Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “model types”

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.

At least 739 records · Page 41
All sourcesNASA NTRSDOE OSTI
DOE OSTI2021

Parameter Reduction of Composite Load Model Using Active Subspace Method

Over the past decades, the increasing penetration of distributed energy resources (DERs) has dramatically changed the power load composition in the distribution networks. The traditional static and dynamic load models can hardly capture the dynamic behavior of modern loads especially for fault-induced delayed voltage recovery (FIDVR) events. Thus, a more comprehensive composite load model with combination of static load, different types of induction motors, single-phase A/C motor, electronic load and DERs has been proposed by Western Electricity Coordinating Council (WECC). However, due to the large number of parameters and model complexity, the WECC composite load model (WECC CMLD) raises new challenges to power system studies. To overcome these challenges, in this paper, a cutting-edge parameter reduction (PR) approach for WECC CMLD based on active subspace method (ASM) is proposed. Firstly, the WECC CMLD is parameterized in a discrete-time manner for the application of the proposed method. Then, parameter sensitivities are calculated by discovering the active subspace, which is a lower-dimensional linear subspace of the parameter space of WECC CMLD in which the dynamic response is most sensitive. The interdependency among parameters can be taken into consideration by our approach. Finally, the numerical experiments validate the effectiveness and advantages of the proposed approach for WECC CMLD model.

active subspace↗
DOE OSTI2026

New physics in multi-lepton tau decays

Dark particles with lepton-flavor-violating couplings to the tau lepton can induce rare neutrinoless $τ$ decays with large final state multiplicities. We study models where transitions of the type $τ^\pm\to \ell^\pm\,ϕ$, with $ϕ$ a light new particle, initiate a chain of decays in the dark sector that terminate with decays into electrons, muons, or pions. These decay cascades appear as rare five or even seven-body $τ$ decays with multiple reconstructable resonances. We survey several representative models: kinetically mixed dark photon, gauged $L_i-L_j$ models, and other more exotic charge assignments such as chiral $U(1)'$ extensions of the Standard Model. The main new ingredient is the possibility of flavor violation at very high scales. In these models, a number of channels that have not yet been searched for experimentally, such as $τ\to 5μ$, $τ\to 3μ\,2e$, $τ\to μ\,4e$, and hadronic channels like $τ\to μ\,4π$, typically dominate over the previously-considered signatures such as $τ\to 3μ$. While some of the models, such as the gauged $L_i-L_j$ ones, also contain more challenging channels with missing energy due to decays to neutrinos, they can still be searched for via fully visible channels.

Ema, Yohei [Florida U.]↗
DOE OSTI2022

Molecular structure models of amorphous bismuth and cerium carboxylate catalyst precursors

As our societal need for materials and energy has grown, so has our need for catalyst processes in hydrogen production. A major function in these applications, for both homogenous and heterogeneous catalysis processes, is the synthesis of an active metal catalyst. It must first be soluble to control the physical properties of the metal being used. Recent work in metal precursors has begun to turn toward these metal carboxylate types of material. Here, structural models are proposed for bismuth 2-ethylhexanoate and 2,2-dimethyloctanoate and cerium 2-ethylhexanoate. The bismuth compounds have been characterized at different ratios of bismuth to carboxylate as solutions of the free acids. Their structures are most consistent with a Bi 4 (RCO 2 ) 12 motif where the Bi ions are arranged in a flattened tetrahedron with Bi – Bi distances of about 4.3 Å. There is evidence for Bi – O – Bi linkages at low free acid concentrations. The cerium compound is most consistent with a linear tetracerium molecule where the Ce – Ce distances repeat at about 4.3 Å out to 16.4 Å. The models were generated by analogy with known crystal structures and compared to high-energy x-ray scattering data. To further evaluate the models, DFT calculations were made, and the equilibrium geometries were compared. The vibrational spectra calculated from those geometries are presented and compared to the experimental results. Magnetization vs. temperature data was collected on the cerium compound, and its behavior was consistent with the proposed model. A geometrical approach to determining the dimensionality and relative positions of the metal ions in these structures is presented.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2020

Predicting the proximity to macroscopic failure using local strain populations from dynamic in situ X-ray tomography triaxial compression experiments on rocks

