Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “variability prediction”

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 361 records · Page 20
All sourcesNASA NTRSDOE OSTI
DOE OSTI2020

COVID-19 biomarkers based on respiratory microbiome content

COVID-19 patient care management would greatly benefit from new tools that enable accurate assessment of disease severity and stage, potentially enabling a personalized medicine approach. Detection of the SARS-CoV-2 virus itself, or even quantitation of viral loads, is not sufficient for accurate assessment of disease state beyond diagnosis of infection [eg, doi:10.1093/cid/ciaa344]. Levels of usual suspect protein biomarkers associated with host response to infection [eg, C-reactive protein (CRP); cytokines like IL-6, TNF-alpha, and IL-10; complement proteins like C3a and C5a], and of individual blood cell types (eg, leukocytes, lymphocytes, and subsets thereof), show limited correlation with disease severity and stage, with high patient-to-patient and study-to-study variability [eg, doi:10.1093/cid/ciaa248]. High-dimensional panels of biomarkers should have greater predictive power and resilience to unavoidable sources of variability; however, their assembly from proteins and cell types is extremely difficult, due to technical limitations in analyte measurement, especially with regard to starting material requirements and detection sensitivity. Host response profiling through Next Generation Sequencing (NGS) of gene expression patterns (ie, RNA-Seq) is a promising approach, but at the time of this project there were only two publicly available datasets of relevance [doi:10.1093/cid/ciaa203, doi:10.1080/22221751.2020.1747363], and close inspection of them revealed that each had at least one major flaw that severely undermined its value in supporting robust analysis of host response to SARS-CoV- 2 infection. However, the first of these studies [doi:10.1093/cid/ciaa203] fortuitously collected NGS data not only from host cells, but also from bacteria present in bronchoalveolar lavage fluid (BALF) recovered from COVID-19 patients; and because the respiratory microbiome (in terms of bacterial species content) is far less complex than the human transcriptome, the NGS data collected were sufficient to provide coverage depth supporting robust analysis. Surprisingly, the authors of the study did not carry out a detailed analysis of these data and their potential for revealing important new information about COVID-19. Therefore, we carried out a meta-analysis of the dataset as a first step in evaluating the potential for profiling of respiratory microbiome dynamics as a means of accurately assessing COVID-19 disease state.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2023

Validation of turbulence intensity as simulated by the Weather Research and Forecasting model off the US northeast coast

We report turbulence intensity (TI) is often used to quantify the strength of turbulence in wind energy applications and serves as the basis of standards in wind turbine design. Thus, accurately characterizing the spatiotemporal variability in TI should lead to improved predictions of power production. Nevertheless, turbulence measurements over the ocean are far less prevalent than over land due to challenges in instrumental deployment, maintenance, and operation. Atmospheric models such as mesoscale (weather prediction) and large-eddy simulation (LES) models are commonly used in the wind energy industry to assess the spatial variability of a given site. However, the TI derivation from atmospheric models has not been well examined. An algorithm is proposed in this study to realize online calculation of TI in the Weather Research and Forecasting (WRF) model. Simulated TI is divided into two components depending on scale, including sub-grid (parameterized based on turbulence kinetic energy (TKE)) and grid resolved. The sensitivity of sea surface temperature (SST) on simulated TI is also tested. An assessment is performed by using observations collected during a field campaign conducted from February to June 2020 near the Woods Hole Oceanographic Institution Martha's Vineyard Coastal Observatory. Results show that while simulated TKE is generally smaller than the lidar-observed value, wind speed bias is usually small. Overall, this leads to a slight underestimation in sub-grid-scale estimated TI. Improved SST representation subsequently reduces model biases in atmospheric stability as well as wind speed and sub-grid TI near the hub height. Large TI events in conjunction with mesoscale weather systems observed during the studied period pose a challenge to accurately estimating TI from models. Due to notable uncertainty in accurately simulating those events, this suggests summing up sub-grid and resolved TI may not be an ideal solution. Efforts in further improving skills in simulating mesoscale flow and cloud systems are necessary as the next steps.

