Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Representation learning”

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 109 records · Page 6
All sourcesNASA NTRSDOE OSTI
NASA NTRS1994

Learning fuzzy logic control system

The performance of the Learning Fuzzy Logic Control System (LFLCS), developed in this thesis, has been evaluated. The Learning Fuzzy Logic Controller (LFLC) learns to control the motor by learning the set of teaching values that are generated by a classical PI controller. It is assumed that the classical PI controller is tuned to minimize the error of a position control system of the D.C. motor. The Learning Fuzzy Logic Controller developed in this thesis is a multi-input single-output network. Training of the Learning Fuzzy Logic Controller is implemented off-line. Upon completion of the training process (using Supervised Learning, and Unsupervised Learning), the LFLC replaces the classical PI controller. In this thesis, a closed loop position control system of a D.C. motor using the LFLC is implemented. The primary focus is on the learning capabilities of the Learning Fuzzy Logic Controller. The learning includes symbolic representation of the Input Linguistic Nodes set and Output Linguistic Notes set. In addition, we investigate the knowledge-based representation for the network. As part of the design process, we implement a digital computer simulation of the LFLCS. The computer simulation program is written in 'C' computer language, and it is implemented in DOS platform. The LFLCS, designed in this thesis, has been developed on a IBM compatible 486-DX2 66 computer. First, the performance of the Learning Fuzzy Logic Controller is evaluated by comparing the angular shaft position of the D.C. motor controlled by a conventional PI controller and that controlled by the LFLC. Second, the symbolic representation of the LFLC and the knowledge-based representation for the network are investigated by observing the parameters of the Fuzzy Logic membership functions and the links at each layer of the LFLC. While there are some limitations of application with this approach, the result of the simulation shows that the LFLC is able to control the angular shaft position of the D.C. motor. Furthermore, the LFLC has better performance in rise time, settling time and steady state error than to the conventional PI controller. This abstract accurately represents the content of the candidate's thesis. I recommend its publication.

Lung, Leung Kam↗
NASA NTRS2021

Assuring Intelligent Systems: Contingency Management for UAS

Unmanned aircraft systems (UAS) collaborate with humans to operate in diverse, safety-critical applications. However, assurance technologies need to be integrated into the design process in order to guarantee safe behavior, thereby enabling UAS operations in the National Airspace System (NAS). In this paper, formal methods are integrated with learning-enabled systems representations. The generation and representation of knowledge are captured via monadic second-order logic rules in the cognitive architecture Soar. These rules are translated into timed automata, and a proof of correctness for the translation is provided so that safety and liveness properties can be checked in the formal verification environment Uppaal. This approach is agnostic to the learning mechanism used to generate the learned rules (e.g., chunking, etc.). An example of a fault-tolerant, learning-enabled UAS deciding which of four contingency procedures to execute under a lost link scenario while overflying an urban area is used to illustrate the approach.

Intelligent Systems↗
DOE OSTI2024

When ancient numerical demons meet physics-informed machine learning: adjoint-based gradients for implicit differentiable modeling

Recent advances in differentiable modeling, a genre of physics-informed machine learning that trains neural networks (NNs) together with process-based equations, have shown promise in enhancing hydrological models' accuracy, interpretability, and knowledge-discovery potential. Current differentiable models are efficient for NN-based parameter regionalization, but the simple explicit numerical schemes paired with sequential calculations (operator splitting) can incur numerical errors whose impacts on models' representation power and learned parameters are not clear. Implicit schemes, however, cannot rely on automatic differentiation to calculate gradients due to potential issues of gradient vanishing and memory demand. Here we propose a “discretize-then-optimize” adjoint method to enable differentiable implicit numerical schemes for the first time for large-scale hydrological modeling. The adjoint model demonstrates comprehensively improved performance, with Kling–Gupta efficiency coefficients, peak-flow and low-flow metrics, and evapotranspiration that moderately surpass the already-competitive explicit model. Therefore, the previous sequential-calculation approach had a detrimental impact on the model's ability to represent hydrological dynamics. Furthermore, with a structural update that describes capillary rise, the adjoint model can better describe baseflow in arid regions and also produce low flows that outperform even pure machine learning methods such as long short-term memory networks. The adjoint model rectified some parameter distortions but did not alter spatial parameter distributions, demonstrating the robustness of regionalized parameterization. Despite higher computational expenses and modest improvements, the adjoint model's success removes the barrier for complex implicit schemes to enrich differentiable modeling in hydrology.

