Distance Learning LDRD: Using Latent Deep Learning Distances to Create Trusted Models
An overview of some results from our first year of analyses.
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.
An overview of some results from our first year of analyses.
Executive Summary The energy development assumptions identified in the Department of Energy's position paper, 20% Wind Energy by 2030, projected an exploding demand for wind energy-related workforce development. These primary assumptions drove a secondary set of assumptions that early stage wind industry workforce development and training paradigms would need to undergo significant change if the workforce needs were to be met. The current training practice and culture within the wind industry is driven by a relatively small number of experts with deep field experience and knowledge. The current training methodology is dominated by face-to-face, classroom based, instructor present training. Given these assumptions and learning paradigms, the purpose of the National Wind Distance Learning Collaborative was to determine the feasibility of developing online learning strategies and products focused on training wind technicians. The initial project scope centered on (1) identifying resources that would be needed for development of subject matter and course design/delivery strategies for industry-based (non-academic) training, and (2) development of an appropriate Learning Management System (LMS). As the project unfolded, the initial scope was expanded to include development of learning products and the addition of an academic-based training partner. The core partners included two training entities, industry-based Airstreams Renewables and academic-based Lake Area Technical Institute. A third partner, Vision Video Interactive, Inc. provided technology-based learning platforms (hardware and software).
The results of DOE Solar Energy Technologies Office project 34233 are presented. The newest version of IEEE Standard 1547 enables photovoltaic inverters to ride through voltage disturbances, improving bulk system reliability, at the expense of removing undervoltage trip as a fast method of de facto fault detection in high PV adoption scenarios. The project explored new methods of fault detection that don't rely on communication systems and could be available quickly, including distance-based schemes, focused directional relays, and two different data-driven schemes. The schemes were evaluated with fast-phasor simulation, electromagnetic transient simulation, and field data collection at partner utilities Chattanooga Electric Power Board and Dominion Energy Virginia. Accomplishments and possible paths forward are summarized.
Explore the source record for details and available documents.
Explore the source record for details and available documents.
Abstract Substantial progresses in protein structure prediction have been made by utilizing deep‐learning and residue‐residue distance prediction since CASP13. Inspired by the advances, we improve our CASP14 MULTICOM protein structure prediction system by incorporating three new components: (a) a new deep learning‐based protein inter‐residue distance predictor to improve template‐free (ab initio) tertiary structure prediction, (b) an enhanced template‐based tertiary structure prediction method, and (c) distance‐based model quality assessment methods empowered by deep learning. In the 2020 CASP14 experiment, MULTICOM predictor was ranked seventh out of 146 predictors in tertiary structure prediction and ranked third out of 136 predictors in inter‐domain structure prediction. The results demonstrate that the template‐free modeling based on deep learning and residue‐residue distance prediction can predict the correct topology for almost all template‐based modeling targets and a majority of hard targets (template‐free targets or targets whose templates cannot be recognized), which is a significant improvement over the CASP13 MULTICOM predictor. Moreover, the template‐free modeling performs better than the template‐based modeling on not only hard targets but also the targets that have homologous templates. The performance of the template‐free modeling largely depends on the accuracy of distance prediction closely related to the quality of multiple sequence alignments. The structural model quality assessment works well on targets for which enough good models can be predicted, but it may perform poorly when only a few good models are predicted for a hard target and the distribution of model quality scores is highly skewed. MULTICOM is available at https://github.com/jianlin-cheng/MULTICOM_Human_CASP14/tree/CASP14_DeepRank3 and https://github.com/multicom-toolbox/multicom/tree/multicom_v2.0 .
