SEARCH · Search NASA
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.
Artificial intelligence will be deployed increasingly in more systems that affect public health, safety, and welfare. These systems will better utilize scarce resources; prevent disasters; and increase safety, reliability, comfort, and convenience. Despite the technological challenges and public fears, these systems will improve the quality of life of millions of people worldwide.
Autonomous systems are complex, diverse, and likely be used in environments that change unpredictably. We must develop mechanisms to cope with failures, potentially caused by both the natural stresses of the operating environment and the system's inadequate environmental models. Failures also arise from system component wear. In 2016, the IEEE launched the Global Initiative on Ethics of Autonomous and Intelligent Systems in response to the proliferation of increasingly-autonomous systems. A cornerstone of this initiative is the IEEE P7000 series of projects, which set the standards for the future of ethical intelligent and autonomous technologies. This paper describes the ongoing development of the IEEE P7009 standard on “Fail-Safe Design of Autonomous and Semi-Autonomous Systems”. We provide a collective perspective on the ongoing development of IEEE P7009, and outline the objectives, current approaches, issues under discussion, and two exemplar use cases from different sectors: one high-regulation, the other low-regulation.
Drawing upon globally recognized efforts by a variety of institutions, the paper develops a practical and defensible framework for consideration and use by the International Atomic Energy Agency (IAEA) to support the adoption of credible ethical standards for autonomous and intelligent systems (AIS). The analysis is based on a future hypothetical AIS that identifies signatures of misuse, diversion, and other research and development (R&D). The hypothetical system serves as an exemplar for subject matter expert (SME) workshop participants to begin to answer ethical AIS questions around how these systems should be governed and maintained, what the internal and external considerations associated with artificial intelligence (AI) tools are, and where the boundaries between ethical and non-ethical uses are. The ethical AIS workshop explored several important topics: (a) Recommendations that can be currently implemented by the IAEA, (b) Proposed defensible criteria and metrics aligned with an ethical AI for safeguards implementation, (c) Discussion of future needs and capabilities, and (d) Derive appropriate next steps and actions to support filling current technological, operational, and cultural gaps and realizing an effective ethical AI for safeguards framework. The Establishing Ethical Guidelines for Applying AI to IAEA Safeguards project creates awareness in the community of the ethical AIS approach.
The profession of lighting design is evolving as contemporary lighting systems increasingly rely on cutting-edge computational technologies, sensors, and IOT systems. This trend requires designers to incorporate ideas of automation, dynamic controls, and user-system interaction into their design logic. However, real-time lighting simulations are constrained by inherent limitations arising from the reductive assumptions inevitably introduced in simulated lighting environments. This raises the question of how can designers account for the discrepancies between simulated and real lighting environments, and how can collaboration between humans and autonomous lighting systems bridge this gap. To address this question, we propose a protocol for designing collaborative interactions between humans and systems. Furthermore, this protocol builds on the Human-Lighting System Interaction Framework and demonstrates how human and system intelligence can be combined to fine-tune lighting qualities in a given space. Our paper shows how interactive lighting systems can customize lighting based on user preferences in real-time and how global lighting configurations can be adjusted over time. Specifically, we demonstrate: a) Human-system collaboration assumptions and goals, as well as how the protocol can be integrated into digitally programmable lighting systems. b) Implementations of collaboration that reveal how system autonomy, performance, and user experience are improved over short and long-term timeframes. c) How lighting design can be enhanced beyond simulation-driven design optimization capacities. The associated affordances and limitations are discussed with respect to existing lighting simulation design frameworks.
Machine intelligence has the potential to revolutionize materials science, enabling autonomous synthesis, self-driving characterization, and accelerated modeling. However, despite the promise, successful implementation of these methods in day-to-day research remains a challenge. This talk will delve into the reasons behind this, exploring how truly intelligent experiments are hindered by opaque experiment control, a lack of domain-specific models, and human-centric design. Through a focus on the characterization of next-generation microelectronics and energy storage materials, I will share insights from both successful and failed attempts to implement machine intelligence. We will then explore the next steps necessary to unlock the full potential of machine intelligence in materials science, creating a future where intelligent systems work seamlessly alongside researchers to drive innovation and discovery.
