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.
OJINN Is an easy-to-use deep neural network model that requires fewer user-specified hyper-parameters than traditional neural networks. The algorithm leverages decision trees trained on the data to determine an appropriate deep neural network architectures and weight Initializations. Optional functions also select the learning rate, batch size. and number of training Iterations necessary to create an accurate model.
Since 1984 INFN scientists performing experiments at Fermilab have been running a two-month summer training program for Italian students at the lab. In 1984 the program involved only a few physics students from the Pisa group, but it was later extended to other groups and to engineering students. Since 2004 the program has been supported in part by DOE in the frame of an exchange agreement with INFN and has been run by the Cultural Association of Italians at Fermilab (CAIF). In 2007 the Sant’Anna School of Advanced Studies (Pisa) established an agreement with Fermilab to share the cost of four engineering students each year. In the 34 years of its history, the program has hosted at Fermilab approximately 530 Italian students from more than 20 Italian universities and from some non-Italian universities . In addition, in the years 2010-2018, with the support of INAF, ASI, and CAIF, 25 students were hosted in other US laboratories and universities. The Fermilab training programs spanned from data analysis to design and construction of particle detectors and accelerator components, R/D on superconductive elements, theory of accelerators, and analysis of astrophysical data. At the other US laboratories the offered training was on Space Science. In 2015 the University of Pisa endorsed the program as one of his own Summer Schools. The interns are enrolled as Pisa students for the duration of the internship. They are required to write summary reports published in the Fermilab and University of Pisa web pages. Upon positive evaluation by a University board, students are acknowledged 6 ECTS credits. In 2017 a new initiative of the Oxford Summer School "MovingKnowledge17" allowed three Fermilab summer students to be trained in neutrino physics to spend the month of July at Oxford to follow an advanced course on HEP.The entire program is expected to expand further under CAIF management. An agreement has been signed between ASI and CAIF, for ASI to support yearly three two-months fellowships in US space science laboratories. The program is also part of the Outreach of the European Projects MUSE (H2020-MSCA-RISE-2015, GA 690835), NEWS (H2020-MSCA-RISE-2016, GA 734303) and INTENSE (H2020-MSCA-RISE-2018, GA 822185 in preparation).
The control of high-dimensional distributed parameter systems (DPS) remains a challenge when explicit coarse-grained equations are unavailable. Classical equation-free (EF) approaches rely on fine-scale simulators treated as black-box timesteppers. However, repeated simulations for steady-state computation, linearization, and control design are often computationally prohibitive, or the microscopic timestepper may not even be available, leaving us with data as the only resource. We propose a data-driven alternative that uses local neural operators, trained on spatiotemporal microscopic/mesoscopic data, to obtain efficient short-time solution operators. These surrogates are employed within Krylov subspace methods to compute coarse steady and unsteady-states, while also providing Jacobian information in a matrix-free manner. Krylov-Arnoldi iterations then approximate the dominant eigenspectrum, yielding reduced models that capture the open-loop slow dynamics without explicit Jacobian assembly. Both discrete-time Linear Quadratic Regulator (dLQR) and pole-placement (PP) controllers are based on this reduced system and lifted back to the full nonlinear dynamics, thereby closing the feedback loop.
A method for on-line Space Shuttle Main Engine (SSME) anomaly detection and fault typing using a feedback neural network is described. The method involves the computation of features representing time-variance of SSME sensor parameters, using historical test case data. The network is trained, using backpropagation, to recognize a set of fault cases. The network is then able to diagnose new fault cases correctly. An essential element of the training technique is the inclusion of randomly generated data along with the real data, in order to span the entire input space of potential non-nominal data.
This work is focused on optimizing the assimilation of hyperspectral infrared (IR) radiances from the Cross-track Infrared Sounder (CrIS) with the goal of improving the representation of tropical cyclones (TCs) in global analyses and forecasts. Current operational assimilation systems rely on subsampling IR radiances on a regular thinning grid. A new and improved adaptive methodology based on machine learning (ML) recognizes TCs from geostationary satellite imagery and is implemented in the Goddard Earth Observing System (GEOS) model and data assimilation framework. The ML methodology is extensively trained on existing TC data sets and creates for each TC a dynamic mask, based on the evolving shape and life cycle of that specific event. Once a TC mask is created, a switch is then activated in the data assimilation system to alter the thinning, ingesting more CrIS radiances within the moving mask, thus increasing the TC sampling. After the TC dissipates, the assimilation of CrIS radiances reverts to normal data density. Results of TC segmentation provided by a state-of-the-art generative machine learning model known as the Denoising Diffusion Probabilistic Model (DDPM) are compared to the previously used U-Net model. The new approach surpasses the performance of the previously developed one. The methodology is applied to both clear-sky and cloud-cleared radiances. Benefits from the latter methodology, particularly in improving the structure of TCs and the intensity forecasts, are presented.