Predicting the proximity of large-scale dynamic failure is a critical concern in the engineering and geophysical sciences. Here we use evolving contractive, dilatational, and shear strain deformation preceding failure in dynamic X-ray tomography experiments to examine which strain components best predict the proximity to failure. We develop machine learning models to predict the proximity to failure using time series of three-dimensional local incremental strain tensor fields acquired in rock deformation experiments under stress conditions of the upper crust. Three-dimensional scans acquired in situ throughout triaxial compression experiments provide a distribution of density contrasts from which we estimate the three-dimensional incremental strain that accumulates between each scan acquisition. Training machine learning models on multiple experiments of six rock types provides suites of feature importance that indicate the predictive power of each feature. Comparing the average importance of groups of features that include information about each strain component quantifies the ability of the contractive, dilatational and shear strain to predict the proximity of macroscopic failure. A total of 24 models of four machine learning algorithms with six rock types indicate that 1) the dilatational strain provides the best predictive power of the strain components, and 2) the intermediate values (25th-75th percentile) of the strain population provide the best predictive power of the statistics of the strain populations. In addition, the success of the predictions of models trained on one rock type and tested on other rock types quantifies the similarities and differences of the precursory strain accumulation process in the six rock types. These similarities suggest the potential existence of a unified theory of brittle rock deformation for a range of rock types.

58 GEOSCIENCES↗
DOE OSTI2023

MODELS FOR ESTIMATING THE AUTOFRETTAGE PRESSURE AND RESIDUAL STRESSES IN WALLS OF TYPE 2 PRESSURE VESSELS

Autofrettage is a manufacturing process used during fabrication of Type 2 pressure vessels designed for usage at high pressures to enhance the fatigue life. The process locks high compressive residual stresses in the vessel’s liner wall that reduce the maximum and the mean stress during service loading. To achieve a consistent residual stress profile across the wall of the vessel, the choice of autofrettage pressure is critical. Several finite element analyses runs were conducted to estimate the correct autofrettage pressure that is a function of the yield strength of the liner material, the wall thickness, and the outside diameter of the liner for a wrap thickness of 17.06 mm (48 wire layers). From the finite element analyses results, models were developed to estimate the correct autofrettage pressure and the residual stress distribution across the liner wall as a function of the yield strength of the liner material, the wall thickness, and the outside diameter of the liner.

08 HYDROGEN↗
DOE OSTI2020

The potential role of organics in new particle formation and initial growth in the remote tropical upper troposphere

Abstract. Global observations and model studies indicate that new particle formation (NPF) in the upper troposphere (UT) and subsequent particles supply 40 %–60 % of cloud condensation nuclei (CCN) in the lower troposphere, thus affecting the Earth's radiative budget. There are several plausible nucleation mechanisms and precursor species in this atmospheric region, which, in the absence of observational constraints, lead to uncertainties in modeled aerosols. In particular, the type of nucleation mechanism and concentrations of nucleation precursors, in part, determine the spatial distribution of new particles and resulting spatial distribution of CCN from this source. Although substantial advances in understanding NPF have been made in recent years, NPF processes in the UT in pristine marine regions are still poorly understood and are inadequately represented in global models. Here, we evaluate commonly used and state-of-the-art NPF schemes in a Lagrangian box model to assess which schemes and precursor concentrations best reproduce detailed in situ observations. Using measurements of aerosol size distributions (0.003 < Dp < 4.8 µm) in the remote marine troposphere between ∼0.18 and 13 km altitude obtained during the NASA Atmospheric Tomography (ATom) mission, we show that high concentrations of newly formed particles in the tropical UT over both the Atlantic and Pacific oceans are associated with outflow regions of deep convective clouds. We focus analysis on observations over the remote Pacific Ocean, which is a region less perturbed by continental emissions than the Atlantic. Comparing aerosol size distribution measurements over the remote Pacific with box model simulations for 32 cases shows that none of the NPF schemes most commonly used in global models, including binary nucleation of sulfuric acid and water (neutral and ion-assisted) and ternary involving sulfuric acid, water, and ammonia, are consistent with observations, regardless of precursor concentrations. Through sensitivity studies, we find that the nucleation scheme among those tested that is able to explain most consistently (21 of 32 cases) the observed size distributions is that of Riccobono et al. (2014), which involves both organic species and sulfuric acid. The method of Dunne et al. (2016), involving charged sulfuric acid–water–ammonia nucleation, when coupled with organic growth of the nucleated particles, was most consistent with the observations for 5 of 32 cases. Similarly, the neutral sulfuric acid–water–ammonia method of Napari (2002), when scaled with a tuning factor and with organic growth added, was most consistent for 6 of 32 cases. We find that to best reproduce both nucleation and growth rates, the mixing ratios of gas-phase organic precursors generally need to be at least twice that of SO2, a proxy for dimethyl sulfide (DMS). Unfortunately, we have no information on the nature of oxidized organic species that participated in NPF in this region. Global models rarely include organic-driven nucleation and growth pathways in UT conditions where globally significant NPF takes place, which may result in poor estimates of NPF and CCN abundance and contribute to uncertainties in aerosol–cloud–radiation effects. Furthermore, our results indicate that the organic aerosol precursor vapors may be important in the tropical UT above marine regions, a finding that should guide future observational efforts.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2022

