Search NASA⌕ Search

SEARCH · Search NASA

Results for “Learning control”

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 1,423 records · Page 79

Machine-Learning-Driven, Site-Specific Weather Forecasting for Grid-Interactive Efficient Buildings: Preprint

Emerging grid-interactive efficient buildings (GEBs) have great potential to provide much-needed demand flexibility to electric grids while fulfilling their own control targets by co-optimizing smart appliances, solar photovoltaics, electric vehicles, and energy storage at buildings. To enable the optimal operation of GEBs, site-specific weather information—such as temperature, solar irradiance, relative humidity, and wind speed—is crucial; however, this information is generally unavailable or expensive to obtain. This paper develops advanced machine learning methods to provide precise weather forecasts for individual building sites using readily available weather station data. Support vector regression and artificial neural networks have been employed to learn the spatiotemporal correlations between the weather conditions at nearby weather stations and the individual building site. The proposed site-specific weather forecasting methods have been validated using 1-year actual weather measurement data collected in the Denver metro area. Results show that the developed machine-learning-driven methods can accurately forecast the temperature at the target building site 1 hour ahead with mean absolute error less than 0.72°C and a 48% improvement over the persistence method. Site-specific weather forecasts will improve the understanding of the microclimate effect and its impact on building energy consumption. This information will drive efficiency upgrades and adjustments of building control strategies to improve energy savings and increase flexibility in building loads.

30 DIRECT ENERGY CONVERSION↗

Physics in the Machine: Integrating Physical Knowledge in Autonomous Phase-Mapping

Application of artificial intelligence (AI), and more specifically machine learning, to the physical sciences has expanded significantly over the past decades. In particular, science-informed AI, also known as scientific AI or inductive bias AI, has grown from a focus on data analysis to now controlling experiment design, simulation, execution and analysis in closed-loop autonomous systems. The CAMEO (closed-loop autonomous materials exploration and optimization) algorithm employs scientific AI to address two tasks: learning a material system’s composition-structure relationship and identifying materials compositions with optimal functional properties. By integrating these, accelerated materials screening across compositional phase diagrams was demonstrated, resulting in the discovery of a best-in-class phase change memory material. Key to this success is the ability to guide subsequent measurements to maximize knowledge of the composition-structure relationship, or phase map. In this work we investigate the benefits of incorporating varying levels of prior physical knowledge into CAMEO’s autonomous phase-mapping. This includes the use of ab-initio phase boundary data from the AFLOW repositories, which has been shown to optimize CAMEO’s search when used as a prior.

97 MATHEMATICS AND COMPUTING↗

Fuzzy Logic Based Anomaly Detection for Embedded Network Security Cyber Sensor

Resiliency and security in critical infrastructure control systems in the modern world of cyber terrorism constitute a relevant concern. Developing a network security system specifically tailored to the requirements of such critical assets is of a primary importance. This paper proposes a novel learning algorithm for anomaly based network security cyber sensor together with its hardware implementation. The presented learning algorithm constructs a fuzzy logic rule based model of normal network behavior. Individual fuzzy rules are extracted directly from the stream of incoming packets using an online clustering algorithm. This learning algorithm was specifically developed to comply with the constrained computational requirements of low-cost embedded network security cyber sensors. The performance of the system was evaluated on a set of network data recorded from an experimental test-bed mimicking the environment of a critical infrastructure control system.

97 MATHEMATICS AND COMPUTING↗

Macroscopic Traffic Modeling Using Probe Vehicle Data: A Machine Learning Approach

Abstract The macroscopic fundamental diagram (MFD) captures an orderly relationship among traffic flow, density, and speed at the network level. It is a simple yet powerful tool for modeling traffic dynamics in large urban networks with broad application in traffic control and management. However, empirically derived MFDs in urban regions require high-resolution traffic data from the network. Having the network flow and vehicular density estimated at the (granular) census tract level using vehicle probe data, we apply machine learning methods to predict the MFDs across U.S. urban areas and capture the impacts of location-specific input features on the network flow–density relationships at a large scale. The results show that, among the four tested machine learning approaches (Random Forest, XGBoost, Support Vector Machine, and Neural Network), XGBoost delivers the best performance in predicting network traffic flow based on vehicular density and location attributes. Using interaction Shapley Additive explanation (SHAP) values and partial correlation analysis, we examine the factors influencing MFD shapes across different locations. Our empirical findings reveal that across U.S. urban areas, network topology, transportation infrastructure, and land use are primary factors shaping MFD curves, while demand and trip-related factors play a lesser role. Specifically, higher ranking roads, centrality, and development levels correlate positively with network capacity and critical density, whereas negative associations are observed for network connectivity, mixed-use development, and road roughness levels.