Since 1984 INFN scientists performing experiments at Fermilab have been running a two month summer training program for Italian students at the lab. In 1984 the program involved only a few physics students from the Pisa group, but it was later extended to other groups and to engineering students. Since 2004 the program has been supported in part by DOE in the frame of an exchange agreement with INFN. The Fermilab training programs spanned from data analysis to design and construction of particle detectors and accelerator components, research on superconductive elements, theory of accelerators, and analysis of astrophysical data. At the other US laboratories the offered training was on Space Science.
In the context of urgent climate challenges and the pressing need for rapid technology development, Reinforcement Learning (RL) stands as a compelling data-driven method for controlling real-world physical systems. However, RL implementation often entails time-consuming and computationally intensive data collection and training processes, rendering them inefficient for real-time applications that lack non-real-time models. To address these limitations, real-time emulation techniques have emerged as valuable tools for the lab-scale rapid prototyping of intricate energy systems. While emulated systems offer a bridge between simulation and reality, they too face constraints, hindering comprehensive characterization, testing, and development. In this research, we construct a surrogate model using limited data from simulated systems, enabling an efficient and effective training process for a Double Deep Q-Network (DDQN) agent for future deployment. Our approach is illustrated through a hydropower application, demonstrating the practical impact of our approach on climate-related technology development.
Sap flow, a critical process in plant water use and ecosystem water cycles, is often measured using thermal dissipation probes (TDP) due to their ease of installation and continuous data collection. However, sap flow data frequently include noise, outliers, and gaps, creating challenges for analysis and requiring substantial manual processing. We developed S AP F LOWER , a tool that automates data preprocessing, model training, gap-filling, sapwood area scaling and modeling, and water use analysis. It integrates autocleaning, machine learning and deep learning models (e.g. random forest, Gaussian process regression, long short-term memory (LSTM), bidirectional LSTM (BiLSTM)), and efficient workflows to process sap flow data. S AP F LOWER can remove over 90% of noisy data while preserving legitimate variations and achieve high accuracy in gap-filling based on user-determined parameters. Random forest, LSTM, and BiLSTM models reduced root mean square error to 10% or less for long-term gaps. Model training and prediction can be performed efficiently within seconds. S AP F LOWER significantly enhances the efficiency and accessibility of TDP data analysis by automating complex tasks, enabling researchers without programming expertise to employ advanced techniques. Future improvements will focus on species-specific corrections for TDP and support for additional measurement methods. S AP F LOWER is openly available on GitHub (https://github.com/JiaxinWang123/SapFlower) and Zenodo (doi: 10.5281/zenodo.13665919).
Here, we present deep learning (DL) networks for three-dimensional (3D) joint inversion of active seismic full waveform and passive seismic traveltime data to image reservoirs and their properties and quantify imaging uncertainties. Active seismic full-waveform data can provide high-resolution monitoring images but are collected only intermittently because of their high acquisition cost. In contrast, passive seismic data can be gathered at relatively low cost between regular active surveys, although their imaging quality can be compromised by factors such as low signal-to-noise ratios and limited ray coverage of the target. Although these datasets are routinely acquired together at CO 2 storage sites, their combined inversion within a 3D DL framework has not been previously demonstrated. To our knowledge, this is the first study to address this gap, combining the strength of both data types. For efficient data storage and DL training with large 3D seismic datasets, we use a 3D data matrix in which a random number of passive seismic traveltime data are stored as parabolic envelopes using one-hot encoding and a 3D full-waveform data matrix in which multiple shot gathers are summed. Two network architectures are evaluated: a single-encoder U-Net for single-data type inversion and a dual-encoder U-Net for joint inversion of active and passive seismic data. We also evaluate the single-encoder U-Net for joint inversion by concatenating full-waveform data and traveltime data. We propose a systematic approach for selecting an optimal dropout rate that balances regularization during training and Monte Carlo dropout-based uncertainty quantification during prediction by examining the correlation coefficient between standard deviation and prediction error, along with the training misfit, across a range of dropout rates. 3D DL inversion experiments include five different network configurations, with evaluations under ideal, noisy and dropout-enabled conditions. Both model and data uncertainties are assessed, as well as their combined effects. Across all conditions, the networks consistently predict accurate CO 2 saturation models with low prediction errors, such as a structural similarity index of 0.993 and CO 2 difference of 1.1%. Uncertainty estimates show strong spatial correlation with prediction errors, confirming the effectiveness of the proposed dropout selection approach. The results demonstrate that our DL approach, utilizing compact data representations and appropriate uncertainty quantification, yields accurate subsurface images under various inversion conditions and provides valuable insights into the reliability of predictions.
