SEARCH · Engineering Papers
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.
Presentation discusses use of data in radiological emergency response and different methods (applied statistics, spectral clustering, spectral anomaly detection, etc.) that could be used in conjunction with machine learning to optimize response to real-world radiological events.
Deep learning has been shown to be an effective tool in solving partial differential equations (PDEs) through physics-informed neural networks (PINNs). PINNs embed the PDE residual into the loss function of the neural network, and have been successfully employed to solve diverse forward and inverse PDE problems. However, one disadvantage of the first generation of PINNs is that they usually have limited accuracy even with many training points. Here, we propose a new method, gradient-enhanced physics-informed neural networks (gPINNs), for improving the accuracy of PINNs. gPINNs leverage gradient information of the PDE residual and embed the gradient into the loss function. We tested gPINNs extensively and demonstrated the effectiveness of gPINNs in both forward and inverse PDE problems. Our numerical results show that gPINN performs better than PINN with fewer training points. Additionally, we combined gPINN with the method of residual-based adaptive refinement (RAR), a method for improving the distribution of training points adaptively during training, to further improve the performance of gPINN, especially in PDEs with solutions that have steep gradients.
The progression of cyber-attacks on the cyber-physical system is analyzed by the Probabilistic, Learning Attacker, and Dynamic Defender (PLADD) model. Although our research does apply to all cyber-physical systems, we focus on power grid infrastructure. The PLADD model evaluates the effectiveness of moving target defense (MTD) techniques. We consider the power grid attack scenarios in the AND configurations and OR configurations. In addition, we consider, for the first time ever, power grid attack scenarios involving both AND configurations and OR configurations simultaneously. Cyber-security managers can use the strategy introduced in this manuscript to optimize their defense strategies. Specifically, our research provides insight into when to reset access controls (such as passwords, internet protocol addresses, and session keys), to minimize the probability of a successful attack. Our mathematical proof for the OR configuration of multiple PLADD games shows that it is best if all access controls are reset simultaneously. For the AND configuration, our mathematical proof shows that it is best (in terms of minimizing the attacker's average probability of success) that the resets are equally spaced apart. We introduce a novel concept called hierarchical parallel PLADD system to cover additional attack scenarios that require combinations of AND and OR configurations.
The optimization concepts are described in relation to an overall design process as opposed to a detailed, part-design process where the requirements are firmly stated, the optimization criteria are well established, and a design is known to be feasible. The overall design process starts with the stated requirements. Some of the design criteria are derived directly from the requirements, but others are affected by the design concept. It is these design criteria that define the performance index, or objective function, that is to be minimized within some constraints. In general, there will be multiple objectives, some mutually exclusive, with no clear statement of their relative importance. The optimization loop that is given adjusts the design variables and analyzes the resulting design, in an iterative fashion, until the objective function is minimized within the constraints. This provides a solution, but it is only the beginning. In effect, the problem definition evolves as information is derived from the results. It becomes a learning process as we determine what the physics of the system can deliver in relation to the desirable system characteristics. As with any learning process, an interactive capability is a real attriubute for investigating the many alternatives that will be suggested as learning progresses.
NASA’s Intelligent Systems Technology Program (IST) is driving a paradigm shift in Earth science through the development of Earth System Digital Twins (ESDT). These integrated information systems create a dynamic "digital replica" of the Earth by harmonizing continuous, multi-source observations with high-fidelity models and state-of-the-art artificial intelligence (AI) that enable “What now?”, “What next?”, and “What if?” scenario building. These scenarios are reflected in NASA IST’s series of ESDTs, from the Coastal Zone Digital Twin that integrates complex data on the current state of the Chesapeake Bay to the Terrestrial Environmental Rapid-Replication and Assimilation Hydrometeorological (TerraHydro) AI-based ESDT that forecasts water movement across Earth’s surface, to the Agriculture Land Information System (AgLIS) which can be used to assess optimal planting dates and crop yield estimates. By bridging the gap between vast data archives and actionable insights, these projects enable a system-of-systems approach to understanding complex, interacting Earth processes. This poster will highlight recent innovations and future directions from NASA’s ESDT initiatives: Continuous Data Assimilation & Multi-Source Fusion. A core requirement of the ESDT work is the transition from static models to dynamic "living" replicas. This involves creating frameworks for the continual assimilation of near-real-time data from uncoordinated, heterogeneous sources, including satellite observations and airborne assets, and ground-based Internet of Things (IoT) sensors. These systems link design, operational status, and environmental data, ensuring the digital twin accurately reflects the current state of the physical Earth system. High-Fidelity Hybrid Modeling & Computational Acceleration to enable interactive "what-if" explorations, programs are moving beyond traditional, slow physical solvers by developing fast surrogate machine learning models and Deep Generative Models (DGMs). These hybrid approaches use neural networks to emulate complex physics, such as cloud feedback or ocean dynamics, at a fraction of the original computing cost, often leveraging advanced hardware like Graphics Processing Units (GPUs) to achieve the necessary scale. Federated Ecosystems & Interoperable Frameworks rather than building isolated tools, NASA IST is moving toward federated ESDTs and reusable analytic collaborative frameworks. This theme focuses on interoperability standards and common ontologies that allow specialized digital twins to interact and share data. This system-of-systems architecture supports multi-discipline investigations, such as analyzing how upstream watershed changes impact downstream urban flooding or how wildfire emissions affect regional air quality. By leveraging these advancements, ESDTs empower researchers and decision-makers to conduct real-time analysis and run complex hypothetical scenarios, ultimately improving our understanding of Earth’s evolving systems and informing critical real-world applications.