Pre-emptive school closures are frontline community mitigation measures recommended by the US Centers for Disease Control and Prevention (CDC) for implementation during severe pandemics. This study describes the spatiotemporal patterns of publicly announced school closures implemented in response to the coronavirus disease 2019 (COVID-19) pandemic and assesses how public K-12 districts adjusted their methods of education delivery and provision of subsidized meals. During February 18–June 30, 2020, we used daily systematic media searches to identify publicly announced COVID-19–related school closures lasting ≥1 day in the United States (US). We also collected statewide school closure policies from state government websites. Data on distance learning and subsidized meal programs were collected from a stratified sample of 600 school districts. The first COVID-19–associated school closure occurred on February 27, 2020 in Washington state. By March 30, 2020, all but one US public school districts were closed, representing the first-ever nearly synchronous nationwide closure of public K-12 schools in the US. Approximately 100,000 public schools were closed for ≥8 weeks because of COVID-19, affecting >50 million K-12 students. Of 600 districts sampled, the vast majority offered distance learning (91.0%) and continued provision of subsidized meal programs (78.8%) during the closures. Despite the sudden and prolonged nature of COVID-19–associated school closures, schools demonstrated flexibility by implementing distance learning and alternate methods to continue subsidized meal programs.
Our goal is to teach a robot to walk in an energy efficient way. Inspired by nature [1], we create a reinforcement learning method that balances distance traveled and energy consumption, which we call “utility.” Further, each step is symmetric to ensure equal strides while walking straight. We achieve our goal by rewarding decisions that lead to the best utility over several training iterations.
A progress report is provided.
Protein structure prediction is an important problem in bioinformatics and has been studied for decades. However, there are still few open-source comprehensive protein structure prediction packages publicly available in the field. In this paper, we present our latest open-source protein tertiary structure prediction system—MULTICOM2, an integration of template-based modeling (TBM) and template-free modeling (FM) methods. The template-based modeling uses sequence alignment tools with deep multiple sequence alignments to search for structural templates, which are much faster and more accurate than MULTICOM1. The template-free (ab initio or de novo) modeling uses the inter-residue distances predicted by DeepDist to reconstruct tertiary structure models without using any known structure as template. In the blind CASP14 experiment, the average TM-score of the models predicted by our server predictor based on the MULTICOM2 system is 0.720 for 58 TBM (regular) domains and 0.514 for 38 FM and FM/TBM (hard) domains, indicating that MULTICOM2 is capable of predicting good tertiary structures across the board. It can predict the correct fold for 76 CASP14 domains (95% regular domains and 55% hard domains) if only one prediction is made for a domain. The success rate is increased to 3% for both regular and hard domains if five predictions are made per domain. Moreover, the prediction accuracy of the pure template-free structure modeling method on both TBM and FM targets is very close to the combination of template-based and template-free modeling methods. This demonstrates that the distance-based template-free modeling method powered by deep learning can largely replace the traditional template-based modeling method even on TBM targets that TBM methods used to dominate and therefore provides a uniform structure modeling approach to any protein. Finally, on the 38 CASP14 FM and FM/TBM hard domains, MULTICOM2 server predictors (MULTICOM-HYBRID, MULTICOM-DEEP, MULTICOM-DIST) were ranked among the top 20 automated server predictors in the CASP14 experiment. After combining multiple predictors from the same research group as one entry, MULTICOM-HYBRID was ranked no. 5. The source code of MULTICOM2 is freely available at https://github.com/multicom-toolbox/multicom/tree/multicom_v2.0 .
