SEARCH · Search NASA

Results for “classifier 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.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 127 records · Page 7

All sources NASA NTRS DOE OSTI

NASA NTRS1993

Convective and stratiform rain: Multichannel microwave sensing over oceans

Measurements made by the Special Sensor Microwave/Imager (SSM/I) radiometer over the oceans, at 19, 37, and 85 GHz in dual polarization, are used to develop a model to classify rain into light-stratiform, moderately convective, and heavy convective types in the mesoscale convective systems (MCS). It is observed that the bulk of the 19- and 37-GHz data are linearly correlated with respect to one another, and generally increase together in brightness as the mean rain rate in the field of view (FOV) of the radiometer increases. However, a significant fraction of the data from these channels departs from this linear relationship, reflecting the nonuniform rain that is convective vs. the relatively light stratiform rain. It is inferred from the SSM/I data, in a MCS, when the slope dT sub 3/dT sub 19 is greater than unity there are optically thin clouds which produce light uniform rain. On the other hand, when dT sub 3/dT sub 19 is close to unity, the rain cells have an open structure and correspond to the convective type of rain. The openings between the cells are apparently a result of the downdrafts and/or entrainment. Relatively low values of 85-GHz brightness temperatures that are present when dT sub 37/dT sub 19 is close to unity support these views and, in addition, leads us to conclude that when the convection is heavy this brightness temperature decreases due to scattering by hydrometeors. On the basis of this explanation of the SSM/I data, an empirical rain retrieval algorithm is developed. Radar backscatter observations over the Atlantic Ocean next to Florida are used to demonstrate the applicability of this method. Three monthly mean maps of rainfall over the oceans from 50 degrees N to 50 degrees S, are presented to illustrate the ability of this method to sense seasonal and interannual variations of rain.

Prabhakara, C.↗

NASA NTRS2011

Impact of Optimized land Surface Parameters on the Land-Atmosphere Coupling in WRF Simulations of Dry and Wet Extremes

Land-atmosphere (L-A) interactions play a critical role in determining the diurnal evolution of both planetary boundary layer (PBL) and land surface temperature and moisture budgets, as well as controlling feedbacks with clouds and precipitation that lead to the persistence of dry and wet regimes. Recent efforts to quantify the strength of L-A coupling in prediction models have produced diagnostics that integrate across both the land and PBL components of the system. In this study, we examine the impact of improved specification of land surface states, anomalies, and fluxes on coupled WRF forecasts during the summers of extreme dry (2006) and wet (2007) conditions in the U.S. Southern Great Plains. The improved land initialization and surface flux parameterizations are obtained through the use of a new optimization and uncertainty module in NASA's Land Information System (LIS-OPT), whereby parameter sets are calibrated in the Noah land surface model and classified according to the land cover and soil type mapping of the observations and the full domain. The impact of the calibrated parameters on the a) spin up of land surface states used as initial conditions, and b) heat and moisture fluxes of the coupled (LIS-WRF) simulations are then assessed in terms of ambient weather, PBL budgets, and precipitation along with L-A coupling diagnostics. In addition, the sensitivity of this approach to the period of calibration (dry, wet, normal) is investigated. Finally, tradeoffs of computational tractability and scientific validity (e.g.,. relating to the representation of the spatial dependence of parameters) and the feasibility of calibrating to multiple observational datasets are also discussed.

Kumar, Sujay↗

NASA NTRS2012

Polarimetric Imaging of Large Cavity Structures in the Pre-transitional Protoplanetary Disk around PDS 70: Observations of the Disk

We present high resolution H-band polarized intensity (PI; FWHM = 0."1: 14 AU) and L'-band imaging data (FWHM = 0."11: 15 AU) of the circumstellar disk around the weak-lined T Tauri star PDS 70 in Centaurus at a radial distance of 28 AU (0."2) up to 210 AU (1."5). In both images, a giant inner gap is clearly resolvro for the first time, and the radius of the gap is approx 70 AU. Our data show that the geometric center of the disk shifts by approx 6 AU toward the minor axis. We confirm that the brown dwarf companion candidate to the north of PDS 70 is a background star based on its proper motion. As a result of SED fitting by Monte Carlo radiative transfer modeling, we infer the existence of an optically thick inner disk at a few AU. Combining our observations and modeling, we classify the disk of PDS 70 as a pre-transitional disk. Furthermore, based on the analysis of L'-band imaging data, we put an upper limit mass of companions at approx 30 to approx 50M(sub J) within the gap. Taking account of the presence of the large and sharp gap, we suggest that the gap could be formed by dynamical interactions of sub-stellar companions or multiple unseen giant planets in the gap.