Jin, Ling↗

Improved deep learning prediction of antigen–antibody interactions

Identifying antibodies that neutralize specific antigens is crucial for developing effective immunotherapies, but this task remains challenging for many target antigens. The rise of deep learning–based computational approaches presents a promising avenue to address this challenge. Here, we assess the performance of a deep learning approach through two benchmark tests aimed at predicting antibodies for the receptor-binding domain of the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) spike protein. Three different strategies for constructing input sequence alignments are employed for predicting structural models of antigen–antibody complexes. In our initial testing set, which comprises known experimental structures, these strategies collectively yield a significant top-ranked prediction for 61% of cases and a success rate of 47%. Notably, one strategy that utilizes the sequences of known antigen binders outperforms the other two, achieving a precision of 90% in a subsequent test set of ~1,000 antibodies, balanced between true and control antibodies for the antigen, albeit with a lower recall of 25%. Our results underscore the potential of integrating deep learning methods with single B cell sequencing techniques to enhance the prediction accuracy of antigen–antibody interactions.

Science & Technology - Other Topics↗

Data-based Aggregate Model of Refrigerators for Electric Power Grid Services

Electrical power system stability under high penetration of intermittent renewable energy generation, such as wind and solar energy, has become a high concern. It is unpredictable and hard to control due to little inertial behavior characteristic to these generation resources. To help mitigate possibly undesirable frequency excursions, demand-side frequency control presents an emerging solution. By observing the frequency deviation, devices could switch operating modes for a short time to rebalance generation. To analyze device level control algorithms, aggregate models for their behavior are needed. Refrigerators are household devices that could help with load modulation. This paper uses real measured data to analyze the refrigerator behavior, learn about its operating mode and power consumption ranges. A Markov chain process is proposed to model the transition of a refrigerator population from one operating mode to another, such that the overall load is modulated according to the control input. The Markov-chain model can be used to design control so that the overall load is modulated according to the control input.

Markov chain model, demand response, refrigerator,↗

World Record Earned Value Management System Certification for Cleanup of the East Tennessee Technology Park, Oak Ridge, Tennessee, USA - 13181

On projects that require Earned Value Management (EVMS) Certification, it is critical to quickly prepare for and then successfully obtain certification. This is especially true for government contracts. Projects that do poorly during the review are subject to financial penalties to their company and they lose creditability with their customer creating problems with the project at the outset. At East Tennessee Technology Park (ETTP), we began preparing for Department of Energy (DOE) certification early during proposal development. Once the contract was awarded, while still in transition phase from the previous contractor to our new company, we immediately began reviewing the project controls systems that were in place on the project and determined if any replacements needed to be made immediately. The ETTP contract required the scheduling software to be upgraded to Primavera P6 and we determined that no other software changes would be done prior to certification. Next, preparation of the Project Controls System Description (PCSD) and associated procedures began using corporate standards as related to the project controls systems. During the transition phase, development was started on the Performance Measurement Baseline which is the resource loaded schedule used to measure our performance on the project and which is critical to good Earned Value Management of the project. Early on, and throughout the baseline review, there was positive feedback from the Department of Energy that the quality of the new baseline was good. Having this superior baseline also contributed to our success in EVMS certification. The combined companies of URS and CH2M Hill had recent experience with certifications at other Department of Energy sites and we were able to capitalize on that knowledge and experience. Generic PCSD and procedures consistent with our co-operations approach to Earned Value Management were available to us and were easily tailorable to the specifics of our contract and site. We also had corporate EVMS experts available to us so as to draw upon their recent certification experiences with lessons learned. This knowledge was especially helpful for training of personnel that were involved in the certification which included Project Controls, Project Management and Control Account Managers. We were also able to bring in these corporate experts to assist with our training efforts. To assure our readiness for the review, we conducted a 'White Hat' review. The 'White Hat' team consisted of corporate experts in EVMS along with an industry expert in EVMS from Humphrey and Associates. This review identified early any weaknesses that we had so corrections could be enacted prior to the EVMS Certification Readiness Review. It also helped give the evaluators confidence that we had done proper due diligence prior to their arrival. Also critical to our success, was early communication with our evaluators. It is important to start the communications early to ensure you understand the expectations of the certification team and the process that will be used during the certification. Communication through the entire process is critical to understand expectations and issues along the way. Very important to the overall process was management commitment, support and reinforcement. Management made sure that all personnel involved knew the importance and made preparations a priority. This was noted as a key strength by the evaluators during the out-brief. As a result of our preparation, our review yielded one Corrective Action Report (CAR) and two Continuous Improvement Opportunities (CIOs). The Certification team in their out-brief explained that this was the lowest number of CARs and CIOs in the history of EVMS certifications in the DOE Complex. (authors)

