Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “robust estimation”

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 883 records · Page 49
All sourcesNASA NTRSDOE OSTI
DOE OSTI2026

Robust Measurement of Stellar Streams around the Milky Way: Correcting Spatially Variable Observational Selection Effects in Optical Imaging Surveys

Observations of density variations in stellar streams are a promising probe of low-mass dark matter substructure in the Milky Way. However, survey systematics such as variations in seeing and sky brightness can also induce artificial fluctuations in the observed densities of known stellar streams. These variations arise because survey conditions affect both object detection and star–galaxy misclassification rates. To mitigate these effects, we use Balrog synthetic source injections in the Dark Energy Survey (DES) Y3 data to calculate detection rate variations and classification rates as functions of survey properties. We show that these rates are nearly separable with respect to survey properties and can be estimated with sufficient statistics from the synthetic catalogs. Applying these corrections reduces the standard deviation of relative detection rates across the DES footprint by a factor of 5, and our corrections significantly change the inferred linear density of the Phoenix stream when including faint objects. Additionally, for artificial streams with DES-like survey properties we are able to recover density power spectra with reduced bias. We also find that uncorrected power-spectrum results for Legacy Survey of Space and Time (LSST)-like data can be around 5 times more biased, highlighting the need for such corrections in future ground-based surveys.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2024

Computationally efficient and error aware surrogate construction for numerical solutions of subsurface flow through porous media

Limiting the injection rate to restrict the pressure below a threshold at a critical location can be an important goal of simulations that model the subsurface pressure between injection and extraction wells. The pressure is approximated by the solution of Darcy’s partial differential equation for a given permeability field. The subsurface permeability is modeled as a random field since it is known only up to statistical properties. This induces uncertainty in the computed pressure. Solving the partial differential equation for an ensemble of random permeability simulations enables estimating a probability distribution for the pressure at the critical location. These simulations are computationally expensive, and practitioners often need rapid online guidance for real-time pressure management. An ensemble of numerical partial differential equation solutions is used to construct a Gaussian process regression model that can quickly predict the pressure at the critical location as a function of the extraction rate and permeability realization. The Gaussian process surrogate analyzes the ensemble of numerical pressure solutions at the critical location as noisy observations of the true pressure solution, enabling robust inference using the conditional Gaussian process distribution. Our first novel contribution is to identify a sampling methodology for the random environment and matching kernel technology for which fitting the Gaussian process regression model scales as O ( n log n ) instead of the typical O ( n 3 ) rate in the number of samples n used to fit the surrogate. The surrogate model allows almost instantaneous predictions for the pressure at the critical location as a function of the extraction rate and permeability realization. Our second contribution is a novel algorithm to calibrate the uncertainty in the surrogate model to the discrepancy between the true pressure solution of Darcy’s equation and the numerical solution. Finally, although our method is derived for building a surrogate for the solution of Darcy’s equation with a random permeability field, the framework broadly applies to solutions of other partial differential equations with random coefficients.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2024

Phonon-mediated quantum efficiency measurement in semiconductors

Accurate quantum efficiency measurement not only provides crucial information for the photovoltaic cell industry but also supports experiments aimed at directly detecting dark matter and elastic neutrino interactions. The dark matter direct searches paradigm has recently expanded to include particles with masses below 1,MeV/c2, where the expected signal in an electron–recoil interaction is approximately in the eV range, just above the energy gap for silicon and germanium. A robust calibration method for ionization signals in this lower energy region is essential. This paper presents a method for measuring quantum efficiency and yield (q/E) in semiconductors using phonon-mediated calorimetry. The Neganov–Trofimov–Luke phonon amplification method in low-temperature semiconductor crystals has been employed to indirectly measure ionization down to single-electron accuracy. Specifically, at zero bias, the phonon readout directly quantifies the total energy deposited within the detector, independent of the ionization yield. This eliminates a significant source of systematic uncertainty in quantum efficiency estimates associated with total energy uncertainty. The paper includes results from an updated ionization efficiency measurement in a germanium detector.

