Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “regression models”

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 433 records · Page 24
All sourcesNASA NTRSDOE OSTI
DOE OSTI2023

Estimating Field-Level Perennial Bioenergy Grass Biomass Yields Using the Normalized Difference Red-Edge Index and Linear Regression Analysis for Central Virginia, USA

We investigated the indicative power of the normalized difference red-edge index (NDRE) for estimating field-level perennial bioenergy grass biomass yields utilizing Sentinel-2 imagery and a linear regression model as a rapid, cost-effective method for biomass yield estimations for bioenergy. We used 2019 data from three study sites containing mature perennial bioenergy grass stands in central Virginia, USA. Of the simulated daily NDRE values based on the temporally weighted averaging of two temporal neighbors, we found the strongest index–yield correlation on 11 August (R = 0.85). We estimated the perennial bioenergy grass biomass yields for (1) all sites using the data pooled from the three sites (all-site estimation) and (2) each site using the data pooled from the other two sites (cross-site estimation). The estimated field-level perennial bioenergy grass biomass yields strongly correlated with the recorded yields (average R2 = 0.76), with a root mean square error (RMSE) of 1.5 Mg/ha and a mean absolute error (MAE) of 1.2 Mg/ha for the all-site estimation. For the cross-site estimation, the site with diverse perennial grass types had the weakest correlation (R2 = 0.44) of the sites, indicating a difficulty in accounting for heterogeneous index–yield relationships in a single model. In addition to identifying a strong indicative power of the NDRE for estimating the overall perennial bioenergy grass biomass yields at a field level, the findings from this study call for an analysis across multiple perennial grasses and a comparison using multiple sites to understand (1) if the indicative power of the index shifts from the biomass of the specific perennial bioenergy grass type to the overall biomass during the growing season and (2) the level of perennial bioenergy grass heterogeneity that may hinder the remotely sensed biomass yield estimation using a single model.

09 BIOMASS FUELS↗
DOE OSTI2024

Cliff Retreat Rates Associated with a Low-Level Radioactive Waste Disposal Facility in Los Alamos, New Mexico, USA

We present an analysis and interpretation of potential cliff stability at a low-level waste disposal facility at Los Alamos National Laboratory, New Mexico, using cliff morphologic and fracture characteristics coupled with carbon-14 surface exposure dating. Our study is important as it directly bears on the licensing criteria for low-level radioactive waste sites. We find that future characteristic cliff failures will likely not breach disposal pits and shafts over the 1000-year minimum regulatory period. Further, we find, using a multivariate regression model, that slope angle and cliff face aspect are sub-equal in importance to predict regions of high risk of failure when combined with surface exposure ages and assuming that old exposure ages are most indicative of stability (instability) and therefore can aid decision making in final design implementation.

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗
DOE OSTI2021

Urban Green Spaces, Greenness Exposure and Species Richness in Residential Environments and Relations with Physical Activity and BMI in Portuguese Adolescents

Environmental factors play an important role in obesity-related behaviors. Evidence indicates significant associations between weight and urban green spaces in adults, but it is not clear whether this relationship applies to adolescents. Therefore, our aim was to determine the associations between urban green spaces, greenness exposure and species richness in residential environments with physical activity and body mass index. Sixty-two adolescents between 12 and 18 years of age answered a self-administered questionnaire, providing information on height, weight, age, sex and home address. Data on socioeconomic deprivation were obtained from the European Index of Deprivation for Small Portuguese Areas. Physical activity levels were assessed using accelerometers. Urban green space counts and the normalized difference vegetation index values were measured using buffers along the roads with distances of 300, 500, 1000 and 1500 m from each participant’s residence. To quantify the species richness, the species richness index was used. Linear regression models were fitted to analyze whether urban green spaces, exposure to green spaces and species richness counts for each distance were associated with physical activity and self-reported body mass index. We did not find significant associations between the independent variables and the probability of overweight or obesity. The relationship between environmental variables, adolescents’ physical activity and body weight seems to be complex and further studies may contribute to better understanding of the topic.