58 GEOSCIENCES↗
NASA NTRS2021

Deep Domain Adaptation based Cloud Type Detection using Active and Passive Satellite Data

Domain adaptation techniques have been developed to handle data from multiple sources or domains. Most existing domain adaptation models assume that source and target domains are homogeneous, i.e., they have the same feature space. Nevertheless, many real world applications often deal with data from heterogeneous domains that come from completely different feature spaces. In our remote sensing application, data in source domain (from an active spaceborne Lidar sensor CALIOP onboard CALIPSO satellite) contain 25 attributes, while data in target domain (from a passive spectroradiometer sensor VIIRS onboard Suomi-NPP satellite) contain 20 different attributes. CALIOP has better representation capability and sensitivity to aerosol types and cloud phase, while VIIRS has wide swaths and better spatial coverage but has inherent weakness in differentiating atmospheric objects on different vertical levels. To address this mismatch of features across the domains/sensors, we propose a novel end-to-end deep domain adaptation with domain mapping and correlation alignment (DAMA) to align the heterogeneous source and target domains in active and passive satellite remote sensing data. It can learn domain invariant representation from source and target domains by transferring knowledge across these domains, and achieve additional performance improvement by incorporating weak label information into the model (DAMA-WL). Our experiments on a collocated CALIOP and VIIRS dataset show that DAMA and DAMA-WL can achieve higher classification accuracy in predicting cloud types.

domain adaptation↗
NASA NTRS1991

On the integration of reinforcement learning and approximate reasoning for control

The author discusses the importance of strengthening the knowledge representation characteristic of reinforcement learning techniques using methods such as approximate reasoning. The ARIC (approximate reasoning-based intelligent control) architecture is an example of such a hybrid approach in which the fuzzy control rules are modified (fine-tuned) using reinforcement learning. ARIC also demonstrates that it is possible to start with an approximately correct control knowledge base and learn to refine this knowledge through further experience. On the other hand, techniques such as the TD (temporal difference) algorithm and Q-learning establish stronger theoretical foundations for their use in adaptive control and also in stability analysis of hybrid reinforcement learning and approximate reasoning-based controllers.

Berenji, Hamid R.↗
DOE OSTI2024

CrossMP: Enabling Cross-Modality Translation between Single-Cell RNA-Seq and Single-Cell ATAC-Seq through Web-Based Portal

In recent years, there has been a growing interest in profiling multiomic modalities within individual cells simultaneously. One such example is integrating combined single-cell RNA sequencing (scRNA-seq) data and single-cell transposase-accessible chromatin sequencing (scATAC-seq) data. Integrated analysis of diverse modalities has helped researchers make more accurate predictions and gain a more comprehensive understanding than with single-modality analysis. However, generating such multimodal data is technically challenging and expensive, leading to limited availability of single-cell co-assay data. Here, we propose a model for cross-modal prediction between the transcriptome and chromatin profiles in single cells. Our model is based on a deep neural network architecture that learns the latent representations from the source modality and then predicts the target modality. It demonstrates reliable performance in accurately translating between these modalities across multiple paired human scATAC-seq and scRNA-seq datasets. Additionally, we developed CrossMP, a web-based portal allowing researchers to upload their single-cell modality data through an interactive web interface and predict the other type of modality data, using high-performance computing resources plugged at the backend.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2026

AI-assisted object condensation clustering for calorimeter shower reconstruction at CLAS12

