Results for “dataset shift” — Page 4

DOE OSTI2025

Supporting Information - How Can Crop Production Adapt to growing groundwater restrictions in the West?

Abstract This data plan outlines the structure and content of datasets generated and utilized in the research presented in the manuscript abstract. Groundwater overdraft has led to serious water supply issues in the US West. Most western states manage groundwater use through a permitting system, but California has only recently begun to restrict groundwater use statewide with the 2014 passage of groundwater restrictions which target the elimination of groundwater overdraft practices by 2042. With groundwater extraction curtailed, crop production in the US West (a $95 billion industry annually) will be affected, and appropriate response strategies will be needed to ensure minimal disruption to food production and the regional economy. In this paper, we explore the adoption of alternative adaptive responses: (a) deficit irrigation; (b) switching to less water-intensive crops; (c) changing the extent of irrigated land (including fallowing); and (d) geographically shifting crop production. Employing an integrated modeling approach, we explicitly capture the interactions and feedbacks between local hydrology, changes in crop yields, crop and land use decision-making, changes in crop prices, and regional shifts in crop production. We find that the optimal adaptive response is spatially heterogeneous and comprises a portfolio of strategies. Southwestern states and California will be the most impacted by groundwater restrictions. The optimal responses in these states are to both adopt deficit irrigation strategies and reduce a portion of their irrigated croplands, resulting in a shift in crop production to northwestern states with a larger supply of water. The datasets detailed in this repository represent the output from these integrated models, specifically designed to support the analysis and visualization presented in the manuscript and supplemental information. These datasets, used in conjunction with the scripts available at our associated GitHub repository (https://github.com/pches/Femeena_etal_How_can_crop_production_adapt), enable the reproduction of figures and facilitate a comprehensive understanding of the optimal adaptive strategies in agriculture for mitigating water stress under varying groundwater extraction scenarios, as outlined in the abstract.

DNDCe↗

DOE OSTI2025

Supporting Information - How Can Crop Production Adapt to growing groundwater restrictions in the West?

Abstract This data plan outlines the structure and content of datasets generated and utilized in the research presented in the manuscript abstract. Groundwater overdraft has led to serious water supply issues in the US West. Most western states manage groundwater use through a permitting system, but California has only recently begun to restrict groundwater use statewide with the 2014 passage of groundwater restrictions which target the elimination of groundwater overdraft practices by 2042. With groundwater extraction curtailed, crop production in the US West (a $95 billion industry annually) will be affected, and appropriate response strategies will be needed to ensure minimal disruption to food production and the regional economy. In this paper, we explore the adoption of alternative adaptive responses: (a) deficit irrigation; (b) switching to less water-intensive crops; (c) changing the extent of irrigated land (including fallowing); and (d) geographically shifting crop production. Employing an integrated modeling approach, we explicitly capture the interactions and feedbacks between local hydrology, changes in crop yields, crop and land use decision-making, changes in crop prices, and regional shifts in crop production. We find that the optimal adaptive response is spatially heterogeneous and comprises a portfolio of strategies. Southwestern states and California will be the most impacted by groundwater restrictions. The optimal responses in these states are to both adopt deficit irrigation strategies and reduce a portion of their irrigated croplands, resulting in a shift in crop production to northwestern states with a larger supply of water. The datasets detailed in this repository represent the output from these integrated models, specifically designed to support the analysis and visualization presented in the manuscript and supplemental information. These datasets, used in conjunction with the scripts available at our associated GitHub repository (https://github.com/pches/Femeena_etal_How_can_crop_production_adapt), enable the reproduction of figures and facilitate a comprehensive understanding of the optimal adaptive strategies in agriculture for mitigating water stress under varying groundwater extraction scenarios, as outlined in the abstract.

DNDCe↗

DOE OSTI2025

Supporting Information - How Can Crop Production Adapt to growing groundwater restrictions in the West?

