SEARCH · Engineering Papers

Results for “Predictive Modeling”

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 1,171 records · Page 65

All sources NASA NTRS DOE OSTI

DOE OSTI2022

In with the old, in with the new: machine learning for time to event biomedical research

The predictive modeling literature for biomedical applications is dominated by biostatistical methods for survival analysis, and more recently some out of the box machine learning approaches. In this article, we show a presentation of a machine learning method appropriate for time-to-event modeling in the area of prostate cancer long-term disease progression. Using XGBoost adapted to long-term disease progression, we developed a predictive model for 118 788 patients with localized prostate cancer at diagnosis from the Department of Veterans Affairs (VA). Our model accounted for patient censoring. Harrell’s c-index for our model using only features available at the time of diagnosis was 0.757 95% confidence interval [0.756, 0.757]. Our results show that machine learning methods like XGBoost can be adapted to use accelerated failure time (AFT) with censoring to model long-term risk of disease progression. Furthermore, the long median survival justifies and requires censoring. Overall, we show that an existing machine learning approach can be used for AFT outcome modeling in prostate cancer, and more generally for other chronic diseases with long observation times.

96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗

DOE OSTI2024

Machine learning-enhanced model-based scenario optimization for DIII-D

Abstract Scenario development in tokamaks is an open area of investigation that can be approached in a variety of different ways. Experimental trial and error has been the traditional method, but this required a massive amount of experimental time and resources. As high fidelity predictive models have become available, offline development and testing of proposed scenarios has become an option to reduce the required experimental resources. The use of predictive models also offers the possibility of using a numerical optimization process to find the controllable inputs that most closely achieve the desired plasma state. However, this type of optimization can require as many as hundreds or thousands of predictive simulation cases to converge to a solution; many of the commonly used high fidelity models have high computational burdens, so it is only reasonable to run a handful of predictive simulations. In order to make use of numerical optimization approaches, a compromise needs to be found between model fidelity and computational burden. This compromise can be achieved using neural networks surrogates of high fidelity models that retain nearly the same level of accuracy as the models they are trained to replicate while reducing the computation time by orders of magnitude. In this work, a model-based numerical optimization tool for scenario development is described. The predictive model used by the optimizer includes neural network surrogate models integrated into the fast Control-Oriented Transport simulation framework. This optimization scheme is able to converge to the optimal values of the controllable inputs that produce the target plasma scenario by running thousands of predictive simulations in under an hour without sacrificing too much prediction accuracy.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

DOE OSTI2019

Measurement of prompt D 0 , D + , D *+ , and DS+$ {\mathrm{D}}_{\mathrm{S}}^{+} $ production in p–Pb collisions at sNN$ \sqrt{{\mathrm{s}}_{\mathrm{NN}}} $ = 5.02 TeV

The measurement of the production of prompt D 0 , D + , D *+, and $D_S^+$ mesons in proton–lead (p–Pb) collisions at the centre-of-mass energy per nucleon pair of \mathrm{\sqrt{s_{NN}}}$ = 5.02 TeV, with an integrated luminosity of 292 ± 11 μb -1 , are reported. Differential production cross sections are measured at mid-rapidity (-96 < y cms < 0.04) as a function of transverse momentum (p T ) in the intervals 0 < p T < 36 GeV/c for D 0 , 1 < p T < 36 GeV/c for D + and D *+ , and 2 < p T < 24 GeV/c for D + mesons. For each species, the nuclear modification factor R pPb is calculated as a function of p T using a proton-proton (pp) reference measured at the same collision energy. The results are compatible with unity in the whole p T range. The average of the non-strange D mesons R pPb is compared with theoretical model predictions that include initial-state effects and parton transport model predictions. The p T dependence of the D 0 , D + , and D *+ nuclear modification factors is also reported in the interval 1 < p T < 36 GeV/c as a function of the collision centrality, and the central-to-peripheral ratios are computed from the D-meson yields measured in different centrality classes. The results are further compared with charged-particle measurements and a similar trend is observed in all the centrality classes. The ratios of the p T -differential cross sections of D 0 , D + , D *+ , and $D_S^+$ mesons are also reported. The $D_S^+$ and D + yields are compared as a function of the charged-particle multiplicity for several p T intervals. No modification in the relative abundances of the four species is observed with respect to pp collisions within the statistical and systematic uncertainties.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