Hashimoto, J.↗

NASA NTRS2012

Polarimetric Imaging of Large Cavity Structures in the Pre-transitional Protoplanetary Disk Around PDS 70: Observations of the Disk

We present high resolution H-band polarized intensity (PI; FWHM = 0."1: 14 AU) and L'-band imaging data (FWHM = 0."11: 15 AU) of the circumstellar disk around the weak-lined T Tauri star PDS 70 in Centaurus at a radial distance of 28 AU (0."2) up to 210 AU (1."5). In both images, a giant inner gap is clearly resolved for the first time, and the radius of the gap is approx.70 AU. Our data show that the geometric center of the disk shifts by approx.6 AU toward the minor axis. We confirm that the brown dwarf companion candidate to the north of PDS 70 is a background star based on its proper motion. As a result of SED fitting by Monte Carlo radiative transfer modeling, we infer the existence of an optically thick inner disk at a few AU. Combining our observations and modeling, we classify the disk of PDS 70 as a pre-transitional disk. Furthermore, based on the analysis of L'-band imaging data, we put an upper limit mass of companions at approx.30 to approx.50MJ within the gap. Taking account of the presence of the large and sharp gap, we suggest that the gap could be formed by dynamical interactions of sub-stellar companions or multiple unseen giant planets in the gap. Subject headings: planetary systems - protoplanetary disks - stars: individual (PDS 70) - stars: pre-main sequence - polarization

Hashimoto, J.↗

NASA NTRS2012

Polarimetric Imaging of Large Cavity Structures in the Pre-transitional Protoplanetary Disk Around PDS 70: Observations of the Disk

We present high-resolution H-band polarized intensity (FWHM=0".1:14AU) and L'-band imaging data(FWHM= 0".11:15 AU) of the circumstellar disk around the weak-lined T Tauri star PDS 70 in Centaurus at a radial distance of 28 AU (0".2) up to 210 AU (1".5). In both images, a giant inner gap is clearly resolved for the first time, and the radius of the gap is approx.70 AU. Our data show that the geometric center of the disk shifts by approx.6 AU toward the minor axis. We confirm that the brown dwarf companion candidate to the north of PDS 70 is a background star based on its proper motion. As a result of spectral energy distribution fitting by Monte Carlo radiative transfer modeling, we infer the existence of an optically thick inner disk at a few AU. Combining our observations and modeling, we classify the disk of PDS 70 as a pre-transitional disk. Furthermore, based on the analysis of L'-band imaging data, we put an upper limit of approx.30 to approx.50 M(sub J) on the mass of companions within the gap. Taking into account the presence of the large and sharp gap, we suggest that the gap could be formed by dynamical interactions of sub-stellar companions or multiple unseen giant planets in the gap. Key words: planetary systems - polarization - protoplanetary disks - stars: individual (PDS 70) - stars: pre-main sequence.

Hashimoto, J.↗

NASA NTRSDate not supplied

Assessing Change in Aspen Extent in Northern Yellowstone National Park

The trophic cascade among wolves, elk, and aspen has influenced the landscape of Yellowstone National Park. Aspen promote greater biodiversity and have been indirectly affected by the 1926 removal and 1995 reintroduction of wolves in the park. Partnered with Yellowstone National Park, Utah State University, and the University of Wisconsin–Stevens Point, NASA DEVELOP analyzed the change in aspen stand extent from 1954 to 2021 over the elk wintering range that occurs in the northern part of Yellowstone and southern Montana. Focusing on 113 stands corresponding with belt transects monitored annually since 1999, the team georeferenced and digitized 1954 historical aerial imagery to determine aspen stand extent. From 1986 to 2019, the team processed Landsat 5 Thematic Mapper (TM) and Sentinel-2 Multispectral Instrument (MSI) imagery for the entire elk wintering range using a random forest model to classify landcover types. Outputs were refined using a phenological approach that distinguishes between deciduous and evergreen landcover by differencing summer and fall vegetation indices. Finally, the team conducted a similar analysis for 2021, utilizing both Landsat 8 Operational Land Imager (OLI) and Sentinel-2 MSI imagery. The team again focused on the stands associated with belt transects for this analysis to compare the beginning and end of the study period. Preliminary results indicate a slight decline over time. These results expand the understanding of the role of wolves on aspen in the Yellowstone ecosystem and inform future rewilding decisions within the park and beyond.

