SEARCH · Search NASA

Results for “Network performance forecasting”

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 253 records · Page 14

All sources NASA NTRS DOE OSTI

DOE OSTI2024

Solving the Orszag–Tang vortex magnetohydrodynamics problem with physics-constrained convolutional neural networks

We study the 2D Orszag–Tang vortex magnetohydrodynamics (MHD) problem through the use of physics-constrained convolutional neural networks (PCNNs) for forecasting the density, ρ, and the magnetic field, B, as well as the prediction of B given the velocity field v of the fluid. In addition to translation equivariance from the convolutional architecture, other physics constraints were embedded: absence of magnetic monopoles, non-negativity of ρ, use of only relevant variables, and the periodic boundary conditions of the problem. The use of only relevant variables and the hard constraint of non-negative ρ were found to facilitate learning greatly. The divergenceless condition ∇·B=0 was implemented as a hard constraint up to machine precision through the use of a magnetic potential to define B=∇×A. Residual networks and data augmentation were also used to improve performance. This allowed for some of the residual models to function as surrogate models and provide reasonably accurate simulations. For the prediction task, the PCNNs were evaluated against a physics-informed neural network, which had the ideal MHD induction equation as a soft constraint. Several models were able to generate highly accurate fields, which are visually almost indistinguishable and have low mean squared error. Only methods with built-in hard constraints produced physical fields with ∇·B=0. The use of PCNNs for MHD has the potential to produce physically consistent real-time simulations to serve as virtual diagnostics in cases where inferences must be made with limited observables.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

DOE OSTI2026

Comparative Analysis of Model Predictive Control and MPC-Informed Rule-Based Control for Thermal Storage Operation in Ultra-Low Temperature 4th Generation District Heating Networks

The integration of thermal storage and heat pumps in district heating networks (DHNs) can significantly enhance operational flexibility and energy efficiency; however, the practical deployment of advanced control strategies is often hindered by forecasting requirements and computational complexity. This study presents a comparative analysis of thermal storage control strategies in an ultra-low-temperature fourth-generation DHN, focusing on the development of a simplified rule-based control (RBC) explicitly informed by Model Predictive Control (MPC) behavior. The proposed methodology systematically analyzes the charging and discharging decisions of an MPC-controlled system under ideal forecasting conditions and extracts recurrent control patterns as a function of key system variables, including outdoor temperature, thermal demand, and electricity price. These patterns are translated into a set of structured time- and condition-based rules, resulting in an MPC-informed RBC that embeds predictive insights while preserving implementation simplicity and operational transparency. The approach is validated on a realistic mixed-use urban district in Denver, Colorado, USA, equipped with a centralized air-source heat pump, distributed water-to-water heat pumps, and a central thermal storage unit. Results show that the tuned RBC attains approximately 96% of ideal MPC economic performance (-27% of costs), preserves values of technical and environmental indicators (reduction only of 2-3%), and substantially reduces complexity. Sensitivity analyses further demonstrate the robustness of the RBC under varying operational conditions (i.e., ambient temperature, electricity price). Overall, the study demonstrates that MPC-informed rule-based control represents an effective trade-off between control performance and real-world applicability, enabling the integration of additional system components while maintaining simplicity, robustness, and ease of implementation.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

NASA NTRSDate not supplied

Applications and Performance of a Lightning Risk Assessment using Geostationary Lightning Mapper (GLM) Data

Lightning is a hazard globally, particularly in lesser-developed countries. Cloud-to-ground lightning strikes are a threat to human safety, motivating a desire to monitor location-based lightning risk to mitigate harm. A lightning risk assessment for human safety was created that uses a combination of probabilistic risk calculation and spatial lightning mapping data to produce a risk magnitude. This risk magnitude evolves with time and changing conditions and is compared to tolerability thresholds in order to evaluate safety. The risk assessment using lightning mapping array (LMA) flash extent density (FED) data was found to perform comparatively (with respect to issuing lightning warnings) to a more standard method of monitoring lightning safety where National Lightning Detection Network (NLDN) flashes were monitored within a 5 nautical mile radius of a location of interest. This research investigates the replacement of LMA FED with FED from the Geostationary Lightning Mapper (GLM) within the risk assessment framework. Using GLM FED would allow for risk to be calculated outside of LMA domains and anywhere within the GLM field of view, including areas outside of the United States (US). A few applications of the risk method with GLM FED are shown and discussed for locations both in and outside of the US. Additionally, the performance of the risk method is compared based on the type of lightning input source (LMA vs GLM). The end goal of this work is to provide forecasters and end users with a tool to help monitor lightning risk in decision support scenarios.

