Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “few-shot 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.

52 records · Page 3
All sourcesNASA NTRSDOE OSTI
NASA NTRSDate not supplied

AI Foundation Models for Science: An Open Collaborative Initiative

Foundation Models (FMs), AI models designed to replace task-specific models, are increasingly being recognized for their versatility across numerous downstream applications. These models, trained using self-supervised techniques on any type of sequence data, circumvent the need for large annotated datasets, a major bottleneck in traditional AI model development. FMs can be applied to downstream tasks using few-shot learning and fine-tuning, significantly reducing the need for large labeled training datasets and computational resources. However, the development of FMs requires substantial resources, including access to data and compute power, expertise in the latest models, and specialized scientific knowledge for systematic evaluation. It is challenging for a single group to possess all these capabilities. To address this, NASA IMPACT has initiated an open collaborative effort, leveraging partnerships with the private sector and other groups within and outside NASA, to jointly build FMs. The overarching goal is to develop a consistent and collaborative approach to building FMs for high-value science datasets. This initiative has fostered collaboration within NASA and with external partners, including IBM Research, Clark University, DOE’s ORNL, ESA, and USGS. The effort focuses on identifying key datasets with a wide range of downstream applications, pretraining and building FMs using modified transformer architectures, evaluating compute infrastructure needs, and sharing models, pretraining and fine-tuning code, and data with the community. Furthermore, it aims to train the Earth science community to fine-tune these models for various downstream applications. Our initial effort resulted in the creation of a 100 million parameter HLS Geospatial Model within six months, which was released on HuggingFace. We are now expanding our scope to include data from weather and climate models and investigating multimodal models. We invite those interested in participating in this effort to join us by sharing their use cases, expertise, or data.

Rahul Ramachandran↗
NASA NTRS2025

A Preliminary Study on the Feasibility of Large Language Models for Detecting Micro-Behaviors Among Team Members in Space Missions

Large-language models (LLMs) have been recently used for spoken language understanding (SLU) to infer meaning and semantics from speech in tasks such as speaker intent and sentiment classification. Due to being trained on large amounts of data, and their ability to understand context and relationships between words, LLMs are competent, enabling them to generalize across tasks without requiring many task-specific training samples. This research examines the feasibility of few-shot learning in LLMs for detecting subtle, brief, and possibly unconscious interactions between team members, called ``micro-behaviors," and provides insights into the appropriate design of LLMs for this task. Our data came from 5 teams participating in a 45-day mission at the US National Aeronautics and Space Administration’s (NASA) Human Exploration Research Analog (HERA). More specifically we used data collected from team interaction battery (TIB) tasks teams performed five times in-mission which comprise an average 1.5 hours of conversation data per day. Micro-behaviors were coded according to an adapted version of Smith & Griffins (2022) theoretical framework in terms of Violation (i.e., presence of valenced behavior, uplifting/positive or discouraging/negative), Intensity (i.e., force of behavior in terms of how uplifting or discouraging is the behavior), and Intent (i.e., motive of the behavior in terms of whether it was deliberate or unintentional). We explore the ability of LLMs to detect the presence and intensity of micro-behaviors. We examine employing and fine-tuning readily available LLMs (i.e., RoBERTa, DistilBERT), as well as prompting state-of-the-art sequence classification models (i.e., Llama-2, Llama-3). In a total of 13,058 conversational turns (17.8% uplifting, 3.3% discouraging, 75.76% neutral, 3.14% nulls), we compute the macro F1-score of the 3-way micro-behavior classification task (i.e., classifying among uplifting, discouraging, and neutral; 33% chance). Results indicate that the RoBERTa model achieves a F1-score of 36.2% (uplift: 43.3% precision (P), 15.1% recall (R); discourage: 20% P, 0.5% R). These results significantly improve when we augment the data via paraphrasing in the RoBERTa model, reaching a 41.2% macro F1-score (uplift: 37.7% P, 86.3% R; discourage: 3.5% P, 1.8% R). Finally, the Llama-2 model with 3-shot prompting yields 38% macro F1-score (uplift: 28.7% P, 20% R; discourage: 7.2% P, 18% R), which is slightly better compared to the RoBERTa model without data augmentation, highlighting the effectiveness of sequence classification models in detecting minority classes with a small sample size. Findings indicate that LLMs hold potential to detect subtle behaviors in conversations, which could be valuable in assessing team behavior in space exploration missions. Future studies will evaluate the performance of different LLM prompting strategies or fine-tuning methods.