13 C metabolic flux analysis (MFA) has emerged as a powerful tool for synthetic biology. This optimization-based approach suffers long computation time and unstable solutions depending on the initial guess. Here, we develop a machine-learning-based framework for 13 C fluxomics. Specifically, training and test data sets are generated by metabolic network decomposition and flux sampling, in which flux ratios at metabolic nodes and simulated labeling patterns of metabolites are used as training targets and features, respectively. To improve prediction accuracy and simplify the model, automated processes are developed for flux ratio selection based on solvability and feature screening based on importance. We found that predictive performance can be significantly improved using both amino acids and central carbon metabolites in comparison with amino acids alone. Together with measured external fluxes, the predicted flux ratios determine the mass balance system, yielding global flux distributions. This approach is validated by flux estimation using both simulated and experimental data in comparison with canonical 13 C MFA. The approach represents a reliable fluxomics method readily applicable to high-throughput metabolic phenotyping, which highlights the advances of intelligent learning algorithms in synthetic biology, specifically in the Test and Learn stage of the Design-Build-Test-Learn cycle.
High-temperature advanced reactors under development, such as sodium fast reactors (SFR) and molten salt cooled reactors (MSCR), are expected to offer lower levelized cost of energy (LCOE) compared to existing light water reactor (LWR’s). In the existing light water reactors (LWR’s), operation and maintenance (O&M) expenses constitute the largest fraction of the total operating cost. Some of the O&M costs are related maintenance of sensors which can fail due to exposure to harsh environment in a reactor. The O&M costs of Advanced Reactor (AR)’s are expected to constitute a significant fraction of the total cost as well, because of high temperature and radiation level in AR are likely to cause material fatigue and premature failure of sensors and components. The O&M costs in AR’s could be reduced through integration of advanced informatics of performance-related sensors into a digital twin designed for reactor monitoring. For example, machine learning (ML) could be employed for real-time validation and correction of performance-related sensors, and reducing the number of performance-related physical sensor units through virtual sensing. As part of the effort, we investigate real-time validation of thermal hydraulic sensors through one-step ahead forecasting of sensor values using long short-term memory (LSTM) recurrent neural networks (RNN). The sensors are installed in a flow loop containing a thermal mixing tee, which is a common experimental model to study thermal fatigue in a thermal hydraulic loop. In addition, nonlinear transients generated in a thermal mixing tee constitute a good challenge data set for training and validation of ML algorithms. Sensors in this study include thermocouples, flow meters, and optical fibers for distributed temperature sensing. In one experiment, measurement data sets were obtained for a loop was filled with water, and in another experiment, measurements were performed on a loop filled with liquid metal Galinstan. We have also conducted preliminary investigation of one-step ahead prediction of fiber optics-based distributed temperature sensing with LSTM networks. In predicting fiber-based temperature measurements, we treated each gauge pitch of the fiber as an independent sensor. Accuracy of one-step ahead forecasting was estimated by calculating root mean square error (RMSE) for the test segment of time series of each sensor. RMSE’s for temperature sensors in water loop were, for the most part, lower than for the same sensors in Galinstan loop. The RMSE’s for flow meters were similar for both loops. The RMSE’s for distributed temperature measured with the fiber optic sensor were similar to those of the point sensors. Results of this study demonstrated the capability of LSTM one-step ahead forecasting with RMSE comparable to uncertainty in sensor measurements.