Kelley Murphy↗

DOE OSTI2014

Quantitative Assessment of Detection Frequency for the INL Ambient Air Monitoring Network

A quantitative assessment of the Idaho National Laboratory (INL) air monitoring network was performed using frequency of detection as the performance metric. The INL air monitoring network consists of 37 low-volume air samplers in 31 different locations. Twenty of the samplers are located on INL (onsite) and 17 are located off INL (offsite). Detection frequencies were calculated using both BEA and ESER laboratory minimum detectable activity (MDA) levels. The CALPUFF Lagrangian puff dispersion model, coupled with 1 year of meteorological data, was used to calculate time-integrated concentrations at sampler locations for a 1-hour release of unit activity (1 Ci) for every hour of the year. The unit-activity time-integrated concentration (TICu) values were calculated at all samplers for releases from eight INL facilities. The TICu values were then scaled and integrated for a given release quantity and release duration. All facilities modeled a ground-level release emanating either from the center of the facility or at a point where significant emissions are possible. In addition to ground-level releases, three existing stacks at the Advanced Test Reactor Complex, Idaho Nuclear Technology and Engineering Center, and Material and Fuels Complex were also modeled. Meteorological data from the 35 stations comprising the INL Mesonet network, data from the Idaho Falls Regional airport, upper air data from the Boise airport, and three-dimensional gridded data from the weather research forecasting model were used for modeling. Three representative radionuclides identified as key radionuclides in INL’s annual National Emission Standards for Hazardous Air Pollutants evaluations were considered for the frequency of detection analysis: Cs-137 (beta-gamma emitter), Pu-239 (alpha emitter), and Sr-90 (beta emitter). Source-specific release quantities were calculated for each radionuclide, such that the maximum inhalation dose at any publicly accessible sampler or the National Emission Standards for Hazardous Air Pollutants maximum exposed individual location (i.e., Frenchman’s Cabin) was no more than 0.1 mrem yr–1 (i.e., 1% of the 10 mrem yr–1 standard). Detection frequencies were calculated separately for the onsite and offsite monitoring network. As expected, detection frequencies were generally less for the offsite sampling network compared to the onsite network. Overall, the monitoring network is very effective at detecting the potential releases of Cs-137 or Sr-90 from all sources/facilities using either the ESER or BEA MDAs. The network was less effective at detecting releases of Pu-239. Maximum detection frequencies for Pu-239 using ESER MDAs ranged from 27.4 to 100% for onsite samplers and 3 to 80% for offsite samplers. Using BEA MDAs, the maximum detection frequencies for Pu-239 ranged from 2.1 to 100% for onsite samplers and 0 to 5.9% for offsite samplers. The only release that was not detected by any of the samplers under any conditions was a release of Pu-239 from the Idaho Nuclear Technology and Engineering Center main stack (CPP-708). The methodology described in this report could be used to improve sampler placement and detection frequency, provided clear performance objectives are defined.

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

DOE OSTI2024

Physics informed neural network can retrieve rate and state friction parameters from acoustic monitoring of laboratory stick-slip experiments