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

Six Machine-Learning Methods for Predicting Hospital-Stay Duration for Patients with Sepsis: A Comparative Study

Sepsis is a life-threatening medical condition that, if not treated promptly, can result in tissue damage, organ failure, and death. According to the Centers for Disease Control, about 270,000 individuals die of sepsis in the US each year. Further, sepsis expenditures accounted for 13% of total US hospital costs in 2013, totaling more than $24 billion. Our project objectives were to determine if Machine Learning algorithms could reliably predict hospital stay duration for patients with sepsis. The data set we used has been de-identified and is freely available through the BupaR package. The data includes 1050 cases, 15214 events, and 16 types of actions related to sepsis patient care. First, we used process mining to determine how long each patient was in the hospital. Using BupaR’s functions, we created several process model graphs. These process models depict the movement of patients at a hospital and provide duration data for each patent case. Second, we identified outlier data and created two dataset versions: one with and one without outliers. We then applied the following analysis methods: Linear Regression, Random Forest, K-Nearest Neighbors, Neural Networks, XGBoost, and lightGBM. We compared the model validations for the six machine learning models using the same data-splitting method. We found that the XGBoost model had the best prediction accuracy of 73.9 percent for cases with outliers, and 79 percent for cases without outliers. We also found that the lightGBM model had the lowest mean absolute error between prediction and actual duration in days with 3.66 days for the case with outliers, and 2.4 days for the case without outliers. These two models outperformed the other four models. This work will be enhanced in the future by exploring new prediction algorithms and comparing them with the results of this study.

Chen, Lingtao↗

Sex-based differences in gene expression in hippocampus following postnatal lead exposure

The influence of sex as an effect modifier of childhood lead poisoning has received little systematic attention. Considering the paucity of information available concerning the interactive effects of lead and sex on the brain, the current study examined the interactive effects of lead and sex on gene expression patterns in the hippocampus, a structure involved in learning and memory. Male or female rats were fed either 1500 ppm lead-containing chow or control chow for 30 days beginning at weaning.Blood lead levels were 26.7 {+-} 2.1 {mu}g/dl and 27.1 {+-} 1.7 {mu}g/dl for females and males, respectively. The expression of 175 unique genes was differentially regulated between control male and female rats. A total of 167 unique genes were differentially expressed in response to lead in either males or females. Lead exposure had a significant effect without a significant difference between male and female responses in 77 of these genes. In another set of 71 genes, there were significant differences in male vs. female response. A third set of 30 genes was differentially expressed in opposite directions in males vs. females, with the majority of genes expressed at a lower level in females than in males. Highly differentially expressed genes in males and females following lead exposure were associated with diverse biological pathways and functions. These results show that a brief exposure to lead produced significant changes in expression of a variety of genes in the hippocampus and that the response of the brain to a given lead exposure may vary depending on sex. - Highlights: > Postnatal lead exposure has a significant effect on hippocampal gene expression patterns. > At least one set of genes was affected in opposite directions in males and females. > Differentially expressed genes were associated with diverse biological pathways.