Vanessa Bailey↗

DOE OSTI2020

Mathematical Models for Optimization of Grid-Integrated Energy Storage Systems

Energy storage has been proven to yield positive effects on planning, operation and control of electric grids. It has become a crucial task to properly model the energy storage systems (ESS) under the framework of grid optimization on transmission and distribution networks including microgrids. This paper presents a review on mathematical models and test cases of ESSs used for grid optimization studies, where the network constraints of power systems are included. The existing ESS models are mainly classified into two categories – linear and nonlinear models. The two main categories are further divided into several subcategories respectively; such as mixed-integer linear and convex nonlinear sub-categories. Based on the review and discussions, this paper aims at providing suggestions for choosing proper ESS models for specific grid optimization studies considering the chosen power network model.

24 POWER TRANSMISSION AND DISTRIBUTION↗

DOE OSTI2022

Classification of Nuclear Reactor Operations Using Spatial Importance and Multisensor Networks

Distributed multisensor networks record multiple data streams that can be used as inputs to machine learning models designed to classify operations relevant to proliferation at nuclear reactors. The goal of this work is to demonstrate methods to assess the importance of each node (a single multisensor) and region (a group of proximate multisensors) to machine learning model performance in a reactor monitoring scenario. This, in turn, provides insight into model behavior, a critical requirement of data-driven applications in nuclear security. Using data collected at the High Flux Isotope Reactor at Oak Ridge National Laboratory via a network of Merlyn multisensors, two different models were trained to classify the reactor’s operational state: a hidden Markov model (HMM), which is simpler and more transparent, and a feed-forward neural network, which is less inherently interpretable. Traditional wrapper methods for feature importance were extended to identify nodes and regions in the multisensor network with strong positive and negative impacts on the classification problem. These spatial-importance algorithms were evaluated on the two different classifiers. The classification accuracy was then improved relative to baseline models via feature selection from 0.583 to 0.839 and from 0.811 ± 0.005 to 0.884 ± 0.004 for the HMM and feed-forward neural network, respectively. While some differences in node and region importance were observed when using different classifiers and wrapper methods, the nodes near the facility’s cooling tower were consistently identified as important—a conclusion further supported by studies on feature importance in decision trees. Node and region importance methods are model-agnostic, inform feature selection for improved model performance, and can provide insight into opaque classification models in the nuclear security domain.

Tibbetts, Jake↗

DOE OSTI2024

Avian Activity Classification Using Recurrent Networks to Fuse Videos with Metadata on Imbalanced Datasets

Activity classification plays a crucial role in various real-life scenarios involving both humans and animals. There is an increasing need for precise activity classification focused on avian-solar interactions, as the usage of solar energy facilities, such as photovoltaic array power stations, has been observed to impact bird species richness, behavior, and activity. However, there has been no work to develop an automated system to monitor and classify these avian-solar interactions. All current methods rely on human observers, which is time and human resources costly and subject to errors related to searcher efficiency. With the recent success of Deep Learning models in activity classification problems, this paper develops a recurrent neural network-based model to automatically classify six avian activities around solar energy facilities. Our proposed model integrates critical feature engineering metadata with video frame data, enabling improved learning and more accurate activity classification. Furthermore, we address the challenge of data imbalance during training and demonstrate the efficacy of our model in detecting and classifying different activities within video tracks. Additionally, we analyze the saliency/backpropagation map of the trained proposed model and validate its decision-making rationale.