Melo, Juliana (ORCID:0000000301275340)↗
DOE OSTI2021

Understanding the Drivers of Mobility during the COVID-19 Pandemic in Florida, USA Using a Machine Learning Approach

As of March 2021, the State of Florida, U.S.A. had accounted for approximately 6.67% of total COVID-19 (SARS-CoV-2 coronavirus disease) cases in the U.S. The main objective of this research is to analyze mobility patterns during a three month period in summer 2020, when COVID-19 case numbers were very high for three Florida counties, Miami-Dade, Broward, and Palm Beach counties. To investigate patterns, as well as drivers, related to changes in mobility across the tri-county region, a random forest regression model was built using sociodemographic, travel, and built environment factors, as well as COVID-19 positive case data. Mobility patterns declined in each county when new COVID-19 infections began to rise, beginning in mid-June 2020. While the mean number of bar and restaurant visits was lower overall due to closures, analysis showed that these visits remained a top factor that impacted mobility for all three counties, even with a rise in cases. Our modeling results suggest that there were mobility pattern differences between counties with respect to factors relating, for example, to race and ethnicity (different population groups factored differently in each county), as well as social distancing or travel-related factors (e.g., staying at home behaviors) over the two time periods prior to and after the spike of COVID-19 cases.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2023

Vehicle Localization in 3D World Coordinates Using Single Camera at Traffic Intersection

Optimizing traffic control systems at traffic intersections can reduce the network-wide fuel consumption, as well as emissions of conventional fuel-powered vehicles. While traffic signals have been controlled based on predetermined schedules, various adaptive signal control systems have recently been developed using advanced sensors such as cameras, radars, and LiDARs. Among these sensors, cameras can provide a cost-effective way to determine the number, location, type, and speed of the vehicles for better-informed decision-making at traffic intersections. In this research, a new approach for accurately determining vehicle locations near traffic intersections using a single camera is presented. For that purpose, a well-known object detection algorithm called YOLO is used to determine vehicle locations in video images captured by a traffic camera. YOLO draws a bounding box around each detected vehicle, and the vehicle location in the image coordinates is converted to the world coordinates using camera calibration data. During this process, a significant error between the center of a vehicle’s bounding box and the real center of the vehicle in the world coordinates is generated due to the angled view of the vehicles by a camera installed on a traffic light pole. As a means of mitigating this vehicle localization error, two different types of regression models are trained and applied to the centers of the bounding boxes of the camera-detected vehicles. The accuracy of the proposed approach is validated using both static camera images and live-streamed traffic video. Based on the improved vehicle localization, it is expected that more accurate traffic signal control can be made to improve the overall network-wide energy efficiency and traffic flow at traffic intersections.

47 OTHER INSTRUMENTATION↗
DOE OSTI2023

Epidemiologic Factors Supporting Triage of Infected Dog Patients Admitted to a Veterinary Hospital Biological Isolation and Containment Unit

The teaching hospital of the Faculty of Veterinary Medicine at the University of Lisbon hosts a Biological Isolation and Containment Unit (BICU) for the hospitalization of both confirmed and suspected animals of an infectious disease. This study targets the BICU dog population to identify and characterize the most frequent infectious diseases recorded in a 7-year period. Several epidemiologic factors were analyzed for their significance to triage infected cases. During the study period, 534 dogs were admitted, of which 263 (49.3%) had a confirmed infectious disease diagnosis: parvovirosis (49.4%; n = 130); leptospirosis (21.7%; n = 57); multidrug-resistant (MDR) bacterial infection; (10.6%; n = 28), and canine distemper (9.9%; n = 26). Several potential risk factors for these diseases were identified: age under 2 years old (p < 0.001), incomplete vaccination for parvovirosis (p < 0.001), age ≥ 10 years old (p < 0.001), and the presence of concomitant disorders for MDR-infected cases (p = 0.03). Logistic regression models were constructed to classify cases and controls. The sensitivity and specificity estimates were very high (>0.83) for parvovirosis, MDR, and distemper infections. A lower sensitivity (0.77) was obtained for identifying cases with leptospirosis. In conclusion, infectious diseases are frequent, hence, it is essential to decrease their occurrence through effective preventive measures such as vaccination. The constructed logistic models can also help in triaging admitted dogs with a potential infectious disease.

