SEARCH · Engineering Papers

Results for “Data Driven Analysis”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 1,117 records · Page 62

All sources NASA NTRS DOE OSTI

DOE OSTI2022

Neural Network-Based Electric Vehicle Range Prediction for Smart Charging Optimization

Range prediction is a standard feature in most modern road vehicles, allowing drivers to make informed decisions about when to refuel. Most vehicles make range predictions through data- or model-driven means, monitoring the average fuel consumption rate or using a tuned vehicle model to predict fuel consumption. The uncertainty of future driving conditions makes the range prediction problem challenging, particularly for less pervasive battery electric vehicles (BEV). Most contemporary machine learning-based methods attempt to forecast the battery SOC discharge profile to predict vehicle range. In this work, we propose a novel approach using two recurrent neural networks (RNNs) to predict the remaining range of BEVs and the minimum charge required to safely complete a trip. Each RNN has two outputs that can be used for statistical analysis to account for uncertainties; the first loss function leads to mean and variance estimation (MVE), while the second results in bounded interval estimation (BIE). These outputs of the proposed RNNs are then used to predict the probability of a vehicle completing a given trip without charging, or if charging is needed, the remaining range and minimum charging required to finish the trip with high probability. Training data was generated using a low-order physics model to estimate vehicle energy consumption from historical drive cycle data collected from medium-duty last-mile delivery vehicles. Here, the proposed method demonstrated high accuracy in the presence of day-to-day route variability, with the root-mean-square error (RMSE) below 6% for both RNN models.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

DOE OSTI2025

Machine learning-driven predictive resource management in complex science workflows

Here, the collaborative efforts of large communities in science experiments, often comprising thousands of global members, reflect a monumental commitment to exploration and discovery. Recently, advanced and complex data processing has gained increasing importance in science experiments. Data processing workflows typically consist of multiple intricate steps, and the precise specification of resource requirements is crucial for each step to allocate optimal resources for effective processing. Estimating resource requirements in advance is challenging due to a wide range of analysis scenarios, varying skill levels among community members, and the continuously increasing spectrum of computing options. One practical approach to mitigate these challenges involves initially processing a subset of each step to measure precise resource utilization from actual processing profiles before completing the entire step. While this two-staged approach enables processing on optimal resources for most of the workflow, it has drawbacks such as initial inaccuracies leading to potential failures and suboptimal resource usage, along with overhead from waiting for initial processing completion, which is critical for fast-turnaround analyses. In this context, our study introduces a novel pipeline of machine learning models within a comprehensive workflow management system, the Production and Distributed Analysis (PanDA) system. These models employ advanced machine learning techniques to predict key resource requirements, overcoming challenges posed by limited upfront knowledge of characteristics at each step. Accurate forecasts of resource requirements enable informed and proactive decision-making in workflow management, enhancing the efficiency of handling diverse, complex workflows across heterogeneous resources.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2022

Automated bubble analysis of high-speed subcooled flow boiling images using U-net transfer learning and global optical flow

Capturing and analyzing the bubble dynamics is crucial to improving the understanding of boiling heat transfer mechanisms and predicting boiling heat transfer coefficient and boiling crisis. High speed video (HSV) imaging has been used for decades towards this end. Still, there is no universal approach to quantitatively analyze bubble dynamics from HSV images. In this study, we propose a data-driven post-processing approach to segment, track, and identify wall-attached vapor bubbles from HSV images of the boiling process in subcooled flow conditions. Firstly, we employ a transfer learning framework with a U-Net-based convolution neural network (CNN) architecture to detect and segment bubbles in HSV images of diverse contrast and surface texture using very little data (e.g., 10 images) for training. Then, we evaluate the trained CNN model with 100 ground-truth images, and the validation results show that the model accuracy and precision in detecting the optical footprint of bubbles are higher than 90%. Finally, we suggest a criterion to identify a condensing bubble based on the divergence of the bubble displacement, which is calculated from sequential segmented bubble images using a global optical flow code. Using this combination of machine learning and optical flow, we can identify nucleation sites and track the growth of bubbles nucleating at each site to quantify nucleation site density, nucleation frequency, and other fundamental boiling parameters. The proposed system is validated using results obtained on a special heater, which enables both infrared (IR) thermometry and HSV imaging on a metallic surface. We compare the fundamental boiling parameters obtained by the two different diagnostics. The results show good agreement. In conclusion, the difference between the measurements of nucleation site density, averaged nucleation frequency, and averaged growth time performed with the two techniques is always within ± 20% and mostly ± 10% of the values measured with IR thermometry.