Eye tracking may be a useful tool to investigate pilot monitoring and develop and conduct training. There is increased interest from airlines to use eye-tracking technologies in flight simulators. However, much is still unknown about how to best utilize eye-tracking data in pilot training. This paper presents eye-tracking results from a pilot-monitoring training study with 19 pilots. All pilots completed 15 monitoring challenges across four operational scenarios in a B737-700 full flight simulator. In addition, the study investigated the impact of having the flight director engaged or disengaged on the pilot monitoring side in the final approach. It was hypothesized that pilots would focus less on the primary flight display with the flight director off and look more around in the cockpit. To assess this, pilots performed half of the scenarios with the flight director on and half with the flight director off. However, pilots monitoring tended to look less at the primary flight display with the flight director on as indicated by lower Proportion Dwell Times, contrary to the hypothesis. Next, eye-tracking data were analyzed from two monitoring challenges involving waypoint restrictions and two involving extending the flaps at appropriate airspeeds. Pilots that successfully completed the challenges appeared to focus more on areas of interest that contained the most relevant information to successfully complete the challenge. In addition, successful pilots seemed to adapt their monitoring strategy more to the challenge at hand as observed by a distinct shift in focus on either the primary flight display or the navigation display depending on the challenge. Our findings suggest the importance of flexible gaze allocation across specific situations and raise the question whether and to what degree prespecified patterns of eye fixation can be identified and trained.
Eye tracking may be a useful tool to investigate pilot monitoring and develop and conduct training. There is increased interest from airlines to use eye-tracking technologies in flight simulators. However, much is still unknown about how to best utilize eye-tracking data in pilot training. This paper presents eye-tracking results from a pilot-monitoring training study with 19 pilots. All pilots completed 15 monitoring challenges across four operational scenarios in a B737-700 full flight simulator. In addition, the study investigated the impact of having the flight director engaged or disengaged on the pilot monitoring side in the final approach. It was hypothesized that pilots would focus less on the primary flight display with the flight director off and look more around in the cockpit. To assess this, pilots performed half of the scenarios with the flight director on and half with the flight director off. However, pilots monitoring tended to look less at the primary flight display with the flight director on as indicated by lower Proportion Dwell Times, contrary to the hypothesis. Next, eye-tracking data were analyzed from two monitoring challenges involving waypoint restrictions and two involving extending the flaps at appropriate airspeeds. Pilots that successfully completed the challenges appeared to focus more on areas of interest that contained the most relevant information to successfully complete the challenge. In addition, successful pilots seemed to adapt their monitoring strategy more to the challenge at hand as observed by a distinct shift in focus on either the primary flight display or the navigation display depending on the challenge. Our findings suggest the importance of flexible gaze allocation across specific situations and raise the question whether and to what degree prespecified patterns of eye fixation can be identified and trained.
HN 3 is a unique liquid energetic material that exhibits ultrafast detonation chemistry and a transition to metallic states during detonation. We combine the Chebyshev interaction model for efficient simulation (ChIMES) many-body reactive force field and the extended-Lagrangian multiscale shock technique molecular dynamics method to calculate the detonation properties of HN 3 with the accuracy of Kohn–Sham density-functional theory. ChIMES is based on a Chebyshev polynomial expansion and can accurately reproduce density-functional theory molecular dynamics (DFT-MD) simulations for a wide range of unreactive and decomposition conditions of liquid HN 3 . We show that addition of random displacement configurations and the energies of gas-phase equilibrium products in the training set allows ChIMES to efficiently explore the complex potential energy surface. Schemes for selecting force field parameters and the inclusion of stress tensor and energy data in the training set are examined. Structural and dynamical properties and chemistry predictions for the resulting models are benchmarked against DFT-MD. We demonstrate that the inclusion of explicit four-body energy terms is necessary to capture the potential energy surface across a wide range of conditions. Our results generally retain the accuracy of DFT-MD while yielding a high degree of computational efficiency, allowing simulations to approach orders of magnitude larger time and spatial scales. The techniques and recipes for MD model creation we present allow for direct simulation of nanosecond shock compression experiments and calculation of the detonation properties of materials with the accuracy of Kohn–Sham density-functional theory.
