Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Building Dataset”

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.

At least 685 records · Page 38

Building a landslide hazard indicator with machine learning and land surface models

The U.S. Pacific Northwest has a history of frequent and occasionally deadly landslides caused by various factors. Using a multivariate, machine-learning approach, we combined a Pacific Northwest Landslide Inventory with a 36-year gridded hydrologic dataset from the National Climate Assessment – Land Data Assimilation System to produce a landslide hazard indicator (LHI) on a daily 0.125-degree grid. The LHI identified where and when landslides were most probable over the years 1979–2016, addressing issues of bias and completeness that muddy the analysis of multi-decadal landslide inventories. The seasonal cycle was strong along the west coast, with a peak in the winter, but weaker east of the Cascade Range. This lagging indicator can fill gaps in the observational record to identify the seasonality of landslides over a large spatiotemporal domain and show how landslide hazard has responded to a changing climate.

XGBoost↗

Ig-VAE: Generative modeling of protein structure by direct 3D coordinate generation

While deep learning models have seen increasing applications in protein science, few have been implemented for protein backbone generation—an important task in structure-based problems such as active site and interface design. We present a new approach to building class-specific backbones, using a variational auto-encoder to directly generate the 3D coordinates of immunoglobulins. Our model is torsion- and distance-aware, learns a high-resolution embedding of the dataset, and generates novel, high-quality structures compatible with existing design tools. We show that the Ig-VAE can be used with Rosetta to create a computational model of a SARS-CoV2-RBD binder via latent space sampling. We further demonstrate that the model’s generative prior is a powerful tool for guiding computational protein design, motivating a new paradigm under which backbone design is solved as constrained optimization problem in the latent space of a generative model.

59 BASIC BIOLOGICAL SCIENCES↗

Towards scalable dataframe systems

Dataframes are a popular abstraction to represent, prepare, and analyze data. Despite the remarkable success of dataframe libraries in R and Python, dataframes face performance issues even on moderately large datasets. Moreover, there is significant ambiguity regarding dataframe semantics. In this paper we lay out a vision and roadmap for scalable dataframe systems. To demonstrate the potential in this area, we report on our experience building Modin, a scaled-up implementation of the most widely-used and complex dataframe API today, Python's pandas. With pandas as a reference, we propose a simple data model and algebra for dataframes to ground discussion in the field. Given this foundation, we lay out an agenda of open research opportunities where the distinct features of dataframes will require extending the state of the art in many dimensions of data management. We discuss the implications of signature dataframe features including flexible schemas, ordering, row/column equivalence, and data/metadata fluidity, as well as the piecemeal, trial-and-error-based approach to interacting with dataframes.

97 MATHEMATICS AND COMPUTING↗

Integration of Simulated and Real Distributed Acoustic Sensor Measurements to Develop AI Enhanced Intelligent Sensing Operations

Distributed acoustic sensors (DAS) have shown remarkable success in monitoring critical civil, energy and transportation assets over long distances and under harsh environmental conditions. Integration of artificial intelligence (AI) technologies with DAS can extend their operational capabilities from conventional tasks (e.g., vibration frequency detection) to more advanced intelligent tasks like anomaly detection. However, these AI technologies often require large labeled/ annotated DAS measurements datasets of the assets in both normal and anomalous operating conditions. This data acquisition task can be both time consuming and costly. This work develops a generative adversarial network based unsupervised domain adaptation framework to build intelligent DAS operational capabilities.

