vision and machine learning techniques allowing for automatic detection of objects in real-time with the ability to correlate these objects with environmental variables and recording the flight paths of each object. The code has gone through five rounds of development with images used to train the models. This advancement allows for automated real-time data collection, identification, and tracking, thereby eliminating the need for long and tedious post-analysis processing of the videos. We will discuss the two open source and publicly available machine learning models developed within this scope of this work: 1) a binary model with a 97.5% accuracy in identifying the difference between an object and an empty scene, including wind turbine and clouds; and 2) a multiple classification model with the capability of identifying the type of object detected: bats (90% accuracy), birds (83% accuracy), insects (69% accuracy) and non-biological (99% accuracy).

Yarbrough, John↗
DOE OSTI2022

3DBFSVBF (3D BatFinder Smart Video BioFilter and Multi-class BatFinder Smart Video BioFilter) [SWR-22-88]

Bats are notoriously difficult to study, therefore, identifying specific behavioral trends and the precise environmental conditions at the time of collision requires a monitoring solution that can reliably collect relevant data. To date, thermal infrared video surveillance has been extensively applied to study bats and has proven to be a powerful yet cumbersome tool. Current analytical approaches are time consuming because data processing data has not been fully automated. In the past, steps have been taken to record avian and bat activity in conjunction with complicated image processing techniques that separate species from other moving objects within the field of view (i.e. clouds and portions of the wind turbine). Once the videos are collected, the post-processing does not allow real time monitoring and identification, leading to a delay in both studying the behavior of these species and determining the effectiveness of any impact reduction strategy being studied. Moreover, object identification capability is lacking, thus limiting the usefulness of video data. To resolve these issues, we are using open source 3D computer vision and machine learning techniques allowing for automatic detection of objects in real-time with the ability to correlate these objects with environmental variables and recording the flight paths of each object. The machine learning has been trained on 3D data and allows for automated real-time data collection, identification and tracking, thereby eliminating the need for long and tedious post-analysis processing of the videos. This machine learning model is an added feature to the previous BatFinder Smart Video BioFilter and increases the accuracy of that systems classification by increasing the accuracy of identifying bats (90% accuracy) and insects (69% accuracy) to a 97% accuracy. There are two object classifier machine learning models, Binary and multi-classification. Binary object classifier labeled BatFinder_Smart_Video_BioFilter.h5 distinguishes between biological objects and non-biological objects. The main goal of this object classifier is to ignore the turbine blades while detecting biological object flying withing the rotor swept area of the turbine. Non-biological objects have a probability of 0 and biological objects have a probability of 1. Multi-classifier labeled Multiclass_BatFinder_Smart_Video_BioFilter.h5 distinguishes between bats, birds, insects and non-biological.

Yarbrough, John↗
DOE OSTI2022

Leveraging Super High Optical Resolution Microscopy to Probe the Interaction Zone Between Clostridium thermocellum and Biomass

This poster, part of the Pacific Northwest National Laboratory-sponsored Integration 2020: Visualizing the Proteome virtual conference, discusses super high optical resolution microscopy to probe the interaction zone between Clostritium thermocellum and biomass. Clostridium thermocellum is one of the most efficient microorganisms for the deconstruction of biomass. To achieve this high level of cellulolytic activity, C. thermocellum uses large multienzyme complexes known as cellulosomes to sugars in 4-5 break down polysaccharides found in plant cell walls. The attachment of bacterial switchgrass 70% cells to the nearby substrate via the cellulosome has been hypothesized to be the reason for this high efficiency. The region lying between the cell and the substrate has shown great variation and dynamics that are affected by the growth stage of cells and the substrate used for growth.

bacteria↗
DOE OSTI2019

CatCost™ (Catalyst Cost Estimation Tool) [SWR-18-74]

CatCost™ is a state-of-the-art cost estimation tool designed to reduce the cost uncertainty associated with pre-commercial catalyst materials. The tool combines industry-standard cost estimation methods and resources into an intuitive suite of tools to bring actionable cost insight to every step of catalyst research and development. CatCost™ allows the rapid development of comprehensive catalyst cost estimates. It incorporates detailed insight into manufacturing methods, especially for pre-commercial catalysts, without requiring any process design experience. The tool has been designed from the ground up with a number of user-selectable estimation methods, pricing libraries, and ease-of-use features to tailor an estimate to a user's skill level and need for customization, empowering researchers of all skill-levels to make better R&D decisions throughout the catalyst development cycle. Our costing methods are fully transparent and enable power-users the ability to adjust any estimate to the economic realities of their operation. The tool has been designed from the ground up with a number of user-selectable estimation methods, pricing libraries, and ease-of-use features to tailor an estimate to a user's skill level and need for customization, empowering researchers of all skill-levels to make better R&D decisions throughout the catalyst development cycle. Our costing methods are fully transparent and enable power-users the ability to adjust any estimate to the economic realities of their operation. Features include: Raw materials pricing: Libraries of common chemicals, cost scaling indices, guidance for obtaining bulk quotes, and methods for extrapolating laboratory-scale prices to bulk. Simplified step method for synthesis by a contract manufacturer: All-in hourly cost for process equipment using methods and data from tollers. (Excel-only in v1.0)

Baddour, Frederick↗
DOE OSTI2012

Spectral Optical Properties of Cu2ZnSnS4 Thin Film Between 0.73 and 6.5 eV

A polycrystalline Cu{sub 2}ZnSnS{sub 4} thin film was deposited on fused quartz by co-evaporation. The selected thickness was {approx}100 nm to avoid artifacts in its optical properties caused by thicker as-grown films. The composition and phase of the film were checked with x-ray fluorescence, Raman shift spectroscopy, scanning transmission electron microscopy, and energy dispersive x-ray spectroscopy. An improved spectroscopic ellipsometry methodology with two-side measurement geometries was applied to extract the complex dielectric function {var_epsilon} = {var_epsilon}{sub 1} + i{var_epsilon}{sub 2} of the Cu{sub 2}ZnSnS{sub 4} thin film between 0.73 and 6.5 eV. Five critical points were observed, at 1.32 (fundamental band gap), 2.92, 3.92, 4.96, and 5.62 eV, respectively. The {var_epsilon} spectra are in reasonable agreement with those from theoretical calculations.

14 SOLAR ENERGY↗