DOE OSTI2016

A simple physiologically based pharmacokinetic model evaluating the effect of anti-nicotine antibodies on nicotine disposition in the brains of rats and humans

Physiologically based pharmacokinetic (PBPK) modeling was applied to investigate the effects of anti-nicotine antibodies on nicotine disposition in the brains of rats and humans. Successful construction of both rat and human models was achieved by fitting model outputs to published nicotine concentration time course data in the blood and in the brain. Key parameters presumed to have the most effect on the ability of these antibodies to prevent nicotine from entering the brain were selected for investigation using the human model. These parameters, which included antibody affinity for nicotine, antibody cross-reactivity with cotinine, and antibody concentration, were broken down into different, clinically-derived in silico treatment levels and fed into the human PBPK model. Model predictions suggested that all three parameters, in addition to smoking status, have a sizable impact on anti-nicotine antibodies' ability to prevent nicotine from entering the brain and that the antibodies elicited by current human vaccines do not have sufficient binding characteristics to reduce brain nicotine concentrations. If the antibody binding characteristics achieved in animal studies can similarly be achieved in human studies, however, nicotine vaccine efficacy in terms of brain nicotine concentration reduction is predicted to meet threshold values for alleviating nicotine dependence. - Highlights: • Modelling of nicotine disposition in the presence of anti-nicotine antibodies • Key vaccine efficacy factors are evaluated in silico in rats and in humans. • Model predicts insufficient antibody binding in past human nicotine vaccines. • Improving immunogenicity and antibody specificity may lead to vaccine success.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2022

Tunable plasmon-enhanced second-order optical nonlinearity in transition-metal dichalcogenide nanotriangles (Final Report for SC0008712)

The control of light-matter interaction at the nanoscale is a grand challenge that cuts across modern photonics, plasmonics, and optoelectronics. The development of simulation tools for predictive modeling of nanostructured light emitters and absorbers is critical to successfully tackling this grand challenge. Existing state-of-the-art tools are not suitable for the following reasons: a) Phenomenological models of materials, commonly employed in the full-wave solutions to Maxwell’s equations, are fit to experimental data for bulk materials and fall short when attempting to analyze nanostructures. b) Nonlinearities in optical response can arise solely from nanostructuring, and require time-dependent quantum electronic transport techniques to capture. c) Emergent materials with exotic and tunable physical properties are increasingly used, but their properties are very sensitive to the substrate, impurities, and edge termination, and require an accurate description of interband and intraband processes, as well as dissipation. d) Microscopic modeling of electronic transport usually employs simplified electrodynamics, and realistic models that couple full electronic transport with full-wave electrodynamics are needed for accurate photonics simulations. The objective of this project was to computational tools that will overcome the limitations faced by current modeling tools and provide an unprecedented level of accuracy for predictive modeling of light-matter interaction at the nanoscale.

36 MATERIALS SCIENCE↗

DOE OSTI2021

Challenges and Potential of Waveform Modeling for Crustal Scale Predictions

Waveform modeling is crucial to improving our understanding of observed seismograms. Forward simulation of wavefields provides quantitative methods of testing interactions between complicated source functions and the propagation medium. Here, we discuss three experiments designed to improve under standing of high frequency seismic wave propagation. First, we compare observed and predicted travel times of crustal phases for a set of real observed earthquakes with calculations and synthetic seismograms. Second, we estimate the frequency content of a series of nearly co-located earthquakes of varying magnitude for which we have a relatively well- known 1D velocity model. Third, we apply stochastic perturbations on top of a 3D tomographic model and qualitatively assess how those variations map to differences in the seismograms. While different in scope and aim, these three vignettes illustrate the current state of crustal scale waveform modeling and the potential for future studies to better constrain the structure of the crust.