Physics↗
DOE OSTI2023

Scaling comb-driven resonator-based DWDM silicon photonic links to multi-Tb/s in the multi-FSR regime

The use of chip-based micro-resonator Kerr frequency combs in conjunction with dense wavelength-division multiplexing (DWDM) enables massively parallel intensity-modulated direct-detection data transmission with low energy consumption. Resonator-based modulators and filters used in such systems can limit the number of usable wavelength channels due to practical constraints on the maximum achievable free spectral range (FSR). In this work, we introduce the design of multi-Tb/s comb-driven resonator-based silicon photonic links by leveraging the multi-FSR regime. We demonstrate the viability of the link architecture with yield estimates that are supported by extensive wafer-scale measurements of 704 micro-resonators fabricated in a commercial complementary metal–oxide–semiconductor foundry. We show that a 2.80 Tb/s link is realizable with a ≥6 σ yield (∼99.999%), and that aggregate bandwidths of 3.76 Tb/s and 4.72 Tb/s are possible if yield targets are relaxed (3 σ and 1 σ , respectively). All designs represent a 1.94−3.28× boost to aggregate link bandwidth while maintaining BER≤10 −10 performance, with a theoretical bandwidth of 10.51 Tb/s being possible for sufficiently robust resonators. We use high-speed BER measurements to inform co-optimization of data rate and aggressor spacing ( λ ag ), limiting any additional loss-based power penalties to off-resonance insertion loss (IL) and routing loss. This work demonstrates that, through the multi-FSR regime, there is a clear path toward Kerr comb-driven ultra-broadband, high bandwidth silicon photonic links that can support next-generation data centers and high-performance computers.

James, Aneek (ORCID:0000000262527807)↗
DOE OSTI2025

Idaho National Laboratory’s Mobile Hot Cell Transportation: Engineering Solutions for Global Disused Sealed Radioactive Sources.

Title: Idaho National Laboratory’s Mobile Hot Cell Transportation: Engineering Solutions for Global Disused Sealed Radioactive Sources. Abstract: The Mobile Hot Cell (MHC), currently under development by Idaho National Laboratory (INL) for the Off-Site Source Recovery Project (OSRP), is designed to help international partners meet the unique challenges of end-of-life radioactive material management. The MHC will provide a critical resource for countries that require assistance securing and disposing of Disused Sealed Radioactive Sources (DSRS) and orphaned sources in challenging environments, allowing these sources to be secured against misuse and nefarious activities. The MHC is a rapidly deployable system for conditioning and preparing end-of-life radioactive sources for transportation or storage. It is designed to handle sources of up to 1,000 Ci Co-60 equivalent while maintaining full radiological and biological containment. It will be deployable within 48 hours of an alert, making it ideal for emergency situations. The MHC features an operational suite for control, support racks for electronics, pneumatics, and welding systems, and a modular robust steel structure providing radiological shielding and internal robotic support. This design allows configurations for multiple device types to be conditioned and the ability to safely manage routine issues such as leaking or damaged sources. The MHC has been designed with the transportation challenges of rapid deployment to difficult environments in mind. The system weighs approximately 150,000 pounds, with individual systems breaking down into pieces not exceeding 20,000 pounds. Components are to be transportable on standard 20ft ISO containers, with shielding shells on 20ft flat racks. It is estimated that a total of eight containers and flat racks will be required. The use of 20ft containers, as opposed to 40ft containers, minimizes the impact on less developed road infrastructures, enabling the MHC to be positioned in constrained environments such as hospital parking lots. The system’s modularity also allows for deployment using smaller equipment, such as a 10-ton boom truck or forklift, which is crucial given the potential logistical challenges in different countries. This transportation strategy, evaluated in collaboration with Utah State University, ensures the MHC can be deployed via ground, rail, sea, or air, addressing the primary concern of international transport logistics.

