SEARCH · Engineering Papers

Results for “dl”

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 109 records · Page 6

All sources NASA NTRS DOE OSTI

DOE OSTI2025

Analyzing and Exploring Training Recipes for Large-Scale Transformer-Based Weather Prediction

Abstract The rapid rise of deep learning (DL) in numerical weather prediction (NWP) has led to a proliferation of models which forecast atmospheric variables with comparable or superior skill than traditional physics-based NWP. However, among these leading DL models, there is a wide variance in both the training settings and architecture used. Further, the lack of thorough ablation studies makes it hard to discern which components are most critical to success. In this work, we show that it is possible to attain high forecast skill even with relatively off-the-shelf architectures, simple training procedures, and moderate compute budgets. Specifically, we train a minimally modified Swin Transformer V2 (SwinV2) on ERA5 data and find that it attains superior skill in terms of mean-square errors of deterministic forecasts when compared against the European Centre for Medium-Range Weather Forecasts’ Integrated Forecasting System (IFS). Almost all DL–NWP systems share a core set of hyperparameters and design decisions. To aid and expedite future DL–NWP research, we present an in-depth, systematic exploration of different loss functions, model sizes and depths, patch sizes, and multistep training objectives. We also examine the model performance with metrics beyond the typical accuracy (ACC) and RMSE and investigate how the performance scales with model size. Through our open-source code, scoring pipelines, and models, we share our findings on key aspects of the training pipeline. These ablations reduce the necessity for expensive hyperparameter tuning and lower the barrier to entry for future DL–NWP research. Significance Statement This study investigates the potential of using large-scale transformer-based models for weather prediction, showing that it is possible to achieve high forecast accuracy with simpler, off-the-shelf architectures. By training a minimally modified SwinV2 transformer on ERA5 data, we show that the model achieves competitive forecast skill in terms of mean-square error for key variables, outperforming the European Centre for Medium-Range Weather Forecasts’ Integrated Forecasting System (IFS) at all lead times. Our findings suggest that effective training strategies, such as multistep fine-tuning and channel-weighted losses, significantly enhance the model’s performance. However, we also highlight that these improvements come with trade-offs in other areas, such as ensemble spread and high-frequency spatial detail. This work highlights the promise of deep learning in improving weather forecasts, which could lead to better preparedness and response to weather events, ultimately benefiting society by providing more reliable weather predictions.

Willard, Jared D. [Lawrence Berkeley National Labo↗

DOE OSTI2023

Deep learning applications in visual data for benign and malignant hematologic conditions: a systematic review and visual glossary

Deep learning (DL) is a subdomain of artificial intelligence algorithms capable of automatically evaluating subtle graphical features to make highly accurate predictions, which was recently popularized in multiple imaging-related tasks. Because of its capabilities to analyze medical imaging such as radiology scans and digitized pathology specimens, DL has significant clinical potential as a diagnostic or prognostic tool. Coupled with rapidly increasing quantities of digital medical data, numerous novel research questions and clinical applications of DL within medicine have already been explored. Similarly, DL research and applications within hematology are rapidly emerging, although these are still largely in their infancy. Given the exponential rise of DL research for hematologic conditions, it is essential for the practising hematologist to be familiar with the broad concepts and pitfalls related to these new computational techniques. This narrative review provides a visual glossary for key deep learning principles, as well as a systematic review of published investigations within malignant and non-malignant hematologic conditions, organized by the different phases of clinical care. In order to assist the unfamiliar reader, this review highlights key portions of current literature and summarizes important considerations for the critical understanding of deep learning development and implementations in clinical practice.