58 GEOSCIENCES↗

DOE OSTI2026

The Use of Machine Learning Models for Predicting the Dielectric Strength of Gases

Technological advancements in high voltage systems have pushed sulfur hexafluoride (SF6) to its operational limits. Furthermore, this gas has other drawbacks including a high liquefaction temperature and a high global warming potential. Therefore, there has been an urgent need to find alternative gases with high dielectric strength (DS). In this work, density functional theory (DFT) is used to calculate molecular descriptors that are fed into an artificial neural network (ANN) and a random forest (RF). These machine learning (ML) models are then used to predict the DS for hundreds of molecules. A finite element model (FEM) is also used to calculate the electric field profile of multiple simple electrode geometries as the applied voltage to the system is increased. Results indicate that the random forest model has better generalization to unseen data than the neural network. The highest DS value predicted by the RF was 2.16 relative to the experimental DS of SF6. The results also demonstrate how choosing a gas with a higher DS and a geometry with minimal edges and corners can significantly increase the operating voltage of an electrical system. Due to its superior generalization, the RF represents the most promising path toward an accurate DS predictor once sufficient experimental data are available.

Mileski, Matthew [AFIT]↗

DOE OSTI2022

Influence of sequential stimulation practices on geochemical alteration of shale

Water-based hydraulic fracturing fluids (HFFs) can chemically interact with formation shale, resulting in altered porosity and permeability of the host rock. Experimental investigations of spatial and temporal shale-HFF interactions are helpful in interpreting chemical compositions of the injectate, as well as predicting alteration of hydraulic properties in the reservoir due to mineral dissolution and precipitation. Most bench-top experiments designed to study shale-HFF chemical interactions, either using batch reactors or flow-through setups, are carried out assuming that the acid spearhead has already become mixed with neutral HFFs. During operations, however, HFFs are typically injected according to a sequenced pumping schedule, starting with a concentrated acid spearhead, followed by multiple additions of near-neutral pH HFFs containing chemical amendments and proppant. In this study, we use geochemical modeling to consider whether this pre-mixed experimental protocol provides results directly comparable to a sequential discrete fluid-shale interaction protocol. Our results show that for the batch system, the transient evolution in major ion concentrations is faster with the sequential procedure. After 2 h of reaction time, the two protocols converge to the same aqueous concentrations. In a flow-through geometry, the pre-mixed model predicts extensive chemical alteration close to the injection point but negligible alteration downstream. In contrast, the sequential model predicts mineral reactions over hundreds of meters along the flow path. The extent of shale alteration in the sequential model at a given location depends on shale mineralogy and where the acid spearhead resides during the shut-in period. The predictive model developed in this study can help experimentalists to design bench-top tests and operators to better translate the results of laboratory experiments into practical applications.

Li, Qingyun↗

DOE OSTI2021

Improving Short Term Predictability of Hydrologic Models with Deep Learning

Focal Area: Focal Area 2. Predictive modeling through the use of AI techniques and AI-derived model components; the use of AI and other tools to design a prediction system comprising of a hierarchy of models (e.g., AI driven model/component/parameterization selection). Science Challenge: A major challenge exists in the lack of reliable predictive modeling of water-cycle extremes using macro-scale hydrologic models that are driven by atmospheric climate data. This causes a critical knowledge gap in understanding the magnitudes, probabilities, and severity of droughts, rainfall, and flooding. Improved understanding of these extreme events requires more accurate modeling at high spatial and temporal resolutions. This shortcoming is especially apparent when complex couplings between atmospheric quantities and engineered systems emerge, such as during extreme precipitation or drought events and at intersections of atmospheric-land-fluvial-ocean systems. Added complexity around representing operations of engineered infrastructure leads to a limited capability to analyze the temporal and spatial implications of compounding extreme events across inland and coastal regions. This results in profound challenges for water and power systems operators, agriculture production, and regional infrastructure planning. The science challenge can be summarized as How can we use AI/ML to improve short term predictability of extreme water-cycle events and associated risk, especially compounding events and extreme rainfall patterns that result in flooding, to inland and coastal communities under different climate scenarios?

