SEARCH · Engineering Papers

Results for “deep potential”

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.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 919 records · Page 51

All sources NASA NTRS DOE OSTI

DOE OSTI2026

Learning genetic perturbation effects with variational causal inference

Advances in sequencing technologies have enhanced the understanding of gene regulation in cells. In particular, Perturb-seq has enabled high-resolution profiling of the transcriptomic response to genetic perturbations at the single-cell level. This understanding has implications in functional genomics and potentially for identifying therapeutic targets. Various computational models have been developed to predict perturbational effects. While deep learning models excel at interpolating observed perturbational data, they tend to overfit in the lack of enough data and may not generalize well to unseen perturbations. In contrast, mechanistic models, such as linear causal models based on gene regulatory networks, hold greater potential for extrapolation, as they encapsulate regulatory information that can predict responses to unseen perturbations. However, their application has been limited to small studies due to overly simplistic assumptions, making them less effective in handling noisy, large-scale single-cell data. We propose a hybrid approach that combines a mechanistic causal model with variational deep learning, termed Single Cell Causal Variational Autoencoder (SCCVAE). The mechanistic model employs a learned regulatory network to represent perturbational changes as shift interventions that propagate through the learned network. SCCVAE integrates this mechanistic causal model into a variational autoencoder, generating rich, comprehensive transcriptomic responses. Our results indicate that SCCVAE exhibits superior performance over current state-of-the-art baselines for extrapolating to predict unseen perturbational responses. Additionally, for the observed perturbations, the latent space learned by SCCVAE allows for the identification of functional perturbation modules and simulation of single-gene knockdown experiments of varying penetrance, presenting a robust tool for interpreting and interpolating perturbational responses at the single-cell level.

59 BASIC BIOLOGICAL SCIENCES↗

DOE OSTI2016

Schottky diodes from 2D germanane

We report on the fabrication and characterization of a Schottky diode made using 2D germanane (hydrogenated germanene). When compared to germanium, the 2D structure has higher electron mobility, an optimal band-gap, and exceptional stability making germanane an outstanding candidate for a variety of opto-electronic devices. One-atom-thick sheets of hydrogenated puckered germanium atoms have been synthesized from a CaGe{sub 2} framework via intercalation and characterized by XRD, Raman, and FTIR techniques. The material was then used to fabricate Schottky diodes by suspending the germanane in benzonitrile and drop-casting it onto interdigitated metal electrodes. The devices demonstrate significant rectifying behavior and the outstanding potential of this material.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

DOE OSTI2014

Electronic quantum effects mapped onto non-Born-Oppenheimer nuclear paths: Nonclassical surmounting over potential barriers and trapping above the transition states due to nonadiabatic path-branching

We develop the path-branching representation for nonadiabatic electron wavepacket dynamics [T. Yonehara and K. Takatsuka, J. Chem. Phys. 132, 244102 (2010)] so as to treat dynamics in an energy range comparable to the barrier height of adiabatic potential energy curves. With this representation two characteristic chemical reaction dynamics are studied, in which an incident nuclear wavepacket encounters a potential barrier, on top of which lies another nonadiabatically coupled adiabatic potential curve: (1) Dynamics of initial paths coming into the nonadiabatic interaction region with energy lower than the barrier height. They branch into two pieces (and repeat branching subsequently), the upper counterparts of which can penetrate into a classically inaccessible high energy region and eventually branch back to the product region on the ground state curve. This is so to say surmounting the potential barrier via nonadiabatically coupled excited state, and phenomenologically looks like the so-called deep tunneling. (2) Dynamics of classical paths whose initial energies are a little higher than the barrier but may be lower than the bottom of the excited state. They can undergo branching and some of those components are trapped on top of the potential barrier, being followed by the population decay down to the lower state flowing both to product and reactant sites. Such expectations arising from the path-branching representation are numerically confirmed with full quantum mechanical wavepacket dynamics. This phenomenon may be experimentally observed as time-delayed pulses of wavepacket trains.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

DOE OSTI2021

Identification and widespread environmental distribution of a gene cassette implicated in anaerobic dichloromethane degradation