60 APPLIED LIFE SCIENCES↗

First-Principles Assessment of ZnTe and CdSe as Prospective Tunnel Barriers at the InAs/Al Interface

Majorana zero modes are predicted to emerge in semiconductor/ superconductor interfaces, such as InAs/Al. Majorana modes could be utilized for fault tolerant topological qubits. However, their realization is hindered by materials challenges. The coupling between the superconductor and the semiconductor may be too strong for Majorana modes to emerge, due to effective doping of the semiconductor by the metallic contact. This could be mediated by adding a tunnel barrier of controlled thickness. We use density functional theory (DFT) with Hubbard U corrections, whose values are machine-learned via Bayesian optimization (BO), to assess ZnTe and CdSe as prospective tunnel barriers for the InAs/Al interface. The results of DFT +U(BO) for ZnTe are validated by comparison to angle resolved photoemission spectroscopy (ARPES). We then study bilayer interfaces of the three semiconductors with each other and with Al, as well as trilayer interfaces with a varying number of ZnTe or CdSe layers inserted between InAs and Al. We find that 16 atomic layers of either material completely insulate the InAs from metal induced gap states (MIGS). However, ZnTe and CdSe differ significantly in their band alignment, such that ZnTe forms an effective barrier for electrons, whereas CdSe forms a barrier for holes. Because of Fermi level pinning in the conduction band at the interface, only electron transport is relevant for InAs-based Majorana devices. Therefore, ZnTe is the better choice. Based on the results of our simulations, we suggest conducting experiments with ZnTe barriers in the thickness range of 6–18 atomic layers.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Integrated design of aluminum-enriched high-entropy refractory B2 alloys with synergy of high strength and ductility

Refractory high-entropy alloys (RHEAs) are promising high-temperature structural materials. Their large compositional space poses great design challenges for phase control and high strength-ductility synergy. The present research pioneers using integrated high-throughput machine learning with Monte Carlo simulations supplemented by ab initio calculations to effectively navigate phase selection and mechanical property predictions, developing single-phase ordered B2 aluminum-enriched RHEAs (Al-RHEAs) demonstrating high strength and ductility. These Al-RHEAs achieve remarkable mechanical properties, including compressive yield strengths up to 1.7 gigapascals, fracture strains exceeding 50%, and notable high-temperature strength retention. They also demonstrate a tensile yield strength of 1.0 gigapascals with a ductility of 9%, albeit with B2 ordering. Furthermore, we identify valence electron count domains for alloy ductility and brittleness with the explanation from density functional theory and provide crucial insights into elemental influence on atomic ordering and mechanical performance. The work sets forth a strategic blueprint for high-throughput alloy design and reveals fundamental principles governing the mechanical properties of advanced structural alloys.

Science & Technology - Other Topics↗

Neuroevolution of Spiking Neural Networks Using Compositional Pattern Producing Networks

Spiking neural networks (SNNs) offer tremendous potential for the future of AI, including the ability to be implemented efficiently on neuromorphic systems. One of the challenges in building functioning SNNs is the training process, as standard error back-propagation cannot be easily applied. In this work, we extend an evolutionary approach for training SNNs by implementing an indirect encoding of individuals. Specifically, we evolve SNNs using Compositional Pattern Producing Networks, which are able to learn the connectivity patterns between neurons defined in a coordinate space. We validate the approach on multiple control and classification tasks.

Elbrecht, Daniel↗

Device Classification for Industrial Control Systems Using Predicted Traffic Features

To achieve a secure interconnected Industrial Control System (ICS) architecture, security practitioners depend on accurate identification of network host behavior. However, accurate machine learning based host identification methods depends on the availability of significant quantities of network traffic data, which can be difficult to obtain due to system constraints such as network security, data confidentiality, and physical location. In this work, we propose a network traffic feature prediction method based on a generative model, which achieves high host identification accuracy. Furthermore, we develop a joint training algorithm to improve host identification performance compared to separate training of the generative model and the classifier responsible for host identification.

97 MATHEMATICS AND COMPUTING↗

Machine Learning Approaches for Nuclear Material Accounting Data from Irradiation and Reprocessing

We are currently exploring data analysis methods for their ability to strengthen the synthesis and evaluation of information generated within domestic and international safeguard regimes. Safeguard data typically includes rich heterogenous datasets amenable to advanced data analytics methods, such as machine learning. We have converted transactional data containing both numerical and categorical attributes from a domestic nuclear material control and accountability (NMC&A) system into a low-dimensional numerical structure via linear principal component analysis. This data representation allows for global structure discovery via cluster analysis, which can characterize the typical behavior of each of the primary types of transaction events. Furthermore, the structure of the top principal components captures the “typical behavior” of the data and is thus amenable to anomaly detection through statistical hypothesis testing. We explored this capability by generating erroneous permutations of the data and computing the Q-residual quantity increase associated with the information loss when these data are projected into the low-dimensional principal component analysis space representative of typical transactions.Future work will focus on identifying data transformations (e.g., graph networks) that more closely align with the inherent structure of these transactions to explain more salient information and disambiguate the underlying nuclear process—in this case, irradiation and reprocessing—from artifacts of NMC&A system transactional record keeping data.