During the last decade, teleoperated robotic systems have extended humans’ sensorimotor competence to digitally fly beyond the physical barrier of distance and scale and thus transmit sensorimotor skills of the human through direct communication. Telepresence capabilities have enabled tele-physical remote access at small scales thanks to telerobotic mediums. Although the concept was initially motivated by space applications, such technologies quickly have expanded into the medical domain and resulted in teleoperated medical robots, including telerobotic surgical systems (such as the da Vinci surgical system). Effective telepresence fundamentally depends on an agile, reliable, and secure communication medium that can transmit real-time information between the operator and a remote device. However, direct telepresence may not be achievable for long-duration exploration spaceflight missions. Thus, autonomous systems and local intelligence represent potential solutions to the aforementioned issues. One example solution employs demonstration systems which enable learning from the pre-captured inputs of a skilled human operator. These will be computationally modeled and later probabilistically replicated toward the completion of remote physical tasks when direct telepresence is not viable - such as under communication blackout conditions. In other words, trained autonomous systems (e.g., robots) can perform remote operations that mimic the physical performance of experts during remote operations/training. Beyond learning the physics of the task, autonomous agents can also be used to conduct algorithmic decision-making that mimics the higher-level cognition of the expert. Thus, using an autonomous system, pre-trained cognitive and manipulation-based skills can be leveraged (acquired during pre-mission events) to produce digital twins of an intelligent operator. Such systems can be used for the real-time conduction of intricate tasks in complex and unstructured environments. Such systems will operationalize “cognitive digital twins” and can expand the reach of human cognition and manipulation through the power of data-driven learning from demonstration algorithms. This system category will be discussed as a fully autonomous operation in this talk. In addition to the above, we will also propose and discuss the possibility of partial-automation using remote intelligence and remote sensing. In contrast to full automation, partial automation can close the loop through a local operator equipped with augmented sensory awareness through wearable systems. Such technologies will allow the local operator to conduct delicate tasks while being guided using sensory augmentation and being monitored to gauge her/his level of cognitive focus and performance. The difference with the previous category is that a remote human will conduct the task. Further, rather than making a digital twin of human cognition, we will augment the control inputs of the local human to match those of the skilled expert operator who is not accessible in real-time. Going beyond classic telepresence and thus approaching intelligent telepresence, our vision is that autonomous agents will eventually enable the safe, consistent and efficient delivery of complex, remote and smart medical care during space exploration across operators in an Earth-independent fashion. We will discuss our collective vision from NASA and MERIIT@NYU lab in this talk.
We apply inverse-design methods to produce two-dimensional plasma metamaterial (PMM) devices. Backpropagated finite-difference frequency-domain (FDFD) simulations are used to design waveguides and demultiplexers operating under both TE and TM modes. Demultiplexing and waveguiding are demonstrated for devices composed of plasma elements with reasonable plasma densities of approximately 7 GHz, allowing for future in situ training and experimental realization of these designs. We also explore the possible applicability of PMMs to nonlinear boolean operations for use in optical computing. Functionally complete logical connectives (or and and) are achieved in the TM mode.
Multimedia learning has always been a topic in physics education—whether through specialized digital data acquisition systems, simulations, or animations. Due to increasing digitalization, more and more media from our everyday lives have also found their way into education in recent decades. This contribution introduces a conceptual framework and illustrative examples for AI-supported experimentation in physics education. It does not yet present empirical data but outlines directions for forthcoming classroom studies evaluating learning outcomes and engagement.