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2013

Defect disorder in UO{sub 2}

A defect disorder model has been developed to determine equilibrium off-stoichiometry and its spatial variations in UO{sub 2} crystals. The model gives the concentrations of atomic defects and electronic carriers as functions of oxygen partial pressure and temperature in the bulk and near crystal surfaces subject to an oxygen environment. Energetic parameters from published density functional theory calculations have been integrated into the defect disorder model for an accurate determination of the defect density and off-stoichiometry. The ionosorption theory has been used to couple the oxygen environment with the defect state in the crystal as we solved for the defect disorder near crystal surfaces. Contrary to the common belief that hyper-stoichiometry of UO{sub 2} is dominated by oxygen interstitials, the current model predicts that this regime is rather dominated by uranium vacancies. The model predictions also show that, in the presence of surfaces, the point defect concentrations vary by orders of magnitude in the subsurface region relative to the bulk region. Highlights: • Defect disorder in bulk UO2+x is modeled in terms of temperature and oxygen pressure. • The densities of atomic defects and electronic charge carriers are determined. • The model is extended to study the heterogeneity of defect density near crystal surfaces. • The surface effect is modeled using ionosorption theory. • The dominant defect type and off-stoichiometry profile near surface are found.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

DOE OSTI2021

DEPRECATED AI-Batt-OS (Autonomous Identification of Battery Life Models - Open Source) [SWR 21-17]

DEPRECATED. This repository was archived by the owner on Jun 30, 2026. It is now read-only. Open source implementation of some of the methods utilized by AI-Batt, a battery lifetime modeling and analysis toolkit provided by the National Laboratory of the Rockies (NLR). This software demonstrates the use of bi-level optimization and symbolic regression techniques to semi-autonomously identify algebraic models predicting the capacity fade of lithium-ion batteries during calendar aging. Modeling the degradation of batteries is a complex task, due to the difficulty in separating the time-dependent and time-independent factors impacting cell level degradation, across multiple data series with different numbers of measurements and/or data quality. Bi-level optimization enables model parameters to be optimized to either the entire data set or to individual data series, allowing statistical disambiguation of global behaviors (data series independent) and local behaviors (data series dependent). Symbolic regression is used to automatically search for optimal low-dimesional models predicting the variation of locally optimized parameters versus time-independent experimental variables from millions of possible models, resulting in a more accurate and repeatable model identification process than is possible by a manual search. The provided tools also implement cross-validation and bootstrap resampling schemes, empowering statistical model comparison/selection and quantification of model uncertainties. An example script replicates the results from the manuscript "Challenging Practices of Algebraic Battery Life Models through Statistical Validation and Model Identification via Machine-Learning", submitted to ECS. All code is written in MATLAB. Requires the Statistics and Machine Learning Toolbox. Contact Dr. Paul Gasper at Paul.Gasper@nlr.gov for any questions.