42 ENGINEERING↗

DOE OSTI2023

Integrated data-driven and experimental approaches to accelerate lead optimization targeting SARS-CoV- 2 main protease

Identification of potential therapeutic candidates can be expedited by integrating computational modeling with domain aware machine learning (ML) approaches followed by experimental validation. Generative deep learning models have been recently developed that can generate thousands of new candidates, but their physiochemical properties are typically not optimized. Using our deep learning models and a scaffold as a starting point, we generated tens of thousands of compounds for SARS-CoV-2 M pro that preserve the core scaffold. Here we utilized and implemented several computational tools such as structural alert and toxicity analysis, high throughput virtual screening, ML-based 3D quantitative structure–activity relationships, multi-parameter optimization, and graph neural networks on libraries of generated candidates to predict biological activity and binding affinity a priori. From these collective computational results, eight promising candidates were identified and tested experimentally using Native Mass Spectrometry (MS) and FRET-based functional assays. Two compounds, with quinazoline-2-thiol and acetylpiperidine core moiety showed IC 50 values in the low micromolar range: 2.95±0.0017 µM and 3.41±0.0015 µM, respectively. The molecular dynamics simulations further highlight that binding of these compounds results in allosteric modulations in the chain B and the interface domains of the M pro . The key fragments from these top hits can be used as input for closed loop lead optimization in the integrated pipeline.

60 APPLIED LIFE SCIENCES↗

DOE OSTI2022

Heterogeneous Visualization: A Call for Empirically Driven Technology Advancement and Adoption; Preprint

Our ability to generate data from simulations and experimental platforms is generally outpacing our ability to analyze those data efficiently and effectively. There are a growing number and variety of possible visualization display modalities, from commodity head-mounted displays to large-scale immersive environments, from desktop and touch displays to high-resolution display walls. Many of these visualization technologies and visual environments are rapidly evolving and could revolutionize analysis for certain classes of complex scientific and engineering data. However, the choice of what technology or combination of technologies to use has historically been largely ad hoc and lacks a carefully validated understanding of how to best utilize different visualization technologies to advance the science. To maximize the impact of our data and analyses, it is imperative that we use the most effective visualization environments for the analysis task at hand.

heterogeneous visualization↗

DOE OSTI2021

Quantitative concentration measurements in a turbulent helium jet using rainbow schlieren deflectometry

Rainbow schlieren deflectometry (RSD) is applied to acquire quantitative concentration measurements in a turbulent environment for the first time. RSD methodology is developed and validated using Rayleigh scattering data available in the literature. Experiments were performed in an initially laminar, momentum-driven helium jet injected into ambient air. Full-field measurements are acquired that span the laminar, transition, and fully turbulent regions of the jet. Furthermore, the RSD results are shown to provide accurate measurements in each region and also confirm the self-similar nature of the fully turbulent jet. Analysis shows that the transition from laminar to turbulent flow occurs across an axial span that decreases with increasing Reynolds number. Experiments with a long exposure time were conducted to evaluate the limitations of hardware averaging of the RSD signal in comparison with software averaging.

02 PETROLEUM↗

DOE OSTI2026

Spatial and temporal characterization of municipal solid waste based on resource recovery pathways

This study presents a two-year, quarterly assessment of MSW across four source sectors (residential, schools, restaurants, and grocery stores) from sixteen sites across five U.S. states. MSW was manually sorted into 27 categories and aggregated into pathway fractions: high-moisture (HM) organics, low-moisture (LM) organics, recyclable (RC) materials, and residuals for disposal. Organics represented 89 % of the MSW stream. The largest fraction was HM organics consisting of food waste (31 %) and yard waste (3 %), with large coefficient of variations (CV), 79 and 278 %, respectively, reflecting high seasonal and site variability that varied significantly (p < 0.01) across sampling periods. The HM fraction showed properties favorable for anaerobic digestion, with moisture content ranging from 56 to 95 % and volatile solids ranges of 86-95 %. In contrast, the LM and RC fractions remained more stable (plastics CV = 41 %; paper CV = 53 %) with heating values up to 26.9 MJ/kg across sources, reflecting suitability for gasification. Microstructural analysis revealed less porosity in residential waste sampled at the landfill, which can influence preprocessing efficiency and microbial accessibility. Pathway informed allocations showed that 35 % of MSW is suitable for anaerobic digestion, 36 % for gasification, and 18 % for recycling, leaving 11 % requiring landfill disposal. These results provide quantitative evidence to determine feedstock allocation, waste-to-energy system design, and the development of data-driven sustainability and resource recovery strategies within a circular bioeconomy.