60 APPLIED LIFE SCIENCES↗

DOE OSTI2024

Using AI for Wave-front Estimation with the Rubin Observatory Active Optics System

Abstract The Vera C. Rubin Observatory will, over a period of 10 yr, repeatedly survey the southern sky. To ensure that images generated by Rubin meet the quality requirements for precision science, the observatory will use an active-optics system (AOS) to correct for alignment and mirror surface perturbations introduced by gravity and temperature gradients in the optical system. To accomplish this, Rubin will use out-of-focus images from sensors located at the edge of the focal plane to learn and correct for perturbations to the wave front. We have designed and integrated a deep-learning (DL) model for wave-front estimation into the AOS pipeline. In this paper, we compare the performance of this DL approach to Rubin’s baseline algorithm when applied to images from two different simulations of the Rubin optical system. We show the DL approach is faster and more accurate, achieving the atmospheric error floor both for high-quality images and low-quality images with heavy blending and vignetting. Compared to the baseline algorithm, the DL model is 40× faster, the median error 2× better under ideal conditions, 5× better in the presence of vignetting by the Rubin camera, and 14× better in the presence of blending in crowded fields. In addition, the DL model surpasses the required optical quality in simulations of the AOS closed loop. This system promises to increase the survey area useful for precision science by up to 8%. We discuss how this system might be deployed when commissioning and operating Rubin.

79 ASTRONOMY AND ASTROPHYSICS↗

DOE OSTI2022

dlppi2 (b1)

The Doppler lidar (DL) is an active remote-sensing instrument that provides range- and time-resolved measurements of the line-of-sight component of air velocity (i.e., radial velocity) and attenuated aerosol backscatter. The DL operates in the near-infrared and is sensitive to backscatter from atmospheric aerosol, which are assumed to be ideal tracers of atmospheric wind fields. The DL works by transmitting short pulses of infrared laser light into the atmosphere. Atmospheric aerosols scatter a small fraction of that light energy back to the transceiver, where it is collected and recorded as a time-resolved signal. From the delay between the outgoing pulse and the backscattered signal, the instrument infers the distance to the scattering volume. Coherent detection is used to measure the Doppler frequency shift of the backscatter signal. This is accomplished by mixing the backscatter signal with a reference laser beam (i.e., local oscillator) of known frequency. The onboard signal processor then determines the Doppler frequency shift from the spectrum of the mixed signal. The Doppler frequency shift and thus the radial air velocity is determined from the peak of the Doppler spectrum. The attenuated backscatter is determined from the energy content of the Doppler spectra. The DL provides accurate measurements of radial velocity in regions of the atmosphere where aerosol concentrations are high enough to ensure good signal-to-noise ratio. Thus, valid data are usually limited to the atmospheric boundary layer where aerosol is ubiquitous. Valid measurements can also be obtained in elevated aerosol layers or in optically thin clouds above the boundary layer. Most of the ARM DLs have full upper-hemispheric scanning capability, enabling 3D mapping of turbulent flows in the atmospheric boundary layer. With the scanner pointed vertically, the DL provides height- and time-resolved measurements of vertical velocity.

54 ENVIRONMENTAL SCIENCES↗

NASA NTRS2008

16 Weeks of Training with the International Space Station Advanced Resistive Exercise Device (aRED) Is not Different than Training with Free Weights

The advanced Resistive Exercise Device (aRED) is a resistive exercise system designed to maintain muscle mass and strength in microgravity by simulating free weight (FW) exercise. aRED utilizes vacuum cylinders and inertial flywheels to replicate the constant mass and inertial components, respectively, of FW exercise in normal gravity. PURPOSE: To compare the effectiveness of aRED and FW resistive exercise training in ambulatory subjects. METHODS: Untrained subjects were assigned to two groups, FW (6 males, 3 females) and aRED (8 males, 3 females), and performed squat (SQ), heel raise (HR), and deadlift (DL) exercises 3 d wk-1 for 16 wks. SQ, HR and DL strength (1RM) were measured using FW hardware pre-, mid- and post-training. Subjects participated in a periodized training protocol with the exercise prescription based on a percentage of 1RM. Thigh and lower leg muscle volume were assessed using Magnetic Resonance Imaging (MRI), and leg (LLM) and total body lean mass (BLM) were measured using Dual Energy X-ray Absorptiometry (DXA) pre- and post-training. RESULTS: SQ 1RM increased in both FW (48.9+/-6.1%) and aRED (31.2+/-3.8%) groups, and there was a greater training response in FW compared with aRED (p=0.01). HR and DL 1RM increased in FW (HR: 12.3+/-2.4%, DL: 23.3+/-4.4%) and aRED (HR: 18.0+/-1.6%, DL: 23.2+'-2.8%), but there were no differences between groups. Thigh muscle volume was greater following training in both groups (FW: 9.8+/-0.9%, aRED: 7.1+/-1.2%) but lower leg muscle volume increased only in the FW group (3.0+/-1.1%). Lean tissue mass increased in both FW (LLM: 3.9+/-1.1%, BLM: 2.5+/-0.7%) and aRED (LLM: 4.8+/-0.7%, BLM: 2.6 0.7%). There were no between group differences in muscle volume or lean mass in response to training. CONCLUSIONS: In general, the increase in muscle strength, muscle volume, and lean tissue mass when training with aRED was not different than when using the same training protocol with FW. The smaller increase in SQ 1RM in the aRED group may be the result of undersizing the aRED flywheels which were intended to mimic the inertial component of the SQ movement when performing FW exercises. However, the biomechanical differences observed in body position during the performance of the aRED SQ, which may have affected training and testing, cannot be excluded as a factor that may have affected SQ 1RM results. PRACTICAL APPLICATIONS: Improvements in muscle strength, muscle volume and lean mass similar to FW exercise training may be elicited using an alternative source of resistance during exercise training. The acceleration of a mass during resistive exercise may result in greater muscle tension when changing the direction of movement resulting in enhanced strength gains. Therefore, to maximize the benefits of resistive exercise, the inertial components of FW exercise should be considered during exercise selection and hardware design. ACKNOWLEDGEMENT: This investigation was supported by NASA-JSC s Exercise Countermeasures Project.