99 - GENERAL AND MISCELLANEOUS↗
DOE OSTI2021

A Spatially Explicit Individual-Based Modeling Approach to Evaluate the Cumulative Effects of Wind Energy Development on the Greater Sage-Grouse: Sensitivity Analysis and Validation of Key Parameters

To address the need for an approach to evaluate cumulative ecological impacts of wind energy development, particularly those on critical wildlife habitats and species, the authors developed a proof-of-concept, landscape-based, spatially explicit individual-based modeling (IBM) framework for populations of the greater sage-grouse (Centrocercus urophasianus) in Albany County, Wyoming, based on published and other available information on the life history of the species. This sage-grouse IBM estimates the spatial and temporal movements of sage-grouse based on modeled effects of habitat characteristics and developments on sage-grouse condition, survivorship, and reproduction. After completing the initial version of the model, we conducted a series of sensitivity analyses of key model parameters and validation of lek occurrences and spatial distributions to better understand performance of the model relative to observed values of important life history characteristics. The parameter sensitivity analysis was conducted as a series of one-factor-at-a-time tests in which the values of selected parameters were individually varied to evaluate the corresponding effects on model output. We examined the model’s response to changes in parameter values to gain insight into the overall robustness of the model, identify key driver parameters, and initiate qualitative validation. Five functions selected for sensitivity analyses were (1) the rate of change in body condition in relationship to habitat suitability index (HSI) of occupied habitat (condition change rate), (2) the effect of competition between individuals with overlapping home ranges expressed as a percentage reduction in HSI (competition factor), (3) value of condition at which survivorship probability is equal to zero (zero survivorship condition), (4) the relationship between female body condition and clutch size, and (5) the relationship between female body condition and nest success. We varied the parameter values to be tested for the sensitivity analysis around the original value used in the model (i.e., tested values were higher and lower than the model’s original value) to examine the effect of this variation on the predicted output of the model. Model outputs evaluated in the sensitivity analysis included (1) predicted age-class distribution (as measured by the percentage of immature individuals within the population); (2) predicted sex ratio; (3) predicted age-sex class distribution (percent of population in each of six age-sex classes, i.e., male and female juveniles, yearlings, and adults); (4) lifespan; (5) population size; and (6) spatial distribution. Of the five parameters analyzed, condition change rate, survivorship, clutch size, and nest success did not substantially affect any of the evaluated model outputs. For the predicted age-class distribution, the percentage of immature individuals predicted by the model for these four parameters ranged from 61.9% to 65.0%, which was reasonable with respect to the reference values of 51.4 to 57.8% in published studies. The ratio of females to males ranged from 1.09 to 1.14, which was comparable to the reference values of 1.2 to 3.0 presented in an existing study. The predicted mean lifespan ranged from 1.62 to 1.74 years, which appears to be reasonable with respect to the reference values of 0.9 to 1.1 years for sharp-tail grouse and greater prairie chickens presented by published studies. The predicted population size ranged from 1,877 to 3,140. This prediction would be reasonable with respect to our estimate of 5,000 yearlings and adults, which was based on the USFWS estimate for the state of Wyoming scaled to the number of leks in the county. The predicted spatial distribution was not substantially affected by the parameter values examined. In our sensitivity analyses, the only tested parameter that had a noticeable effect on model output was competition factor. Over the range of values tested for this parameter, predicted population size exhibited the largest range (from 1,833 to 4,737) of all parameters tested. As the competition factor increased, the predicted population size decreased. This reflects the effect competition had on the number of individuals that could co occur in high-quality habitat patches. Despite this apparently significant effect, the range of values appears to be reasonable with respect to our estimate of 5,000 yearlings and adults, which was based on the USFWS estimate for the state of Wyoming scaled to the number of leks in the county.