Several nuclear physics studies using the CLAS12 detector rely on the accurate reconstruction of neutrons and photons from its forward angle calorimeter system. These studies often place restrictive cuts when measuring neutral particles due to an overabundance of false clusters created by the existing calorimeter reconstruction software. In this work, we present a new AI approach to clustering CLAS12 calorimeter hits based on the object condensation framework. The model learns a latent representation of the full detector topology using GravNet layers, serving as the positional encoding for an event’s calorimeter hits which are processed by a Transformer encoder. This unique structure allows the model to contextualize local and long range information, improving its performance. Evaluated on one million simulated $e^-$ $+$ $p$ collision events, our method significantly improves cluster trustworthiness: the fraction of reliable neutron clusters, increasing from 8.88% to 30.73%, and photon clusters, increasing from 51.07% to 64.73%. In conclusion, our study also marks the first application of AI clustering techniques for hodoscopic detectors, showing potential for usage in many other experiments.

Calorimeters↗
DOE OSTI2026

Multimodal framework for the joint analysis of single-cell RNA and T cell receptor sequencing data predicts T cell response to cancer immunotherapy

T cell states are prognostic in different cancer types. Recent technologies enable joint profiling of T cell RNA and T cell receptor (TCR) sequences at single-cell resolution. Here we present the TCR-RNA Integrating Model (TRIM), a multi-modal variational autoencoder framework that integrates RNA-TCR data and predicts T cell clonality and transcriptional states. TRIM learns a shared representation of the data conditioned on patient, tissue source, and treatment timepoint. We applied TRIM to three independent datasets that included T cells collected before and after checkpoint inhibitor treatment, sourced either from blood and tumor biopsies in patients with head and neck squamous cell carcinoma and colorectal cancer, or from tumor and adjacent tissue in a pan-cancer dataset. In all settings, TRIM accurately predicted intra-tumor T cell clonal expansion and transcriptional status based on T cells from blood or normal tissue before treatment, demonstrating its utility in modeling multimodal T cell data and predicting T cell response to treatment and disease progression.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2025

AI-powered exploration of molecular vibrations, phonons, and spectroscopy

The vibrational dynamics of molecules and solids play a critical role in defining material properties, particularly their thermal behaviors. However, theoretical calculations of these dynamics are often computationally intensive, while experimental approaches can be technically complex and resource-demanding. Recent advancements in data-driven artificial intelligence (AI) methodologies have substantially enhanced the efficiency of these studies. This review explores the latest progress in AI-driven methods for investigating atomic vibrations, emphasizing their role in accelerating computations and enabling rapid predictions of lattice dynamics, phonon behaviors, molecular dynamics, and vibrational spectra. Key developments are discussed, including advancements in databases, structural representations, machine-learning interatomic potentials, graph neural networks, and other emerging approaches. Compared to traditional techniques, AI methods exhibit transformative potential, dramatically improving the efficiency and scope of research in materials science. The review concludes by highlighting the promising future of AI-driven innovations in the study of atomic vibrations.

Han, Bowen [Oak Ridge National Laboratory (ORNL), ↗
DOE OSTI2024

Observational evidence for groundwater influence on crop yields in the United States

As climate change shifts crop exposure to dry and wet extremes, a better understanding of factors governing crop response is needed. Recent studies identified shallow groundwater—groundwater within or near the crop rooting zone—as influential, yet existing evidence is largely based on theoretical crop model simulations, indirect or static groundwater data, or small-scale field studies. Here, we use observational satellite yield data and dynamic water table simulations from 1999 to 2018 to provide field-scale evidence for shallow groundwater effects on maize yields across the United States Corn Belt. We identify three lines of evidence supporting groundwater influence: 1) crop model simulations better match observed yields after improvements in groundwater representation; 2) machine learning analysis of observed yields and modeled groundwater levels reveals a subsidy zone between 1.1 and 2.5 m depths, with yield penalties at shallower depths and no effect at deeper depths; and 3) locations with groundwater typically in the subsidy zone display higher yield stability across time. We estimate an average 3.4% yield increase when groundwater levels are at optimum depth, and this effect roughly doubles in dry conditions. Groundwater yield subsidies occur ~35% of years on average across locations, with 75% of the region benefitting in at least 10% of years. Overall, we estimate that groundwater-yield interactions had a net monetary contribution of approximately $10 billion from 1999 to 2018. This study provides empirical evidence for region-wide groundwater yield impacts and further underlines the need for better quantification of groundwater levels and their dynamic responses to short- and long-term weather conditions.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2026