Abstract This data plan outlines the structure and content of datasets generated and utilized in the research presented in the manuscript abstract. Groundwater overdraft has led to serious water supply issues in the US West. Most western states manage groundwater use through a permitting system, but California has only recently begun to restrict groundwater use statewide with the 2014 passage of groundwater restrictions which target the elimination of groundwater overdraft practices by 2042. With groundwater extraction curtailed, crop production in the US West (a $95 billion industry annually) will be affected, and appropriate response strategies will be needed to ensure minimal disruption to food production and the regional economy. In this paper, we explore the adoption of alternative adaptive responses: (a) deficit irrigation; (b) switching to less water-intensive crops; (c) changing the extent of irrigated land (including fallowing); and (d) geographically shifting crop production. Employing an integrated modeling approach, we explicitly capture the interactions and feedbacks between local hydrology, changes in crop yields, crop and land use decision-making, changes in crop prices, and regional shifts in crop production. We find that the optimal adaptive response is spatially heterogeneous and comprises a portfolio of strategies. Southwestern states and California will be the most impacted by groundwater restrictions. The optimal responses in these states are to both adopt deficit irrigation strategies and reduce a portion of their irrigated croplands, resulting in a shift in crop production to northwestern states with a larger supply of water. The datasets detailed in this repository represent the output from these integrated models, specifically designed to support the analysis and visualization presented in the manuscript and supplemental information. These datasets, used in conjunction with the scripts available at our associated GitHub repository (https://github.com/pches/Femeena_etal_How_can_crop_production_adapt), enable the reproduction of figures and facilitate a comprehensive understanding of the optimal adaptive strategies in agriculture for mitigating water stress under varying groundwater extraction scenarios, as outlined in the abstract.

DNDCe↗

NASA NTRS2007

The Spatiotemporal Structure of 20th Century Climate Variations in Observations and Reanalyses: Pacific Pan-Decadal Variability - Part 2

The dominant interannual El Nino-Southern Oscillation phenomenon (ENSO) and the short length of climate observation records make it difficult to study long-term climate variations in the spatiotemporal domain. Based on the fact that the ENS0 signal spreads to remote regions and induces delayed climate variation through atmospheric teleconnections, we develop an ENSO-removal method through which the ENS0 signal can be approximately removed at the grid box level from the spatiotemporal field of a climate parameter. After this signal is removed, long-term climate variations, namely, the global warming trend (GW) and the Pacific pan-decadal variability (PDV), are isolated at middle and low latitudes in the climate parameter fields from observed and reanalyses datasets. In this study, we show that one of several PDV interdecadal regime shifts occurred during the 1990s. This significant change in the Pacific basin is comparable but opposite in phase to the 1976 climate regime shift, which results persisting warming in the central-eastern Pacific, and cooling in the North and South Pacific. The 1990s PDV regime shift is consistent with observed changes in ocean biosphere and ocean circulation. A comprehensive picture of PDV as manifested in the troposphere and at the surface is described. In general, the PDV spatial patterns in different parameter fields share some similarities with the patterns associated with ENSO, but important differences exist. First, the PDV atmospheric circulation pattern is shifted westward by about 20deg and its zonal extent is limited to approx.60deg compared to approx.110deg for ENS0 pattern. The westward shift of the PDV wave train produces a different, more west-east oriented, North American teleconnection pattern. The lack of a strong PDV surface temperature (ST) signal in the western equatorial Pacific and the relatively strong ST signal in the subtropical regions are consistent with an atmospheric overturning circulation response that differs from the one associated with ENSO.

Chen, Junye↗

DOE OSTI2020

Assessing Shifts in Regional Hydroclimatic Conditions of U.S. River Basins in Response to Climate Change over the 21st Century