In recent years, the field of data-driven neural network-based machine learning (ML) algorithms has grown significantly and spurred research in its applicability to instrumentation and control systems. While they are promising in operational contexts, the trustworthiness of such algorithms is not adequately assessed. Failures of ML-integrated systems are poorly understood; the lack of comprehensive risk modeling can degrade the trustworthiness of these systems. In recent reports by the National Institute for Standards and Technology, trustworthiness in ML is a critical barrier to adoption and will play a vital role in intelligent systems' safe and accountable operation. Thus, in this work, we demonstrate a real-time model-agnostic method to evaluate the relative reliability of ML predictions by incorporating out-of-distribution detection on the training dataset. It is well documented that ML algorithms excel at interpolation (or near-interpolation) tasks but significantly degrade at extrapolation. This occurs when new samples are "far" from training samples. The method, referred to as the Laplacian distributed decay for reliability (LADDR), determines the difference between the operational and training datasets, which is used to calculate a prediction's relative reliability. LADDR is demonstrated on a feedforward neural network-based model used to predict safety significant factors during different loss-of-flow transients. LADDR is intended as a "data supervisor" and determines the appropriateness of well-trained ML models in the context of operational conditions. Ultimately, LADDR illustrates how training data can be used as evidence to support the trustworthiness of ML predictions when utilized for conventional interpolation tasks.
In recent years, the field of machine learning (ML), specifically neural networks, has grown significantly and has spurred research in its applicability to digital instrumentation and control systems (DI&C). While ML models have shown promise in operational contexts, the trustworthiness of using such algorithms has not been adequately assessed. Failures of ML integrated systems are not well understood, and the lack of comprehensive risk modeling can degrade the trustworthiness in these systems. In recent reports by the National Institute for Standards and Technology (NIST) [1] and the Nuclear Regulatory Commission (NRC) [2], they indicate that trustworthiness in ML is a critical barrier and will play a vital role in the safe, accountable, and secure operation of intelligent systems. Thus, in this work, we demonstrate a dynamic model-agnostic method to quantify the relative reliability of AI/ML predictions by incorporating out-of-distribution (OOD) detection on the training dataset. It is well documented that most ML algorithms excel at interpolation (or near-interpolation) tasks but experience significant performance degradation at extrapolation. The method, referenced as the Laplacian distributed decay for reliability (LADDR), determines the difference between the operational and training datasets which can used to the relative reliability of AI/ML predictions. LADDR is then demonstrated on a feedforward neural network based digital twin used for the prediction of safety significant factors during a loss-of-flow transient. LADDR is used to demonstrate how training data can be used as evidence to support the relative reliability of ML/AI predictions enhancing the overall trustworthiness of the system.
For leveraging wearable technologies to advance precision medicine, personalized and learning-based analysis of continuously acquired health data is indispensable, for which neuromorphic computing could provide the most efficient implementation of artificial intelligence (AI) data processing. For realizing on-body neuromorphic computing, skin-like stretchability is required, but yet to be combined with the suite of desired neuromorphic metrics, including linear, symmetric weight update, and sufficient state retention, for achieving high computing efficiency. Here, we report an intrinsically stretchable neuromorphic device based on an electrochemical transistor, which provides a large number (>800) of states, linear/symmetric weight update, excellent switching endurance (>100 million), good state retention (>10 4 s), together with high stretchability of 100% strain. Further integration into a prototype array successfully realized the implementation of vector-matrix multiplication even at 100% strain. Finally, we demonstrate the feasibility of implementing AI-based classification of health signals (as exemplified by electrocardiograms) with a high accuracy that is minimally influenced by the stretched state of the neuromorphic hardware. Finally, this work breaks the ground for combining AI data analysis into skin-like wearable electronics for achieving human-integrated/mimetic intelligent systems.
The Spallation Neutron Source (SNS) at Oak Ridge National Laboratory (ORNL) will undergo proton power upgrade (PPU), increasing the proton beam power from 1.4 MW to 2.8 MW. From 2.8 MW, 2.0 MW will go to the current First Target Station and the rest will go to the future Second Target Station (STS). The First Target Station uses a liquid mercury target that is contained in a 316L stainless steel vessel. The proton beam is pulsed at 60 Hz, with a pulse of about 0.7μs. When the proton beam hits the target, the intense energy deposition leads to a rapid rise in temperature in the mercury. This temperature rise creates pressure waves that propagate through the mercury and cause cavitation erosion. The power upgrade will cause stronger pressure waves that will further increase damage because of cavitation. Injecting small helium bubbles in the mercury has been an efficient method of mitigating the pressure wave at 1.4 MW. However, at higher power, additional mitigation is necessary. Therefore, the 2 MW target vessel will be equipped with swirl bubblers and an additional gas injection port near the nose to inject more gas in the target. To develop a gas injection strategy and design, flow visualization in water with a transparent prototypical target (“visual target”) was performed. Bubble sizes and their spatial distribution in the flow loop are crucial to understanding the effectiveness of the bubbles in mitigating pressure waves. Bubbles were generated in the visual target under varied conditions of input pressures with helium and air. Images were captured using a high-speed camera at varied frame rates at different positions away from the swirl bubbler and different depths in the flow loop under varying lighting conditions. Initially, methods such as circular Hough transforms were applied after a series of images processing to obtain a general distribution of bubble sizes. Bubbles smaller than 500 μm are preferred to effectively mitigate the effect of pressure waves, which demands an accurate bubble detection and sizing system. Intelligent detection and identification of bubble sizes alleviate misdetection and improves accuracies. Employing neural networks, intelligent detection of bubble sizes and their distribution was developed and provides a robust alternative to traditional techniques. Human intervention was employed to label in-focus and out-of-focus bubbles in the set of training images. An object detection network using a pretrained convolutional neural network was created that extracted the features from the training images. Data augmentation was used to improve network accuracy through a random transformation of the original data.