Machado, Inês Cunha (ORCID:0000000238151125)↗
DOE OSTI2025

Do Piperonyl Butoxide Long-Lasting Insecticide Treated Nets Provide Additional Protection Against Malaria Infections Compared with Conventional Nets in an Operational Setting in Western Kenya?

Malaria control in sub-Saharan Africa has stagnated despite widespread adoption of control measures such as long-lasting insecticidal nets (LLINs). Progress has stalled, in part, because of pyrethroid insecticide resistance, driving the need for retooling to increase the effectiveness of bed nets. Consequently, LLINs have been treated with the chemical synergist piperonyl butoxide (PBO). Piperonyl butoxide LLINs have been shown to be efficacious in controlled settings; however, their effectiveness in real-world settings warrants investigation. In Bungoma County, Western Kenya, a cohort of 768 participants was followed from June 2017 to December 2023 via active and passive surveillance. Household visits were conducted monthly, during which LLIN use for nets distributed in 2017 and 2021 was recorded, and symptomatic malaria cases were identified using rapid diagnostic tests (RDTs). The comparative effectiveness of PBO versus conventional LLINs was assessed in terms of malaria infections. A multilevel logistic regression model was fit with monthly RDT results as the dependent variable. The study results indicate that PBO LLINs provide greater protection against malaria at the individual level than conventional LLINs (odds ratio: 0.70; 95% CI: 0.47–1.03), although the findings were not statistically significant. The added protection against malaria infections provided by PBO LLINs compared with conventional LLINs observed in the current study aligns with findings from most previous studies, although this finding was not statistically significant. In areas with documented pyrethroid resistance, the use of LLINs with an added synergist, such as PBO, can provide additional protection against malaria infections (compared with pyrethroid-only LLINs) and should be considered for scaled-up scenarios despite the additional cost.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2020

Using machine learning to derive cloud condensation nuclei number concentrations from commonly available measurements

Cloud condensation nuclei (CCN) number concentrations are an important aspect of aerosol–cloud interactions and the subsequent climate effects; however, their measurements are very limited. We use a machine learning tool, random decision forests, to develop a random forest regression model (RFRM) to derive CCN at 0.4 % supersaturation ([CCN0.4]) from commonly available measurements. The RFRM is trained on the long-term simulations in a global size-resolved particle microphysics model. Using atmospheric state and composition variables as predictors, through associations of their variabilities, the RFRM is able to learn the underlying dependence of [CCN0.4] on these predictors, which are as follows: eight fractions of PM 2.5 (NH 4 , SO 4 , NO 3, secondary organic aerosol (SOA), black carbon (BC), primary organic carbon (POC), dust, and salt), seven gaseous species (NO x , NH 3 , O 3 , SO 2 , OH, isoprene, and monoterpene), and four meteorological variables (temperature (T), relative humidity (RH), precipitation, and solar radiation). The RFRM is highly robust: it has a median mean fractional bias (MFB) of 4.4 % with ≈96.33 % of the derived [CCN0.4] within a good agreement range of -60% 2.5 speciation (NH 4 , SO 4 , NO 3 , and organic carbon (OC)), NO x , O 3 , SO 2 , T, and RH, as well as [CCN0.4] are available. We modify, optimize, and retrain the developed RFRM to make predictions from 19 to 9 of these available predictors. This retrained RFRM (RFRM-ShortVars) shows a reduction in performance due to the unavailability and sparsity of measurements (predictors); it captures the [CCN0.4] variability and magnitude at SGP with ≈67.02 % of the derived values in the good agreement range. This work shows the potential of using the more commonly available measurements of PM 2.5 speciation to alleviate the sparsity of CCN number concentrations' measurements.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2024