Drescher, Adam↗

Grid-connected heat pump water heater benefits for low-income households in the Southeastern United States

Energy efficient heat pump water heaters (HPWHs) reduce customer energy costs; grid-connected controls further increase HPWH value by enabling energy storage and shifting demand to cheaper, off-peak periods. However, a HPWH’s first cost premium can put it out of reach for low-income customers. This paper will present results of an ongoing study exploring the benefits of load shifting HPWHs for 24 low-income households, aiming to support increased product deployment in this demographic. The study uses EcoPort modules to shift HPWH load for a study sample consisting primarily of low-income adults and seniors in North Carolina. Building upon prior studies, the study’s HPWH operating schedules are designed to maximize shifted energy and minimize participant electricity costs based on local time-of-use rates. The study documents load profiles of grid-connected HPWHs in a less-studied demographic group and explores how certain groups may have particularly flexible loads due to their unique usage profiles. The results are relevant for HPWH product performance in the Southeast. The study will quantify HPWH load shifting performance during North Carolina’s hot summer, temperate shoulder, and occasionally sub-freezing winter seasons, and the study includes installations in conditioned, semi-conditioned, and unconditioned spaces. Finally, study results will also explore how controlled HPWHs can provide value to the regional grid by reducing seasonal peaks via demand response. Lessons learned include HPWH acceptance for low-income and senior users, best practices for maintaining HPWH connectivity among users without prior product experience, and strategies to leverage remote monitoring to ensure optimal operation and enhance HPWH reliability.

Urigwe, Daniela↗

Efficient Machine Learning Approach for Optimizing Scientific Computing Applications on Emerging HPC Architectures

Efficient parallel implementations of scientific applications on multi-core CPUs with accelerators such as GPUs and Xeon Phis is challenging. This requires - exploiting the data parallel architecture of the accelerator along with the vector pipelines of modern x86 CPU architectures, load balancing, and efficient memory transfer between different devices. It is relatively easy to meet these requirements for highly structured scientific applications. In contrast, a number of scientific and engineering applications are unstructured. Getting performance on accelerators for these applications is extremely challenging because many of these applications employ irregular algorithms which exhibit data-dependent control-ow and irregular memory accesses. Furthermore, these applications are often iterative with dependency between steps, and thus making it hard to parallelize across steps. As a result, parallelism in these applications is often limited to a single step. Numerical simulation of charged particles beam dynamics is one such application where the distribution of work and memory access pattern at each time step is irregular. Applications with these properties tend to present significant branch and memory divergence, load imbalance between different processor cores, and poor compute and memory utilization. Prior research on parallelizing such irregular applications have been focused around optimizing the irregular, data-dependent memory accesses and control-ow during a single step of the application independent of the other steps, with the assumption that these patterns are completely unpredictable. We observed that the structure of computation leading to control-ow divergence and irregular memory accesses in one step is similar to that in the next step. It is possible to predict this structure in the current step by observing the computation structure of previous steps. In this dissertation, we present novel machine learning based optimization techniques to address the parallel implementation challenges of such irregular applications on different HPC architectures. In particular, we use supervised learning to predict the computation structure and use it to address the control-ow and memory access irregularities in the parallel implementation of such applications on GPUs, Xeon Phis, and heterogeneous architectures composed of multi-core CPUs with GPUs or Xeon Phis. We use numerical simulation of charged particles beam dynamics simulation as a motivating example throughout the dissertation to present our new approach, though they should be equally applicable to a wide range of irregular applications. The machine learning approach presented here use predictive analytics and forecasting techniques to adaptively model and track the irregular memory access pattern at each time step of the simulation to anticipate the future memory access pattern. Access pattern forecasts can then be used to formulate optimization decisions during application execution which improves the performance of the application at a future time step based on the observations from earlier time steps. In heterogeneous architectures, forecasts can also be used to improve the memory performance and resource utilization of all the processing units to deliver a good aggregate performance. We used these optimization techniques and anticipation strategy to design a cache-aware, memory efficient parallel algorithm to address the irregularities in the parallel implementation of charged particles beam dynamics simulation on different HPC architectures. Experimental result using a diverse mix of HPC architectures shows that our approach in using anticipation strategy is effective in maximizing data reuse, ensuring workload balance, minimizing branch and memory divergence, and in improving resource utilization.