As an emerging non-volatile memory device technology, Ferroelectric Field-Effect Transistors (FeFETs) can enable low-power, adaptive intelligent system design. However, device dimension and operating voltage dependent reliability issues of scaled FeFETs can ultimately lead to degraded performance in solving machine learning tasks. In this article, detailed experimental characterization of FeFET devices of different dimensions have been carried out to explicitly evaluate the non-ideal behavior in device conductance programming properties like number of programming states, cycle-to-cycle (C2C) variations, device-to-device (D2D) variations, and state retention. A hardware-aware software simulation approach has been adopted to capture the adversarial effects of the non-idealities on recognition accuracy through algorithm-level performance assessment by including them in NeuroSim, a popular neural network hardware simulator, to execute a neural network model considering all other hardware constraints. With the added non-idealities, significant accuracy degradation has been observed compared to the ideal scenarios where D2D variations play the most critical role. Thereafter, feasibility of a variation-aware training method has been evaluated to tackle the accuracy drop.
The advancement of artificial intelligence systems enables the use of data-driven physics-based surrogate models to explore design spaces rapidly and deeply for engineering projects. This work presents a surrogate model workflow that accelerates electric traction motor design optimization by replacing finite element analysis (FEA) with an artificial neural network (ANN) and using this model in a genetic algorithm for design optimization. A baseline interior permanent-magnet motor is parameterized and sampled to generate FEA-labeled training data, after which a feed-forward ANN predicts key outputs (e.g., loss components and weight). The validated surrogate enables genetic-algorithm optimization and deep search over the design space without new FEA runs, producing Pareto-optimal trade-offs between weight and losses and set of optimized designs for rapid downselection of manufacturable motor designs.
Stretchable optoelectronics made of elastomeric semiconductors could enable the integration of intelligent systems with soft materials, such as those of the biological world. Organic semiconductors and photodiodes have been engineered to be elastomeric; however, for photodetector applications, it remains a challenge to identify an elastomeric bulk heterojunction (e-BHJ) photoactive layer that combines a low Young’s modulus and a high strain at break that yields organic photodiodes with low electronic noise values and high photodetector performance. Here, a blend of an elastomer, a donor-like polymer, and an acceptor-like molecule yields a skin-like e-BHJ with a Young’s modulus of a few megapascals, comparable to values of human tissues, and a high strain at break of 189%. Elastomeric organic photodiodes based on e-BHJ photoactive layers maintain low electronic noise current values in the tens of femtoamperes range and noise equivalent power values in the tens of picowatts range under at least 60% strain.
The 26th annual Bioinformatics Open Source Conference (BOSC 2025, open-bio.org/events/bosc-2025) brought its community-driven focus on open-source bioinformatics and open science to the 2025 conference on Intelligent Systems for Molecular Biology and the European Conference on Computational Biology (ISMB/ECCB 2025). Since its launch in 2000, BOSC has been the premier annual meeting covering open-source bioinformatics and open science. Framed by two keynote addresses and a thought-provoking panel discussion, the two-day conference included sessions dedicated to open data, analytic tools and pipelines, workflow platforms, knowledge representation, and the application of AI/ML. The first keynote talk was delivered by Christine Orengo: “Working together to develop, promote and protect our data resources: Lessons learnt developing CATH and TED.” A joint session with the Bio-Ontologies and Knowledge Representation (BOKR) track the second day of BOSC started with a keynote talk by Chris Mungall entitled “Open Knowledge Bases in the Age of Generative AI”. A closing panel on Data Sustainability, moderated by Mónica Muñoz Torres, featured panelists Scott Edmunds, Varsha Khodiyar, Tony Burdett, Nicky Mulder, and Chris Mungall. This year, the CollaborationFest collaborative work event that typically precedes or follows ISMB was incorporated as part of the main conference and organized by BOSC with help from the Function and 3D-SIG tracks.