Augmenting Molecular Graphs with Geometries via Machine Learning Interatomic Potentials

Accurate molecular property predictions require 3D geometries, which are typically obtained using expensive methods such as density functional theory (DFT). Here, we attempt to obtain molecular geometries by relying solely on machine learning interatomic potential (MLIP) models. To this end, we first curate a large-scale molecular relaxation dataset comprising 3.5 million molecules and 300 million snapshots. Then MLIP pre-trained models are trained with supervised learning to predict energy and forces given 3D molecular structures. Once trained, we show that the pre-trained models can be used in different ways to obtain geometries either explicitly or implicitly. First, it can be used to obtain approximate low-energy 3D geometries via geometry optimization. While these geometries do not consistently reach DFT-level chemical accuracy or convergence, they can still improve downstream performance compared to non-relaxed structures. To mitigate potential biases and enhance downstream predictions, we introduce geometry fine-tuning based on the relaxed 3D geometries. Second, the pre-trained models can be directly fine-tuned for property prediction when ground truth 3D geometries are available. Our results demonstrate that MLIP pre-trained models trained on relaxation data can learn transferable molecular representations to improve downstream molecular property prediction and can provide practically valuable but approximate molecular geometries that benefit property predictions. Our code is publicly available at: https://github.com/divelab/AIRS/.

Fu, Cong [Texas A & M Univ., College Station, TX (↗
DOE OSTI2026

Leveraging machine learning to enhance aerosol classification using Single-Particle Mass Spectrometry

Advancing automated classification of atmospheric aerosols from Single-Particle Mass Spectrometry (SPMS) data remains challenging due to overlapping ion signatures, compositional diversity, and limited labeled data. This study evaluates supervised and semi-supervised learning frameworks to enhance aerosol identification by jointly leveraging labeled and unlabeled spectra. Four models were compared: a supervised Support Vector Machine (SVM), a self-training SVM, a stacked autoencoder classifier, and a stacked autoencoder trained using a temporal-ensembling Mean Teacher approach. All models achieved high and stable accuracies (90.0 %–91.1 %), surpassing previous results on the same dataset (87 %) and matching the performance of state-of-the-art deep learning methods. Despite small global metric differences (≤ 1 %), semi-supervised variants yielded up to 5 %–10 % improvements for compositionally rare particle types – such as soot (0.77 % of spectra, F1-score: 0.93–0.97) and hazelnut pollen (0.98 % of spectra, F1-score: 0.97–1.00) – equating to roughly ∼ 187 additional correctly classified spectra. These gains are scientifically significant, as such rare particles exert disproportionate influence on radiative absorption and ice nucleation processes; their improved detection reduces modeled uncertainties in aerosol absorption optical depth and mixed-phase cloud ice nucleation rates. The models' residual misclassifications (≈ 9 %) largely arise from true spectral overlap among chemically adjacent species (e.g., Na- vs. K-feldspar, coated vs. uncoated feldspars), reflecting physical compositional continuity rather than algorithmic error. Collectively, these findings demonstrate that leveraging unlabeled data to learn robust spectral representations and refine classification enhances both fidelity and interpretability, bridging data-driven analysis with aerosol–climate process understanding.

54 ENVIRONMENTAL SCIENCES↗
NASA NTRS1988

A survey of planning and scheduling research at the NASA Ames Research Center

NASA Ames Research Center has a diverse program in planning and scheduling. This paper highlights some of our research projects as well as some of our applications. Topics addressed include machine learning techniques, action representations and constraint-based scheduling systems. The applications discussed are planetary rovers, Hubble Space Telescope scheduling, and Pioneer Venus orbit scheduling.