Anthropogenic activities and natural processes release dichloromethane (DCM, methylene chloride), a toxic chemical with substantial ozone-depleting capacity. Specialized anaerobic bacteria metabolize DCM; however, the genetic basis for this process has remained elusive. Comparative genomics of the three known anaerobic DCM-degrading bacterial species revealed a homologous gene cluster, designated the methylene chloride catabolism (mec) gene cassette, comprising 8–10 genes encoding proteins with 79.6%–99.7% amino acid identities. Functional annotation identified genes encoding a corrinoid-dependent methyltransferase system, and shotgun proteomics applied to two DCM-catabolizing cultures revealed high expression of proteins encoded on the mec gene cluster during anaerobic growth with DCM. In a DCM-contaminated groundwater plume, the abundance of mec genes strongly correlated with DCM concentrations (R 2 = 0.71–0.85) indicating their potential value as process-specific bioremediation biomarkers. mec gene clusters were identified in metagenomes representing peat bogs, the deep subsurface, and marine ecosystems including oxygen minimum zones (OMZs), suggesting a capacity for DCM degradation in diverse habitats. Here, the broad distribution of anaerobic DCM catabolic potential infers a role for DCM as an energy source in various environmental systems, and implies that the global DCM flux (i.e., the rate of formation minus the rate of consumption) might be greater than emission measurements suggest.

59 BASIC BIOLOGICAL SCIENCES↗

NASA NTRS2024

Feasibility Assessment of Magnetohydrodynamic Control for Aerocapture at Neptune

The Planetary Science Decadal Survey released in 2022 posed a mission to one of the Ice Giants as the top priority for flagship missions for NASA. However, current technologies limit the amount of scientific payload available for future Uranian and Neptunian missions due to the need for fuel for orbit insertion maneuvers. Thus, to maximize the scientific potential of future missions, aerocapture has been heavily researched. While aerocapture simulations using only aerodynamic control have proven enabling for capturing around Ice Giants like Neptune, the deep atmospheric pass requires an aeroshell with robust thermal protection systems (TPS). Magnetohydrodynamically controlled (MHD) aerocapture serves as a potential improvement to the limitations of both fully propulsive orbit insertion and aerodynamically controlled aerocapture. Using NASA tools for modeling planetary exploration missions, both the aerodynamic-only and magnetohydrodynamic aerocapture methods were simulated and compared for identical missions to an Ice Giant, with Neptune chosen as the target planet. After applying a guidance algorithm for both methods, the results showed that magnetohydrodynamics has not only the control authority to successfully capture around Neptune, but also the unique advantage of a shallower atmospheric pass, decreasing the maximum heat load and the required TPS mass.

Aerocapture↗

DOE OSTI2023

Harness the power of atomistic modeling and deep learning in biofuel separation

Biofuels offer a remarkable, sustainable energy source for a future of clean energy. The development of efficient biofuel separation plays a crucial role in achieving cost-effective utilization of biofuel. In this chapter, we provide an overview of the recent advancements in atomistic-level modeling and deep learning in the rational design of novel, efficient biofuel separation. The fundamental principles of quantum and statistical mechanics are covered in appropriate detail to highlight their underlying differences in theory. The methodologies of several molecular representations and deep learning algorithms applicable to biofuel separation are briefly demonstrated as well. The applications, successes, and risks of employing density functional theory, ab initio molecular dynamics, classical molecular dynamics, and deep learning are provided to showcase their recent accomplishments in biofuel separation as well as potential improvements in both methodology and application. Lastly, a vision for the future growth of these methods is illustrated.