09 BIOMASS FUELS↗

DOE OSTI2022

Cavity evolution and void swelling in dual ion irradiated tempered martensitic steels

Microstructural evolutions in two variants of the F82H 8 wt%Cr tempered martensitic steel under dual (He + plus Fe 3+ ) ion irradiations at 500 °C have been characterized by transmission electron microscopy. Emphasis is on understanding the combined effects of displacements per atom (dpa) and the helium/dpa ratio (He/dpa) on cavity evolution and void swelling (f v ). The dual ion database includes 231 alloy-dpa-He/dpa conditions for irradiations up to ~ 82 dpa and 3700 appm helium. Here, we hypothesize that the large “scatter” observed in the f v data is primarily due to local microstructural variations, especially those that shield regions at shallower depths from the effects of injected interstitial atoms, which would otherwise reduce f v . More generally, our hypothesis is that the highest f v data, at a specified dpa and He/dpa, provides the most appropriate estimate of swelling for fusion neutron irradiation conditions. The dose dependence of f v can be described by an incubation dpa i , marking the onset of significant void growth, and a post-incubation swelling rate, f v ’ = Δf v /Δdpa. Both dpa i and f v ’ decrease with increasing He/dpa. The f v ’ data are quantitatively consistent with a simple model for defect partitioning between evolving bubble, void, and dislocation sinks strengths and biases. Most notably, the model correctly predicts both the incubation dpa i , and the subsequent f v ’, in spite of the fact that they reflect somewhat different physics. Our analysis also suggests that defect recombination is modest at 500 °C. Along with other considerations, this supports the hypothesis that, even at high dpa rates, dual ion irradiations can be used to reasonably emulate void nucleation and growth for a range of fusion-relevant neutron irradiation service conditions. A companion paper incorporates the results of this study in a reduced-order, data-driven void swelling model.

36 MATERIALS SCIENCE↗

DOE OSTI2026

A simulation framework for evaluating electronic order workflows in integrated health records

Electronic health record (EHR) systems are critical to modern healthcare delivery, yet the dynamic workflows that govern electronic order processing remain underexplored. Inefficiencies in these digital pathways can cause delays in care, repetitive workloads, and even patient harm. This study presents a discrete-event simulation framework used to reconstruct and evaluate EHR-based order workflows in a large integrated healthcare system. Using real-world data extracted from the Veterans Health Administration’s Corporate Data Warehouse, the authors mapped order events to standardized state transitions and modeled their progression across different facilities of varying complexity levels. After being calibrated with empirical distributions of transition times and validated against observed time-in-system metrics, the simulation demonstrates close alignment with historical performance. Scenario analyses reveal that resource capacity constraints significantly amplify the impact of electronic order surges, which are reflected in the disproportionate growth in backlogs and processing delays. Adjustments in transition probabilities further increased recirculation and extended workflow paths. Network-based analysis identified Reserved, InProgress, and Completed as structurally critical states that function as hubs within the process network but the transitions in-between also act as major bottlenecks. These results showcased the effectiveness of simulation-based approaches in monitoring EHR order processing performance and evaluating consequences of workflow changes on healthcare network resources planning. The proposed simulation framework provides a scalable data-driven tool to support operational decision-making and improve the efficiency of electronic order management in complex healthcare environments.