17 WIND ENERGY↗
DOE OSTI2024

High dimensional predictions of suicide risk in 4.2 million US Veterans using ensemble transfer learning

We present an ensemble transfer learning method to predict suicide from Veterans Affairs (VA) electronic medical records (EMR). A diverse set of base models was trained to predict a binary outcome constructed from reported suicide, suicide attempt, and overdose diagnoses with varying choices of study design and prediction methodology. Each model used twenty cross-sectional and 190 longitudinal variables observed in eight time intervals covering 7.5 years prior to the time of prediction. Ensembles of seven base models were created and fine-tuned with ten variables expected to change with study design and outcome definition in order to predict suicide and combined outcome in a prospective cohort. The ensemble models achieved c-statistics of 0.73 on 2-year suicide risk and 0.83 on the combined outcome when predicting on a prospective cohort of ~4.2 M veterans. The ensembles rely on nonlinear base models trained using a matched retrospective nested case-control (Rcc) study cohort and show good calibration across a diversity of subgroups, including risk strata, age, sex, race, and level of healthcare utilization. In addition, a linear Rcc base model provided a rich set of biological predictors, including indicators of suicide, substance use disorder, mental health diagnoses and treatments, hypoxia and vascular damage, and demographics. Similar content being viewed by others

60 APPLIED LIFE SCIENCES↗
DOE OSTI2020

A Hybrid AI/ML and Computational Mechanics Based Approach for Time-Series State and Fatigue Life Estimation of Nuclear Reactor Components

Environmental fatigue modeling is a complex problem due to multiple failure modes and their intermixing. The failure modes are function of various underlying causes in addition to the corrosive effect of reactor coolant environment. Some of the major causes are time-dependence of material associated with cyclic loading, load sequence effect associated with random/variable amplitude loading, effect of strain amplitude and rates, effect of varying temperature (along both temporal and spatial directions) and the effect of mean strain and stress. The nonlinear intermixing of failure modes associated with above mentioned causing parameters makes the environmental fatigue modeling is a challenging task. Because of this challenge, fatigue is traditionally being modeled based on experimental data. However, test based empirical approach often requires hundreds of fatigue tests to model the above-mentioned intermixing failure causes even for a single material system. The problem is further exaggerated for reactor component made from multi-material systems such as made from both carbon and stainless-steel base metals and their similar and dissimilar metal welds. With the difficulty of conducting hundreds of fatigue tests to capture the above-mentioned intermixing failure causes, fatigue modeling approaches often depends on empirical models based on limited available test data such as available through ASME code and NUREG 6909. However, these limited test-data-based models may not be enough to accurately predict the life of reactor components. Accurate prediction of life of reactor component would become a necessity, particularly when the license of the reactors to be extended for long-term-operation (LTO) that is for well beyond its original design life of 40 years. The requirement of extending the license of reactor under LTO requires hundreds of fatigue tests to be conducted to understand the mechanism associated with the above-mentioned interdependent failure causes. However, conducting large number of fatigue tests is not a feasibility due to the cost involved. To address this issues Argonne National Laboratory (ANL) with the sponsorship of DOE Light Water Reactor Sustainability (LWRS) program trying to develop a hybrid predictive modeling approach. This is based on limited experiment-data, Artificial-intelligence (AI) – Machine-Learning (ML) - Deep-Learning (DL) based techniques and Multiphysics-computational-mechanics based modeling tools. The hybrid approach not-only can improve the accuracy of the existing stress analysis and fatigue modeling approach but also can reduce the over-dependency on test-based approach. Towards this goal following are some of the major contributions based on ANL’s FY-20 environmental fatigue modeling activities: 1) A cyclic plasticity material model database for 82/182 dissimilar metal weld, which can be readily shared with US nuclear industry and regulatory agency on request. 2) A well validated analytical modeling methodology to perform cycle-by-cycle stress prediction under both constant amplitude fatigue loading and variable amplitude fatigue loading (with load-sequence effect). 3) An AI/ML/DL based methodology to predict unmeasurable cyclic strain based on other available sensor signals. This type of approach can be used for estimating strain in real reactor components from other sensor readings. 4) An AI/ML based approach to improve the US capability on environmental fatigue testing. This is by improving ANL’s existing environmental fatigue testing capacity to conduct ASME required strain-controlled tests (by controlling strain amplitudes and its rate), while not measuring the strain (due to the difficulty of placing an extensometer in a narrow autoclave in a PWR-water-test system). 5) A simulation and experiment based probabilistic modeling methodology for time-series fatigue state and life estimation of reactor metal such as dissimilar metal weld.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2023