Arumugam, Kamesh↗

Optimization of Water-Alternating-CO2 Injection Field Operations Using a Machine-Learning-Assisted Workflow

Summary This paper will present a robust workflow to address multiobjective optimization (MOO) of carbon dioxide (CO2)-enhanced oil recovery (EOR)-sequestration projects with a large number of operational control parameters. Farnsworth unit (FWU) field, a mature oil reservoir undergoing CO2 alternating water injection (CO2-WAG) EOR, will be used as a field case to validate the proposed optimization protocol. The expected outcome of this work would be a repository of Pareto-optimal solutions of multiple objective functions, including oil recovery, carbon storage volume, and project economics. FWU’s numerical model is used to demonstrate the proposed optimization workflow. Because using MOO requires computationally intensive procedures, machine-learning-based proxies are introduced to substitute for the high-fidelity model, thus reducing the total computation overhead. The vector machine regression combined with the Gaussian kernel (Gaussian-SVR) is used to construct proxies. An iterative self-adjusting process prepares the training knowledge base to develop robust proxies and minimizes computational time. The proxies’ hyperparameters will be optimally designed using Bayesian optimization to achieve better generalization performance. Trained proxies will be coupled with multiobjective particle swarm Optimization (MOPSO) protocol to construct the Pareto-front solution repository. The outcomes of this workflow will be a repository containing Pareto-optimal solutions of multiple objectives considered in the CO2-WAG project. The proposed optimization workflow will be compared with another established methodology using a multilayer neural network (MLNN) to validate its feasibility in handling MOO with a large number of parameters to control. Optimization parameters used include operational variables that might be used to control the CO2-WAG process, such as the duration of the water/gas injection period, producer bottomhole pressure (BHP) control, and water injection rate of each well included in the numerical model. It is proved that the workflow coupling Gaussian-SVR proxies and the iterative self-adjusting protocol is more computationally efficient. The MOO process is made more rapid by squeezing the size of the required training knowledge base while maintaining the high accuracy of the optimized results. The outcomes of the optimization study show promising results in successfully establishing the solution repository considering multiple objective functions. Results are also verified by validating the Pareto fronts with simulation results using obtained optimized control parameters. The outcome from this work could provide field operators an opportunity to design a CO2-WAG project using as many inputs as possible from the reservoir models. The proposed work introduces a novel concept that couples Gaussian-SVR proxies with a self-adjusting protocol to increase the computational efficiency of the proposed workflow and to guarantee the high accuracy of the obtained optimized results. More importantly, the workflow can optimize a large number of control parameters used in a complex CO2-WAG process, which greatly extends its utility in solving large-scale MOO problems in various projects with similar desired outcomes.

Energy & Fuels↗

Discovery of Self-Assembling π-Conjugated Peptides by Active Learning-Directed Coarse-Grained Molecular Simulation

Electronically active organic molecules have demonstrated great promise as novel soft materials for energy harvesting and transport. Self-assembled nanoaggregates formed from π-conjugated oligopeptides composed of an aromatic core flanked by oligopeptide wings offer emergent optoelectronic properties within a water-soluble and biocompatible substrate. Nanoaggregate properties can be controlled by tuning core chemistry and peptide composition, but the sequence–structure–function relations remain poorly characterized. Here, we employ coarse-grained molecular dynamics simulations within an active learning protocol employing deep representational learning and Bayesian optimization to efficiently identify molecules capable of assembling pseudo-1D nanoaggregates with good stacking of the electronically active π-cores. We consider the DXXX-OPV3-XXXD oligopeptide family, where D is an Asp residue and OPV3 is an oligophenylenevinylene oligomer (1,4-distyrylbenzene), to identify the top performing XXX tripeptides within all 20 3 = 8000 possible sequences. By direct simulation of only 2.3% of this space, we identify molecules predicted to exhibit superior assembly relative to those reported in prior work. Spectral clustering of the top candidates reveals new design rules governing assembly. This work establishes new understanding of DXXX-OPV3-XXXD assembly, identifies promising new candidates for experimental testing, and presents a computational design platform that can be generically extended to other peptide-based and peptide-like systems.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