Avian activity classification; bidirectional LSTM;↗

DOE OSTI2022

Application of the metabolic modeling pipeline in KBase to categorize reactions, predict essential genes, and predict pathways in an isolate genome

The DOE Systems Biology Knowledgebase (KBase) platform offers a range of powerful tools for the reconstruction, refinement, and analysis of genome-scale metabolic models built from microbial isolate genomes. In this chapter, we describe and demonstrate these tools in action with an analysis of isoprene production in the Bacillus subtilis DSM genome. Two different methods are applied to build initial metabolic models for the DSM genome, then the models are gapfilled in three different growth conditions. Next, flux balance analysis (FBA) and flux variability analysis (FVA) techniques are applied to both study the growth of these models in minimal media and classify reactions within each model based on essentiality and functionality. The models are applied with the FBA method to predict essential genes, which are then compared to an updated list of essential genes obtained for B. subtilis 168, a very similar strain to the DSM isolate. The models are also applied to simulate Biolog growth conditions, and these results are compared with Biolog data collected for B. subtilis 168. Finally, the DSM metabolic models are applied to explore the pathways and genes responsible for producing isoprene in this strain. These studies demonstrate the accuracy and utility of models generated from the KBase pipelines, as well as exploring the tools available for analyzing these models.

DOE knowledgebase↗

NASA NTRSDate not supplied

Enabling Space Biological Knowledge Discovery Through Image and Video Data Sharing

Increased biomedical risks and challenges associated with deep space missions and experiments (cis-Lunar, Mars transit/surface) require new knowledge discovery and development of novel ecosystems. Supporting distant and long-duration missions and experiments requires biological data (from yeast, microbes, fruit flies, C. elegans, plants, crops, rodents, humans) be findable, accessible, interoperable, reusable (FAIR), and maximally open-access. As data-intensive, bioinformatic, meta-analytical, and computer-assisted approaches continue to be a centerpiece of modern research, the NASA Biological and Physical Sciences division is expanding its Open Science capabilities beyond NASA GeneLab. The NASA Ames Life Sciences Data Archive (ALSDA) is a repository which is responsible for collecting and access to space biological imagery and video, alongside tabular and environmental data. In this presentation, we will discuss strategies dealing with archiving, curating, and accessibility of images from very distinct imaging modalities (e.g., micro-computed tomography, magnetic resonance imaging, photographic images of plants, fluorescence microscopy, behavioral videos, etc.). There are two main challenges: 1. Open-source data storage and 2. Metadata related to the imagery-video. Both have been solved by leveraging two existing open-source systems. For data storage, ALSDA is utilizing components through the Open Microscopy Environment (OME), which can read most imaging proprietary formats and display on a web interface complex multidimensional images (Z stack, multi-channel, temporal, spectral). Most technical metadata from imaging modalities are captured seamlessly. For metadata capturing experimental details, ALSDA (like GeneLab) uses the ISA-Tab specification which relies on the ISA data model to order and classify metadata. The ISA data model uses a tree structure with three files to capture the metadata: The top layer is the Investigations file, the second layer is the Study file(s), and the last layer is the Assay file(s). We believe such an approach may be useful for other types of image research data from other investigators in the AGU community.

imaging↗

DOE OSTI2021

Application of the Metabolic Modeling Pipeline in KBase to Categorize Reactions, Predict Essential Genes, and Predict Pathways in an Isolate Genome