Uncertainties in estimating global potential yields and their impacts for long-term modeling

Estimating realistic potential yields by crop type and region is challenging; such yields depend on both biophysical characteristics (e.g., soil characteristics, climate, etc.), and the crop management practices available in any site or region (e.g., mechanization, irrigation, crop cultivars). A broad body of literature has assessed potential yields for selected crops and regions, using several strategies. In this study we first analyze future potential yields of major crop types globally by two different estimation methods, one of which is based on historical observed yields (“Empirical”), while the other is based on biophysical conditions (“Simulated”). Potential yields by major crop and region are quite different between the two methods; in particular, Simulated potential yields are typically 200% higher than Empirical potential yields in tropical regions for major crops. Applying both of these potential yields in yield gap closure scenarios in a global agro-economic model, GCAM, the two estimates of future potential yields lead to very different outcomes for the agricultural sector globally. In the Simulated potential yield closure scenario, Africa, Asia, and South America see comparatively favorable outcomes for agricultural sustainability over time: low land use change emissions, low crop prices, and high levels of self-sufficiency. In contrast, the Empirical potential yield scenario is characterized by a heavy reliance on production and exports in temperate regions that currently practice industrial agriculture. At the global level, this scenario has comparatively high crop commodity prices, and more land allocated to crop production (and associated land use change emissions) than either the baseline or Simulated potential yield scenarios. This study highlights the importance of the choice of methods of estimating potential yields for agro-economic modeling.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2022

Predicting spring green-up across diverse North American grasslands

Vegetation phenology influences many ecosystem and climate processes, such as carbon uptake and energy and water cycles. Thus, understanding drivers of vegetation phenology is crucial for predicting current and future impacts of climate change on ecological systems. Existing models can accurately predict the date of spring green-up in temperate forests but tend to perform poorly in grassland systems. We hypothesize this is because most do not incorporate water availability, a primary limiting factor for grassland plants. In this study, we used long-term datasets of digital imagery from the PhenoCam Network of 43 diverse North American grassland sites (195 site-years) to test existing spring phenology models, as well as develop several new models that incorporate precipitation or soil moisture (53 models). As a result, most of the new models performed substantially better, with the best model requiring sufficient accumulated precipitation followed by warm temperatures to trigger spring onset (root mean square error, RMSE, between predicted and observed dates = 16.0 days). Importantly, the best model performed well across all grassland types using a single set of parameters, from temperate to arid grasslands. Since plants are adapted to their local climates, model performance was further improved when parameters were independently optimized for four separate climate regions (RMSE = 10.4 days). Therefore, both sufficient precipitation and temperature are required for grassland green-up, but optimal thresholds vary by region. Running the top model with projected climate data (representative concentration pathway 8.5) suggests that, depending on the climate region, spring onset will occur up to 12 days earlier within 100 years in temperature-limited sites, but the trend is unclear for precipitation-limited sites (3.5 ± 8.0 days later). This new phenology model improves our ability to understand and predict grassland dynamics, with implications for both current and future ecosystem processes related to carbon and water cycling.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2021

Estimation of constituent properties of concrete materials with an artificial neural network based method