Venketeswaran, Abhishek↗

Data-driven modeling of dynamic occupant thermostat override behavior for demand response applications

Buildings consume nearly 40% of global energy and produce similar emissions. Whiletechnological advances address efficiency, occupant behavior causes energy use variations up to 300% between identical buildings. This gap between predicted and actual building performance impacts building design, operations, and grid demand management programs. Through analyses of smart thermostat data from 1,400 single-occupant homes, the researchdemonstrates that occupants respond to 8°F thermostat setpoint changes within a median of 15 minutes, while 2°F changes trigger responses within a median of 30 minutes. This highlights an understudied temporal relationship between thermostat setbacks and response time of occupant behaviors. Models of such behavior dynamics are required to incorporate occupant impacts into building performance simulation. A key contribution of this dissertation is the Thermal Frustration Theory (TFT), which positsthat thermal discomfort driven behaviors are caused by the time-accumulation of discomfort, not simply a temperature deviation threshold or a delay from an initiating event. Using a dataset of 634 thermostats, each with 25+ manual setpoint changes, a comparative analysis of TFT and comfort zone and a delayed response theories demonstrated that personalized TFT models better predict when manual setpoint change occur. This was measured by the area under the curve statistical measure (AUC); all three models perform similarly by a Matthews Correlation Coefficient measure. Higher AUC performance is especially important for modeling occupant behavior in demand response programs where false negatives of rare occupant interactions could adversely affect grid stability. EnergyPlus based simulations were conducted with TFT-derived occupant models, demonstrating the ability to identify parameters of known TFT models from only data observable with smart thermostats, even under the presence of noise from routine overrides. Overall, the dissertation highlights that thermostat interactions are neither static,instantaneous, nor driven solely by the environment. Instead, temporal accumulation of discomfort and routine-based behavior play important roles. The methodology and results offer a pathway towards more accurate modeling of human-building interactions for policy assessment, building design, and demand response programs.

Sharma, Kunind [Northeastern University] (ORCID:00↗

Data mining of space heating system performance in affordable housing

The space heating in residential buildings accounts for a considerable amount of the primary energy use. Therefore, understanding the operation and performance of space heating systems becomes crucial in improving occupant comfort while reducing energy use. This study investigated the behavior of occupants adjusting their thermostat settings and heating system operations in a 62-unit affordable housing complex in Revere, Massachusetts, USA. The data mining methods, including clustering approach and decision trees, were used to ascertain occupant behavior patterns. Data tabulating ON/OFF space heating states was assessed, to provide a better understanding of the intermittent operation of space heating systems in terms of system cycling frequency and the duration of each operation. The decision tree was used to verify the link between room temperature settings, house and heating system characteristics and the heating energy use. The results suggest that the majority of apartments show fairly constant room temperature profiles with limited variations during a day or between weekday and weekend. Data clustering results revealed six typical patterns of room temperature profiles during the heating season. Space heating systems cycled more frequently than anticipated due to a tight range of room thermostat settings and potentially oversized heating capacities. In conclusion, from this study affirm data mining techniques are an effective method to analyze large datasets and extract hidden patterns to inform design and improve operations.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

Reduced-order model for microstructure evolution prediction in the electrodes of solid oxide fuel cell with dynamic discrepancy reduced modeling

Microstructure evolution in the electrodes of solid oxide fuel cell is an important degradation mechanism which reduces active sites for redox reaction and the electric conductivity. Phase field models for microstructure evolution simulation are usually expensive for large scale simulations. In this paper, a reduced-order coarsening model is developed using dynamic discrepancy reduced modeling, which reduces the model order by inserting Gaussian process stochastic functions into the dynamic equations of Ostwald ripening. The reduced order model has been calibrated on a dataset generated by a phase field model that has been well validated to experiments. A validating dataset has also been generated with which the model prediction show good agreement. This model is further applied to predict long term microstructure evolution in different SOFC electrodes. Finally, this work is the first attempt of building a degradation model of SOFC using data science techniques.