Abstract Motivation Accurate prediction of residue–residue distances is important for protein structure prediction. We developed several protein distance predictors based on a deep learning distance prediction method and blindly tested them in the 14th Critical Assessment of Protein Structure Prediction (CASP14). The prediction method uses deep residual neural networks with the channel-wise attention mechanism to classify the distance between every two residues into multiple distance intervals. The input features for the deep learning method include co-evolutionary features as well as other sequence-based features derived from multiple sequence alignments (MSAs). Three alignment methods are used with multiple protein sequence/profile databases to generate MSAs for input feature generation. Based on different configurations and training strategies of the deep learning method, five MULTICOM distance predictors were created to participate in the CASP14 experiment. Results Benchmarked on 37 hard CASP14 domains, the best performing MULTICOM predictor is ranked 5th out of 30 automated CASP14 distance prediction servers in terms of precision of top L/5 long-range contact predictions [i.e. classifying distances between two residues into two categories: in contact (<8 Angstrom) and not in contact otherwise] and performs better than the best CASP13 distance prediction method. The best performing MULTICOM predictor is also ranked 6th among automated server predictors in classifying inter-residue distances into 10 distance intervals defined by CASP14 according to the precision of distance classification. The results show that the quality and depth of MSAs depend on alignment methods and sequence databases and have a significant impact on the accuracy of distance prediction. Using larger training datasets and multiple complementary features improves prediction accuracy. However, the number of effective sequences in MSAs is only a weak indicator of the quality of MSAs and the accuracy of predicted distance maps. In contrast, there is a strong correlation between the accuracy of contact/distance predictions and the average probability of the predicted contacts, which can therefore be more effectively used to estimate the confidence of distance predictions and select predicted distance maps. Availability and implementation The software package, source code and data of DeepDist2 are freely available at https://github.com/multicom-toolbox/deepdist and https://zenodo.org/record/4712084#.YIIM13VKhQM. Supplementary information Supplementary data are available at Bioinformatics online.
1) How the project adds to the education of engineering students in the area of vehicle electrification: This project created and implemented a significant interdisciplinary curriculum in HEV engineering that includes courses focused on the major components (engines, battery cells, e-machines, and power electronics). The new curriculum, rather uniquely, features two new classes and two new labs that emphasize a vehicle level integration of a hybrid electric powertrain that parallels the vehicle development process used by the OEMs - commercial grade software is used to design a hybrid electric vehicle, hardware-in-the-loop testing is performed on each component until the entire powertrain is optimized, the calibration is flashed to a vehicle, ride-and-drives are executed including on board data acquisition. In addition, nine existing courses were modified by adding HEV material to the courses. 2) The educational effectiveness and economic feasibility of the new curriculum: The new courses are offered at both the undergraduate and graduate levels. They are listed across the college in mechanical, chemical, electrical, and materials science and engineering. They are offered both on campus and to distance learning students. Students across the college of engineering and at all degree levels are integrating these courses into their degree programs. Over the three year project the course enrollments on-campus has totaled 1,249. The distance learning enrollments has totaled 315. With such robust enrollments we absolutely expect that these courses will be in the curriculum for the long run. 3) How the project is otherwise of benefit to the public: One outcome of the project is the construction of the Michigan Tech Mobile Lab. Two complete HEV dynamometer test cells, and four work stations are installed in the 16.2 meter Mobile Laboratory and hauled by a class 8 truck. The Mobile Lab is used to teach the university courses. It is also used to deliver short courses to industry, K-12 outreach, and public education. In 2012 the Mobile Lab participated in 22 outreach events, locally, throughout Michigan, and including events in Washington DC, Illinois, and Wisconsin. The Mobile Lab is a hit wherever it goes. In 2013 we will partner with the US Army TARDEC and be featured in their Green Warrior Convoy, a ten city tour starting in Detroit and finishing in Washington DC.
Crystallographic representations and machine learning predict inorganic synthesis conditions for arbitrary zeolites, as validated with literature-mined data.