Multi-scale models are developed for heterogeneous concrete materials to estimate their macroscopic mechanical properties in terms of micro-structural data. One crucial challenge of those models is the identification of local properties of constituent phases. In this paper, we present an efficient method based on Artificial Neural Networks (ANN). Typical concrete materials are taken as example. A macroscopic analytical strength criterion is established from three steps of nonlinear homogenization procedure. The macroscopic strength of materials is determined as a function of the frictional coefficient and cohesion of solid cement particles at nanometer scale, intra-particle pores, inter-particle pores and aggregates (inclusions). The objective is to identify the nanoscopic frictional coefficient and cohesion of cement particle from measured macroscopic values of uniaxial compression and tensile strengths. For this purpose, a numerical method based on the ANN is developed. With the analytical macroscopic strength criterion, sensitivity studies are first realized to identify the most important micro-structural parameters influencing the macroscopic strength of concrete. A simplified analytical macroscopic strength criterion is then proposed. A large dataset is further constructed through the inversion of the analytical strength criterion by using the aggregates volume fraction, porosity, macroscopic uniaxial tensile and compressive strengths as input variables and the frictional coefficient and cohesion of cement particles as output unknowns. An ANN model containing four hidden layers and 100 neurons in each layer is constructed and trained by using this dataset. Various types of validation of the ANN model are performed. It is found that the proposed ANN based model can effectively predict the frictional coefficient and cohesion of porous cement paste at the microscopic scale with a very good accuracy.

36 MATERIALS SCIENCE↗
DOE OSTI2023

Constraining High-energy Neutrino Emission from Supernovae with IceCube

Core-collapse supernovae are a promising potential high-energy neutrino source class. We test for correlation between seven years of IceCube neutrino data and a catalog containing more than 1000 core-collapse supernovae of types IIn and IIP and a sample of stripped-envelope supernovae. We search both for neutrino emission from individual supernovae as well as for combined emission from the whole supernova sample, through a stacking analysis. No significant spatial or temporal correlation of neutrinos with the cataloged supernovae was found. All scenarios were tested against the background expectation and together yield an overall p-value of 93%; therefore, they show consistency with the background only. The derived upper limits on the total energy emitted in neutrinos are 1.7 × 10 48 erg for stripped-envelope supernovae, 2.8 × 10 48 erg for type IIP, and 1.3 × 10 49 erg for type IIn SNe, the latter disfavoring models with optimistic assumptions for neutrino production in interacting supernovae. We conclude that stripped-envelope supernovae and supernovae of type IIn do not contribute more than 14.6% and 33.9%, respectively, to the diffuse neutrino flux in the energy range of about [ 10 3 –10 5 ] GeV, assuming that the neutrino energy spectrum follows a power-law with an index of –2.5. Under the same assumption, we can only constrain the contribution of type IIP SNe to no more than 59.9%. Thus, core-collapse supernovae of types IIn and stripped-envelope supernovae can both be ruled out as the dominant source of the diffuse neutrino flux under the given assumptions.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2025

Marine Hydrogen Demonstration

This report summarizes Phase 1 of a project involving the design of a Floating Hydrogen Production and Dispensing Barge destined for the Port of San Francisco (SF). The H 2 Barge is designed to produce renewable H 2 at the rate of ~ 530 kg/day, storing 512 kg of hydrogen at 517-bar, allowing fast refueling of hydrogen fuel cell vessels and land-side hydrogen delivery trailers for distribution into the nascent SF hydrogen ecosystem. The broader considerations that impacted the H2 Barge design are also described. An account is given of a new review process formulated by the United States Coast Guard (USCG) to review this first-of-its-kind maritime implementation of hydrogen technology. The immediate goals of the H 2 Barge Project are to 1) demonstrate the feasibility, viability and methods of hydrogen production, storage and fueling in a maritime context, 2) help shape (where needed) and navigate the required local, state and federal regulatory gauntlet and 3) catalyze a “green hydrogen ecosystem” (both marine and landside) with locally produced renewable hydrogen at the San Francisco waterfront. A summary is also given of the modeling and experimental activity of Phase 1 directed to the development of science-based refueling protocols for large marine Type IV 250-bar hydrogen tanks. Combined modeling and experimental studies are reported of the filling of large (28 kg) 250-bar Type IV hydrogen tanks of the type being deployed on early hydrogen ferries, such as the MV Sea Change. The primary question was to determine how such tanks can be successfully filled (state of charge greater than 97%) within 45 minutes without exceeding the 82 °C temperature limit historically set for such tanks. The studies show that a gas injector is needed avoid thermal stratification during filling which can result in potential hot spots. Pre-cooling of the hydrogen was found to be essential in most cases, as ambient conditions greatly affect the need for a pre-cooling to achieve the 45-minute fill time. Pre-cooling cannot be supplied by nearby water, such as that found in nature (bays, lakes, rivers, etc.) because pre-cooling cooling below 0 °C was found to be necessary to avoid excessive compression heating. The experimental results afforded a calibration of the engineering model (SOFIL) for these large 250-bar tanks, which now enables using SOFIL to predict volume-averaged hydrogen filling temperatures to an accuracy of +/- 2.7°C for these tanks. The model can therefore be used to evaluate potential scenarios for development of a standardized fueling methodology for ferries utilizing large Type-IV tanks of the type examined here.