36 MATERIALS SCIENCE↗

A Machine Learning-based Approach to Predict the Aggregate Flexibility of HVAC Systems

Use of renewable energy resources can play a significant role in mitigation of climate change since they reduce the dependency on fossil fuels. However, high penetration of renewable energy resources into the power grid may cause some reliability problems. Ancillary services are key to realize the potential of renewable resources without disturbing the grid reliability. In recent years, many control approaches focused on exploiting the aggregate flexible heating, ventilation, and air-conditioning (HVAC) loads of buildings. However, there are still research gaps in assessing in advance the resulting indoor temperature responses for given total power and weather profiles before implementing the controls in the buildings. Such an assessment is critical to guarantee satisfying both the grid related objective (reliability) and the building related objective (occupants' comfort). Towards addressing this research gap, this paper presents a machine-learning approach for predicting the ratings of indoor temperature responses. In this approach, a prediction model was developed using a dataset generated by a set of model-free control simulations. The developed model achieved high prediction accuracy and showed the potential of the proposed approach.

Amasyali, Kadir↗

Solar Row Zero Energy Townhomes - Boulder, CO

Wonderland Development has constructed a new "near zero energy" row home design in North Boulder consisting of 9 units: one 5-plex and two duplexes. NREL has performed short-term tests and installed long-term monitoring equipment in three of these units. Two of these units used a solar thermal combi system with a boiler for radiant space heating and water heating and mini-split system for space conditioning. The third unit used a high efficiency tank water heater for space heating. In addition to studying the overall performance of the homes, one unit was used for a detailed study on hot water draws at each fixture. Several reports and presentations were produced on this project, however, due to shifting funding and staffing priorities, a comprehensive final report for this project was never completed. This dataset contains a wealth of raw and analyzed data and several unpublished reports.

Array↗

A General Model for the Electrochemical Double Layer in Solids

It has long been clear that electrochemical double layer / space charge zone in the vicinity of interfaces and other extended defects greatly influences transport and reactivity. Over the past several years, multiple microscopic measurements of defect concentrations in the vicinity of solid-solid interfaces made clear that dilute-case thermodynamic theories to describe the behavior of charged species in space charge zones are untenable. Inhomogeneous thermodynamics – i.e., phase field models – have delivered the most success in describing both microscopic and macroscopic experiments. We still need a generalized approach that quantitatively reproduces the microscopic and macroscopic evidence, while remaining accessible to a wide range of researchers and engineers. In my talk I will present such a framework, which builds on the previously introduced Poisson-Cahn theory but utilizes data science methods which come into the thermodynamic framework in a well-defined way. I will review recent applications to both microscopic and macroscopic datasets while previewing our plans for connecting the theory to atomistic / first principles calculations and experiment simultaneously. I will also review plans for releasing open source code that runs on desktop-level computational resources.

David Mebane↗

Low-Temperature Geothermal Resources: Relevant Data and PFA Methods to Reduce Development Risk: Preprint

This project is part of a larger national effort focused on demonstrating the multi-faceted value of integrating low-temperature geothermal resources into national decarbonization strategies and community energy plans. Low-temperature geothermal resources are defined as reservoirs-natural or engineered-with temperatures < 150 degrees C. While the focus in the NREL effort is on geothermal heating and cooling (GHC), resources at the upper end of this temperature range can also be used for small-scale power generation. However, low-temperature geothermal resources have not been studied as extensively as higher-temperature geothermal resources. We identified three major classes of low-temperature geothermal play types: sedimentary basins, orogenic systems, and radiogenic systems. We developed workflows for evaluating the potential of these resources building off the Play Fairway Analysis (PFA) approach to de-risking geothermal exploration. This PFA-based approach to low-temperature geothermal resources includes: (1) identifying relevant data; (2) grouping and weighting of relevant datasets into PFA criteria (e.g., geological, risk, economic criteria); (3) developing favorability or common risk maps for low-temperature geothermal resources to identify potential locations for more focused data collection; and (4) estimating electric power generation and heating potential at those locations using the GeoRePORT Resource Size Assessment Tool. This project will facilitate future deployment of GHC by providing data, tools, and workflows applicable to low-temperature geothermal resources.

favorability maps↗

Low-Temperature Geothermal Resources: Relevant Data and PFA Methods to Reduce Development Risk