Various machine learning (ML) and deep learning (DL) techniques have been recently applied to the forecasting of laboratory earthquakes from friction experiments. The magnitude and timing of shear failures in stick-slip cycles are predicted using features extracted from the recorded ultrasonic or acoustic emission (AE) signals. In addition, the Rate and State Friction (RSF) constitutive laws are extensively used to model the frictional behavior of faults. In this work, we use data from shear experiments coupled with passive acoustic (variance, kurtosis, and AE rate) interleaved with active source ultrasonic monitoring (transmitted wave amplitude) to develop physics-informed neural network (PINN) models incorporating the RSF law and AE rate generation equation with wave amplitude serving as a proxy for friction state variable. This PINN framework allows learning RSF parameters from stick-slip experiments rather than measuring them through a series of velocity step experiments. We observe that when the stick-slip cycles are irregular, the PINN models outperform the data-driven DL models. Transfer learning (TL) PINN models are also developed by pre-training on data collected at one normal stress level followed by forecasting shear failures and retrieving RSF parameters at other stress levels (i.e., with different recurrence intervals) after retraining on a limited amount of new data. Our findings suggest that TL models perform better compared to standalone models. Both standalone and TL PINN-estimated RSF parameters and their ground truth values show excellent agreements thus demonstrating that RSF parameters can be retrieved from laboratory stick-slip experiments using the corresponding acoustic data and that the transmitted wave amplitude provides a good representation of the evolving frictional state during stick-slips.

58 GEOSCIENCES↗

DOE OSTI2017

Sean Michaletz Directors Post Doc Fellow Report

Predicting climate change effects on plant function is a central challenge of global change biology and a primary mission of DOE. Although increasing temperatures and drought have been associated with reduced growth and increased mortality of plants, accurate prediction of such responses is limited by a lack of process-based theory linking climate and whole-plant physiology. This inability to predict forest mortality can cause significant biases in climate forecasts. One way forward is metabolic scaling theory (MST), which proposes that physiologic rates – from cells to the globe – are governed by the rates of resource distribution through vascular networks and the kinetics of resource utilization by metabolic reactions. MST has traditionally not considered rates of resource acquisition from organism-environment interactions, but it has an ideal mechanistic basis for doing so. As a first step towards integrating these processes, Sean has extended MST to characterize effects of temperature and precipitation on plant growth and ecosystem production. Sean’s post doc fellowship aimed to address a remaining shortcoming in that the new theory does not yet consider the physical processes of resource acquisition, and thus cannot mechanistically predict plant performance in a changing climate.

54 ENVIRONMENTAL SCIENCES↗

NASA NTRS1994

Galileo mission planning for Low Gain Antenna based operations

The Galileo mission operations concept is undergoing substantial redesign, necessitated by the deployment failure of the High Gain Antenna, while the spacecraft is on its way to Jupiter. The new design applies state-of-the-art technology and processes to increase the telemetry rate available through the Low Gain Antenna and to increase the information density of the telemetry. This paper describes the mission planning process being developed as part of this redesign. Principal topics include a brief description of the new mission concept and anticipated science return (these have been covered more extensively in earlier papers), identification of key drivers on the mission planning process, a description of the process and its implementation schedule, a discussion of the application of automated mission planning tool to the process, and a status report on mission planning work to date. Galileo enhancements include extensive reprogramming of on-board computers and substantial hard ware and software upgrades for the Deep Space Network (DSN). The principal mode of operation will be onboard recording of science data followed by extended playback periods. A variety of techniques will be used to compress and edit the data both before recording and during playback. A highly-compressed real-time science data stream will also be important. The telemetry rate will be increased using advanced coding techniques and advanced receivers. Galileo mission planning for orbital operations now involves partitioning of several scarce resources. Particularly difficult are division of the telemetry among the many users (eleven instruments, radio science, engineering monitoring, and navigation) and allocation of space on the tape recorder at each of the ten satellite encounters. The planning process is complicated by uncertainty in forecast performance of the DSN modifications and the non-deterministic nature of the new data compression schemes. Key mission planning steps include quantifying resource or capabilities to be allocated, prioritizing science observations and estimating resource needs for each, working inter-and intra-orbit trades of these resources among the Project elements, and planning real-time science activity. The first major mission planning activity, a high level, orbit-by-orbit allocation of resources among science objectives, has already been completed; and results are illustrated in the paper. To make efficient use of limited resources, Galileo mission planning will rely on automated mission planning tools capable of dealing with interactions among time-varying downlink capability, real-time science and engineering data transmission, and playback of recorded data. A new generic mission planning tool is being adapted for this purpose.