Using automated machine learning for the upscaling of gross primary productivity

Estimating gross primary productivity (GPP) over space and time is fundamental for understanding the response of the terrestrial biosphere to climate change. Eddy covariance flux towers provide in situ estimates of GPP at the ecosystem scale, but their sparse geographical distribution limits larger-scale inference. Machine learning (ML) techniques have been used to address this problem by extrapolating local GPP measurements over space using satellite remote sensing data. However, the accuracy of the regression model can be affected by uncertainties introduced by model selection, parameterization, and choice of explanatory features, among others. Recent advances in automated ML (AutoML) provide a novel automated way to select and synthesize different ML models. In this work, we explore the potential of AutoML by training three major AutoML frameworks on eddy covariance measurements of GPP at 243 globally distributed sites. We compared their ability to predict GPP and its spatial and temporal variability based on different sets of remote sensing explanatory variables. Explanatory variables from only Moderate Resolution Imaging Spectroradiometer (MODIS) surface reflectance data and photosynthetically active radiation explained over 70 % of the monthly variability in GPP, while satellite-derived proxies for canopy structure, photosynthetic activity, environmental stressors, and meteorological variables from reanalysis (ERA5-Land) further improved the frameworks' predictive ability. We found that the AutoML framework Auto-sklearn consistently outperformed other AutoML frameworks as well as a classical random forest regressor in predicting GPP but with small performance differences, reaching an r 2 of up to 0.75. We deployed the best-performing framework to generate global wall-to-wall maps highlighting GPP patterns in good agreement with satellite-derived reference data. This research benchmarks the application of AutoML in GPP estimation and assesses its potential and limitations in quantifying global photosynthetic activity.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2024

Quantifying wildfire drivers and predictability in boreal peatlands using a two-step error-correcting machine learning framework in TeFire v1.0

Abstract. Wildfires are becoming an increasing challenge to the sustainability of boreal peatland (BP) ecosystems and can alter the stability of boreal carbon storage. However, predicting the occurrence of rare and extreme BP fires proves to be challenging, and gaining a quantitative understanding of the factors, both natural and anthropogenic, inducing BP fires remains elusive. Here, we quantified the predictability of BP fires and their primary controlling factors from 1997 to 2015 using a two-step correcting machine learning (ML) framework that combines multiple ML classifiers, regression models, and an error-correcting technique. We found that (1) the adopted oversampling algorithm effectively addressed the unbalanced data and improved the recall rate by 26.88 %–48.62 % when using multiple datasets, and the error-correcting technique tackled the overestimation of fire sizes during fire seasons; (2) nonparametric models outperformed parametric models in predicting fire occurrences, and the random forest machine learning model performed the best, with the area under the receiver operating characteristic curve ranging from 0.83 to 0.93 across multiple fire datasets; and (3) four sets of factor-control simulations consistently indicated the dominant role of temperature, air dryness, and climate extreme (i.e., frost) for boreal peatland fires, overriding the effects of precipitation, wind speed, and human activities. Our findings demonstrate the efficiency and accuracy of ML techniques in predicting rare and extreme fire events and disentangle the primary factors determining BP fires, which are critical for predicting future fire risks under climate change.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2023

Warming of the Willamette River, 1850–present: the effects of climate change and river system alterations

Abstract. Using archival research methods, we recovered and combined data from multiple sources to produce a unique, 140-year record of daily water temperature (Tw) in the lower Willamette River, Oregon (1881–1890, 1941–present). Additional daily weather and river flow records from the 1850s onwards are used to develop and validate a statistical regression model of Tw for 1850–2020. The model simulates the time-lagged response of Tw to air temperature and river flow and is calibrated for three distinct time periods: the late 19th, mid-20th, and early 21st centuries. Results show that Tw has trended upwards at 1.1 ∘C per century since the mid-19th century, with the largest shift in January and February (1.3 ∘C per century) and the smallest in May and June (∼ 0.8 ∘C per century). The duration that the river exceeds the ecologically important threshold of 20 ∘C has increased by about 20 d since the 1800s, to about 60 d yr−1. Moreover, cold-water days below 2 ∘C have virtually disappeared, and the river no longer freezes. Since 1900, changes are primarily correlated with increases in air temperature (Tw increase of 0.81 ± 0.25 ∘C) but also occur due to alterations in the river system such as depth increases from reservoirs (0.34 ± 0.12 ∘C). Managed release of water affects Tw seasonally, with an average reduction of up to 0.56 ∘C estimated for September. River system changes have decreased variability (σ) in daily minimum Tw by 0.44 ∘C, increased thermal memory, reduced interannual variability, and reduced the response to short-term meteorological forcing (e.g., heat waves). These changes fundamentally alter the response of Tw to climate change, posing additional stressors on fauna.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2020