Climate-driven changes in the predictability of seasonal precipitation

Climate-driven changes in precipitation amounts and their seasonal variability are expected in many continental-scale regions during the remainder of the 21st century. However, much less is known about future changes in the predictability of seasonal precipitation, an important earth system property relevant for climate adaptation. Here, on the basis of CMIP6 models that capture the present-day teleconnections between seasonal precipitation and previous-season sea surface temperature (SST), we show that climate change is expected to alter the SST-precipitation relationships and thus our ability to predict seasonal precipitation by 2100. Specifically, in the tropics, seasonal precipitation predictability from SSTs is projected to increase throughout the year, except the northern Amazonia during boreal winter. Concurrently, in the extra-tropics predictability is likely to increase in central Asia during boreal spring and winter. The altered predictability, together with enhanced interannual variability of seasonal precipitation, poses new opportunities and challenges for regional water management.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2020

Consistency-Enhanced Evolution for Variable Selection Can Identify Key Chemical Information from Spectroscopic Data

In the last few decades, spectroscopic techniques such as near-infrared (NIR) spectroscopy have gained wide applications in several industries, such as the pharmaceutical, agricultural, oil, and gas industries. As a result, various soft sensors have been developed to predict sample properties from spectroscopic readings. Because the spectroscopic readings at different wavelengths, especially at the adjacent wavelengths, are highly correlated, it has been shown that variable selection could significantly improve a soft sensor’s prediction performance while reducing the model complexity. To improve the prediction performance, most variable selection methods focus on identifying the variables (i.e., wavelengths or wavelength segments) that are strongly correlated with the dependent variable. Although many successful applications have been reported, these variable selection methods do have their limitations. Specifically, the selected wavelengths sometimes show little connection to the chemical bounds or functional groups presenting in the sample. In addition, the selected variables can be quite sensitive to the choice of the training samples. In this work, we address these limitations from a different perspective: if a variable selection algorithm can identify the truly relevant input variables, it should consistently identify the same subset of variables regardless of the choice of the training samples. Therefore, we propose a variable selection method that aims to improve the consistency of variable selection resulting from different training samples. Furthermore, the new algorithm is termed consistency-enhanced evolution for variable selection (CEEVS). To demonstrate the performance and robustness of CEEVS, we compare the proposed method with three representative variable selection methods using five published NIR data sets. These case studies clearly demonstrate that by improving the variable selection consistency, we can not only achieve improved prediction performance, but also identify key chemical information from spectroscopic data.

42 ENGINEERING↗
DOE OSTI2026

Assessing the Accuracy of Property Model Predictions for Cost Optimization of Desalination Technologies

Accurate modeling of seawater thermophysical and thermodynamic properties is critical for optimizing desalination processes. This study compares three seawater property models, a Reaktoro multicomponent model, the thermophysical seawater properties library from the Massachusetts Institute of Technology, and a simplified sodium chloride model, in the context of levelized cost of water (LCOW) minimization for reverse osmosis (RO) and mechanical vapor compression systems. Process simulations and cost optimizations reveal that although all three models yield comparable LCOW and specific energy consumption (SEC) estimates under baseline conditions, deviations among their predictions increase with salinity. Relative differences in LCOW and SEC reach up to 6% and 8%, respectively. RO results show greater variability due to differences in osmotic pressure predictions, which affect pressure constraints at high recoveries. Computational performance varies substantially; specifically, Reaktoro simulations are up to 28 times slower than empirical models due to their detailed equilibrium calculations. These results suggest that empirical models offer acceptable accuracy for routine desalination process design, while Reaktoro provides advantages in scenarios requiring detailed speciation, such as scaling or pH adjustment studies. These findings underscore the importance of selecting appropriate property models based on the modeling objective of desalination applications and motivate future work integrating thermodynamic rigor with empirical efficiency.