Ankush Raut↗
DOE OSTI2022

Development of Multimodal Few-Shot Analytics for Electron Micrographs

Recent advances in materials data analytics have provided new avenues for determining process-structure-property (PSP) linkages in a variety of materials. Machine learning techniques including few-shot learning have increased the efficiency of classifying microscopy images for the purposes of material characterization. Attempts at creating a multimodal approach can provide further improvements to current models and help extract more salient features from data. In this vein, raw spectrum data was taken to provide an additional modality to our current pyCHIP classifier. Modifications in segmentation also show potential in improving the accuracy of the pyCHIP classifier. Classifier output was analyzed using network graphs and unsupervised clustering algorithms such as spectral clustering to detect better segmentation methods than the current “chipping” approach. We suggest that the chip selection process can be automated in the future using a combination of these techniques to enable high-throughput analyses.

36 MATERIALS SCIENCE↗
DOE OSTI2022

pnnl/Multimodal-Few-Shot

This project combines few-shot machine learning with a multimodal framework for electron microscope data quantification.

Doty, Christina↗
DOE OSTI2022

Multimodal sensor fusion framework for residential building occupancy detection

For several years now, smart building energy systems have been a research area of intensive activity. In light of the increasing need for sustainable buildings and energy systems, this trend motivates an increasing need for a solution to reduce carbon dioxide emissions and improve energy efficiency. This work proposes a high-performing and transferable occupancy detection framework that combines sensor data from different data modalities, including time series environmental data (temperature, humidity, and illuminance), image data, and acoustic energy data using ensemble method. To draw out the best prediction performance in each modality, the proposed framework was developed, including various models that were designed to learn the occupancy patterns reflected in the physical data streams. To tackle the time series environmental data, we designed two variants of an occupancy detection spatiotemporal pattern network (Occ-STPN) that performs both feature level and decision level fusion, respectively. We also propose a new metric; the fading memory mean square error (FMMSE), that provides a fair evaluation and penalization of delayed occupancy predictions. Multiple open-sourced datasets, including the Electricity Consumption and Occupancy and the University of California, Irvine's (UCI) building occupancy detection dataset, along with our own real data collected from six different houses, were used to validate the algorithms' performance. The experimental results presented herein break down the performance for each sensing modality, and a detailed analysis of the performance is also discussed.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2025

Dynamic in-context learning with conversational models for data extraction and materials property prediction

The advent of natural language processing and large language models (LLMs) has revolutionized the extraction of data from unstructured scholarly papers. However, ensuring data trustworthiness remains a significant challenge. In this paper, we introduce PropertyExtractor, an open-source tool that leverages advanced conversational LLMs such as Google gemini-pro and OpenAI gpt-4, blends zero-shot with few-shot in-context learning, and employs engineered prompts for the dynamic refinement of structured information hierarchies—enabling autonomous, efficient, scalable, and accurate identification, extraction, and verification of material property data. Our tests on material data demonstrate precision and recall that exceed 95% with an error rate of ∼9%, highlighting the effectiveness and versatility of the toolkit. Finally, databases for 2D material thicknesses, a critical parameter for device integration, and energy bandgap values are developed using PropertyExtractor. In particular, for the thickness database, the rapid evolution of the field has outpaced both experimental measurements and computational methods, creating a significant data gap. Our work addresses this gap and showcases the potential of PropertyExtractor as a reliable and efficient tool for the autonomous generation of various material property databases, advancing the field.

Ekuma, Chinedu E. (ORCID:0000000258527556)↗
DOE OSTI2023

Multimodal Few-Shot Segmentation of Electron Micrographs

Scanning transmission electron microscopy (STEM) is one of the most used methods of analyzing the chemistry and composition of materials. By analyzing microstructures, these microscopes can help scientists better understand the molecular underpinnings of microelectronics, batteries, and more. However, STEM data can be difficult to interpret, so recent developments have been made in applications of machine learning to analyze these images. The PNNL-developed pyCHIP Classifier has achieved results in segmenting STEM these images via few-shot learning, a method which requires little data and human input, perfect for quickly analysis. In my internship I (Eli Meyers) investigated a multimodal improvement of this classifier by incorporating energy dispersive x-ray spectroscopy (EDS) data into the classification process for a more accurate segmentation. Furthermore, I encoded the spectral data by training a mass spectrometry encoder on the EDS data to extract a more meaningful representation of the data.