Considerations for Short-Term Load Forecasting of Morocco

There are many factors that determine how demand for electricity may change over time. The analysis described in this report is focused on using auto-regressive models and neural networks to examine load-forecasting techniques for the next 24 hours.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2023

Image-based solar estimates

An example device is configured to determine, based on a sky image of a portion of sky over a power distribution network and using a convolutional neural network (CNN)-based image regression model, an estimated global horizontal irradiance (GHI) value and manage or control the power distribution network using the estimated GHI value. The device may also be configured to determine, based on GHI values and aggregate load values for at least a portion of the power distribution network, using a Bayesian Structural Time Series model, an estimated photovoltaic power output value for the at least a portion of the power distribution network. The device may manage or control the power distribution network using the estimated photovoltaic power output value.

Bernstein, Andrey↗
DOE OSTI2024

Efficient Parallelization of Irregular Applications on GPU Architectures

With the enlarging computation capacity of general Graphics Processing Units (GPUs), leveraging GPUs to accelerate parallel applications has become a critical topic in academia and industry. However, a wide range of irregular applications with the computation-/memory-intensive nature cannot easily achieve high GPU utilization. The challenges mainly involve the following aspects: first, data dependence leads to coarse-grained kernel and inefficient parallelism; second, heavy GPU memory usage may cause frequent memory evictions and extra overhead of I/O; third, specific computation patterns produce memory redundancies; last, workload balance and data reusability conjunctly benefit the overall performance, but there may exist a dynamic trade-off between them. Targeting these challenges, this dissertation proposes multiple optimizations to accelerate two real-world applications: many-body correlation functions to simulate nuclear physics in a large-scale scientific system; the other is the eALS-based matrix factorization recommendation system. To accelerate the calculations of many-body correlation functions, this dissertation presents three frameworks in GPU memory management and multi-GPU scheduling. Firstly, an optimized systematic GPU memory management framework, MemHC, utilizes a series of new memory reduction designs in GPU memory allocation, CPU/GPU communications, and GPU memory oversubscription. Secondly, an enhanced multi-GPU scheduling framework, MICCO, particularly by taking both data dimension (e.g., data reuse and data eviction) and computation dimension into account. MICCO designs a heuristic scheduling algorithm and a machine learning-based regression model to generate the optimal settings of a proposed new concept to manage the trade-off. Thirdly, a locality-aware multi-GPU scheduling framework. This scheduler leverages pipeline batch generation with a looking-ahead strategy by building local dependency graphs for memory transfer reduction and better data reuse, achieving up to 79.92% memory cost reduction and 1.67x speedup. To parallelize the eALS-based recommendation system, this dissertation proposes an efficient CPU/GPU heterogeneous recommendation system, HEALS. HEALS employs newly designed architecture-adaptive data formats to achieve load balance and good data locality on CPU and GPU. To mitigate the data dependence, HEALS presents a CPU/GPU collaboration model for both task parallelism and data parallelism with multiple kernel computation optimizations. In summary, this dissertation efficiently accelerates two typical irregular applications on GPUs by building four frameworks, including CPU/GPU collaboration, GPU memory management, and multi-GPU scheduling.