Physical and chemical properties↗
DOE OSTI2020

Spectral Variability of VHS J1256–1257b from 1 to 5 μm

Multiwavelength time-resolved observations of rotationally modulated variability from brown dwarfs and giant exoplanets are the most effective method for constraining their heterogeneous atmospheric structures. In a companion paper, we reported the discovery of strong near-infrared variability in HST/WFC3/G141 light curves of the very red L-dwarf companion VHS J1256–1257b. In this paper, we present a follow-up 36 hr Spitzer/IRAC Channel 2 light curve together with an in-depth analysis of the Hubble space telescope (HST) and the Spitzer data. The combined data set provides time-resolved light curves of VHS1256b sampling 1.1 to 4.5 μm. The Spitzer light curve is best fit with a single sine wave with a period of 22.04 ± 0.05 hr and a peak-to-peak amplitude of 5.76 ± 0.04%. Combining the period with a previously measured projected rotational velocity (v sin i), we find that VHS1256b is most consistent with equatorial viewing geometry. The HST/G141+Spitzer spectral energy distribution favors a model with a T{sub eff} of 1000 K and low surface gravity with disequilibrium chemistry. The spectral variability of VHS1256b is consistent with predictions from partly cloudy models, suggesting that heterogeneous clouds are the dominant source of the observed modulations. We find evidence at the 3.3σ level for amplitude variations within the 1.67 μm CH{sub 4} band, which is the first such detection for a variable L-dwarf. We compare the HST/G141 time-resolved spectra of three red L-dwarfs with high-amplitude near-infrared rotational modulations and find that although their time-averaged spectra are similar, their spectroscopic variabilities exhibit notable differences. This diversity reinforces the advantage of time-resolved spectroscopic observations for understanding the atmospheres of brown dwarfs and directly imaged exoplanets.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2025

Simulating Isotropic Rayleigh Wave Horizontal to Vertical Ratios at Rock Valley

Elastic anisotropy in the subsurface can manifest from pre-existing structure or stress-induced cracking – both phenomena are of interest at the Rock Valley site in Nevada. The azimuthal dependence of Rayleigh wave ellipticity, also known as H/V, can reveal elastic anisotropy, but the effect of isotropic variability in H/V must first be accounted for. To that end, we simulate synthetic seismograms from a ring of sources in a fully 3-D isotropic velocity model that captures the geology at Rock Valley. We measure H/V from these waveforms and compare them with H/V predictions obtained using 1D models extracted at specific locations from the 3D model. We find that an average of the azimuthal H/V measurements from the 3-D simulations and 1-D predictions agree, but that the azimuthal variability of H/V is a large fraction of the mean value. These results estimate the noise character in azimuthal H/V so it can be factored out of future anisotropic simulations.

58 GEOSCIENCES↗
DOE OSTI2022

Detection of Forced Change Within Combined Climate Fields Using Explainable Neural Networks

Abstract Assessing forced climate change requires the extraction of the forced signal from the background of climate noise. Traditionally, tools for extracting forced climate change signals have focused on one atmospheric variable at a time, however, using multiple variables can reduce noise and allow for easier detection of the forced response. Following previous work, we train artificial neural networks to predict the year of single‐ and multi‐variable maps from forced climate model simulations. To perform this task, the neural networks learn patterns that allow them to discriminate between maps from different years—that is, the neural networks learn the patterns of the forced signal amidst the shroud of internal variability and climate model disagreement. When presented with combined input fields (multiple seasons, variables, or both), the neural networks are able to detect the signal of forced change earlier than when given single fields alone by utilizing complex, nonlinear relationships between multiple variables and seasons. We use layer‐wise relevance propagation, a neural network explainability tool, to identify the multivariate patterns learned by the neural networks that serve as reliable indicators of the forced response. These “indicator patterns” vary in time and between climate models, providing a template for investigating inter‐model differences in the time evolution of the forced response. This work demonstrates how neural networks and their explainability tools can be harnessed to identify patterns of the forced signal within combined fields.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2026

Experimental protocol for phase 1 of the APARC QUOCA (QUasibiennial oscillation and Ozone Chemistry interactions in the Atmosphere) working group