Multispectral scanner reflectance data were sampled for bare soil, cotton, sorghum, corn, and citrus at four dates during a growing season (April, May, June, and July 1969) to develop a time-dependent signature for crop and soil discrimination. Discrimination tests were conducted for single-date and multidate formats using training and test data sets. For classifications containing several crops, the multidate or temporal approach improved discrimination compared with the single-date approach. The multidate approach also preserved recognition accuracy better in going from training fields to test fields than the single-date analysis. The spectral distinctiveness of bare soil versus vegetation resulted in essentially equal discrimination using single-date versus multidate data for those two categories.
Flame spray pyrolysis (FSP) is a process used to synthesize nanoparticles through the combustion of an atomized precursor solution; this process has applications in catalysts, battery materials, and pigments. Current limitations revolve around understanding how to consistently achieve a stable flame and the reliable production of nanoparticles. Machine learning and artificial intelligence algorithms that detect unstable flame conditions in real time may be a means of streamlining the synthesis process and improving FSP efficiency. In this study, the FSP flame stability is first quantified by analyzing the brightness of the flame's anchor point. This analysis is then used to label data for both unsupervised and supervised machine learning approaches. The unsupervised learning approach allows for autonomous labeling and classification of new data by representing data in a reduced dimensional space and identifying combinations of features that most effectively cluster it. The supervised learning approach, on the other hand, requires human labeling of training and test data but is able to classify multiple objects of interest (such as the burner and pilot flames) within the video feed. The accuracy of each of these techniques is compared against the evaluations of human experts. Both the unsupervised and supervised approaches can track and classify FSP flame conditions in real time to alert users of unstable flame conditions. This research has the potential to autonomously track and manage flame spray pyrolysis as well as other flame technologies by monitoring and classifying the flame stability.
Recent advancements in scientific equipment and the adaptation of electronics and the Internet of Things (IoT) in our everyday lives resulted in large and complex data production at a high rate. Making meaningful and timely knowledge discovery at a modest cost from this big data is difficult for computing power and storage limitations. Training deep learning models incrementally in a streaming setting can help us with overcoming these limitations. However, in a well-known phenomenon named catastrophic forgetting, incrementally trained models increasingly perform poorly on the past data. To mitigate catastrophic forgetting in training in a streaming setting, we propose constructing a historical summary over time and use the summary with newly arrived data during incremental training. We propose various data summarization techniques such as random sampling, micro clustering, coreset computation, and Auto Encoders to counteract catastrophic forgetting. We built a pipeline for incremental training with a historical summary for training deep learning models for streaming data. We demonstrate the effectiveness of historical summary in mitigating catastrophic forgetting using three case studies involving three different deep learning applications: an Artificial Neural Network (ANN) for classification task on MNIST dataset, a language model (RNN-LM) on the WikiText2 dataset, and a Convolutional Neural Network (CNN), ResNet50 to classify the ImageNet dataset. Through the training of the models, we observe that catastrophic forgetting is evident in ANN and CNN but not in an RNN. For the first task, our method recovers up to 47.9% lost accuracy due to catastrophic forgetting. For the third task, the historical summary recovers classification accuracy by up to 25%. For the second task, though there is not proof of catastrophic forgetting, the training performance (PPL) improves by up to 26% with historical summary.
Scientific applications of artificial intelligence (AI) often remain limited by device-specific training and unexplained “black-box” approaches, creating fundamental barriers to cross-system generalization. This challenge is critical for nuclear fusion, where future reactors will have limited operational data for AI training. Here, we demonstrate that our neural network, trained solely on megahertz-scale turbulence measurements from one machine (DIII-D), forecasts Type-I edge localized mode (ELM) onsets in a different tokamak (KSTAR) through zero-shot weight transfer following physics-consistent preprocessing without device-specific retraining. Through an explainable AI framework combining gradient-weighted class activation mapping with physics validation, we reveal that our network can internalize physics relationships governing the ELM instabilities rather than memorizing device-specific patterns. The network perceives spatiotemporal features that correlate consistently with independently calculated instability growth rates, magnetohydrodynamic stability limits, and pedestal structure dynamics. Statistical analyses of dimensionally-reduced saliency features reveal the identical triangular features between the saliency representations, instability growth rates, and prediction probability across tokamaks, providing evidence that our forecasting system can show tokamak-agnostic generalization. This work contributes to a foundation for explainable scientific AI systems, where cross-system developments are essential for transcending traditional domain-specific constraints.
Refine your search to explore more results.