deep learning, artificial intelligence, biofuels, ↗

NASA NTRSDate not supplied

AI-Enhanced Computational Tools for Entry Systems Modeling

To advance the understanding of complex atmospheric entry phenomena, NASA’s Entry Systems Modeling (ESM) team [1] has developed high-fidelity computational tools addressing multiscale challenges, from material microstructures to full-scale heatshield response. This abstract highlights a subset of ESM tools, focusing on AI integration to enhance workflows and predictive modeling. - PuMA [2] computes effective material properties from high-resolution micro-CT scans, supporting TPS analysis for NASA missions. - TomoSAM [3] automates 3D tomography dataset segmentation for PuMA using the Segment Anything Model, reducing manual effort and improving accuracy. - PATO [4] models porous reactive materials under extreme conditions, with advancements such as unified solvers, mechanical erosion, and TPS coatings for NASA missions. - arcjetCV [5] employs deep learning to analyze arc jet test footage, measuring recession rates, shape changes, and shock standoff distances, bridging simulations, and experiments to reveal TPS ablation behavior. - ARCHeS [6] simulates arc heater plasma flows, modeling turbulence, radiation, and electromagnetic interactions to optimize arc heater performance, validate TPS under extreme conditions, and serve as a foundation for developing digital twins of arc heater facilities. - SPARTA [7] simulates rarefied hypersonic flows and gas-surface interactions for planetary entry missions, leveraging GPU architectures for scalable and efficient aerothermal and ablation analyses. AI-driven solutions, such as deep learning segmentation, have streamlined workflows in ESM tools and still hold significant potential to further accelerate processes and enhance automation in entry systems modeling. [1] Haskins, J.B. (2023), [2] Ferguson, J.C. (2018), [3] Meurisse, J.B.E. (2018), [4] Semeraro, F. (2023), [5] Quintart, A. (2024) [6] Meurisse, J.B.E. (2022), [7] Plimpton, S.J. (2019)

Predictive Modeling↗

DOE OSTI2020

Metagenome-assembled genome distribution and key functionality highlight importance of aerobic metabolism in Svalbard permafrost

Permafrost underlies a large portion of the land in the Northern Hemisphere. It is proposed to be an extreme habitat and home for cold-adaptive microbial communities. Upon thaw permafrost is predicted to exacerbate increasing global temperature trend, where awakening microbes decompose millennia old carbon stocks. Yet our knowledge on composition, functional potential and variance of permafrost microbiome remains limited. In this study, we conducted a deep comparative metagenomic analysis through a 2 m permafrost core from Svalbard, Norway to determine key permafrost microbiome in this climate sensitive island ecosystem. To do so, we developed comparative metagenomics methods on metagenomic-assembled genomes (MAG). We found that community composition in Svalbard soil horizons shifted markedly with depth: the dominant phylum switched from Acidobacteria and Proteobacteria in top soils (active layer) to Actinobacteria, Bacteroidetes, Chloroflexi and Proteobacteria in permafrost layers. Key metabolic potential propagated through permafrost depths revealed aerobic respiration and soil organic matter decomposition as key metabolic traits. We also found that Svalbard MAGs were enriched in genes involved in regulation of ammonium, sulfur and phosphate. Here, we provide a new perspective on how permafrost microbiome is shaped to acquire resources in competitive and limited resource conditions of deep Svalbard soils.

59 BASIC BIOLOGICAL SCIENCES↗

DOE OSTI2015

Understanding the contribution of non-carbon dioxide gases in deep mitigation scenarios

The combined 2010 emissions of methane (CH4), nitrous oxide (N2O) and the fluorinated gasses (F-gas) account for about 20-30% of total emissions and about 30% of radiative forcing. At the moment, most studies looking at reaching ambitious climate targets project the emission of carbon dioxide (CO2) to be reduced to zero (or less) by the end of the century. As for non-CO2 gases, the mitigation potential seem to be more constrained, we find that by the end of the century in the current deep mitigation scenarios non-CO2 emissions could form the lion’s share of remaining greenhouse gas emissions. In order to support effective climate policy strategies, in this paper we provide a more in-depth look at the role of non-CO2¬ emission sources (CH4, N2O and F-gases) in achieving deep mitigation targets (radiative forcing target of 2.8 W/m2 in 2100). Specifically, we look at the sectorial mitigation potential and the remaining non-CO2 emissions. By including a set of different models, we provide some insights into the associated uncertainty. Most of the remaining methane emissions in 2100 in the climate mitigation scenario come from the livestock sector. Strong reductions are seen in the energy supply sector across all models. For N2O, less reduction potential is seen compared to methane and the sectoral differences are larger between the models. The paper shows that the assumptions on remaining non-CO2 emissions are critical for the feasibility of reaching ambitious climate targets and the associated costs.