The quasi-biennial oscillation (QBO) is the main mode of variability in the tropical stratosphere, influencing the predictability of other regions in the atmosphere through its teleconnections to the stratospheric polar vortices and coupling to surface tropical and extratropical variability. However, climate and forecasting models consistently underestimate QBO amplitudes in the lower stratosphere, likely contributing to their failure to simulate these teleconnections. One underexplored contributor to model biases is missing representation of ozone-radiative feedbacks, which enhance temperature variability in the lower stratosphere, particularly at periods at and greater than the QBO (>28 months). While previous studies suggest that ozone-radiative feedbacks can impact QBO periods, amplitudes and the associated secondary circulation in the lower stratosphere, the reported impacts differ widely among models and are hard to interpret due to differences in methodology. To this end, here we propose a coordinated experimental protocol – held joint between the Atmospheric Processes and their Role in Climate (APARC) Quasi-Biennial Oscillation Initiative (QBOi) and Chemistry Climate Modeling Initiative (CCMI) activities – which is aimed at assessing the coupling between stratospheric ozone, temperature and the circulation. We use the proposed experiments to define the ozone feedback on the QBO in both present-day and idealized (abrupt quadrupling of carbon dioxide) climates. While primary focus is on the QBO, the proposed protocol also enables analysis of other aspects of ozone-radiative-dynamical coupling in the atmosphere, including impacts on the Brewer-Dobson Circulation and tropospheric eddy-driven jet responses to future climate change. Here we document the scientific rationale and design of the QUOCA Phase 1 experiments, summarize the data request, and give a brief overview of participating models. Preliminary results using the NASA Goddard Institute for Space Studies E2-2 climate model are used to illustrate sensitivities to certain methodological choices.

Environmental sciences↗
DOE OSTI2022

Release Timing and Duration Control the Fate of Photolytic Compounds in Stream-Hyporheic Systems

Predicting environmental fate requires an understanding of the underlying, spatiotemporally variable interaction of transport and transformation processes. Photolytic compounds, for example, interact with both time-variable photolysis and the perennially dark hyporheic zone, generating potentially unexpected dynamics that arise from time-variable reactivity. This interaction has been found to significantly impact environmental fate but is commonly oversimplified in predictive models. Our primary objective was to explore how time-variable photolysis and hyporheic storage interact across a range of photolysis rates to control the fate and transport of photolytic solutes in stream-hyporheic systems. In this study, we released a photolytic compound in a natural system at different times of day and simulated variable release timing and durations of photolytic compounds spanning half-lives ranging from about 2 min to 900 hr. To contextualize these results, we simulated five photolytic compounds with varied half-lives to systematically study the interaction between release timing, duration, and reactivity. We found that the environmental fate and transport of photolytic compounds are highly variable as a function of release timing, which controls when, where, and for how long solute is stored in the hyporheic zone or exposed to in-channel photolysis. Finally, this knowledge can be used to improve predictions for photolytic compounds or assess potential impacts for an anticipated discharge or treatment.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2024

A general mechanistic framework for cross-scale understanding of hot spots and hot moments in carbon and water fluxes

Semi-arid ecosystems, like those in the American Southwest, exert a massive impact on the interannual variability of carbon and water cycling. Unfortunately, these carbon and water fluxes are notoriously difficult to predict due to their high spatial and temporal variability, which is poorly captured by the current generation of vegetation models. Indeed, this region is exemplified by the ‘hot spots and hot moments’ concept, which states that small areas in space (‘hot spots’) and transient moments in time (‘hot moments’) exert an outsized influence on biogeochemical cycling. However, the factors that regulate these pulses in biogeochemical activity are unknown, as is their variability across space and time. These uncertainties severely limit efforts to better represent hot spots and hot moments in models. Here, we seek to develop a generalized method for detecting and quantifying the importance of hot spots and hot moments from individual plant to regional scales. Underpinning this method is our recently developed statistical approach for identifying hot spots and hot moments. By applying this method to semi-continuous measurements of plant water status, a depth profile of soil water potential, and ecosystem fluxes via eddy covariance, we will track the fate of water through the soil-plant-atmosphere continuum and identify the mechanistic drivers of these transient pulses in biogeochemical activity. Then, we will expand this approach across a broad network of Ameriflux towers, and apply a machine learning approach that will allow us to upscale measurements of hot spots and hot moments across the American Southwest and quantify their impact on carbon and water cycles. These products will allow us to identify hot spots and hot moments across spatio-temporal scales and will serve as crucial data sources for validating a new generation of models that can better capture highly dynamic carbon and water fluxes. The proposed method will be easily transferable across biomes and will serve as a framework for future research on hot spots and hot moments across the plant ecophysiology, biometeorology, and vegetation modeling communities.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2025