Gershman, R.↗

DOE OSTI2022

Development of lean, efficient, and fast physics-framed deep-learning-based proxy models for subsurface carbon storage

In this work, we present deep-learning-based surrogate models for CCUS developed with four different algorithms and a physics-framed two-phase flow problem involving displacement of water by CO 2 . The deep-learning models were trained using 3D datasets describing the pressure plume, CO 2 saturation plume, and water extraction rate generated by numerical simulation. The hyperparameters defining the architecture of the neural networks were optimized to determine the slimmest network size and training parameters that give the most efficient performance at the least training cost. To develop a robust model that closely mimics the governing physical laws, the discretized form of the two-phase fluid transport equation was used to formulate the supervised deep-learning task. The algorithms investigated in this study predicted the data to above 95% accuracy, with the multi-layer perceptron model demonstrating the best performance by balancing training speed, prediction time, and prediction accuracy with lean network capacity. Furthermore, the surrogate models simultaneously predict reservoir pressure and CO 2 saturation in every grid block, including the surface well extraction rate and bottomhole pressure, at all simulation times for a given static model realization in just a few seconds on a standard desktop computer. A key outcome of this study is that limits can be placed on network design parameters to avoid over designing neural networks, with associated efficiencies in training and prediction times. This is very useful because large volumes of data may be generated in CCUS projects and over-design of neural network architectures imposes penalties that are antithetical to the goal of near-real time forecasting.

58 GEOSCIENCES↗

DOE OSTI2024

Automated Framework for Groundwater Monitoring Using DWT with LSTM and Transformers

Environmental monitoring is critical for safeguarding public health and ecological well-being. Traditional data structuring and workflow monitoring methods consume significant time and effort, hindering timely insights and effective decision-making. Our study addresses this challenge by presenting an AI framework that automates data cleaning, structuring, and modeling processes, specifically targeting applications in groundwater monitoring. By leveraging automation for data processing and model training, our framework establishes a novel and efficient paradigm for environmental monitoring, with its potential application to the vast network of over a hundred Department of Energy Environmental Management (DoE-EM) cleanup sites across the country. It analyzes data streams from a network of groundwater Internet-of-Things (IoT) sensors deployed at the Savannah River Site (SRS) for prediction modeling. This allows human experts to focus on analysis and decision-making, ultimately leading to better environmental outcomes.The framework employs multivariate time-series forecasting methods to study and model the behavior of varying chemical analytes. The continuous learning process is enabled by utilizing deep learning techniques. It allows the framework to become more nuanced in its analysis over time, adapting to the specific characteristics of the environmental site and the evolving nature of contaminant behavior. Deep learning models known for sequence modeling, LSTM, and Transformers are employed for time series forecasting. Data processing and structuring are essential components significantly impacting the final model's performance. This hypothesis was proven by presenting a comparative analysis of model performance with processed and unprocessed data. The feature engineering approach utilized was the Discrete Wavelet Transform, which works well with time series data.

Discrete Wavelet Transform (DWT)↗

DOE OSTI2019

Forecasting district-scale energy dynamics through integrating building network and long short-term memory learning algorithm

With the development of data-driven techniques, building energy prediction on a district level has attracted increasing attention in recent years for revealing energy use patterns and reduction potentials. However, data acquisition in large building groups is difficult and adjacent buildings also interact with each other. To reduce data cost and incorporate the inter-building impact with the data-driven building energy model, this study proposes a deep learning predictive approach that fuses the building network model with a long short-term memory learning model for district-scale building energy modeling. The building network was constructed based on correlations between the energy use intensity of buildings, which can significantly reduce the computational complexity of the deep learning models for energy dynamic prediction. Five typical building groups with energy use data from 2015 to 2018 on two institutional campuses were selected to perform the validation experiment with TensorFlow. Based on the prediction error assessments, the results suggest that for total building energy use intensity prediction, the proposed model can achieve a mean absolute percentage error of 6.66% and a root mean square error of 0.36 kWh/m 2 , compared to 12.05% and 0.63 kWh/m 2 of the conventional artificial neural network model and to 11.06% and 0.89 kWh/m 2 for the support vector regression model.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