17 WIND ENERGY↗
DOE OSTI2020

State-of-the-art on research and applications of machine learning in the building life cycle

Fueled by big data, powerful and affordable computing resources, and advanced algorithms, machine learning has been explored and applied to buildings research for the past decades and has demonstrated its potential to enhance building performance. This study systematically surveyed how machine learning has been applied at different stages of building life cycle. By conducting a literature search on the Web of Knowledge platform, we found 9579 papers in this field and selected 153 papers for an in-depth review. The number of published papers is increasing year by year, with a focus on building design, operation, and control. However, no study was found using machine learning in building commissioning. There are successful pilot studies on fault detection and diagnosis of HVAC equipment and systems, load prediction, energy baseline estimate, load shape clustering, occupancy prediction, and learning occupant behaviors and energy use patterns. None of the existing studies were adopted broadly by the building industry, due to common challenges including (1) lack of large scale labeled data to train and validate the model, (2) lack of model transferability, which limits a model trained with one data-rich building to be used in another building with limited data, (3) lack of strong justification of costs and benefits of deploying machine learning, and (4) the performance might not be reliable and robust for the stated goals, as the method might work for some buildings but could not be generalized to others. Finally, findings from the study can inform future machine learning research to improve occupant comfort, energy efficiency, demand flexibility, and resilience of buildings, as well as to inspire young researchers in the field to explore multidisciplinary approaches that integrate building science, computing science, data science, and social science.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2026

Signal Whisperers: Enhancing Wireless Reception Using DRL-Guided Reflector Arrays

This paper presents a multi-agent reinforcement learning (MARL) approach for controlling adjustable metallic reflector arrays to enhance wireless signal reception in non-line-of-sight (NLOS) scenarios. Unlike conventional reconfigurable intelligent surfaces (RIS) that require complex channel estimation, our system employs a centralized training with decentralized execution (CTDE) paradigm where individual agents corresponding to reflector segments autonomously optimize reflector element orientation in three-dimensional space using spatial intelligence based on user location information. Through extensive ray-tracing simulations with dynamic user mobility, the proposed multi-agent beam-focusing framework demonstrates substantial performance improvements over single-agent reinforcement learning baselines, while maintaining rapid adaptation to user movement within one simulation step. Comprehensive evaluation across varying user densities and reflector configurations validates system scalability and robustness. The results demonstrate the potential of learning-based approaches for adaptive wireless propagation control.

deep reinforcement learning↗
DOE OSTI2021

An initial exploration of Bayesian model calibration for estimating the composition of rocks and soils on Mars

The Mars Curiosity rover carries an instrument, ChemCam, designed to measure the composition of surface rocks and soil using laser-induced breakdown spectroscopy (LIBS). The measured spectra from this instrument must be analyzed to identify the component elements in the target sample, as well as their relative proportions. This process, which we call disaggregation, is complicated by so-called matrix effects, which describe nonlinear changes in the relative heights of emission lines as an unknown function of composition due to atomic interactions within the LIBS plasma. In this work, we explore the use of the plasma physics code ATOMIC, developed at Los Alamos National Laboratory, for the disaggregation task. ATOMIC has recently been used to model LIBS spectra and can robustly reproduce matrix effects from first principles. The ability of ATOMIC to predict LIBS spectra presents an exciting opportunity to perform disaggregation in a manner not yet tried in the LIBS community, namely via Bayesian model calibration. However, using it directly to solve our inverse problem is computationally intractable due to the large parameter space and the computation time required to produce a single output. Therefore, we also explore the use of emulators as a fast solution for this analysis. We discuss a proof of concept Gaussian process emulator for disaggregating two-element compounds of sodium and copper. The training and test datasets were simulated with ATOMIC using a Latin hypercube design. After testing the performance of the emulator, we successfully recover the composition of 25 test spectra with Bayesian model calibration.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Machine learning application to single channel design of molten salt reactor