08 HYDROGEN↗
DOE OSTI2023

On the Low Risk of SSR in Type III Wind Turbines Operating in Grid-Forming Control: Preprint

We have shown in a previous work that the risk of sub-synchronous resonance (SSR) between a wind power plant with Type III wind turbines and series-compensated transmission lines is low when the wind turbines in the plant are operated in grid-forming mode, instead of the standard grid-following mode. The fundamental mechanism behind the improved damping characteristics is explained in this paper by modeling the positive and negative sequence impedances of Type III wind turbines for GFM operation mode. It is discovered that the GFM control naturally acts against the negative resistance of Type III wind turbines that results from an interaction between the proportional gain of the rotor-side converter current controller and negative slip. The developed sequence impedance models and improved damping behavior are verified using PSCAD simulations of a 2.5-MW Type III GFM wind turbine. The modeling predictions are also supported by experimentally measuring the sequence impedance response of a 2.5-MW Type III wind turbine during operation in GFL and GFM modes.

grid-following turbine↗
DOE OSTI2022

Optimization of the deep neural network parameters for generating homogenized fuel assembly data for nodal codes

Homogenized fuel assembly (FA) data is a typical input data for nodal codes. Generating that data, however, could be time-consuming. One of promising ways to mitigate the computational burden of generating macroscopic cross-sections is to use trained artificial neural network (ANN) models for predicting nuclear data. However, there is a challenge to make the model support variable FA geometry. In this work, two most common types of FA were combined in one ANN model. Since there could be multiple ways of converting 2-dimensional FA data into 1-dimensional input vector for ANN, three different approaches of data flattening were evaluated. The input parameters included each fuel pin enrichment, fuel temperature, moderator temperature and boron concentration. The output parameters were 2-group macroscopic cross-sections (XS) and pin power distribution (HFF). A fully connected deep neural network (DNN) model was trained and tested using pre-generated data obtained with lattice physics code STREAM. The results of this study showed no statistically significant difference in the accuracy of XS and HFF generation for all 3 tested input vector orders. This means that fully connected DNN for XS generation demonstrated input sequence invariance. Results of comparing predicted XS data with reference solutions were found sufficiently close considering the reduction of computation time offered by ANN. Mean relative difference (MRD) for all output XS parameters was found below 0.7%, while HFF MRD was found higher compared to XS values, in some cases slightly exceeding 1%, mostly near guide tube locations. (authors)

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2023

Light Scalars at FASER

FASER, the ForwArd Search ExpeRiment, is a currently operating experiment at the Large Hadron Collider (LHC) that can detect light long-lived particles produced in the forward region of the LHC interacting point. In this paper, we study the prospect of detecting light CP-even and CP-odd scalars at FASER and FASER 2. Considering a model-independent framework describing the most general interactions between a CP-even or CP-odd scalar and SM particles using the notation of coupling modifiers in the effective Lagrangian, we develop the general formalism for the scalar production and decay. We then analyze the FASER and FASER 2 reaches of light scalars in the large tan β region of the Type-I two Higgs double model as a case study, in which light scalars with relatively long lifetime could be accommodated. In the two benchmark scenarios we considered, the light (pseudo)scalar decay length varies in (10 –8 , 10 5 ) meters. Both FASER and FASER 2 can probe a large part of the parameter space in the large tan β region up to 10 7 , extending beyond the constraints of the other existing experiments.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2025