The Bioinformatics Open Source Conference is a volunteer-organized meeting that covers open source software development and open science in bioinformatics. Launched in 2000, BOSC has been held every year since. BOSC 2019, the 20th annual BOSC, took place as one of the Communities of Special Interest (COSIs) at the Intelligent Systems for Molecular Biology meeting (ISMB/ECCB 2019). The two-day meeting included a total of 46 talks and 55 posters, as well as eight Birds of a Feather interest groups. The keynote speaker was University of Cape Town professor Dr. Nicola Mulder, who spoke on “Building infrastructure for responsible open science in Africa”. Immediately after BOSC 2019, about 50 people participated in the two-day CollaborationFest (CoFest for short), an open and free community-driven event at which participants work together to contribute to bioinformatics software, documentation, training materials, and use cases.
The deployment of artificial intelligence systems in critical applications requires higher levels of assurance for safety, security, and interpretability. While neurosymbolic (NESY) approaches combining neural networks with symbolic reasoning offer potential advantages for assured AI, existing differentiable neurosymbolic frameworks face significant limitations including computational overhead and performance constraints. This report investigates the ISED (InferSampleEstimateDescend) framework as an alternative approach that enables neurosymbolic learning without requiring endtoend differentiability. We evaluate ISED’s utility for geointelligence applications by comparing neurosymbolic models against standard neural networks on aircraft classification tasks using the RarePlanes and MTARSI imagery datasets. Our results demonstrate that while ISEDbased models achieve slightly lower accuracy (89.7% vs 92.1% on RarePlanes; 91.1% vs 92.5% on MTARSI), they provide critical explainability capabilities that enable tracing incorrect predictions back to specific attribute misclassifications. We also present an automated pipeline that generates both attributeclass mappings and neurosymbolic model architectures from natural language descriptions, significantly reducing the manual effort required for NESY model deployment. These findings suggest that ISED offers a promising direction for developing assured AI systems where interpretability and reasoning transparency are prioritized alongside performance.
Machine intelligence has the potential to revolutionize materials science, enabling autonomous synthesis, self-driving characterization, and accelerated modeling. However, despite the promise, successful implementation of these methods in day-to-day research remains a challenge. This talk will delve into the reasons behind this, exploring how truly intelligent experiments are hindered by opaque experiment control, a lack of domain-specific models, and human-centric design. Through a focus on the characterization of next-generation microelectronics and energy storage materials, I will share insights from both successful and failed attempts to implement machine intelligence. We will then explore the next steps necessary to unlock the full potential of machine intelligence in materials science, creating a future where intelligent systems work seamlessly alongside researchers to drive innovation and discovery.
Adaptive and self-optimizing intelligent systems such as digital twins are increasingly important in science and engineering. Digital twins utilize mathematical models to provide added precision to decision-making. However, physics-informed models are challenging to build, calibrate, and validate with existing data science methods. Model-based design of experiments (MBDoE) is a popular framework for optimizing data collection to maximize parameter precision in mathematical models and digital twins. In this work, we apply MBDoE, facilitated by the open-source package Pyomo.DoE, to train and validate mathematical models for batch crystallization. We quantitatively examined the estimability of the model parameters for experiments with different cooling rates. This analysis provides a quantitative explanation for the heuristic of using multiple experiments at different cooling rates.
There is a growing demand for an intelligent system to continually learn knowledge from a data stream. Continual learning requires both the preservation of previous knowledge (i.e., avoiding catastrophic forgetting) and the acquisition of new knowledge. Different from previous works that focus only on model adaptation (e.g., regularization, network expansion, memory rehearsal, etc.), we propose a novel training scheme named acquisitive learning (AL), which emphasizes both the knowledge inheritance and knowledge acquisition. AL starts from an elaborately selected model with pre-trained knowledge (the inherited model) and then adapts it to new data using segmented training. The selection is achieved by injecting random noise to various inherited models for better model robustness, which promises higher accuracy in further knowledge acquisition. The approach is validated by the visualization of the loss landscape and quantitative roughness measurement. The combination of the selective inherited model and knowledge acquisition reduces catastrophic forgetting by 10X on the CIFAR-100 dataset.