This study proposes a robust approach to quickly design a nuclear reactor core and explores the best performing machine learning (ML) technique for predicting feature parameters of the core. Here we implemented the approach into a hypothetical channel of molten salt reactors to demonstrate the applicability of the method. We prepared a Python tool, named Plankton, which couples to a reactor physics code and an optimization tool, and imports ML methods. The tool performs three consecutive phases: reactor database generation, machine learning application, and design optimization. We identified the extra trees method as the best performing estimator. With the estimator, we found nine optimum designs in total, one for each fuel-salt pair, and estimated all the performance metrics of the designs with a <5% prediction error compared to their actual values. U-Pu-NaCl fuel-salt gave promising results with the highest conversion ratio, the most negative feedback coefficient, and the lowest fast flux.

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗
DOE OSTI2026

End-To-End Decentralized Transmission Line Protection in IBR-Dominated Weak Grids Using Interpretable Data-Driven Methods

Traditional transmission line protection relies on predictable synchronous-based fault signatures, which frequently fail under the non-standard, current-limited fault characteristics of Inverter-Based Resources (IBRs). This study investigates how to achieve secure, communication-free fault isolation in IBR-dominated weak grids without relying on opaque, computationally heavy "black-box" machine learning algorithms. To address this, we propose a novel, standalone, and inherently interpretable data-driven protection framework. Unlike centralized methods requiring multi-terminal communication, this decentralized approach relies solely on local measurements using a hierarchical linear-kernel Support Vector Machine (SVM). The methodology decomposes the protection task into four sequential stages that mimic traditional protection elements: fault detection and fault direction identification, fault type classification, zone classification, and location estimation. This multi-stage architecture allows for specialized feature engineering at each stage, combining high computational efficiency with logic traceability. The framework's end-to-end performance was validated via C-code and PSCAD/EMTDC co-simulation, utilizing a real-world utility network and an OEM black-box IBR model. The proposed relay achieves 97.2% overall accuracy and provides a reliable trip decision within a 2.5-cycle window. The results confirm 100% accuracy in fundamental fault detection, reliable zone selectivity across low to moderate fault resistances, and robust security against non-fault transients, proving its immediate viability for integration into commercial numerical relays.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2026

The Potential and Cost of Carbon Dioxide Removal Using Direct Air Capture with Land-Based Wind and Utility-Scale Photovoltaics

The rapid deployment of direct air capture and storage (DACS) is critical for achieving emission targets, necessitating precise evaluation of the scale and cost of carbon dioxide removal. This study examines the availability of land, electricity generation, and geologic CO 2 storage within the United States, estimating a technical potential for low-temperature, adsorbent-based DACS to remove approximately 9 gigatonnes of CO 2 annually. By 2050, a substantial portion of this removal could be achieved at net-removed costs below $\$$300/tonneCO 2 , though costs are highly variable depending on factors such as facility scale, construction expenses, climate-dependent productivity and heating efficiency, and geologic storage conditions. In the short term, DACS deployment will help identify key research priorities for advancing technology and reducing removal costs. Concurrently, there is an urgent need for scientifically robust and standardized frameworks for monitoring, reporting, and verifying DACS performance across both established and emerging technologies and energy sources.

Carbon capture↗
DOE OSTI2026

Machine learning method for enforcing variable independence in background estimation with LHC data: ABCDisCoTEC