Deep Learning for Subsurface Flow: A Comparative Study of U‐Net, Fourier Neural Operators, and Transformers in Underground Hydrogen Storage

Subsurface flow research is essential for the sustainable management of natural resources and the environment. Deep learning (DL) has significantly advanced this field by developing efficient and accurate surrogate models to replace computationally expensive physics‐based simulations. These surrogate models are commonly used to predict the spatiotemporal evolution of state variables, such as gas saturation and reservoir pressure, in heterogeneous geological formations. Despite the various DL models applied to this task, there is a lack of studies systematically comparing their performance. This absence of comparative analysis leads to somewhat arbitrary DL model selection in subsurface flow research, resulting in suboptimal performance and potentially inaccurate predictions. To bridge this gap, we conduct a systematic comparison study of three popular DL architectures—U‐Net, Fourier Neural Operators (FNO), and Segmentation Transformer (SETR)—in surrogate modeling of underground hydrogen storage (UHS). We focus on UHS due to its promise of enhancing clean energy resilience and its cyclic operational conditions that represent common scenarios in various subsurface applications. We evaluate the models based on accuracy, training cost, and inference speed. The comparison shows that U‐Net achieves the highest accuracy, followed by SETR and FNO. Despite its lower accuracy, FNO has the highest inference speed. SETR offers competitive accuracy with the least training memory usage, demonstrating the potential of transformers in learning subsurface flow. Our results provide guidance for selecting DL models for surrogate modeling in a wide range of subsurface flow problems.

42 ENGINEERING↗
DOE OSTI2023

Machine Learning for Daily Forecasts of Arctic Sea Ice Motion: An Attribution Assessment of Model Predictive Skill

Physics-based simulations of Arctic sea ice are highly complex, involving transport between different phases, length scales, and time scales. Resultantly, numerical simulations of sea ice dynamics have a high computational cost and model uncertainty. We employ data-driven machine learning (ML) to make predictions of sea ice motion. The ML models are built to predict present-day sea ice velocity given present-day wind velocity and previous-day sea ice concentration and velocity. Models are trained using reanalysis winds and satellite-derived sea ice properties. We compare the predictions of three different models: persistence (PS), linear regression (LR), and a convolutional neural network (CNN). We quantify the spatiotemporal variability of the correlation between observations and the statistical model predictions. Additionally, we analyze model performance in comparison to variability in properties related to ice motion (wind velocity, ice velocity, ice concentration, distance from coast, bathymetric depth) to understand the processes related to decreases in model performance. Results indicate that a CNN makes skillful predictions of daily sea ice velocity with a correlation up to 0.81 between predicted and observed sea ice velocity, while the LR and PS implementations exhibit correlations of 0.78 and 0.69, respectively. The correlation varies spatially and seasonally: lower values occur in shallow coastal regions and during times of minimum sea ice extent. LR parameter analysis indicates that wind velocity plays the largest role in predicting sea ice velocity on 1-day time scales, particularly in the central Arctic. Regions where wind velocity has the largest LR parameter are regions where the CNN has higher predictive skill than the LR.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2021

EPIsembleVis: A geo-visual analysis and comparison of the prediction ensembles of multiple COVID-19 models

In this work, we present EPIsembleVis, a web-based comparative visual analysis tool for evaluating the consistency of multiple COVID-19 prediction models. Our approach analyzes a collection of COVID-19 predictions from different epidemiological models as an ensemble and utilizes two metrics to quantify model performance. These metrics include (a) prediction uncertainty (represented as the dispersion of predictions in each ensemble) and (b) prediction error (calculated by comparing individual model predictions with the recorded data). Through an interactive visual interface, our approach provides a data-driven workflow for (a) selecting and constructing the COVID-19 model prediction ensemble based on the spatiotemporal overlap of available predictions of multiple epidemiological models, (b) quantifying the model performance using both the uncertainty of each model prediction ensemble, and the error of each ensemble member that represents individual model predictions, and (c) visualizing the spatiotemporal variability in the projection performance of individual models using a suite of novel ensemble visualization techniques, such as the data availability map, a spatiotemporal textured-tile calendar, multivariate rose chart, and time-series leaflet glyph. We demonstrate the capability of our ensemble visual interface through a case study that investigates the performance of weekly COVID-19 predictions, which are provided through the COVID-19 Forecast Hub UMass-Amherst Influenza Forecasting Center of Excellence [47] for the United States and United States Territories. The EPIsembleVis tool is implemented using open-source web technologies and adaptive system design, rendering it interoperable with Elasticsearch and Kibana for automatically ingesting COVID-19 predictions from online repositories, and it is generalizable for analyzing worldwide projections from more epidemiological models.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2023