Characterization of shifts in regional hydroclimatic conditions helps reduce negative consequences on agriculture, environment, economy, society, and ecosystem. This study assesses shifts in regional hydroclimatic conditions across the conterminous United States in response to climate change over the 21 st Century. The hydrological responses of five downscaled climate models from the Multivariate Adaptive Constructed Analogs (MACA) dataset ranging from the driest to wettest and least warm to hottest were simulated using the Variable Infiltration Capacity (VIC) model. Shifts in regional hydroclimatic conditions at 8-digit hydrologic unit scale (HUC8) were evaluated by the magnitude and direction of movements in the Budyko space. HUC8 river basins were then clustered into seven unique hydroclimatic behavior groups using the K-means method. A tree classification method was proposed to illustrate the relationships between hydroclimatic behavior groups and regional characteristics. The results indicate that hydroclimatic responses may vary from a river basin to another, but basins in the same neighborhood follow a similar movement in the Budyko space. The systematic hydroclimatic behavior of river basins is highly associated with their regional landform, climate, and ecosystem characteristics. Most HUC8s with Mountain, Plateau and Basin landform types will likely experience less arid conditions. However, most HUC8s with Plain landform type behave differently according to the regional ecosystem and climate. This study provides a potential roadmap of shifts in regional hydroclimatic conditions of U.S. river basins, which can be used to improve regional preparedness and ability of various sectors to mitigate or adapt to the impacts of future hydroclimate change.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2022

Latitudinal shifts of soil microbial biomass seasonality

Soil microbes ultimately drive the mineralization of soil organic carbon and thus ecosystem functions. We compiled a dataset of the seasonality of microbial biomass carbon (MBC) and developed a semi-mechanistic model to map monthly MBC across the globe. MBC exhibits an equatorially symmetric seasonality between the Northern and Southern Hemispheres. In the Northern Hemisphere, MBC peaks in autumn and is minimal in spring at low latitudes (<25°N), peaks in the spring and is minimal in autumn at mid-latitudes (25°N to 50°N), while peaks in autumn and is minimal in spring at high latitudes (>50°N). This latitudinal shift of MBC seasonality is attributed to an interaction of soil temperature, soil moisture, and substrate availability. The MBC seasonality is inconsistent with patterns of heterotrophic respiration, indicating that MBC as a proxy for microbial activity is inappropriate at this resolution. This study highlights the need to explicitly represent microbial physiology in microbial models. The interactive controls of environments and substrate on microbial seasonality provide insights for better representing microbial mechanisms in simulating ecosystem functions at the seasonal scale.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2025

Cross-functional transferability in foundation machine learning interatomic potentials

The rapid development of foundation potentials (FPs) in machine learning interatomic potentials demonstrates the possibility for generalizable learning of the universal potential energy surface. The accuracy of FPs can be further improved by bridging the model from lower-fidelity datasets to high-fidelity ones. In this work, we analyze the challenge of this transfer learning (TL) problem within the CHGNet framework. We show that significant energy scale shifts and poor correlations between GGA and r 2 SCAN hinder cross-functional transferability. By benchmarking different TL approaches on the MP-r 2 SCAN dataset, we demonstrate the importance of elemental energy referencing in the TL of FPs. By comparing the scaling law with and without the pre-training on a low-fidelity dataset, we show that significant data efficiency can still be achieved through TL, even with a target dataset of sub-million structures. We highlight the importance of proper TL and multi-fidelity learning in creating next-generation FPs on high-fidelity data.

Huang, Xu [University of California, Berkeley, CA ↗

DOE OSTI2024

Uncertainty-refined image segmentation under domain shift

Digital image segmentation is provided. The method comprises training a neural network for image segmentation with a labeled training dataset from a first domain, wherein a subset of nodes in the neural net are dropped out during training. The neural network receives image data from a second, different domain. A vector of N values that sum to 1 is calculated for each image element, wherein each value represents an image segmentation class. A label is assigned to each image element according to the class with the highest value in the vector. Multiple inferences are performed with active dropout layers for each image element, and an uncertainty value is generated for each image element. Uncertainty is resolved according to expected characteristics. The label of any image element with an uncertainty above a threshold is replaced with a new label corresponding to a segmentation class based on domain knowledge.