36 MATERIALS SCIENCE↗
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)↗
DOE OSTI2020

Accelerating quantum optics experiments with statistical learning

Quantum optics experiments, involving the measurement of low-probability photon events, are known to be extremely time-consuming. We present a methodology for accelerating such experiments using physically motivated ansatzes together with simple statistical learning techniques such as Bayesian maximum a posteriori estimation based on few-shot data. We show that it is possible to reconstruct time-dependent data using a small number of detected photons, allowing for fast estimates in under a minute and providing a one-to-two order of magnitude speed-up in data acquisition time. We test our approach using real experimental data to retrieve the second order intensity correlation function, G (2) ($τ$), as a function of time delay τ between detector counts, for thermal light as well as anti-bunched light emitted by a quantum dot driven by periodic laser pulses. The proposed methodology has a wide range of applicability and has the potential to impact the scientific discovery process across a multitude of domains.

36 MATERIALS SCIENCE↗
DOE OSTI2021

GEDet: Detecting Erroneous Nodes with A Few Examples

Detecting nodes with erroneous values in real-world graphs re- mains challenging due to the lack of examples and various error scenarios. We demonstrate GEDet, an error detection engine that can detect erroneous nodes in graphs with a few examples. The GEDet framework tackles error detection as a few-shot node classification problem. We invite the attendees to experience the following unique features. (1) Few-shot detection. Users only need to provide a few examples of erroneous nodes to perform error detection with GEDet. GEDet achieves desirable accuracy with (a) a graph augmentation module, which automatically generates synthetic examples to learn the classifier, and (b) an adversarial detection module, which improves classifiers to better distinguish erroneous nodes from both cleaned nodes and synthetic examples. We show that GEDet significantly improves the state-of-the-art error detection methods. (2) Diverse error scenarios. GEDet profiles data errors with a built-in library of transformation functions from correct values to errors. Users can also easily “plug in” new error types or examples. (3) User-centric detection. GEDet supports (a) an active learning mode to engage users to verify detected results, and adapts the error detection process accordingly; and (b) visual interfaces to interpret and track detected errors.

Guan, Sheng↗
DOE OSTI2021

Data-Driven Multi-agent Deep Reinforcement Learning for Distribution System Decentralized Voltage Control with High Penetration of PVs

This paper proposes a novel model-free/data-driven centralized training and decentralized execution multi-agent deep reinforcement learning (MADRL) framework for distribution system voltage control with high penetration of PVs. The proposed MADRL can coordinate both the real and reactive power control of PVs with existing static var compensators and battery storage systems. Unlike the existing DRL-based voltage control methods, our proposed method does not rely on a system model during both the training and execution stages. This is achieved by developing a new interaction scheme between the surrogate modeling of the original system and the multi-agent soft actor critic (MASAC) MADRL algorithm. In particular, the sparse pseudo-Gaussian process with a few-shots of measurements is utilized to construct the surrogate model of the original environment, i.e., power flow model. This is a data-driven process and no model parameters are needed. Furthermore, the MASAC enabled MADRL allows to achieve better scalability by dividing the original system into different voltage control regions with the aid of real and reactive power sensitivities to voltage, where each region is treated as an agent. This also serves as the foundation for the centralized training and decentralized execution, thus significantly reducing the communication requirements as only local measurements are required for control. Comparative results with other alternatives on the IEEE 123-nodes and 342-nodes systems demonstrate the superiority of the proposed method.

14 SOLAR ENERGY↗
DOE OSTI2022

Adversarial autoencoder ensemble for fast and probabilistic reconstructions of few-shot photon correlation functions for solid-state quantum emitters