Microbial metabolic dependency and its impacts on the soil carbon cycle (Final Technical Report, DE-SC0016364)

The terrestrial biosphere contains a large fraction of global carbon (C) and nearly 70% of the organic C in terrestrial systems is found in soils. Global changes in atmospheric CO 2 , temperature, precipitation, and ecosystem N inputs, will impact primary production and carbon inputs to soils, but it remains difficult to predict soil responses to these environmental conditions. Our ability to predict C-cycle responses to global change remains limited by unexplained variability within the terrestrial C-cycle. Our difficulty in predicting responses of the soil C-cycle to environmental change suggests a need for a greater understanding of the biotic mechanisms that govern soil C-transformations. Changes in microbial community structure and function have been proposed to impact soil processes, but mechanistic connections between microbial activity and C-cycle transformations remain poorly described. We assembled an interdisciplinary team to conduct cross-scale examination of microbial contributions to C-cycle dynamics and C-fate in soils. We investigated microbial contributions to soil C-transformations using a suite of complementary isotopic techniques including DNA-Stable Isotope Probing (DNA-SIP), metagenomic-SIP, metabolomic-SIP, proteomic-SIP, and microspatial analysis of soil organic C. These techniques were deployed in experiments that tested fundamental assumptions that underlie terrestrial C-cycle models. We characterized the functional characteristics of soil microorganisms responsible for major C-transformations in soil, evaluated the metabolic and ecological interactions that underlie soil C-cycle dynamics, and evaluated the degree to which these interactions impact rates of C mineralization and stabilization in soils.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2024

Integrating multi-modal remote sensing, deep learning, and attention mechanisms for yield prediction in plant breeding experiments

In both plant breeding and crop management, interpretability plays a crucial role in instilling trust in AI-driven approaches and enabling the provision of actionable insights. The primary objective of this research is to explore and evaluate the potential contributions of deep learning network architectures that employ stacked LSTM for end-of-season maize grain yield prediction. A secondary aim is to expand the capabilities of these networks by adapting them to better accommodate and leverage the multi-modality properties of remote sensing data. In this study, a multi-modal deep learning architecture that assimilates inputs from heterogeneous data streams, including high-resolution hyperspectral imagery, LiDAR point clouds, and environmental data, is proposed to forecast maize crop yields. The architecture includes attention mechanisms that assign varying levels of importance to different modalities and temporal features that, reflect the dynamics of plant growth and environmental interactions. The interpretability of the attention weights is investigated in multi-modal networks that seek to both improve predictions and attribute crop yield outcomes to genetic and environmental variables. This approach also contributes to increased interpretability of the model's predictions. The temporal attention weight distributions highlighted relevant factors and critical growth stages that contribute to the predictions. The results of this study affirm that the attention weights are consistent with recognized biological growth stages, thereby substantiating the network's capability to learn biologically interpretable features. Accuracies of the model's predictions of yield ranged from 0.82-0.93 R 2 ref in this genetics-focused study, further highlighting the potential of attention-based models. Further, this research facilitates understanding of how multi-modality remote sensing aligns with the physiological stages of maize. The proposed architecture shows promise in improving predictions and offering interpretable insights into the factors affecting maize crop yields, while demonstrating the impact of data collection by different modalities through the growing season. By identifying relevant factors and critical growth stages, the model's attention weights provide valuable information that can be used in both plant breeding and crop management. The consistency of attention weights with biological growth stages reinforces the potential of deep learning networks in agricultural applications, particularly in leveraging remote sensing data for yield prediction. To the best of our knowledge, this is the first study that investigates the use of hyperspectral and LiDAR UAV time series data for explaining/interpreting plant growth stages within deep learning networks and forecasting plot-level maize grain yield using late fusion modalities with attention mechanisms.

59 BASIC BIOLOGICAL SCIENCES↗