Zweben, Monte↗
NASA NTRS1989

A survey of planning and scheduling research at the NASA Ames Research Center

NASA Ames Research Center has a diverse program in planning and scheduling. Some research projects as well as some applications are highlighted. Topics addressed include machine learning techniques, action representations and constraint-based scheduling systems. The applications discussed are planetary rovers, Hubble Space Telescope scheduling, and Pioneer Venus orbit scheduling.

Zweben, Monte↗
DOE OSTI2024

Counter Data Paucity through Adversarial Invariance Encoding: A Case Study on Modeling Battery Thermal Runaway

Lithium-ion batteries, widely used for their durability and high energy storage, face the risk of internal short circuits leading to catastrophic thermal runaway events. These events, triggered by external stimuli like mechanical loads, pose safety concerns in applications such as electric vehicles. Detecting and understanding thermal runaway events is crucial, but physics-driven models struggle to explain the non-linear evolution of battery temperature during these events, considering factors like material composition and state-of-charge. Due to the rarity of these events and the cost of data collection, we propose a deep learning (DL) model to predict battery temperature responses during thermal runaway. The challenge lies in the scarcity of data, making traditional DL models prone to overfitting and learning low-quality representations of the complex process.Our approach introduces a novel few-shot architecture that incorporates an adversarially governed invariant encoding process. This architecture aims to distill "invariant" relationships by addressing distributional shifts in data across various battery properties, facilitating the detection of thermal runaway events. Specifically, our results demonstrate that deep learning models conditioned on these "invariant" representations outperform state-of-the-art baselines, achieving a remarkable 96.8% performance improvement in terms of the popular metric MAPE. This framework presents a promising direction for enhancing battery safety modeling, particularly in the context of rare and complex events like thermal runaway. Our code and code and dataset used for the paper are public1.

Tabassum, Anika [ORNL] (ORCID:0000000254600955)↗
NASA NTRS1998

Preliminary Work for Examining the Scalability of Reinforcement Learning

Researchers began studying automated agents that learn to perform multiple-step tasks early in the history of artificial intelligence (Samuel, 1963; Samuel, 1967; Waterman, 1970; Fikes, Hart & Nilsonn, 1972). Multiple-step tasks are tasks that can only be solved via a sequence of decisions, such as control problems, robotics problems, classic problem-solving, and game-playing. The objective of agents attempting to learn such tasks is to use the resources they have available in order to become more proficient at the tasks. In particular, each agent attempts to develop a good policy, a mapping from states to actions, that allows it to select actions that optimize a measure of its performance on the task; for example, reducing the number of steps necessary to complete the task successfully. Our study focuses on reinforcement learning, a set of learning techniques where the learner performs trial-and-error experiments in the task and adapts its policy based on the outcome of those experiments. Much of the work in reinforcement learning has focused on a particular, simple representation, where every problem state is represented explicitly in a table, and associated with each state are the actions that can be chosen in that state. A major advantage of this table lookup representation is that one can prove that certain reinforcement learning techniques will develop an optimal policy for the current task. The drawback is that the representation limits the application of reinforcement learning to multiple-step tasks with relatively small state-spaces. There has been a little theoretical work that proves that convergence to optimal solutions can be obtained when using generalization structures, but the structures are quite simple. The theory says little about complex structures, such as multi-layer, feedforward artificial neural networks (Rumelhart & McClelland, 1986), but empirical results indicate that the use of reinforcement learning with such structures is promising. These empirical results make no theoretical claims, nor compare the policies produced to optimal policies. A goal of our work is to be able to make the comparison between an optimal policy and one stored in an artificial neural network. A difficulty of performing such a study is finding a multiple-step task that is small enough that one can find an optimal policy using table lookup, yet large enough that, for practical purposes, an artificial neural network is really required. We have identified a limited form of the game OTHELLO as satisfying these requirements. The work we report here is in the very preliminary stages of research, but this paper provides background for the problem being studied and a description of our initial approach to examining the problem. In the remainder of this paper, we first describe reinforcement learning in more detail. Next, we present the game OTHELLO. Finally we argue that a restricted form of the game meets the requirements of our study, and describe our preliminary approach to finding an optimal solution to the problem.

Clouse, Jeff↗