Martinez, Carianne↗

DOE OSTI2025

A new database website for nuclear level densities

We introduce a new open-access, web-based database (http://nld.ascsn.net), Current Archive of Nuclear Density of Levels (CANDL), that hosts experimental nuclear level density (NLD) datasets from a variety of techniques and energy ranges. Built using the Dash framework in Python, the database is designed to be interactive and user-friendly, allowing researchers to search, visualize, fit, and export NLD data with minimal effort. This resource includes data extracted from evaporation spectra, Oslo method variants, and other experimental techniques that cover excitation energies beyond the neutron resonance region. The database supports on-the-fly fitting with two widely-used phenomenological models—the Constant Temperature (CT) model and the Back-Shifted Fermi Gas (BSFG) model—selected for their simplicity and computational efficiency. Future versions aim to include additional datasets and model types, as well as easy-to-use interfaces to data science techniques. Here, this platform offers a vital tool for the nuclear physics, astrophysics, medicine, and reactor design communities.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗

NASA NTRS2021

Land-Use Harmonization Datasets for Global Carbon Budget 2019 and Beyond

Land-use change has been the dominant source of anthropogenic carbon emissions for most of the historical period, and is currently one of the largest and most uncertain components of the global carbon cycle. Advancing the scientific understanding on this topic requires that the best data be used as input to the best models in well-organized scientific assessments. The Land-Use Harmonization dataset (LUH2), previously developed and used as input for CMIP6 simulations, has been updated annually to provide required input to land models in the annual Global Carbon Budget (GCB) assessment. These annual LUH2-GCB updates and extensions have incorporated annual FAO wood harvest data updates for dataset years after 2015 and HYDE gridded agriculture area data updates (based on annual FAO agricultural area data updates) for dataset years after 2012, along with extrapolations to the current year due to a lag of one or more years in the FAO data releases. The resulting updated LUH2-GCB datasets have provided global, annual gridded land-use and land-use change data relating toagricultural expansion, deforestation, wood harvesting, shifting cultivation, regrowth and afforestation, and crop rotationsand pasture managementand are used by both book-keeping models and Dynamic Global Vegetation Models (DGVMs) for the GCB. For GCB 2019,a more significant update to LUH2 was produced (LUH2-GCB2019) to correct cropland and grazing area errors in the underlying input datasets for the globally important region of Brazil, as far back as 1950. From 1951-2012 the LUH2-GCB2019 dataset begins to diverge from the LUH2 v2hdataset, with peak differences in Brazil in the year 2000 for grazing land (difference of 100,000 km2) and in the year 2009 for cropland (difference of 77,000 km2), along with significant sub-national reorganization of agricultural land-use patterns within Brazil. These LUH2-GCB2019 corrections for Brazil provide the base for future LUH2-GCB updates including the recent LUH2-GCB2020 dataset, and present a starting point for operationalizing the creation of these datasets toreduce time-lags due to the multiple input dataset and model latencies.

L Chini↗

DOE OSTI2025

Scalable 3D reconstruction for X-ray single particle imaging with online machine learning

X-ray free-electron lasers offer unique capabilities for measuring the structure and dynamics of biomolecules, helping us understand the basic building blocks of life. Notably, high-repetition-rate free-electron lasers enable single particle imaging, where individual, weakly scattering biomolecules are imaged under near-physiological conditions with the opportunity to access fleeting states that cannot be captured in cryogenic or crystallized conditions. Existing X-ray single particle reconstruction algorithms, which estimate the particle orientation for each image independently, are slow and memory-intensive when handling the massive datasets generated by emerging free-electron lasers. Here, we introduce X-RAI (X-Ray single particle imaging with Amortized Inference), an online reconstruction framework that estimates the structure of 3D macromolecules from large X-ray single particle datasets. X-RAI consists of a convolutional encoder, which amortizes pose estimation over large datasets, as well as a physics-based decoder, which employs an implicit neural representation to enable high-quality 3D reconstruction in an end-to-end, self-supervised manner. We demonstrate that X-RAI achieves state-of-the-art performance for small-scale datasets in simulation and challenging experimental settings and demonstrate its unprecedented ability to process large datasets containing millions of diffraction images in an online fashion. These abilities signify a paradigm shift in X-ray single particle imaging towards real-time reconstruction.