Gernaat, David↗

DOE OSTI2024

Characterization of the Triassic Newark Basin of New York and New Jersey for Geologic Storage of Carbon Dioxide

The project Characterization of the Triassic Newark Basin of New York and New Jersey for Geologic Storage of Carbon Dioxide is one of 9 site characterization projects that were implemented as part of ARRA (American Recovery and Reinvestment Act). Data from this project was used to improve resolution of data in NATCARB in the area of study. Data related to this study has already been incorporated in NATCARB Atlas. Sandia Technologies, LLC, and co-investigator Conrad Geoscience Corporation, examined the potential for large-scale, permanent CO2 storage in sedimentary strata within the Newark Rift Basin. The Newark Rift Basin underlies an industrialized, developed region comprising parts of New York, New Jersey, and Pennsylvania. The project characterized and investigated the suitability of Triassic age sedimentary formations for potential geologic CO2 storage. The project team drilled and cored two test wells to define the sedimentary geologic formations underlying the basin and to document or reach basement rock. With this geologic characterization phase, an integration of seismic, geologic, borehole, and formation core results provided a higher resolution assessment of CO2 storage potential. The Stockton Formation is known to be a potentially favorable geologic storage formation in the basin. In 2011, the 1-NYSTA Tandem Lot stratigraphic test well was drilled to a depth of 6,855 feet in the northern portion of the Newark Basin in southern New York State. Approximately 9 miles south-southeast on the Lamont Doherty Campus, TW-4 was drilled and cored in 2013 to a depth of 1,802 feet and contacted apparent igneous basement at a depth of 1,712 feet. Both wells penetrated the Palisades Sill ranging from 800 feet thick in the eastern well to approximately 1,800 feet in thickness at the 1-NYSTA Tandem Lot deep drill site. A diabase sill can provide an excellent seal and dense confining layer for potential CO2 storage reservoirs and flow layers that are situated beneath it within the Stockton Sandstone. The Stockton Sandstone was encountered beneath the sill in the TW-4 well on the Lamont campus, and data integration suggests that it was likely observed near total depth in the deep 1-NYSTA Tandem Lot well. The test wells confirm and define reservoirs are present beneath the sill and offer CO2 storage potential. The integration of geologic and reservoir characterization of well logs, formation cores, and formation fluids indicated Triassic age lacustrine playa lake and mudbank shales of the Upper Passaic Group can provide an effective seal for the porous and permeable underlying sandstone reservoir layers. This project acquired seismic data, drilled borehole well logs, acquired core samples, and integrated these findings to provide a better understanding of the subsurface geologic formations in the Newark Rift Basin. These findings have contributed to a higher degree of accuracy in predicting potential geologic storage opportunities, while refining geologic storage capacity estimates for the indicated reservoirs and flow units.

.las↗

DOE OSTI2018

Deep Learning for Unsupervised Insider Threat Detection in Structured Cyber Security Data Streams

Analysis of an organization's computer network activity is a key component of early detection and mitigation of insider threat, a growing concern for many organizations. Raw system logs are a prototypical example of streaming data that can quickly scale beyond the cognitive power of a human analyst. As a prospective filter for the human analyst, we present an online unsupervised deep learning approach to detect anomalous network activity from system logs in real time. Our models decompose anomaly scores into the contributions of individual user behavior features for increased interpretability to aid analysts reviewing potential cases of insider threat. Using the CERT Insider Threat Dataset v6.2 and threat detection recall as our performance metric, our novel deep and recurrent neural network models outperform Principal Component Analysis, Support Vector Machine and Isolation Forest based anomaly detection baselines. For our best model, the events labeled as insider threat activity in our dataset had an average anomaly score in the 95.53 percentile, demonstrating our approach's potential to greatly reduce analyst workloads.

Deep Learning, Insider Threat↗

NASA NTRS1987

Electron dynamics and potential jump across slow mode shocks

In the de Hoffmann-Teller reference frame, the cross-shock electric field is simply the thermoelectric field responsible for preserving charge neutrality. As such, it gives information regarding the heating and dissipation occurring within the shock. The total cross-shock potential can be determined by integrating a weighted electron pressure gradient through the shock, but this requires knowledge of the density and temperature profiles. Here, a recently proposed alternative approach relying on particle dynamics is exploited to provide an independent estimate of this potential. Both determinations are applied to slow mode shocks which form the plasma sheet boundary in the deep geomagnetic tail as observed by ISEE 3. The two methods correlate well. There is no indication of the expected transition from resistive to viscous shocks, although the highest Mach number shocks show the highest potentials. The implications of these results for the electron dissipation mechanisms and turbulence at the shock are discussed.