DOE OSTI2020

Probabilistic Prediction of Geomagnetic Storms and the K p index

Geomagnetic activity is often described using summary indices to summarize the likelihood of space weather impacts, as well as when parameterizing space weather models. The geomagnetic index K p in particular, is widely used for these purposes. Current state-of-the-art forecast models provide deterministic K p predictions using a variety of methods – including empirically-derived functions, physics-based models, and neural networks – but do not provide uncertainty estimates associated with the forecast. This paper provides a sample methodology to generate a 3-hour-ahead K p prediction with uncertainty bounds and from this provide a probabilistic geomagnetic storm forecast. Specifically, we have used a two-layered architecture to separately predict storm (K p ≥ 5 – ) and non-storm cases. As solar wind-driven models are limited in their ability to predict the onset of transient-driven activity we also introduce a model variant using solar X-ray flux to assess whether simple models including proxies for solar activity can improve the predictions of geomagnetic storm activity with lead times longer than the L1-to-Earth propagation time. By comparing the performance of these models we show that including operationally-available information about solar irradiance enhances the ability of predictive models to capture the onset of geomagnetic storms and that this can be achieved while also enabling probabilistic forecasts.

79 ASTRONOMY AND ASTROPHYSICS↗

DOE OSTI2025

Temporally-consistent koopman autoencoders for forecasting dynamical systems

Absence of sufficiently high-quality data often poses a key challenge in data-driven modeling of high-dimensional spatio-temporal dynamical systems. Koopman Autoencoders (KAEs) harness the expressivity of deep neural networks (DNNs), the dimension reduction capabilities of autoencoders, and the spectral properties of the Koopman operator to learn a reduced-order feature space with simpler, linear dynamics. However, the effectiveness of KAEs is hindered by limited and noisy training datasets, leading to poor generalizability. To address this, we introduce the Temporally-Consistent Koopman Autoencoder (tcKAE), designed to generate accurate long-term predictions even with limited and noisy training data. This is achieved through a consistency regularization term that enforces prediction coherence across different time steps, thus enhancing the robustness and generalizability of tcKAE over existing models. We provide analytical justification for this approach based on Koopman spectral theory and empirically demonstrate tcKAE’s superior performance over state-of-the-art KAE models across a variety of test cases, including simple pendulum oscillations, kinetic plasma, and fluid flow data.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

DOE OSTI2026

Monitoring of Liquid Metal Reactor Heater Zones with Recurrent Neural Network Learning of Temperature Time Series

Advanced high-temperature fluid reactors (ARs), such as sodium fast reactors (SFRs) and molten salt cooled reactors (MSCRs) utilize high-temperature fluids at ambient pressure. To melt the fluid during reactor startup and prevent fluid freezing during cooldown, the thermal–hydraulic systems of such ARs include heater zones consisting of specific heaters with controllers, temperature sensors, and thermal insulation. The failure of heater zones due to insulation material degradation or improper installation, resulting in parasitic heat losses, can lead to fluid freezing. The detection of faults using a heat-transfer model is difficult because of a lack of knowledge of the experimental details. Data-driven machine learning of heater zone temperature time series offers a viable alternative. In this study, we benchmarked the performance of recurrent neural networks (RNNs) in an analysis of heat-up transient temperature time series of heater zones installed on a liquid sodium vessel. The RNN models include long short-term memory (LSTM) and gated recurrent unit (GRU) networks, as well as their bi-directional variants, BiLSTM and BiGRU. Anomalous temperature points were designated using a percentile-based threshold applied to residual fluctuations in the detrended temperature time series. Additionally, the impact of the exponentially weighted moving average (EWMA) method on detection accuracy was examined. The RNN models’ performance was assessed using precision, recall, and F 1 score metrics. Results demonstrated that RNN models effectively detect anomalies in temperature time series with the best models for each heater zone achieving F 1 scores of over 93%. To explain the variations in RNN model performance across different heater zones, we used Kullback–Leibler (KL) divergence to quantify the relative entropy between training and testing data, and the Detrended Fluctuation Analysis (DFA) to assess long-range temporal correlations. For datasets with strong long-range correlations and minimal relative entropy between training and testing data, GRU is the best-performing model. When the data exhibits weaker long-term correlations and a significant relative entropy between training and testing distributions, BiGRU shows the best performance. For the data sets with intermediate values of both KL divergence and DFA, the best performance is obtained with LSTM and BiLSTM, respectively.