This project is part of a larger national effort focused on demonstrating the multi-faceted value of integrating low-temperature geothermal resources into national decarbonization strategies and community energy plans. Low-temperature geothermal resources are defined as reservoirs-natural or engineered-with temperatures < 150 degrees C. While the focus in the NREL effort is on geothermal heating and cooling (GHC), resources at the upper end of this temperature range can also be used for small-scale power generation. However, low-temperature geothermal resources have not been studied as extensively as higher-temperature geothermal resources. We identified three major classes of low-temperature geothermal play types: sedimentary basins, orogenic systems, and radiogenic systems. We developed workflows for evaluating the potential of these resources building off the Play Fairway Analysis (PFA) approach to de-risking geothermal exploration. This PFA-based approach to low-temperature geothermal resources includes: (1) identifying relevant data; (2) grouping and weighting of relevant datasets into PFA criteria (e.g., geological, risk, economic criteria); (3) developing favorability or common risk maps for low-temperature geothermal resources to identify potential locations for more focused data collection; and (4) estimating electric power generation and heating potential at those locations using the GeoRePORT Resource Size Assessment Tool. This project will facilitate future deployment of GHC by providing data, tools, and workflows applicable to low-temperature geothermal resources.

favorability maps↗

IEA Wind TCP Task 49: Reference Site Conditions for Floating Wind Arrays

This report, prepared within Work package 1 of IEA Wind Task 49, presents reference site conditions for floating wind arrays to serve as a design basis for the techno-economic design of reference floating wind arrays. Data of the reference sites presented here are publicly available in an open database and thus support fast development and comparable design of floating wind arrays for various relevant conditions. The development of these reference sites drew on existing open access datasets and ongoing research projects of task participants. Six classes were identified that describe relevant key conditions for the design and development of floating wind arrays: met-ocean conditions, seabed conditions, coastal infrastructure, environmental impact, socio-economic impact, as well as regulations and permissions. The reference sites for the techno-economic design of floating wind arrays are based on a concept with building blocks to synthesize purpose-built site representations. In each of the identified classes with influencing design factors, building blocks are used to describe the characteristic properties and their spread. However, the latter three classes (i.e., environmental impact, socio-economic impact, regulations and permissions) are not included in the reference site conditions due to limited knowledge and lack of reliable criteria to quantify their impact on the techno-economic design in numeric parameters. Building blocks with key parameters for the techno-economic design of floating wind arrays are provided for met-ocean conditions, seabed conditions, and coastal infrastructure. For met-ocean conditions, multiple sites were selected for detailed analysis that represent a range of conditions across the pipeline of floating wind projects. Wind conditions and sea states are separated, and each location considers both the severity of wind and waves e.g. one site may have a moderate wave condition but severe wind condition. From this pipeline, eleven representative sites were selected where both site-specific analysis was available within the consortium, and where they represent different parts of the global pipeline. The eleven sites are: Hannibal (Italy), Humboldt (US), Ulsan (South Korea), MoneyPoint One (Ireland), Havbredey (UK), Fukushima (Japan), Utsira Nord (Norway), Gulf of Maine (US), Sud de la Bretagne II (France), Sorlige Nordsjo II (Norway). Each of these sites is summarized in the main report while more details about the studies and analyses behind the datasets are provided in the appendix. For seabed conditions, general information about the geotechnical parameters is provided and a baseline is established for the geotechnical parameters and stratigraphy that may be encountered on the sites. A set of six 'synthetic cases' is defined as building blocks providing the different parameters required for design under each case/soil condition. For the coastal infrastructure, general information about the main requirements is provided that a port should comply with to provide a satisfactory service during the construction of floating offshore wind arrays. Minimum port infrastructural requirements are provided for three types of ports.