Allen, Benjamin↗

DOE OSTI2020

A Survey of Multizone Airflow Simulation Software

H-Canyon simulates the building and process ventilation to ensure positive contamination control for any modifications as well as evaluating off-normal conditions. Simulations can also be used to identify air quality of personnel occupied areas. The models can be classified into two groups, single and multi-zone models. As the name states, a single zone model assumes that the building can be described by a single, well-mixed zone. Whereas large buildings have structures that must be described as multizone. Multizone airflow models deal with the difficulty of flows in a building by distinguishing the effects of internal flow restrictions. Several models have been developed that take internal partitions into account. CONTAM (currently used) is a multizone airflow program created by NIST to determine airflows including infiltration, exfiltration, wind pressures acting outside the building, buoyancy effects caused by the indoor and outdoor air temperature difference. COMIS is a multizone air infiltration, ventilation, and contaminant transport model that was developed at Lawrence Berkeley National Laboratory. COMIS deals with applied pressure distribution, airflow components, HVAC systems, schedules, and contaminant transport. EnergyPlus is designed by DOE. It supports flexible component level configuration of HVAC models and simulates sub-hourly time steps to control fast dynamic systems. The program features include providing accurate environmental performance data including energy consumption and carbon emissions, and reporting solar gains on surfaces. Heavent is used to model industrial ventilation systems to control airborne contaminants. It's designed based on the American Conference of Governmental Industrial Hygienists (ACGIH) Ventilation manual. DesignBuilder is the most recognized and advanced user interface to EnergyPlus. It gives access to all of the most frequently required simulation capabilities covering building fabric, thermal mass, glazing, shading renewables, and HVAC analysis. The objective of this study is to identify all relevant software available including commercially licensed, freely licensed, and open source, that can be used to simulate large, complex process facility ventilation systems. All discovered software tools are evaluated for salient features and compared to the software tool currently used to simulate the H-Canyon ventilation system. The design criteria of a ventilation system has two basic requirements: Supplying fresh air for the occupants and changing the air in the room sufficiently; therefore, the smells, fumes, and contaminants will be removed. In this study, first, whether the software simulates airflow (infiltration, natural ventilation, and interzonal) or considers them to be inputs is discussed. Second, if indoor contaminant levels are considered; and finally suggestions on how airflow analysis can be more appropriately accounted for when performing airflow simulation of a building. All of the airflow software reviewed for this study can account for constant infiltration and natural ventilation rates that are not affected by changes in indoor and outdoor conditions. Modelling infiltration in EnergyPlus or DesignBuilder are applicable for small buildings and not appropriate for larger buildings like the H-Canyon. The effect of wind on external pressures, infiltration, and natural and mechanical ventilation, can also be calculated using all of these software. These programs have control options to switch between natural to mechanical ventilation modes or both (hybrid). Interzonal airflow can be applied which means one zone can be specified to receive a fixed amount of air from another zone. The following ventilation modeling software is recommended for further testing: CONTAM, COMIS, Heavent. The next step in evaluating the software will consist of creating test facility simulations using evaluation copies of the software.

42 ENGINEERING↗

DOE OSTI2023

Image Classification Using Convolutional Neural Networks to Automate Visual Inspection of CCO Containers (Rev. 1)

The Savannah River Site is automating the receipt and inspection of Criticality Control Overpack drums to aid in nuclear waste disposal. The Advanced Engineering group is automating this receipt and inspection process to assist the site’s goals. Part of this process includes visually inspecting CCO drums to ensure that no defects or security risks are present. This research focuses on developing a machine learning model to automatically classify drums as passing or failing inspection. The machine learning model was implemented using the open-source Tensorflow library and uses a Convolutional Neural Network architecture to extract features and differentiate between images. The model was able to achieve an average of 85% accuracy on a dataset of 288 drums. This project’s goal was to prove the validity of computer vision in an automation process and provide a starting place for continued research.

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

DOE OSTI2022

Inter-Domain Fusion for Enhanced Intrusion Detection in Power Systems: An Evidence Theoretic and Meta-Heuristic Approach

False alerts due to misconfigured or compromised intrusion detection systems (IDS) in industrial control system (ICS) networks can lead to severe economic and operational damage. However, research using deep learning to reduce false alerts often requires the physical and cyber sensor data to be trustworthy. Implicit trust is a major problem for artificial intelligence or machine learning (AI/ML) in cyber-physical system (CPS) security, because when these solutions are most urgently needed is also when they are most at risk (e.g., during an attack). To address this, the Inter-Domain Evidence theoretic Approach for Inference (IDEA-I) is proposed that reframes the detection problem as how to make good decisions given uncertainty. Specifically, an evidence theoretic approach leveraging Dempster–Shafer (DS) combination rules and their variants is proposed for reducing false alerts. A multi-hypothesis mass function model is designed that leverages probability scores obtained from supervised-learning classifiers. Using this model, a location-cum-domain-based fusion framework is proposed to evaluate the detector’s performance using disjunctive, conjunctive, and cautious conjunctive rules. The approach is demonstrated in a cyber-physical power system testbed, and the classifiers are trained with datasets from Man-In-The-Middle attack emulation in a large-scale synthetic electric grid. For evaluating the performance, we consider plausibility, belief, pignistic, and general Bayesian theorem-based metrics as decision functions. To improve the performance, a multi-objective-based genetic algorithm is proposed for feature selection considering the decision metrics as the fitness function. Finally, we present a software application to evaluate the DS fusion approaches with different parameters and architectures.