gated recurrent unit↗

NASA NTRS2008

Applications of TRMM-based Multi-Satellite Precipitation Estimation for Global Runoff Simulation: Prototyping a Global Flood Monitoring System

Advances in flood monitoring/forecasting have been constrained by the difficulty in estimating rainfall continuously over space (catchment-, national-, continental-, or even global-scale areas) and flood-relevant time scale. With the recent availability of satellite rainfall estimates at fine time and space resolution, this paper describes a prototype research framework for global flood monitoring by combining real-time satellite observations with a database of global terrestrial characteristics through a hydrologically relevant modeling scheme. Four major components included in the framework are (1) real-time precipitation input from NASA TRMM-based Multi-satellite Precipitation Analysis (TMPA); (2) a central geospatial database to preprocess the land surface characteristics: water divides, slopes, soils, land use, flow directions, flow accumulation, drainage network etc.; (3) a modified distributed hydrological model to convert rainfall to runoff and route the flow through the stream network in order to predict the timing and severity of the flood wave, and (4) an open-access web interface to quickly disseminate flood alerts for potential decision-making. Retrospective simulations for 1998-2006 demonstrate that the Global Flood Monitor (GFM) system performs consistently at both station and catchment levels. The GFM website (experimental version) has been running at near real-time in an effort to offer a cost-effective solution to the ultimate challenge of building natural disaster early warning systems for the data-sparse regions of the world. The interactive GFM website shows close-up maps of the flood risks overlaid on topography/population or integrated with the Google-Earth visualization tool. One additional capability, which extends forecast lead-time by assimilating QPF into the GFM, also will be implemented in the future.

Hong, Yang↗

DOE OSTI2015

Improving in vitro to in vivo extrapolation by incorporating toxicokinetic measurements: A case study of lindane-induced neurotoxicity

Approaches for extrapolating in vitro toxicity testing results for prediction of human in vivo outcomes are needed. The purpose of this case study was to employ in vitro toxicokinetics and PBPK modeling to perform in vitro to in vivo extrapolation (IVIVE) of lindane neurotoxicity. Lindane cell and media concentrations in vitro, together with in vitro concentration-response data for lindane effects on neuronal network firing rates, were compared to in vivo data and model simulations as an exercise in extrapolation for chemical-induced neurotoxicity in rodents and humans. Time- and concentration-dependent lindane dosimetry was determined in primary cultures of rat cortical neurons in vitro using “faux” (without electrodes) microelectrode arrays (MEAs). In vivo data were derived from literature values, and physiologically based pharmacokinetic (PBPK) modeling was used to extrapolate from rat to human. The previously determined EC{sub 50} for increased firing rates in primary cultures of cortical neurons was 0.6 μg/ml. Media and cell lindane concentrations at the EC{sub 50} were 0.4 μg/ml and 7.1 μg/ml, respectively, and cellular lindane accumulation was time- and concentration-dependent. Rat blood and brain lindane levels during seizures were 1.7–1.9 μg/ml and 5–11 μg/ml, respectively. Brain lindane levels associated with seizures in rats and those predicted for humans (average = 7 μg/ml) by PBPK modeling were very similar to in vitro concentrations detected in cortical cells at the EC{sub 50} dose. PBPK model predictions matched literature data and timing. These findings indicate that in vitro MEA results are predictive of in vivo responses to lindane and demonstrate a successful modeling approach for IVIVE of rat and human neurotoxicity. - Highlights: • In vitro to in vivo extrapolation for lindane neurotoxicity was performed. • Dosimetry of lindane in a micro-electrode array (MEA) test system was assessed. • Cell concentrations at the MEA EC{sub 50} equaled rat brain levels associated with seizure. • PBPK-predicted human brain levels at seizure also equaled EC{sub 50} cell concentrations. • In vitro MEA results are predictive of lindane in vivo dose–response in rats/humans.