A novel solution is presented for the problem of estimating the backgrounds of a signal search using observed data while simultaneously maximizing the sensitivity of the search to the signal. The 'ABCD method' provides a reliable framework for background estimation by partitioning events into one signal-enhanced region (A) and three background-enhanced control regions (B, C, and D) via two smoothly varying, statistically independent variables. In practice, even slight correlations between the two variables can significantly undermine the method's performance. Thus, choosing appropriate variables by hand can present a formidable challenge, especially when background and signal differ only subtly. To address this issue, the ABCD with distance correlation (ABCDisCo) method was developed to construct two learned variables via a neural network trained to provide strong signal-background discrimination with small values of the distance correlation (DisCo) measure between the two learned variables. However, relying solely on minimizing the DisCo can result in learned variables that may not have distributions of background events that are smoothly varying and localized at extreme values, as necessary for the validity of the background estimation. The ABCDisCo training enhanced with closure (ABCDisCoTEC) method is introduced to solve this issue by directly minimizing the nonclosure, expressed as a dedicated differentiable loss term. This extended method is applied to a data set of proton-proton collisions at a center-of-mass energy of 13 TeV recorded by the CMS detector at the CERN Large Hadron Collider. Additionally, given the complexity of the minimization problem with constraints on multiple loss terms, the modified differential method of multipliers is applied and shown to greatly improve the stability and robustness of the ABCDisCoTEC method, compared to grid search hyperparameter optimization procedures.

Hayrapetyan, Aram [Yerevan Phys. Inst.]↗
DOE OSTI2024

Constituent Data Replacement Tool

The purpose of this tool is to estimate key parameters that may be missing in public wastewater composition datasets. The tool can be applied to develop complete treatment and critical mineral extraction profiles for leachate, produced water and other aqueous waste streams. The tool applies machine learning algorithms to replace missing data in a user’s water data set that are adjusted based on user preferences for options including algorithm type, number of features, and classification variables. The tool can use the user’s data alone or combine user data with the NEWTS USGS Produced Water Database for more robust training. This research was funded by the U.S. Department of Energy’s Office Fossil Energy and Carbon Management (FECM) through National Energy Technology Laboratory’s ongoing research under the Water Management for Power System Field Work Proposal, DE-FECM 1022428 and Critical Minerals Field Work Proposal, DE-FECM 1022420.

Aqueous Chemistry↗
DOE OSTI2022

Photometric redshift estimation with convolutional neural networks and galaxy images: Case study of resolving biases in data-driven methods

Deep-learning models have been increasingly exploited in astrophysical studies, but these data-driven algorithms are prone to producing biased outputs that are detrimental for subsequent analyses. In this work, we investigate two main forms of biases: class-dependent residuals, and mode collapse. We do this in a case study, in which we estimate photometric redshift as a classification problem using convolutional neural networks (CNNs) trained with galaxy images and associated spectroscopic redshifts. We focus on point estimates and propose a set of consecutive steps for resolving the two biases based on CNN models, involving representation learning with multichannel outputs, balancing the training data, and leveraging soft labels. The residuals can be viewed as a function of spectroscopic redshift or photometric redshift, and the biases with respect to these two definitions are incompatible and should be treated individually. We suggest that a prerequisite for resolving biases in photometric space is resolving biases in spectroscopic space. Experiments show that our methods can better control biases than benchmark methods, and they are robust in various implementing and training conditions with high-quality data. Our methods hold promises for future cosmological surveys that require a good constraint of biases, and they may be applied to regression problems and other studies that make use of data-driven models. Nonetheless, the bias-variance tradeoff and the requirement of sufficient statistics suggest that we need better methods and optimized data usage strategies.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2026

Two-Level Sketching Alternating Anderson Acceleration for Complex Physics Applications

We present a novel two-level sketching extension of the Alternating Anderson–Picard (AAP) method for accelerating fixed-point iterations in challenging single- and multiphysics simulations governed by discretized PDEs. Our approach combines a static, physics-based projection that reduces the least-squares (LS) problem to the most informative field (e.g., via Schur-complement insight) with a dynamic, algebraic sketching stage driven by a backward stability analysis under Lipschitz continuity. We introduce inexpensive estimators for stability thresholds and cache-aware randomized selection strategies to balance computational cost against memory access overhead. The resulting algorithm solves reduced LS systems in place, minimizes memory footprints, and seamlessly alternates between low-cost Picard updates and Anderson mixing. Implemented in Julia, our two-level sketching AAP achieves up to 50% time-to-solution reductions compared to standard Anderson acceleration—without degrading convergence rates—on benchmark problems including Stokes, 𝑝-Laplacian, bidomain, and Navier–Stokes formulations at varying problem sizes. These results demonstrate the method’s robustness, scalability, and potential for integration into high-performance scientific computing frameworks. Our implementation is available open source in the AAP.jl library.