Engineering↗

DOE OSTI2023

Toward implementing autonomous adaptive data acquisition for scanning hyperspectral imaging of biological systems

Autonomous experimentation is an emerging area of research, primarily related to autonomous vehicles, scientific combinatorial discovery approaches in materials science and drug discovery, and iterative research loops of planning, experimentation, and analysis. However, autonomous approaches developed in these contexts are difficult to apply to high-dimensional mapping technologies, such as scanning hyperspectral imaging of biological systems, due to sample complexity and heterogeneity. We briefly cover the history of adaptive sampling algorithms and surrogate modeling in order to define autonomous adaptive data acquisition as an objective-based, flexible building block for future biological imaging experimentation driven by intelligent infrastructure. We subsequently summarize the recent implementations of autonomous adaptive data acquisition (AADA) for scanning hyperspectral imaging, assess how these address the difficulties of autonomous approaches in hyperspectral imaging, and highlight the AADA design variation from a goal-oriented perspective. Finally, we present a modular AADA architecture that embeds AADA-driven flexible building blocks to address the challenge of time resolution for high-dimensional scanning hyperspectral imaging of nonequilibrium dynamical systems. In our example research-driven experimental design case, we propose an AADA infrastructure for time-resolved, noninvasive, and label-free scanning hyperspectral imaging of living biological systems. This AADA infrastructure can accurately target the correct state of the system for experimental workflows that utilize subsequent expensive, high-information-content analytical techniques.

59 BASIC BIOLOGICAL SCIENCES↗

DOE OSTI2025

Spatially resolved charge-transfer kinetics at the quantum dot–microbe interface using fluorescence lifetime imaging microscopy

Integrating the optoelectronic properties of quantum dots (QDs) with biological enzymatic systems to form microbe-semiconductor biohybrids offers promising prospects for both solar-to-chemical conversion and light-modulated biochemical processes. Developing these nano–bio hybrid systems necessitates a deep understanding of charge-transfer dynamics at the nano–bio interface. Photoexcited carrier transfer from QDs to microbes is driven by complex interactions, with emerging insights into the relevant thermodynamic and kinetic factors. The heterogeneities of both microbes and QD ensembles pose significant challenges in mechanistic understanding, which is critical for designing advanced nano–bio hybrids. We used fluorescence lifetime imaging microscopy to analyze charge transfer between a CdSe QD film andShewanella oneidensismicrobes. We correlated the spatiotemporal fluorescence data with an analytical model. Our analysis revealed two distinct distributions of QD de-excitation pathways. The characteristics of these distributions: 1) a faster transfer rate ( k ¯ E T 1 = 1.5 10 9 s - 1 ), with a lower acceptor number ( N ¯ a 1 = 0.03 ) and 2) a slower transfer rate ( k ¯ E T 2 = 4.1 10 8 s - 1 ) with a higher acceptor number ( N ¯ a 2 = 0.18 ). We assign these distributions to the indirect and direct electron transfer mechanisms, respectively. Our findings demonstrate how spectroscopic imaging can uncover fundamental electron transfer mechanisms at complex interfaces, offering valuable design principles for future nano–bio hybrids.

Science & Technology - Other Topics↗

DOE OSTI2020

Uncertainty Quantification for Capacity Expansion Planning

This report quantifies the uncertainty in output decisions from a Capacity Expansion Planning (CEP) model. The need to understand how uncertainties within CEP models and modeling assumptions affect Quantities of Interest (QoIs) such as expansion and operating costs, as well as expansion decisions remains an ongoing challenge in scientific research and industrial operations. This area of research is particularly important for models which seek to capture how large networks will evolve and operate under increased sources of variable generation, i.e., higher penetration of renewable technologies such as solar and wind generators. Uncertainty quantification (UQ) of CEP models which estimate expansion costs and decisions, and production cost models which estimate operating costs and dispatch decisions, is a key focus of research at NREL. The Regional Energy Deployment System (ReEDS) represents a state-of-the-art CEP model and considers a range of possible grid evolutions in an attempt to identify key drivers, ramifications, and decisions which contribute to better informed investment and policy decisions. However, research to quantify how uncertainties and model assumptions, such as unit commitment (UC), within ReEDS may be affecting its outputs remains challenging due to to size and complexity of the model

24 POWER TRANSMISSION AND DISTRIBUTION↗

DOE OSTI2025

Model Development and Analysis of a High-Fidelity Neutron Transport Sensor: The Quadrupole Detector Concept for Measurement of the Neutron Flux Gradient