Gasper, Paul↗

DOE OSTI2021

Development of Explainable, Knowledge-Guided AI Models to Enhance the E3SM Land Model Development and Uncertainty Quantification

Focal Area(s): (2)Predictive modeling using AI techniques and AI-derived model components; use of AI and other tools to design a prediction system comprising of a hierarchy of models. (3) Insight gleaned from complex data (both observed and simulated) using AI, big data analytics, and other advanced methods, including explainable AI and physics- or knowledge- guided AI. Science Challenge: The Energy Exascale Earth System Model (E3SM) is a fully coupled, state-of-the-science Earth system model that uses code optimized for DOE's advanced computers to address the most critical scientific questions facing our nation and society (Golaz et al., 2019). The E3SM Land model (ELM) is designed to understand how the changes in terrestrial land surfaces will interact with other Earth system components and has been used to understand hydrologic cycles, biogeophysics, and ecosystem dynamics. In spite of great successes, the ELM has several known issues that restrain rapid improvements. For example, the ELM uses equilibrium models to simulate dynamic land-climate interactions and it requires long model spin-up time to identify suitable initial conditions for transient simulations. The ELM lacks built-in uncertainty mechanisms that can improve the robustness of model predictions. The ELM is a holistic, deterministic model system with a rigid design, and in many situations, it is hard to modify the ELM system to incorporate new theory/hypothesis and new data across scales to address emerging science problems (such as predicting the impacts of water cycle extremes). In addition, The ELM is technically optimized for traditional CPU-centric computers and it cannot fully utilize the current and incoming leadership computers for model simulations and uncertainty quantification (UQ). The success of artificial intelligence (AI) has inspired scientists to use AI models to discover intrinsic features from simulation data (Chattopadhyay et al., 2020) and observational data (Reichstein et al., 2019) to gain further process understanding of Earth science problems. However, autonomous AI model training through deep learning usually requires a huge amount of annotated data. To overcome the limitations from the data and computing resources, knowledge-guided AI models are necessary where human-knowledge is ingested in model construction (Banino et al., 2018) and training process (Silver et al., 2016) for efficient learning. Herein, we present a new way that leverages the process understanding from the ELM to guide AI model development for the ELM enhancement and UQ. We hope this study can inspire further Earth and environmental system model developments and transformations.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2023

Integration of Biorelevant Pediatric Dissolution Methodology into PBPK Modeling to Predict In Vivo Performance and Bioequivalence of Generic Drugs in Pediatric Populations: a Carbamazepine Case Study

This study investigated the impact of gastro-intestinal fluid volume and bile salt (BS) concentration on the dissolution of carbamazepine (CBZ) immediate release (IR) 100 mg tablets and to integrate these in vitro biorelevant dissolution profiles into physiologically based pharmacokinetic modelling (PBPK) in pediatric and adult populations to determine the biopredictive dissolution profile. Dissolution profiles of CBZ IR tablets (100 mg) were generated in 50–900 mL biorelevant adult fasted state simulated gastric and intestinal fluid (Ad-FaSSGF and Ad-FaSSIF), also in three alternative compositions of biorelevant pediatric FaSSGF and FaSSIF medias at 200 mL. This study found that CBZ dissolution was poorly sensitive to changes in the composition of the biorelevant media, where dissimilar dissolution (F2 = 46.2) was only observed when the BS concentration was changed from 3000 to 89 μM (Ad-FaSSIF vs Ped-FaSSIF 50% 14 BS). PBPK modeling demonstrated the most predictive dissolution volume and media composition to forecast the PK was 500 mL of Ad-FaSSGF/Ad-FaSSIF media for adults and 200 mL Ped-FaSSGF/FaSSIF media for pediatrics. A virtual bioequivalence simulation was conducted by using Ad-FaSSGF and/or Ad-FaSSIF 500 mL or Ped-FaSSGF and/or Ped-FaSSIF 200 mL dissolution data for CBZ 100 mg (reference and generic test) IR product. The CBZ PBPK models showed bioequivalence of the product. This study demonstrates that the integration of biorelevant dissolution data can predict the PK profile of a poorly soluble drug in both populations. Further work using more pediatric drug products is needed to verify biorelevant dissolution data to predict the in vivo performance in pediatrics.