60 APPLIED LIFE SCIENCES↗

NASA NTRSDate not supplied

Temporal Interpolation of Geostationary Satellite Imagery with Task Specific Optical Flow

Applications of satellite data in areas such as weather tracking and modeling, ecosystem monitoring, wildfire detection, and land-cover change are heavily dependent on the trade-offs to spatial, spectral and temporal resolutions of observations. In weather tracking, high-frequency temporal observations are critical and used to improve forecasts, study severe events, and extract atmospheric motion, among others. However, while the current generation of geostationary satellites have hemispheric coverage at 10-15 minute intervals, higher temporal frequency observations are ideal for studying mesoscale severe weather events. In this work, we apply a task specific optical flow approach to temporal up-sampling using deep convolutional neural networks. We apply this technique to 16-bands of GOES-R/Advanced Baseline Imager mesoscale dataset to temporally enhance full disk hemispheric snapshots of different spatial resolutions from 15 minutes to 1 minute. Experiments show the effectiveness of task specific optical flow and multi-scale blocks for interpolating high-frequency severe weather events relative to bilinear and global optical flow baselines. Lastly, we demonstrate strong performance in capturing variability during convective precipitation events.

Optical flow, temporal interpolation, geostationar↗

DOE OSTI2025

High‐Resolution National‐Scale Water Modeling Is Enhanced by Multiscale Differentiable Physics‐Informed Machine Learning

Abstract The National Water Model (NWM) is a key tool for flood forecasting, planning, and water management. Key challenges facing the NWM include calibration and parameter regionalization when confronted with big data. We present two novel versions of high‐resolution (∼37 km 2 ) differentiable models (a type of hybrid model): one with implicit, unit‐hydrograph‐style routing and another with explicit Muskingum‐Cunge routing in the river network. The former predicts streamflow at basin outlets whereas the latter presents a discretized product that seamlessly covers rivers in the conterminous United States (CONUS). Both versions use neural networks to provide a multiscale parameterization and process‐based equations to provide a structural backbone, which were trained simultaneously (“end‐to‐end”) on 2,807 basins across the CONUS and evaluated on 4,997 basins. Both versions show great potential to elevate future NWM performance for extensively calibrated as well as ungauged sites: the median daily Nash‐Sutcliffe efficiency of all 4,997 basins is improved to around 0.68 from 0.48 of NWM3.0. As they resolve spatial heterogeneity, both versions greatly improved simulations in the western CONUS and also in the Prairie Pothole Region, a long‐standing modeling challenge. The Muskingum‐Cunge version further improved performance for basins >10,000 km 2 . Overall, our results show how neural‐network‐based parameterizations can improve NWM performance for providing operational flood predictions while maintaining interpretability and multivariate outputs. The modeling system supports the Basic Model Interface (BMI), which allows seamless integration with the next‐generation NWM. We also provide a CONUS‐scale hydrologic data set for further evaluation and use.

Song, Yalan [Civil and Environmental Engineering T↗

DOE OSTI2020

Long short-term memory embedded nudging schemes for nonlinear data assimilation of geophysical flows

Reduced rank nonlinear filters are increasingly utilized in data assimilation of geophysical flows, but often require a set of ensemble forward simulations to estimate forecast covariance. On the other hand, predictor-corrector type nudging approaches are still attractive due to their simplicity of implementation when more complex methods need to be avoided. However, optimal estimate of nudging gain matrix might be cumbersome. In this paper, we put forth a fully nonintrusive recurrent neural network approach based on a long short-term memory (LSTM) embedding architecture to estimate the nudging term, which plays a role not only to force the state trajectories to the observations but also acts as a stabilizer. Furthermore, our approach relies on the power of archival data and the trained model can be retrained effectively due to power of transfer learning in any neural network applications. In order to verify the feasibility of the proposed approach, we perform twin experiments using Lorenz 96 system. Our results demonstrate that the proposed LSTM nudging approach yields more accurate estimates than both extended Kalman filter (EKF) and ensemble Kalman filter (EnKF) when only sparse observations are available. With the availability of emerging AI-friendly and modular hardware technologies and heterogeneous computing platforms, we articulate that our simplistic nudging framework turns out to be computationally more efficient than either the EKF or EnKF approaches.

42 ENGINEERING↗