Accurate reconstruction of the neutron flux distribution within a reactor core is essential for safe and efficient reactor operation. Traditional power shape synthesis in Light Water Reactors relies on hundreds of in-core detectors. However, this approach becomes impractical for Advanced Reactors and Microreactors due to limited space and harsh environments. To address this challenge, we propose a data-driven methodology that combines high-fidelity modeling with real-time ex-core sensor measurements, enabling the reconstruction of core power distribution while minimizing the reliance on intrusive in-core instrumentation. This project began in FY24 and achieved two initial milestones: (1) the definition of a three-year development plan for a Digital Twin framework and (2) the development of high-fidelity neutronics models of the Purdue University Reactor One (PUR-1) using both MCNP6 and OpenMC. The PUR-1 reactor, a zero-power facility, was selected due to its suitability for neutronics-focused modeling and the availability of experimental data for validation. Both models were benchmarked using neutron flux measurements obtained from irradiated gold foils, which were strategically placed within the core during a dedicated campaign in July 2024. This report marks the continuation and completion of those foundational tasks. The OpenMC model has been refined (improved geometric accuracy, expanded cross-section libraries, and refined sampling) and validated using additional experimental data. An updated sensor design—based on quadrupole configuration—was designed to measure both ex-core flux and its spatial gradient. These measurements will serve as inputs to a neural network-based reconstruction algorithm. Finally, the methodology was demonstrated on a two-dimensional test case representative of the heterogeneous material composition of the PUR-1 reactor core. A neural network implementation of the Kirchhoff-Helmholtz integral equation was employed to solve the boundary value problem using peripheral sensor measurements. The preliminary results confirm the strong potential of the proposed approach for accurate and minimally invasive neutron flux reconstruction.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

NASA NTRS1997

Interannual Variability in Soil Trace Gas (CO2, N2O, NO) Fluxes and Analysis of Controllers

Interannual variability in flux rates of biogenic trace gases must be quantified in order to understand the differences between short-term trends and actual long-term change in biosphere-atmosphere interactions. We simulated interannual patterns (1983-1988) of global trace gas fluxes from soils using the NASA Ames model version of CASA (Carnegie-Ames-Stanford Approach) in a transient simulation mode. This ecosystem model has been recalibrated for simulations driven by satellite vegetation index data from the NOAA Advanced Very High Resolution Radiometer (AVHRR) over the mid-1980s. The predicted interannual pattern of soil heterotropic CO2 emissions indicates that relatively large increases in global carbon flux from soils occurred about three years following the strong El Nino Southern Oscillation (ENSO) event of 1983. Results for the years 1986 and 1987 showed an annual increment of +1 Pg (1015 g) C-CO2 emitted from soils, which tended to dampen the estimated global increase in net ecosystem production with about a two year lag period relative to plant carbon fixation. Zonal discrimination of model results implies that 80-90 percent of the yearly positive increments in soil CO2 emission during 1986-87 were attributable to soil organic matter decomposition in the low-latitudes (between 30 N and 30 S). Soils of the northern middle-latitude zone (between 30 N and 60 N) accounted for the residual of these annual increments. Total annual emissions of nitrogen trace gases (N2O and NO) from soils were estimated to vary from 2-4 percent over the time period modeled, a level of variability which is consistent with predicted interannual fluctuations in global soil CO2 fluxes. Interannual variability of precipitation in tropical and subtropical zones (30 N to 20 S appeared to drive the dynamic inverse relationship between higher annual emissions of NO versus emissions of N2O. Global mean emission rates from natural (heterotrophic) soil sources over the period modeled (1983-1988) were estimated at 57.1 Pg C-CO2yr-1, 9.8Tg (1012 g) N-NO yr-1, and 9.7 Tg N-N2O yr-1. Chemical fertilizer contributions to global soil N gas fluxes were estimated at between 1.3 to 7.3 Tg N-NO yr-1, and 1.2 to 4.0 Tg N-N2O yr-1.