Restricted Boltzmann machines (RBMs) are simple statistical models defined on a bipartite graph which have been successfully used in studying more complicated many-body systems, both classical and quantum. In this work, we exploit the representation power of RBMs to provide an exact decomposition of many-body contact interactions into one-body operators coupled to discrete auxiliary fields. This construction generalizes the well known Hirsch's transform used for the Hubbard model to more complicated theories such as pionless effective field theory in nuclear physics, which we analyze in detail. Finally, we also discuss possible applications of our mapping for quantum annealing applications and conclude with some implications for RBM parameter optimization through machine learning.
Classification machine learning models require high-quality labeled datasets for training. Among the most useful datasets for photovoltaic array fault detection and diagnosis are module or string current-voltage (IV) curves. Unfortunately, such datasets are rarely collected due to the cost of high fidelity monitoring, and the data that is available is generally not ideal, often consisting of unbalanced classes, noisy data due to environmental conditions, and few samples. In this paper, we propose an alternate approach that utilizes physics-based simulations of string-level IV curves as a fully synthetic training corpus that is independent of the test dataset. In our example, the training corpus consists of baseline (no fault), partial soiling, and cell crack system modes. The training corpus is used to train a 1D convolutional neural network (CNN) for failure classification. The approach is validated by comparing the model’s ability to classify failures detected on a real, measured IV curve testing corpus obtained from laboratory and field experiments. Results obtained using a fully synthetic training dataset achieve identical accuracy to those obtained with use of a measured training dataset. When evaluating the measured data’s test split, a 100% accuracy was found both when using simulations or measured data as the training corpus. When evaluating all of the measured data, a 96% accuracy was found when using a fully synthetic training dataset. The use of physics-based modeling results as a training corpus for failure detection and classification has many advantages for implementation as each PV system is configured differently, and it would be nearly impossible to train using labeled measured data.
While short-range noncovalent interactions (NCIs) are proving to be of importance in many chemical and biological systems, these atypical bindings happen within the so-called van der Waals envelope and pose an enormous challenge for current computational methods. We introduce SNCIAA, a database of 723 benchmark interaction energies of short-range noncovalent interactions between neutral/charged amino acids originated from protein x-ray crystal structures at the “gold standard” coupled-cluster with singles, doubles, and perturbative triples/complete basis set [CCSD(T)/CBS] level of theory with a mean absolute binding uncertainty less than 0.1 kcal/mol. Subsequently, a systematic assessment of commonly used computational methods, such as the second-order Møller−Plesset theory (MP2), density functional theory (DFT), symmetry-adapted perturbation theory (SAPT), composite electronic-structure methods, semiempirical approaches, and the physical-based potentials with machine learning (IPML) on SNCIAA is carried out. It is shown that the inclusion of dispersion corrections is essential even though these dimers are dominated by electrostatics, such as hydrogen bondings and salt bridges. Overall, MP2, ωB97M-V, and B3LYP+D4 turned out to be the most reliable methods for the description of short-range NCIs even in strongly attractive/repulsive complexes. SAPT is also recommended in describing short-range NCIs only if the δMP2 correction has been included. The good performance of IPML for dimers at close-equilibrium and long-range conditions is not transferable to the short-range. We expect that SNCIAA will assist the development/improvement/validation of computational methods, such as DFT, force-fields, and ML models, in describing NCIs across entire potential energy surfaces (short-, intermediate-, and long-range NCIs) on the same footing.
The MBX software provides an advanced platform for molecular dynamics simulations, leveraging state-of-the-art MB-pol and MB-nrg data-driven many-body potential energy functions. Developed over the past decade, these potential energy functions integrate physics-based and machine-learned many-body terms trained on electronic structure data calculated at the "gold standard" coupled-cluster level of theory. Recent advancements in MBX have focused on optimizing its performance, resulting in the release of MBX v1.2. While the inherently many-body nature of MB-pol and MB-nrg ensures high accuracy, it poses computational challenges. MBX v1.2 addresses these challenges with significant performance improvements, including enhanced parallelism that fully harnesses the power of modern multicore CPUs. In conclusion, these advancements enable simulations on nanosecond time scales for condensed-phase systems, significantly expanding the scope of high-accuracy, predictive simulations of complex molecular systems powered by data-driven many-body potential energy functions.
We introduce a conditional pseudo-reversible normalizing flow (PR-NF) that directly learns conditional probability distributions from noisy physical models to efficiently quantify both forward and inverse uncertainty propagation. Traditional surrogate modeling approaches approximate only the deterministic component of physical models, requiring separate noise characterization and computationally expensive sampling methods for inverse problems. Here, in this work, we develop the conditional PR-NF model to directly learn and efficiently generate samples from the conditional probability density functions (PDFs). The training process utilizes dataset consisting of input-output pairs without requiring prior knowledge about the noise and the function. Once trained, our model efficiently generates samples from conditional PDFs for any input within the training domain. Moreover, the pseudo-reversibility feature allows for the use of fully connected neural network architectures, which simplifies the implementation and enables theoretical analysis. We provide a rigorous convergence analysis of the conditional PR-NF model, showing its ability to converge to the target conditional PDF using the Kullback−Leibler divergence. To demonstrate the effectiveness of our method, we apply it to several benchmark tests and a real-world geologic carbon storage problem.