Computer science↗

DOE OSTI2026

Frequentist cosmological constraints from full-shape clustering measurements in DESI DR1

We present a frequentist analysis of clustering measurements from Data Release 1 of the Dark Energy Spectroscopic Instrument (DESI) using the standard profile likelihood method. While Bayesian inferences for effective field theory models of galaxy clustering can be highly sensitive to prior choices for extended cosmological models, frequentist inferences are not susceptible to such effects. We compare frequentist and Bayesian constraints for the parameter set {σ 8 , H 0 , Ω m , w 0 , w a } using the full-shape power spectrum multipoles, post-reconstruction baryon acoustic oscillation (BAO) measurements, and external datasets from the CMB and type Ia supernovae measurements. The frequentist confidence intervals are significantly shifted relative to the Bayesian credible intervals for the w 0 w a CDM model, unless supernovae data are included. When DESI full-shape and BAO data are fit jointly, we obtain the following 1σ frequentist confidence intervals for ΛCDM (w 0 w a CDM): σ 8 = 0.863 +0.048 -0.040 , H 0 = 68.96 +0.81 -0.80 km s -1 Mpc -1 , Ω m = 0.3034 ± 0.0110 (σ 8 = 0.782 +0.060 -0.036 , H 0 = 63.7 +4.2 -2.0 km s -1 Mpc -1 , Ω m = 0.378 +0.024 -0.047 , w 0 = -0.16 +0.10 -0.50 , w a = -3.0 +1.7 ), corresponding to 0.8σ, 0.3σ, 0.7σ (2.1σ, 4.1σ, 6.5σ, 6.3σ, 6.6σ) shifts between the maximum likelihood estimate and the Bayesian posterior mean for ΛCDM (w 0 w a CDM) respectively.

Bayesian reasoning↗

NASA NTRSDate not supplied

NASA POWER: Providing Analysis-Ready, Cloud-Optimized Data for AI /ML Training and Applications in Earth Science

As global demand for sustainable development grows, the integration of Earth Observation (EO) data into decision making frameworks has become a primary objective for the scientific community. The NASA Prediction of Worldwide Energy Resources (POWER) project serves as a bridge between NASA EO data and the specialized needs of the renewable energy, sustainable infrastructure and agroclimatology communities. In this poster presentation we will present an overview of POWER data products and services along with its use in diverse research to decision-making workflows. By providing over 40 years of high-resolution historical, hourly and daily solar and meteorological data, POWER transforms satellite observations and global model reanalysis into actionable, Analysis-Ready Dataset (ARD). Currently, the project delivers over 250 industry-friendly parameters to the users from different NASA datasets like CERES SYN1Deg, MERRA-2, and IMERG alongside downscaled CMIP6 climate model data, fulfilling over 16 million requests from 50,000 unique users monthly. To ensure data quality and traceability, these parameters are rigorously validated against the ground-based observations from the Baseline Surface Radiation Network (BSRN) and the Global Surface Summary of the Day (GSOD) – these results will be discussed in the presentation. A newly introduced web-based PaRameter Uncertainty ViEwer (PRUVE) tool will be presented that provides an online validation platform to the users that benchmarks satellite-based and assimilation data products against these surface measurements. To reduce technical barriers to data adoption, POWER data is accessible through RESTful APIs, ESRI ArcGIS Image Services, a web-based Data Access Viewer tool, allowing users to visualize, validate and apply the dataset. For efficient data delivery POWER data is cloud-optimized into Zarr datastore accessible through NASA managed Amazon S3 ensures high-performance allowing users to integrate EO directly into operational pipelines. These customized services will be presented. Use cases from application will be presented from the energy sector - such as for design of generation systems, performance monitoring of solar power plants, in infrastructure sector- optimizing building energy efficiency and thermal comfort, in agriculture – such as driving crop simulation and yield forecasting models to enable climate resilient farming. Furthermore, the shift toward machine learning (ML) in EO research that has positioned POWER as a key provider for training datasets which will be discussed. Use-cases will be presented to showcase how NASA data is enabling the development of predictive tools for climate variability and resource management. The poster will present POWER’s future plans including technology development to enhance data traceability and reproducibility and improving I/O performance to support the rapid integration of new EO products, ensuring that POWER remains a robust scalable backend for the evolving landscape of AI-driven Earth Science. Additionally, POWER is developing an AI Agent and an MCP-Server to enable industry AI-Agentic workflows.