Potter, C.↗

NASA NTRS2021

Cosmology with the Roman Space Telescope - Multiprobe Strategies

We simulate the scientific performance of the Nancy Grace Roman Space Telescope High Latitude Survey (HLS) on dark energy and modified gravity. The 1.6-yr HLS Reference survey is currently envisioned to image 2000 deg2 in multiple bands to a depthof∼26.5 in Y, J, H and to cover the same area with slit-less spectroscopy beyond z=3. The combination of deep, multiband photometry and deep spectroscopy will allow scientists to measure the growth and geometry of the Universe through a variety of cosmological probes (e.g. weak lensing, galaxy clusters, galaxy clustering, BAO, Type Ia supernova) and, equally, it will allow an exquisite control of observational and astrophysical systematic effects. In this paper, we explore multiprobe strategies that can be implemented, given the telescope’s instrument capabilities. We model cosmological probes individually and jointly and account for correlated systematics and statistical uncertainties due to the higher order moments of the density field. We explore different levels of observational systematics for the HLS survey (photo-z and shear calibration) and ultimately run a joint likelihood analysis in N-dim parameter space. We find that the HLS reference survey alone can achieve a standard dark energy FoM of>300 when including all probes. This assumes no information from external data sets, we assume a flat universe however, and includes realistic assumptions for systematics. Our study of the HLS reference survey should be seen as part of a future community-driven effort to simulate and optimize the science return of the Roman Space Telescope.

Cosmological parameters↗

NASA NTRS2022

The Mars 2020 Ground Data System Architecture

The Mars 2020 Mission’s primary objective is to collect 20 geographically unique samples during its prime mission of one and a quarter Martian years, or just over 2 Earth years. Mission planners determined the project needed to develop a system that would enable the operations team to analyze engineering and science data, make science decisions, select viable rover targets at a millimeter resolution and validate an uplink bundle for a car sized rover with more complex science instruments than any previous Mars surface mission. All this had to be done within a five hour time frame. Doing this with a small team would be a challenge, but this had to be accomplished by a large team of engineers and scientists located across North America and Europe. Achieving this level of operational efficiency was unheard of in the prime mission. In addition, the mission had another set of requirements that had nothing to do with surface operations; the Mars 2020 Ground Data System (GDS) was also expected to comply with a new set of security requirements to keep up with the ever changing cybersecurity landscape. The Mars 2020 Ground Data System (GDS) is a re-architected version of the Mars Science Laboratory GDS. The primary goal was to integrate the lessons learned from previous Mars surface missions, accommodate a set of new requirements and capabilities required to ensure mission success, and comply with a new set of cybersecurity controls. The new architecture includes several unique qualities including a data lake, language-agnostic system-wide event-based operations, containerization, automated deployment, network segmentation, infrastructure-as-code, API-driven interfaces, and the first Mars surface GDS to operate primarily in the cloud. The new architecture enabled greater access to the system’s data, tighter integration with the operations team, and a higher level of traceability. The availability of the data also enabled a new set of capabilities previously not possible on surface missions. These new capabilities include an autonomous data to information, pipeline for downlink analysis, horizontal scaling of science data processing capabilities, autonomous round trip data tracking of science and engineering data, integration of flight system state into the tactical planning cycle, high fidelity targeting utilizing kinematic data, and hierarchical image and 3d meshes data representations. This paper will introduce the requirements for the Mars 2020 Mission, the heritage architecture, and the rationale for the changes to achieve the new architecture. The paper will continue to describe the fundamental changes made to the GDS architecture, how these changes enabled a more tightly integrated GDS, and the new capabilities that were enabled by the new architecture. The paper will conclude with the lessons learned from the process of rearchitecting a heritage GDS system and from the first 200 days of operations supporting over 800 users from around the world.

Lopez-Roig, Reynaldo↗

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 OSTI2024

Ensemble modeling of global lake evaporation under climate change

Global projections of lake evaporation are typically based on simulations using single mechanistic models. However, because of its complex interactions with various lake physical properties, environmental and anthropogenic drivers, lake evaporation is highly variable and sensitive to the choice of model used. In this study, we present a multi-model analysis to investigate differences across global simulations of lake evaporation during the warm-season using three different lake models driven by outputs from four general circulation models (GCM) (i.e. 12 model combinations in total) for historic and future scenarios. Our results suggest substantial differences among lake-climate model simulations of lake evaporation. These differences varied throughout the 20th and 21st century, with model driver data explaining 74% of the variance in future projections of warm- season lake evaporation. Our projections indicate that, by the end of the 21st century (2070–2099), global annual lake evaporation rates will increase by 10–27% under Representative Concentration Pathways (RCPs) 2.6–8.5. Finally, we highlight the importance of using a multi-model approach for the prediction of future global lake evaporation responses to climate change.

54 ENVIRONMENTAL SCIENCES↗