Faith is located in the northeast corner of Meade County South Dakota. The economy is agricultural; principally large cattle operations on sizeable ranches. As with most rural communities, the economy is under pressure with inadequate taxes and few economic development opportunities. In 2004 the single school house, constructed in the early 1900s, was condemned by the state fire marshal. The school serves K-12 and the school board had to locate, acquire and install modular trailers to support the children; population about 200. The state has not, and will not, provide funds to construct a new school as the political agenda is to focus on higher education. While a new school is being constructed, the Fox Ridge participants believe that the new school provides less than optimum services and facilities for the students. Fox Ridge Energy and Educational Institute has dedicated significant development funds and time in attempting to expand the public education system through the proceeds of this wind farm A group of concerned citizens formed a 501C-3 tax exempt entity to examine methods of obtaining the capital to increase the capabilities of the school. In considering the resources available to the community, it was clear that the wind resource was excellent and with the continuing growth of the commercial wind industry, the group focused on wind energy as the primary opportunity to create a successful economic enterprise. The group lobbied for and received an ear mark from Congress in 2005 for $\$$500,000 to conduct feasibility and project development studies for the project. Matching funds of $\$$125,000 were required, which were raised locally along with an additional $\$$700,000. The community has provided additional support letters. Affected landowners also supported Fox Ridge. Three (3) fifty meter anemometers were installed in September 2005. Planning began for finance structures that would provide the targeted funds for the construction of a LEED certified school of about $\$$20 million. Further, the group has a goal of obtaining about $\$$2 million per year to support the operation of the school, including increased pay for teachers and restoration of educational programs which had to be reduced. The Faith School currently remains accredited through the use of distance learning for some of its core classes. The group has requested that Dale Osborn, Manager of Disgen Holdings, LLC (Disgen), an experienced wind energy developer, provide assistance in this opportunity. Osborn has agreed and is the author of this paper.
The promotional presentation discusses the graduate degree program at the University of California, San Diego, Jacobs School of Engineering, related to structural engineering. Structural Health Monitoring (SHM) encompasses the integration of a broad range of technologies from sensing/actuating, data interrogation, and statistical modeling to enable system-level or component-level health assessment and predictive modeling. The course is available via distance learning to Los Alamos National Laboratory engineers.
In a concerted effort supported by the National Science Foundation, the Department of Commerce, and the Department of Energy, the United States is rebuilding its leadership in neutron scattering capability through a significant investment in U.S. neutron scattering user facilities and related instrumentation. These unique facilities provide opportunities in neutron scattering to a broad community of researchers from academic institutions, federal laboratories, and industry. However, neutron scattering is often considered to be a tool for 'experts only' and in order for the U.S. research community to take full advantage of these new and powerful tools, a comprehensive education and outreach program must be developed. The workshop described below is the first step in developing a national program that takes full advantage of modern education methods and leverages the existing educational capacity at universities and national facilities. During March 27-28, 2008, a workshop entitled 'Building a Network for Neutron Scattering Education' was held in Washington, D.C. The goal of the workshop was to define and design a roadmap for a comprehensive neutron scattering education program in the United States. Successful implementation of the roadmap will maximize the national intellectual capital in neutron sciences and will increase the sophistication of research questions addressed by neutron scattering at the nation's forefront facilities. (See Appendix A for the list of attendees, Appendix B for the workshop agenda, Appendix C for a list of references. Appendix D contains the results of a survey given at the workshop; Appendix E contains summaries of the contributed talks.) The workshop brought together U.S. academicians, representatives from neutron sources, scientists who have developed nontraditional educational programs, educational specialists, and managers from government agencies to create a national structure for providing ongoing neutron scattering education. A concerted effort was made to involve representatives from historically black colleges and universities (HBCUs) and minority educational institutions (MEIs). The roadmap contained herein provides the path to a national infrastructure for education of students, faculty, and professional researchers who wish to make use of national neutron scattering facilities but do not have (or do not believe they have) the educational background to do so. Education of other stakeholders, including the public, students in kindergarten through twelfth grade (K-12), and policy makers is also included. The opening sessions of the workshop provided the current status of neutron scattering education in North America, Europe, and Australia. National neutron sources have individually developed outreach and advertising programs aimed at increasing awareness among researchers of the potential applications of neutron scattering. However, because their principal mission is to carry out scientific research, their outreach efforts are necessarily self-limiting. The opening session was designed to build awareness that the individual programs need to be coupled with, and integrated into, a broader education program that addresses the complete range of experience, from the student to the experienced researcher, and the wide range of scientific disciplines covered by neutron scattering. Such a program must also take full advantage of existing educational programs and expertise at universities and expand them using modern distance learning capabilities, recognizing that the landscape of education is changing.