Subsurface energy activities such as unconventional resource recovery, enhanced geothermal energy systems, and geologic carbon storage require fast and reliable methods to account for complex, multiphysical processes in heterogeneous fractured and porous media. Although reservoir simulation is considered the industry standard for simulating these subsurface systems with injection and/or extraction operations, reservoir simulation requires spatio-temporal “Big Data” into the simulation model, which is typically a major challenge during model development and computational phase. In this work, we developed and applied various deep neural network-based approaches to (1) process multiscale image segmentation, (2) generate ensemble members of drainage networks, flow channels, and porous media using deep convolutional generative adversarial network, (3) construct multiple hybrid neural networks such as convolutional LSTM and convolutional neural network-LSTM to develop fast and accurate reduced order models for shale gas extraction, and (4) physics-informed neural network and deep Q-learning for flow and energy production. We hypothesized that physicsbased machine learning/deep learning can overcome the shortcomings of traditional machine learning methods where data-driven models have faltered beyond the data and physical conditions used for training and validation. We improved and developed novel approaches to demonstrate that physics-based ML can allow us to incorporate physical constraints (e.g., scientific domain knowledge) into ML framework. Outcomes of this project will be readily applicable for many energy and national security problems that are particularly defined by multiscale features and network systems.
Motivated by the high computational costs of classical simulations, machine-learned generative models can be extremely useful in particle physics and elsewhere. They become especially attractive when surrogate models can efficiently learn the underlying distribution, such that a generated sample outperforms a training sample of limited size. This kind of GANplification has been observed for simple Gaussian models. We show the same effect for a physics simulation, specifically photon showers in an electromagnetic calorimeter.
The rich history of observing system simulation experiments (OSSEs) does not yet include a well-established framework for using climate models. The need for a climate OSSE is triggered by the need to quantify the value of a particular measurement for reducing the uncertainty in climate predictions, which differ from numerical weather predictions in that they depend on future atmospheric composition rather than the current state of the weather. However, both weather and climate modeling communities share a need for motivating major observing system investments. Here, we outline a new framework for climate OSSEs that leverages the use of machine learning to calibrate climate model physics against existing satellite data. We demonstrate its application using NASA’s GISS-E3 model to objectively quantify the value of potential future improvements in spaceborne measurements of Earth’s planetary boundary layer. A mature climate OSSE framework should be able to quantitatively compare the ability of proposed observing system architectures to answer a climate-related question, thus offering added value throughout the mission design process, which is subject to increasingly rapid advances in instrument and satellite technology. Technical considerations include selection of observational benchmarks and climate projection metrics, approaches to pinpoint the sources of model physics uncertainty that dominate uncertainty in projections, and the use of instrument simulators. Community and policy-making considerations include the potential to interface with an established culture of model intercomparison projects and a growing need to economically assess the value-driven efficiency of social spending on Earth observations.
A major obstacle for machine learning (ML) in chemical science is the lack of physically informed feature representations that provide both accurate prediction and easy interpretability of the ML model. In this work, we describe adsorption systems using novel two-dimensional energy histogram (2D-EH) features, which are obtained from the probe-adsorbent energies and energy gradients at grid points located throughout the adsorbent. The 2D-EH features encode both energetic and structural information of the material and lead to highly accurate ML models (coefficient of determination R2 ~ 0.94–0.99) for predicting single-component adsorption capacity in metal–organic frameworks (MOFs). Here, we consider the adsorption of spherical molecules (Kr and Xe), linear alkanes with a wide range of aspect ratios (ethane, propane, n-butane, and n-hexane), and a branched alkane (2,2-dimethylbutane) over a wide range of temperatures and pressures. The interpretable 2D-EH features enable the ML model to learn the basic physics of adsorption in pores from the training data. We show that these MOF-data-trained ML models are transferrable to different families of amorphous nanoporous materials. We also identify several adsorption systems where capillary condensation occurs, and ML predictions are more challenging. Nevertheless, our 2D-EH features still outperform structural features including those derived from persistent homology. The novel 2D-EH features may help accelerate the discovery and design of advanced nanoporous materials using ML for gas storage and separation in the future.