17 WIND ENERGY↗

The Matchmaker Exchange: A Platform for Rare Disease Gene Discovery

There are few better examples of the need for data sharing than in the rare disease community, where patients, physicians, and researchers must search for "the needle in a haystack" to uncover rare, novel causes of disease within the genome. Impeding the pace of discovery has been the existence of many small siloed datasets within individual research or clinical laboratory databases and/or disease-specific organizations, hoping for serendipitous occasions when two distant investigators happen to learn they have a rare phenotype in common and can "match" these cases to build evidence for causality. However, serendipity has never proven to be a reliable or scalable approach in science. As such, the Matchmaker Exchange (MME) was launched to provide a robust and systematic approach to rare disease gene discovery through the creation of a federated network connecting databases of genotypes and rare phenotypes using a common application programming interface (API). The core building blocks of the MME have been defined and assembled. In conclusion, three MME services have now been connected through the API and are available for community use. Additional databases that support internal matching are anticipated to join the MME network as it continues to grow.

59 BASIC BIOLOGICAL SCIENCES↗

DeePKS: A Comprehensive Data-Driven Approach toward Chemically Accurate Density Functional Theory

We propose a general machine learning-based framework for building an accurate and widely applicable energy functional within the framework of generalized Kohn–Sham density functional theory. To this end, we develop a way of training self-consistent models that are capable of taking large datasets from different systems and different kinds of labels. Here, we demonstrate that the functional that results from this training procedure gives chemically accurate predictions on energy, force, dipole, and electron density for a large class of molecules. It can be continuously improved when more and more data are available.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Machine learning with persistent homology and chemical word embeddings improves prediction accuracy and interpretability in metal-organic frameworks

Machine learning has emerged as a powerful approach in materials discovery. Its major challenge is selecting features that create interpretable representations of materials, useful across multiple prediction tasks. We introduce an end-to-end machine learning model that automatically generates descriptors that capture a complex representation of a material’s structure and chemistry. This approach builds on computational topology techniques (namely, persistent homology) and word embeddings from natural language processing. It automatically encapsulates geometric and chemical information directly from the material system. We demonstrate our approach on multiple nanoporous metal–organic framework datasets by predicting methane and carbon dioxide adsorption across different conditions. Our results show considerable improvement in both accuracy and transferability across targets compared to models constructed from the commonly-used, manually-curated features, consistently achieving an average 25–30% decrease in root-mean-squared-deviation and an average increase of 40–50% in R 2 scores. A key advantage of our approach is interpretability: Our model identifies the pores that correlate best to adsorption at different pressures, which contributes to understanding atomic-level structure–property relationships for materials design.

97 MATHEMATICS AND COMPUTING↗

High Throughput WAN Data Transfer with Hadoop-Based Storage

Hadoop distributed file system (HDFS) is becoming more popular in recent years as a key building block of integrated grid storage solution in the field of scientific computing. Wide Area Network (WAN) data transfer is one of the important data operations for large high energy physics experiments to manage, share and process datasets of PetaBytes scale in a highly distributed grid computing environment. In this paper, we present the experience of high throughput WAN data transfer with HDFS-based Storage Element. Two protocols, GridFTP and fast data transfer (FDT), are used to characterize the network performance of WAN data transfer.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

Distance preserving machine learning for uncertainty aware accelerator capacitance predictions

Abstract Accurate uncertainty estimations are essential for producing reliable machine learning models, especially in safety-critical applications such as accelerator systems. Gaussian process models are generally regarded as the gold standard for this task; however, they can struggle with large, high-dimensional datasets. Combining deep neural networks with Gaussian process approximation techniques has shown promising results, but dimensionality reduction through standard deep neural network layers is not guaranteed to maintain the distance information necessary for Gaussian process models. We build on previous work by comparing the use of the singular value decomposition against a spectral-normalized dense layer as a feature extractor for a deep neural Gaussian process approximation model and apply it to a capacitance prediction problem for the High Voltage Converter Modulators in the Oak Ridge Spallation Neutron Source. Our model shows improved distance preservation and predicts in-distribution capacitance values with less than 1% error.

43 PARTICLE ACCELERATORS↗