Barnafi, Nicolas [University of Chile, Santiago]↗
DOE OSTI2021

Sea Surface Salinity Reemergence in an Updated North Atlantic In Situ Salinity Dataset

Monthly sea surface salinity (SSS) fields are constructed from observations, using objective mapping on a 1° x 1° grid in the Atlantic between 30°S and 50°N in the 1970-2016 period in an update of the dataset of Reverdin et al. Data coverage is heterogeneous, with increased density in 2002 when Argo floats become available, high density along Voluntary Observing Ship lines, and low density south of 10°S. Using lag correlation, the seasonal reemergence of SSS anomalies is investigated between 20° and 50°N in 5° x 5° boxes during the 1993-2016 period, both locally and remotely following the displacements of the deep mixed-layer waters estimated from virtual float trajectories derived from the daily AVISO surface geostrophic currents. Although SSS data are noisy, local SSS reemergence is detected in about half of the boxes, notably in the northeast and southeast, while little reemergence is seen in the central and part of the eastern subtropical gyre. In the same period, sea surface temperature (SST) reemergence is found only slightly more frequently, reflecting the short data duration. However, taking geostrophic advection into account degrades the detection of remote SSS and even SST reemergence. When anomalies are averaged over broader areas, robust evidence of a second and third SSS reemergence peak is found in the northeastern and southeastern parts of the domain, indicating long cold-season persistence of large-scale SSS anomalies, while only a first SST reemergence is seen. Finally, an oceanic reanalysis is used to confirm that the correlation analysis indeed reflects the reemergence of subsurface salinity anomalies.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2026

A hybrid Penman-Monteith and machine learning model for simulating evapotranspiration and its components

Integrating physical processes with machine learning has advanced evapotranspiration (ET) simulation, yet most hybrid models fail to partition total ET into its components: soil evaporation (E) and vegetation transpiration (T). This study introduces Residual Neural Network–Penman–Monteith (RNN-PM), a novel hybrid dual-source ET model designed to overcome this limitation. The model synergizes the physically-based Penman–Monteith framework with three specialized residual neural networks trained to estimate key conductance parameters (canopy conductance, soil surface conductance, and aerodynamic conductance). Furthermore this explicit parameterization allows for the direct partitioning of total ET. Validation at National Ecological Observatory Network (NEON) flux sites using high-frequency partitioned E and T shows that RNN-PM reliably reproduces ET and the transpiration fraction (T/ET). For ET, the model achieves an average Kling–Gupta efficiency (KGE) of 0.89 and a root-mean-square error (RMSE) of 0.55 mm/day; for T/ET, the KGE is 0.87 with an RMSE of 0.06. Furthermore, RNN-PM demonstrates robust generalization, accurately simulating ET and its components well beyond the initial training dataset, even under extreme climatic conditions. This study extended the analysis by comparing the RNN-PM model with seven established dual-source ET models. The results indicate that RNN-PM outperforms both conventional machine learning models and purely physical process-based models in simulating ET components in most cases. Among the purely physical process-based dual-source models, those based on surface temperature decomposition showed improved performance as the leaf area index (LAI) decreased when evaluated against high-frequency ET component datasets. In contrast, the performance of conductance-based dual-source models declined with decreasing LAI. Although purely machine learning-based models can produce relatively accurate simulations of ET components, they often exhibit limited generalization capability, an issue that the RNN-PM model effectively overcomes. Ultimately, the RNN-PM model represents a significant advance in simulating ET components, offering a novel and scalable approach for improving the representation of land–atmosphere interactions in Earth system models.

54 ENVIRONMENTAL SCIENCES↗