Wang, Qihan↗
DOE OSTI2023

Interactive Corpus Analysis Tool

The Interactive Corpus Analysis Tool (ICAT) is an interactive machine learning dashboard for unlabeled text/natural language processing datasets that allows a user to iteratively and visually define features, explore and label instances of their dataset, and simultaneously train a logistic regression model. ICAT was created to allow subject matter experts in a specific domain to directly train their own models for unlabeled datasets visually, without needing to be a machine learning expert or needing to know how to code the models themselves. This approach allows users to directly leverage the power of machine learning, but critically, also involves the user in the development of the machine learning model.

Martindale, Nathan [Oak Ridge National Lab. (ORNL)↗
DOE OSTI2023

Generalizing the Gurson model using symbolic regression and transfer learning to relax inherent assumptions

Abstract To generate material models with fewer limiting assumptions while maintaining closed-form, interpretable solutions, we propose using genetic programming based symbolic regression (GPSR), a machine learning (ML) approach that describes data using free-form symbolic expressions. To maximize interpretability, we start from an analytical, derived material model, the Gurson model for porous ductile metals, and systematically relax inherent assumptions made in its derivation to understand each assumption’s contribution to the GPSR model forms. We incorporate transfer learning methods into the GPSR training process to increase GPSR efficiency and generate models that abide by known mechanics of the system. The results show that regularizing the GPSR fitness function is critical for generating physically valid models and illustrate how GPSR allows a high level of interpretability compared with other ML approaches. The method of systematic assumption relaxation allows the generation of models that address limiting assumptions found in the Gurson model, and the symbolic forms allow conjecture of decreased material strength due to void interaction and non-symmetric void shapes.

36 MATERIALS SCIENCE↗
DOE OSTI2024

Quantile regression-enriched event modeling framework for dropout analysis in high-temperature superconductor manufacturing

High-temperature superconductor (HTS) tapes have shown promising characteristics of high critical current, which are prerequisites for applications in high-field magnets. Due to the unstable growth conditions in the HTS manufacturing process, however, the frequent occurrences of dropouts in the critical current impede the consistent performance of HTS tapes. To manufacture HTS tapes with large scale, high yield, and uniform performance, it is essential to develop novel data analysis approaches for modeling the dropouts and identifying the related important process parameters. Conventional methods for modeling recurrent events, such as the point process, require the extraction of events from quality measurements. As the critical current is a continuous process, it may not comprehensively represent the drop patterns by transforming the time-series measurements into a set of events. Here, to solve this issue, we develop a novel quantile regression-enriched event modeling (QREM) framework that integrates the non-homogeneous Poisson process for modeling the occurrence of dropouts and the quantile regression for capturing the drop patterns. By incorporating the feature selection and regularization, the proposed framework identifies a set of significant process parameters that can potentially cause the dropouts of HTS tapes. The proposed method is tested on real HTS tapes produced using an advanced manufacturing process, successfully identifying important parameters that influence dropout events including the substrate temperature and voltage. The results demonstrate that the proposed QREM method outperforms the standard point process in predicting the occurrence of dropouts.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗
DOE OSTI2022

Computer Model Calibration with Time Series Data Using Deep Learning and Quantile Regression

Computer models play a key role in many scientific and engineering problems. One major source of uncertainty in computer model experiments is input parameter uncertainty. Computer model calibration is a formal statistical procedure to infer input parameters by combining information from model runs and observational data. The existing standard calibration framework suffers from inferential issues when the model output and observational data are high-dimensional dependent data, such as large time series, due to the difficulty in building an emulator and the nonidentifiability between effects from input parameters and data-model discrepancy. To overcome these challenges, we, in this work, propose a new calibration framework based on a deep neural network (DNN) with long short-term memory layers that directly emulates the inverse relationship between the model output and input parameters. Adopting the “learning with noise” idea, we train our DNN model to filter out the effects from data-model discrepancy on input parameter inference. We also formulate a new way to construct interval predictions for DNN using quantile regression to quantify the uncertainty in input parameter estimates. Through a simulation study and real data application with the Weather Research and Forecasting Model Hydrological modeling system (WRF-Hydro), we show our approach can yield accurate point estimates and well-calibrated interval estimates for input parameters.

97 MATHEMATICS AND COMPUTING↗