Second-order photon correlation measurements [g (2) (τ) functions] are widely used to classify single-photon emission purity in quantum emitters or to measure the multiexciton quantum yield of emitters that can simultaneously host multiple excitations – such as quantum dots – by evaluating the value of g (2) (τ = 0). Accumulating enough photons to accurately calculate this value is time consuming and could be accelerated by fitting of few-shot photon correlations. Here, we develop an uncertainty-aware, deep adversarial autoencoder ensemble (AAE) that reconstructs noise-free g (2) (τ) functions from noise-dominated, few-shot inputs. The model is trained with simulated g (2) (τ) functions that are facilely generated by Poisson sampling time bins. The AAE reconstructions are performed orders-of-magnitude faster, with reconstruction errors and estimates of g (2) (τ = 0) that are lower in variance and similar in accuracy compared to Maximum likelihood estimation and Levenberg-Marquardt least-squares fitting approaches, for simulated and experimentally measured few-shot g (2) (τ) functions (~100 two-photon events) of InP/ZnS/ZnSe and CdS/CdSe/CdS quantum dots. The deep-ensemble model comprises eight individual autoencoders, allowing for probabilistic reconstructions of noise-free g (2) (τ) functions, and we show that the predicted variance scales inversely with number of shots, with comparable uncertainties to computationally intensive Markov chain Monte Carlo sampling. Furthermore, this work demonstrates the advantage of machine learning models to perform uncertainty-aware, fast, and accurate reconstructions of simple Poisson-distributed photon correlation functions, allowing for on-the-fly reconstructions and accelerated materials characterization of solid-state quantum emitters.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗
DOE OSTI2024

GOLEM: GOld standard for Learning and Evaluation of Motifs

Motifs are distinctive, recurring, widely used idiom-like words or phrases, often originating from folklore, whose meaning is anchored in a narrative and have a significance as communicative devices across a wide range of media, including news, literature, and propaganda. Many motifs concisely imply a large constellation of culturally relevant information, and their broad usage suggests their cognitive importance as touchstones of cultural knowledge. As such, their detection is a step towards culturally aware natural language processing. We present GOLEM (GOld standard for Learning and Evaluation of Motifs) a dataset of English news articles, opinion pieces, and broadcast transcripts annotated for motific information. The dataset identifies 25,737 motif candidates across 34 motif types drawn from three cultural or national groups: Jewish, Irish, and Puerto Rican. The dataset contains 2,024,141 words split into 25,737 text snippets drawn from 8,073 articles. Each motif candidate is labeled according to a scheme which identifies the type of usage (motific, referential, eponymic, or unrelated), resulting in 1,743 actual motific instances in the data. Annotation was performed by individuals identifying as members of each group and achieved a Fleiss’ kappa (?) of > 0.55. In addition to the data, we demonstrate that classification of the candidate type is a challenging task for Large Language Models (LLMs) using a few-shot approach; recent models such as T5, FLAN-T5, GPT-2, and Llama 2 (7B) achieved a performance of 41% accuracy at best, where the majority class accuracy is 41% and the average chance accuracy is 27%. These data will support development of new models and approaches for detecting (and reasoning about) motific information in text.

motif, culture, natural language, artificial intel↗
DOE OSTI2026

A unified large language model–based framework for heterogeneous PV image diagnosis

With advances in imaging technologies, modern photovoltaic (PV) systems generate large volumes of heterogeneous image data, including visible, electroluminescence (EL), and infrared (IR) images. Existing PV image analysis models, particularly deep learning approaches, are typically task-specific and lack cross-modality generalization. To address this limitation, this paper proposes an open-source large language model (LLM)–based unified framework for heterogeneous PV image diagnostics. Through task-aware diagnostic prompting, the framework enables analysis of visible, EL, and IR images within a single pipeline, supporting both zero-shot and few-shot inference and binary and multiclass classification. It is compatible with state-of-the-art multimodal LLMs, including ChatGPT, Gemini, Claude, Qwen, and CLIP. The framework is evaluated on PV module condition classification (clean, soiling, snow, hail, and bird droppings) using visible images, cell crack detection using EL images, and hotspot detection using IR images. GPT-5.1 in few-shot mode achieves the best performance, with classification accuracy exceeding 97.3%. Open-source models such as Qwen and CLIP also deliver competitive results on visible images (around 90% accuracy), though their performance is more limited on EL and IR modalities. On the full ELPV dataset, the framework achieves 83.5% zero-shot accuracy, within 2.8% of the supervised CNN baseline, confirming scalability to larger benchmarks. Practical aspects such as reproducibility, response latency, and confidence estimation are systematically analyzed. The framework operates across PV image modalities without modality- or task-specific training, making it well suited as a rapid pre-screening tool to support downstream detailed diagnostics. A benchmark dataset of diverse labeled PV images is also released.

Li, Baojie↗