Schwartz, Steven J.↗

DOE OSTI2026

The effect of hydroxyl spacing in diols on the solvation structure, dynamics, and transport properties of choline chloride-based deep eutectic solvents

Deep eutectic solvents (DESs) are a class of liquids that offer great potential in alleviating some of the challenges present in today's long-term energy storage methods because they have physical properties that are favorable for storable electrolyte solutions. In this work, a series of glycols (ethylene glycol, 1,3-propanediol, 1,4-butanediol, and 1,5-pentanediol) were studied as potential hydrogen bond donors (HBD) with a common choline chloride (ChCl) as the hydrogen bond acceptor (HBA). The solvation dynamics of the prepared systems were studied by measuring the solvent reorganization response using femtosecond transient absorption spectroscopy (fs-TA). Conductivity, viscosity, density, ET(30) polarity, and dynamics of the prepared DESs were analyzed, with a particular interest in determining the effect of HBD chain length on these parameters. Here, classical molecular dynamics simulations were employed to investigate how the local liquid structure, solvent dynamics, and bulk solvent properties vary with changes in glycol chain length.

Conductivity↗

DOE OSTI2025

Incentivizing Cooperative Merging Control: Insights from Multi-Agent Deep Reinforcement Learning

Cooperative driving automation enables connected and automated vehicles (CAVs) to devise cooperative merging control, introducing great potentials to alleviate traffic congestion, reduce energy consumption, and enhance safety for highway on-ramp operations. Although numerous CAV cooperative merging algorithms have been developed to improve energy and traffic performance, the agreement-seeking among CAV users and their local benefits have been understudied. This can lead to rejections of cooperative merging plans and jeopardizing CAV performance, as a cooperation may entail certain CAVs to sacrifice their local benefits to achieve a system optimum. To address this issue, the study first leverages multi-agent deep reinforcement learning (MADRL) factoring both local reward and regional reward to demonstrate the discrepancies between CAV users’ local benefits and system optimum. Next, the existence of a correlated equilibrium is proved to characterize the convergence of MADRL training. This further facilitates the incorporation of incentives (computed based on reward discrepancies) to compensate for CAV users’ local benefits and facilitate system-optimal agreements in cooperative merging operations.

Zhou, Anye [ORNL] (ORCID:0000000301455579)↗

NASA NTRS2016

Proving Ground Potential Mission and Flight Test Objectives and Near Term Architectures

NASA is developing a Pioneering Space Strategy to expand human and robotic presence further into the solar system, not just to explore and visit, but to stay. NASA's strategy is designed to meet technical and non-technical challenges, leverage current and near-term activities, and lead to a future where humans can work, learn, operate, and thrive safely in space for an extended, and eventually indefinite, period of time. An important aspect of this strategy is the implementation of proving ground activities needed to ensure confidence in both Mars systems and deep space operations prior to embarking on the journey to the Mars. As part of the proving ground development, NASA is assessing potential mission concepts that could validate the required capabilities needed to expand human presence into the solar system. The first step identified in the proving ground is to establish human presence in the cis-lunar vicinity to enable development and testing of systems and operations required to land humans on Mars and to reach other deep space destinations. These capabilities may also be leveraged to support potential commercial and international objectives for Lunar Surface missions. This paper will discuss a series of potential proving ground mission and flight test objectives that support NASA's journey to Mars and can be leveraged for commercial and international goals. The paper will discuss how early missions will begin to satisfy these objectives, including extensibility and applicability to Mars. The initial capability provided by the launch vehicle will be described as well as planned upgrades required to support longer and more complex missions. Potential architectures and mission concepts will be examined as options to satisfy proving ground objectives. In addition, these architectures will be assessed on commercial and international participation opportunities and on how well they develop capabilities and operations applicable to Mars vicinity missions.