42 ENGINEERING↗

DOE OSTI2025

Decoding substrate specificity determining factors in glycosyltransferase-B enzymes – insights from machine learning models

Substrate specificity is an essential characteristic of any enzyme's function and an understanding of the factors that determine this specificity is crucial for enzyme engineering. Unlike the structure of an enzyme which is directly impacted by its sequence, substrate specificity as an enzyme attribute involves a rather indirect relationship with sequence as it also depends on structural aspects that dictate substrate accessibility and active site dynamics. In this study, we explore the performance of classifier-based machine learning models trained on curated sequence and structural data for a class of glycosyltransferases (GTs), namely GT-Bs, to understand their substrate specificity determining factors. GTs enable the transfer of sugar moieties to other biomolecules such as oligosaccharides or proteins and are found in all kingdoms of life. In plants, GTs participate in the biosynthesis of plant cell wall biopolymers (e.g.: hemicelluloses and pectins) and are an integral part of the enzymatic machinery that enables the storage of carbon and energy as plant biomass. To elucidate the substrate specificity of uncharacterized GT-Bs, we constructed multi-label machine learning models (Support Vector Classifier, K-Nearest Neighbors, Gaussian Naïve-Bayes, Random Forest) that incorporate both sequence and structural features. These models achieve good predictive accuracies on test datasets. However, despite our use of structural information, we highlight that there is further scope for improvement in training these models to draw interpretable relationships between sequence, structure and substrate specificity determining motifs in GT-Bs.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2022

Exploring New Ways to Classify Industries for Energy Analysis and Modeling

As the US moves closer to embracing a net zero greenhouse gas emissions position, combustion processes outside the power sector are becoming urgent concerns. Industry is an important end user of energy and relies on fossil fuels used directly for process heating and as feedstocks for a diverse range of applications. Fuel and energy use by industry is heterogeneous, meaning that even a single product group can vary broadly in its production routes and associated energy usage. In the US, the North American Industry Classification System (NAICS) serves as the basis for data collection and reporting. In turn, data based on NAICS is the foundation of most US energy modeling. Thus, the effectiveness of NAICS at representing energy use is a limiting condition for plans to improve energy efficiency and alternatives to fossil fuels in industry. Facility-level data to build more detail into heterogeneous sectors is scarce. This work explores alternative classification schemes for industry based on energy use characteristics, and provides a validation of an approach to make facility-level energy use estimates based on publicly available data from the greenhouse gas reporting program. First, several approaches to industrial taxonomies and their usefulness for industrial energy modeling are summarized. Data from Industrial Assessment Centers is analyzed using unsupervised machine learning techniques to detect clusters. Cladistics, an approach from biology, is adapted to energy and process characteristics of industries. A cladogram is presented for evolutionary directions in the iron and steel sector. Cladograms are a promising tool for constructing scenarios and summarizing directions of sectoral innovation. Finally, validation is performed for facility-level energy estimates from the US EPA Greenhouse Gas Reporting Program. This validation assists in making this data source available for use in energy modeling. Together, this work explores alternative approaches for categorizing industries in a way that aids understanding energy use, and presenting pathways for the future.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗

DOE OSTI2024

An Overview of Electric Vehicle Load Modeling Strategies for Grid Integration Studies

The adoption of electric vehicles (EVs) has emerged as a solution to reduce greenhouse gas emissions in the transportation sector, which has motivated the implementation of public policies to promote their use in several countries. However, the high adoption of EVs poses challenges for the electricity sector, as it would imply an increase in energy demand and possible impacts on the power quality (PQ) of the power grid. Therefore, it is important to conduct EV integration studies in the power grid to determine the amount that can be incorporated without causing problems and identify the areas of the power sector that will require reinforcements. Accurate EV load patterns are required for this type of study that, through mathematical modeling, reflect both the dynamic behavior and the factors that influence the decision to recharge EVs. This article aims to present an overview of EVs, examine the different factors considered in the literature for modeling EV load patterns, and review modeling methods. EV load modeling methods are classified into deterministic, statistical, and machine learning. The article shows that each modeling method has its advantages, disadvantages, and data requirements, ranging from simple load modeling to more accurate models requiring large datasets.

Computer Science↗