Selection of Sampling and Surrogate Modeling Methods for State-Point Evaluations of an AGN-201M Reactor

Nuclear reactor digital twins (DTs) have been proposed for use as a safeguards technology to efficiently monitor new and novel reactors as they come online. A safeguards DT needs to be capable of detecting misuse and diversion as they occur, requiring physics models to be accurate and efficient. Mathematical surrogate models are capable of achieving the necessary efficiency and can largely maintain the accuracy of higher-order models given a quality training sample. The Multiphysics Object-Oriented Simulation Environment (MOOSE) code framework is specifically equipped to generate training samples and create surrogate models using full-order reactor physics models. Utilizing an operational AGN-201M reactor’s specifications, two surrogate types were trained on samples of variable size, and using Cartesian products, Latin hypercube sampling, and quadrature sampling, each was compared and evaluated on accuracy when compared to a full-order Monte Carlo model. Both surrogate types were able to capture reactivity changes within 0.05 $ of the Monte Carlo model while reducing the computation costs by eight orders of magnitude.

MOOSE↗
DOE OSTI2022

Probabilistic Cloud Optimized Day-Ahead Forecasting System Based on WRF-Solar (Final Report)

The most persistent challenge in both intraday and day-ahead solar forecasting is to get numerical weather prediction models to produce the right type of clouds with the right frequency at the right time and place. Another challenge is to understand and communicate the forecast uncertainty. The objective of this project was to develop an optimized ensemble-based solar irradiance forecasting system that will (1) demonstrably improve the current state-of-the-art solar forecasts from the deterministic Weather Research and Forecasting-Solar (WRF-Solar) model and (2) provide probabilistic forecasts for grid operations. This probabilistic solar forecasting system, referred to as the WRF-Solar Ensemble Prediction System (WRF-Solar EPS), aims to significantly enhance both the intraday and the day-ahead solar forecasting capability for grid operations. This technical report summarizes the work performed in the past 3 years through a collaboration between the National Renewable Energy Laboratory and the National Center for Atmospheric Research as part of the U.S. Department of Energy's Solar Forecasting 2 program that aims to improve the accuracy of solar energy forecasts and enable increased deployment of solar energy on the electric grid.

14 SOLAR ENERGY↗
DOE OSTI2023

Understanding the Computing and Analysis Needs for Resiliency of Power Systems from Severe Weather Impacts

As the frequency and intensity of severe weather has increased, its effect on the electric grid has manifested in the form of significantly more and larger outages in the United States. This has become especially true for regions that were previously isolated from weather extremes. In this paper, we analyze the weather impacts on the electric power grid across a variety of weather conditions, draw correlations, and provide practical insights into the operational state of these systems. High resolution computational modeling of specific meteorological variables, computational approaches to solving power system models under these conditions, and the types of resiliency needs are highlighted as goal-oriented computing approaches are being built to address grid resiliency needs. An example analysis correlating outages to 1km day-ahead weather from two historical winter storms, calculated on a large cluster using a combination of interpolated and extrapolated inputs from multiple instrumented sites to workflows that produce primary meteorological outputs, is shown as initial proof of concept.

analysis↗
DOE OSTI2024

Live cell imaging of cellular dynamics in poplar wood using computational cannula microscopy

This study presents significant advancements in computational cannula microscopy for live imaging of cellular dynamics in poplar wood tissues. Leveraging machine-learning models such as pix2pix for image reconstruction, we achieved high-resolution imaging with a field of view of 55µm using a 50µm-core diameter probe. Our method allows for real-time image reconstruction at 0.29 s per frame with a mean absolute error of 0.07. We successfully captured cellular-level dynamics in vivo , demonstrating morphological changes at resolutions as small as 3µm. We implemented two types of probabilistic neural network models to quantify confidence levels in the reconstructed images. This approach facilitates context-aware, human-in-the-loop analysis, which is crucial for in vivo imaging where ground-truth data is unavailable. Using this approach we demonstrated deep in vivo computational imaging of living plant tissue with high confidence (disagreement score ⪅0.2). This work addresses the challenges of imaging live plant tissues, offering a practical and minimally invasive tool for plant biologists.

Ingold, Alexander (ORCID:0009000752380016)↗