Smith, R. Marshall↗

DOE OSTI2025

A generative artificial intelligence framework for long-time plasma turbulence simulations

Generative deep learning techniques are employed in a novel framework for the construction of surrogate models capturing the spatiotemporal dynamics of 2D plasma turbulence. The proposed Generative Artificial Intelligence Turbulence (GAIT) framework enables the acceleration of turbulence simulations for long-time transport studies. GAIT leverages a convolutional variational auto-encoder and a recurrent neural network to generate new turbulence data from existing simulations, extending the time horizon of transport studies with minimal computational cost. The application of the GAIT framework to plasma turbulence using the Hasegawa–Wakatani (HW) model is presented, evaluating its performance via various analyses. Very good agreement is found between the GAIT and the HW models in the spatiotemporal Fourier and Proper Orthogonal Decomposition spectra, the flow topology characterized by the Okubo–Weiss parameter, and the time autocorrelation function of turbulent fluctuations. Excellent agreement has also been obtained in the probability distribution function of particle displacements and the effective turbulent diffusivity. In-depth analyses of the latent space of turbulent states, choice of hyperparameters and alternative deep learning models for the time prediction are presented. Our results highlight the potential of Artificial Intelligence-based surrogate models to overcome the computational challenges in turbulence simulation, which can be extended to other situations such as geophysical fluid dynamics.

Artificial intelligence↗

NASA NTRS2008

Extreme Helicity and Intense Convective Towers in Hurricane Bonnie

Helicity was calculated in Hurricane Bonnie (1998) using tropospheric-deep dropsonde soundings from the NASA Convection and Moisture Experiment. Large helicity existed downshear of the storm center with respect to the ambient vertical wind shear. It was associated with veering, semicircular hodographs created by strong, vortex-scale, radial-vertical flow induced by the shear. The most extreme values of helicity, among the largest ever reported in the literature, occurred in the vicinity of deep convective cells in the downshear-left quadrant. These cells reached as high as 17.5 km and displayed the temporal and spatial scales of supercells. Convective available potential energy (CAPE) averaged 861 J/kg downshear, but only about one-third as large upshear. The soundings nearest the deep cells were evaluated using two empirical supercell parameters that make use of CAPE, helicity, and/or shear. These parameters supported the possible existence of supercells as a consequence of the exceptional helicity combined with moderate but sufficient CAPE. Ambient vertical wind shear exceeded 12 m/s for 30 h, yet the hurricane maintained 50 m/s maximum winds. It is hypothesized that the long-lived convective cells enabled the storm to resist the negative impact of the shear. Supercells in large-helicity, curved-hodograph environments appear to provide a useful conceptual model for intense convection in the hurricane core. Helicity calculations might also give some insight into the behavior of vortical hot towers, which share some characteristics with supercells.

Molinari, John↗

DOE OSTI2022

A Combined Computer Vision and Deep Learning Approach for Rapid Drone-Based Optical Characterization of Parabolic Troughs

Optical accuracy is a primary driver of parabolic trough concentrating solar power (CSP) plant performance, but can be damaged by wind loads, gravity, error during installation, and regular plant operation. Collecting and analyzing optical measurements over an entire operating parabolic trough plant is difficult, given the large scale of typical installations. Distant Observer, a software tool developed at the National Renewable Energy Laboratory, uses images of the absorber tube reflected in the collector mirror to measure both surface slope in the parabolic mirror and offset of the absorber tube from the ideal focal point. This technology has been adapted for fast data collection using low-cost commercial drones, but until recently still required substantial human labor to process large amounts of data. A new method leveraging advanced deep learning and computer vision tools can drastically reduce the time required to process images. This new method addresses the primary analysis bottleneck, identifying featureless, reflective mirror corner points to a high degree of accuracy. Recent work has shown promising results using computer vision methods. The combined deep learning and computer vision approach presented here proved highly effective and has the potential to further automate data collection and analysis, making the tool more robust. The method presented in this paper automatically identified 74.3% of mirror corners within 2 pixels of their manually marked counterparts and 91.9% within 3 pixels. This level of accuracy is sufficient for practical Distant Observer analysis within a target uncertainty. A commercial drone collected video of over 100 parabolic trough modules at an operating CSP plant to demonstrate the deep learning and computer vision method's usefulness in processing large amounts of data. These troughs were successfully analyzed using Distant Observer, paired with the new deep learning and computer vision algorithm, and can provide plant operators and trough designers with valuable insight about plant performance, operating strategies, and plant-wide optical error trends.

computer vision↗