60 APPLIED LIFE SCIENCES↗

DOE OSTI2024

The use of digital thread for reconstruction of local fiber orientation in a compression molded pin bracket via deep learning

A deep convolutional neural network (DCNN) was used for microstructure reconstruction using artificial intelligence (MR-AI) by predicting local average fiber orientation distributions (FOD) in a 3D prepreg platelet molded composite (PPMC) pin bracket. To train the MR-AI model, surface strain fields from residual stresses simulated in PPMC plates were used as the input to the DCNN. A training dataset included PPMC plates with various degrees of global fiber alignment, based on the information obtained from high-fidelity flow simulation of a pin bracket. Further, the MR-AI model was then deployed to analyze FOD in the 3D pin bracket by conducting thermo-elastic residual stress analysis. Initially, the MR-AI model was established entirely on the synthetic simulation data. Then, a μCT scan of a physically molded pin bracket was used to create a finite element model that provided data for additional validation of the DCNN model. For the μCT scan finite element pin bracket the MR-AI model predicted the distribution of fiber orientation tensor components with MAE of 0.10 indicating a global prediction error of 10%. For the flow simulated pin bracket, the MR-AI model predicted the distribution of fiber orientation tensor components with a global prediction error of 11%. The MR-AI model showed the ability to predict regions of varying alignment in the base and flange of the pin bracket. The proposed MR-AI methodology allows for rapid prediction of FOD in geometrically complex parts and offers a promising path to detecting unique fiber orientation states in molded components.

42 ENGINEERING↗

DOE OSTI2020

Predictive Integrated Modeling of Heated Tokamak Plasmas (Final Technical Report)

The research carried out by the Lehigh University fusion group during this reporting period: (1) Self-consistent predictive core-pedestal ITER scenario modeling; (2) Microtearing instabilities and electron thermal transport in standard and spherical tokamak discharges; (3) Neural network model of the Multi-Mode anomalous transport module; (4) Anomalous transport in KSTAR, JET, EAST, Alcator C-Mod and DIII-D discharges; (5) Theory for transport in magnetized plasmas; (6) Control-oriented modeling of the q-profile dynamic response in preparation for advanced scenario control in KSTAR and in EAST; (7) Modeling of edge harmonic oscillation in DIII-D QH mode discharges; (8) Elucidating plasma dynamics in Hasegawa-Wakatani turbulence by information geometry; (9) Non-linear Langevin and Fractional Fokker–Planck equations for anomalous diffusion by Levy stable processes; and (10) Investigation of the plasma shaping effects on the H-mode pedestal structure.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

DOE OSTI2022

Accelerated screening of functional atomic impurities in halide perovskites using high-throughput computations and machine learning

The pressing need for novel materials that can serve rising demands in solar cell and optoelectronic technologies makes the nexus of halide perovskites, high-throughput computations, and machine learning, very promising. Ever increasing amounts of data on the structure, fundamental properties, and device performance of halide perovskites provide opportunities for learning chemical rules and design principles that make these materials attractive, and applying them across wide chemical spaces. In this work, we show that impurity properties of halide perovskites computed using density functional theory (DFT) can be combined with machine learning (ML) to deliver predictive models and quick identification of optoelectronically active impurity atoms. Our computation lead to the largest reported dataset of the formation energies and charge transition levels of Pb-site impurities in methylammonium lead halide (MAPbX 3 ) perovskites. Descriptors are defined to uniquely represent any impurity atom in any MAPbX 3 compound and mapped to the computed impurity properties using regression techniques such as Gaussian process regression, neural networks, and random forests. We use the best optimized predictive models to make predictions for hundreds of impurities across 9 MAPbX 3 compounds and create lists of dominating impurities, that is, impurities that can shift the equilibrium Fermi level in the perovskite as determined by native point defects. Finally, this accelerated screening powered by computations and machine learning can guide the identification of problematic impurities that may cause undesired recombination of charge carriers, as well as impurities that can be deliberately introduced to tune the perovskite conductivity and resulting photovoltaic absorption.