Neha Khadka↗

DOE OSTI2022

Rapidly changing high-latitude seasonality: Implications for the 21st century carbon cycle in Alaska: Modeling Archive

This Modeling Archive is in support of an NGEE Arctic publication "Rapidly changing high-latitude seasonality: Implications for the 21st century carbon cycle in Alaska" DOI: 10.1088/1748-9326/ac4362.The dataset contains "ecosys" model outputs reported in Shirley et al. (2022) that explored how climate warming will shift carbon cycle seasonality in Alaska. The study used analysis of seasonal dynamics to support the prediction that high-latitude ecosystems are carbon sinks and will continue to accumulate carbon throughout the century. The study predicts surprisingly large increases in spring net carbon uptake that result in larger net carbon uptake in spring than in summer by year 2100. Included as *.nc files are modeled daily net ecosystem exchange (NEE), net primary productivity (NPP), heterotrophic respiration (Rh), autotrophic respiration (Ra), gross primary productivity (GPP), and plant nitrogen uptake. The output is provided (1) at 25 km resolution across Alaska; (2) for years 2010 through 2100. Scripts to generate publication figures included as text files (*.m) from MATLAB. A user guide included as *.pdf.The Next-Generation Ecosystem Experiments: Arctic (NGEE Arctic), was a research effort to reduce uncertainty in Earth System Models by developing a predictive understanding of carbon-rich Arctic ecosystems and feedbacks to climate. NGEE Arctic was supported by the Department of Energy's Office of Biological and Environmental Research. The NGEE Arctic project had two field research sites: 1) located within the Arctic polygonal tundra coastal region on the Barrow Environmental Observatory (BEO) and the North Slope near Utqiagvik (Barrow), Alaska and 2) multiple areas on the discontinuous permafrost region of the Seward Peninsula north of Nome, Alaska. Through observations, experiments, and synthesis with existing datasets, NGEE Arctic provided an enhanced knowledge base for multi-scale modeling and contributed to improved process representation at global pan-Arctic scales within the Department of Energy's Earth system Model (the Energy Exascale Earth System Model, or E3SM), and specifically within the E3SM Land Model component (ELM).

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2023

Self-diagnosis of model suitability for continuous measurements of stream-dissolved organic carbon derived from in situ UV–visible spectroscopy

Application of high-frequency monitoring of dissolved organic carbon (DOC) is difficult in instances where training datasets are challenging to develop (e.g., remote locations) and the relationship between optical features and DOC concentration changes due to environmental or landscape shifts (e.g., climate or land-use change). We developed and compared three partial least squares (PLS) models using in situ water level measurements, conductivity, and UV–Vis spectral attenuation to predict DOC. Two site-specific models were developed using data from a hillslope-dominated forest or a low-relief wetland-pond-dominated stream catchment. The third model, using data from both sites, exhibited the best performance (DOC range = 4–15.5 mg C L −1 , mean = 8.38 mg C L −1 , training RMSE = 0.34 mg C L −1 , internal validation RMSE = 0.50 mg C L −1 , external validation RMSE = 2.43 mg C L −1 ). We further demonstrate using PLS model statistics to monitor performance and elucidate when and how models should be updated. These statistics, Hotelling's T 2 and squared prediction errors, are useful consistency checks for the predictions made and detect underlying inconsistencies that, if undetected, can reduce the robustness of DOC prediction. For example, via the T 2 statistic, we identified the summer–autumn transition as a period when DOC composition differed from what was represented in the training dataset. We also determined that elevated SUVA 254 values contributed to the overall bias observed in predictions made during the subsequent year as part of the external validation. This enabled the application of a bias correction that reduced the RMSE from 2.43 to 0.89 mg C L −1 . The method presented here could be applied to future monitoring programs enabling model updates to monitor DOC fluxes accurately from optical datasets (e.g., attenuance or fluorescence) in the face of developing datasets in remote locations or environmental change. In conclusion, implementation of this approach may also identify possible regime shifts or landscape and hydrologic change associated with climate and other environmental changes relevant to terrestrial to aquatic fluxes.