36 MATERIALS SCIENCE↗

DOE OSTI2017

Infrared Emission from Kilonovae: The Case of the Nearby Short Hard Burst GRB 160821B

In this paper, we present constraints on Ks-band emission from one of the nearest short hard gamma-ray bursts, GRB 160821B, at z = 0.16, at three epochs. We detect a red relativistic afterglow from the jetted emission in the first epoch but do not detect any excess kilonova emission in the second two epochs. We compare upper limits obtained with Keck I/MOSFIRE to multi-dimensional radiative transfer models of kilonovae, that employ composition-dependent nuclear heating and LTE opacities of heavy elements. We discuss eight models that combine toroidal dynamical ejecta and two types of wind and one model with dynamical ejecta only. We also discuss simple, empirical scaling laws of predicted emission as a function of ejecta mass and ejecta velocity. Our limits for GRB 160821B constrain the ejecta mass to be lower than 0.03 M ⊙ for velocities greater than 0.1 c. At the distance sensitivity range of advanced LIGO, similar ground-based observations would be sufficiently sensitive to the full range of predicted model emission including models with only dynamical ejecta. Finally, the color evolution of these models shows that I–K color spans 7–16 mag, which suggests that even relatively shallow infrared searches for kilonovae could be as constraining as optical searches.

79 ASTRONOMY AND ASTROPHYSICS↗

DOE OSTI2018

Charging Decision Making for Automated Electric Vehicles

Abstract: Overview/Significance With the emerging of autonomous driving and its application in electric vehicles, the charging decision making should be taken over by the vehicles. Autonomous electric vehicles will require the capability to make charging decisions according to the battery energy state, the travel demand and also the available charging infrastructure. The introduction of autonomous driving technology would remove the challenge of co-locating charging infrastructure with driver destinations and presents a driver-free method for EVs to reach nearby charging stations. This will significantly change the charging behavior of electric vehicles. EV driver will no longer need to be present at charging stations for charging actions. Automated EVs can drive to nearby charging stations to perform charging actions by themselves when necessary. Meanwhile, connected vehicles technology makes electric vehicles have the capability to sense and obtain pertinent information from nearby charging station networks and then calculate the corresponding costs and availability for charging. All these promising capabilities bring new opportunities to construct an automatic charging decision making system and improve energy efficiency of charging actions for automatic electric vehicles. Abstract: Methodology This research introduces optimization tools and case studies on charging decision making for automated electric vehicles under personal usage scenario. The designed optimization tools aim to provide charging strategies, i.e. the optimal choice of charging station outside home and the amount of charged energy, by considering constraints from personal daily itineraries and existing charging infrastructure. Abundant real world EV data is utilized to construct stochastic energy consumption prediction model under realistic driving conditions. Advanced dynamic programming technology is utilized to model and solve the potential multi-stage decision making process by considering realistic uncertainties of EV energy cost and dynamics of itinerary information. Large-scale simulation studies using Chicago itinerary data are demonstrated to illustrate energy benefits from automatic charging decision making for future autonomous EVs. Abstract: Results/Conclusions Optimal automatic charging decision making and its energy benefits have been studied for personal automated electric vehicles. A data-driven method based on large amount of real-world data and the corresponding real-time update algorithm have been proposed to construct multi-channel stochastic energy consumption prediction model. Based on the energy cost prediction, dynamic multi-stage charging decision-making models are established for optimal strategies during a daily itinerary. Derived charging strategies can minimize the monetary and energy cost of charging actions for autonomous vehicles. Simulations and case studies show the potential ability of autonomous electric vehicles to reduce the range anxiety and charging infrastructure dependency. Automatic charging decision making can mitigate the pain from electric vehicle charging necessity outside home. In conclusion, automated electric vehicles equipped with an appropriate automatic charging decision making system will help EV driver to relieve from heavy time cost of recharging, reduce the energy cost of performing charging actions and improve the energy efficiency in future electrified transportation system.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