UV-VIS spectroscopy↗

DOE OSTI2021

Phase-sensitive γ-encoded recoupling of heteronuclear dipolar interactions and 1 H chemical shift anisotropy

γ-encoded recoupling sequences are known to produce strong amplitude modulations that lead to sharp doublets when Fourier transformed. These doublets depend very little on the recoupled tensor asymmetry and thus enable for the straightforward determination of dynamic order parameters. It can, however, be difficult to measure small anisotropies, or small order parameters, using such sequences; the resonances from the doublet may overlap with each other, or with the zero-frequency glitch. This limitation has prevented the widespread use of 1 H chemical shift anisotropy (CSA) for the measurement of dynamics, particularly for CH protons which typically have CSAs of only a few ppm when immobile. In this work, we introduce a simple modification to the traditional 1 H CSA and proton-detected local field pulse sequences that enables the acquisition of a hypercomplex dataset and the removal of the uncorrelated magnetization that results in the zero-frequency glitch. These new sequences then yield a frequency shift in the indirect dimension, rather than a splitting, which is easily identifiable even in cases of weak interactions.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

DOE OSTI2026

Data and scripts associated with a manuscript analyzing ELM-FATES parameter sensitivity under pre-fire and postfire scenarios using machine learning

NOTE: The manuscript associated with this data package is currently in review. The data may be revised based on reviewer feedback. Upon manuscript acceptance, this data package will be updated with the final dataset and additional metadata. This data package is associated with the manuscript “Fire Severity-Dependent Shifts in Vegetation Parameter Sensitivity: A Pre- and Post-Fire Analysis Using ELM-FATES and Explainable AI” submitted to Journal of Advances in Modeling Earth Systems (Zahura et al. 2026). The study examines vegetation physiological parameters controlling pre-fire and post-fire vegetation dynamics. To support this analysis, 73 vegetation parameters in Functionally Assembled Terrestrial Ecosystem Simulator (FATES) (Fisher et al., 2018) , which is coupled with E3SM (Energy Exascale Earth System Model) land model (ELM, ELM-FATES), were perturbed using a Sobol sequence to generate 1,024 ensemble members for two plant functional types: needleleaf evergreen extratropical trees (NEET) and C3 grass. Simulations were conducted for the pre-fire period (2016) and post-fire period (2018–2023). Burn severity was represented by modifying the Nesterov index in FATES to 75,000, 150,000, and 300,000 for low, moderate, and high severity, respectively. A no-fire scenario was also included. Simulations were performed for 16 grid cells in the American River Watershed across different burn severities and plant functional types. XGBoost (eXtreme Gradient Boosting) models were trained using the parameter ensembles and ELM-FATES-simulated outputs, including leaf area index (LAI), gross primary productivity (GPP), aboveground biomass, vegetation evaporation, transpiration, and soil evaporation. Models were trained separately for each year and burn severity, followed by SHAP (SHapley Additive exPlanations) analysis to identify changes in dominant parameters after fire disturbance. For details on how to navigate data packages generated by this project, see https://data.ess-dive.lbl.gov/portals/PNNLRiverCorridorSFA/About. The data package contains the ELM-FATES simulation data. The scripts and data related to the analysis will be added later. The inputs and outputs from ELM-FATES are inside the “FATES” folder. “FATES_domain_surface” contains the domain and surface netcdfs that were used to run ELM-FATES in the study area. “FATES_parameters” contains the 1024 ensembles that were generated using Sobol sequence. “FATES_outputs” folder contains ELM-FATES simulated variables. All files are .csv and .nc (NetCDF).

Aboveground biomass↗

DOE OSTI2022

Uncertainty-refined image segmentation under domain shift

A method for digital image segmentation is provided. The method comprises training a neural network for image segmentation with a labeled training dataset from a first domain, wherein a subset of nodes in the neural net are dropped out during training. The neural network receives image data from a second, different domain. A vector of N values that sum to 1 is calculated for each image element, wherein each value represents an image segmentation class. A label is assigned to each image element according to the class with the highest value in the vector. Multiple inferences are performed with active dropout layers for each image element, and an uncertainty value is generated for each image element. The label of any image element with an uncertainty value above a predefined threshold is replaced with a new label corresponding to the class with the next highest value.

Martinez, Carianne↗