Loehr, J. A.↗

NASA NTRS2009

Muscle Volume Increases Following 16 Weeks of Resistive Exercise Training with the Advanced Resistive Exercise Device (ARED) and Free Weights

Space flight-induced muscle atrophy, particularly in the postural and locomotorymuscles, may impair task performance during long-duration space missions and planetary exploration. High intensity free weight (FW) resistive exercise training has been shown to prevent atrophy during bed rest, a space flight analog. NASA developed the Advanced Resistive Exercise Device (ARED) to simulate the characteristics of FW exercise (i.e. constant mass, inertial force) and to be used as a countermeasure during International Space Station (ISS) missions. PURPOSE: To compare the efficacy of ARED and FW training to induce hypertrophy in specific muscle groups in ambulatory subjects prior to deploying ARED on the ISS. METHODS: Twenty untrained subjects were assigned to either the ARED (8 males, 3 females) or FW (6 males, 3 females) group and participated in a periodizedtraining protocol consisting of squat (SQ), heel raise (HR), and deadlift(DL) exercises 3 d wk-1 for 16 wks. SQ, HR, and DL muscle strength (1RM) was measured before, after 8 wks, and after 16 wks of training to prescribe exercise and measure strength changes. Muscle volume of the vastigroup (V), hamstring group (H), hip adductor group (ADD), medial gastrocnemius(MG), lateral gastrocnemius(LG), and deep posterior muscles including soleus(DP) was measured using MRI pre-and post-training. Consecutive cross-sectional images (8 mm slices with a 2 mm gap) were analyzed and summed. Anatomical references insured that the same muscle sections were analyzed pre-and post-training. Two-way repeated measures ANOVAs (p<0.05) were used to test for differences in muscle strength and volume between training devices. RESULTS: SQ, HR, and DL 1RM increased in both FW (SQ: 49+/-6%, HR: 12+/-2%, DL: 23+/-4%) and ARED (SQ: 31+/-4%, HR: 18+/-2%, DL: 23+/-3%) groups. Both groups increased muscle volume in the V (FW: 13+/-2%, ARED: 10+/-2%), H (FW: 3+/-1%, ARED: 3+/-1 %), ADD (FW: 15=/-2%, ARED: 10+/-1%), LG (FW: 7+/-2%, ARED: 4+/-1%), MG (FW: 7+/-2%, ARED: 5+/-2%), and DP (FW: 2+/-1%; ARED: 2+/-1%) after training. There were no between group differences in muscle strength or volume. CONCLUSIONS: The increase in muscle volume and strength following ARED training is not different than FW training. With the training effects similar to FW and a 600 lb load capacity, ARED likely will protect against muscle atrophy in microgravity.

Nash, R. E.↗

NASA NTRSDate not supplied

A Temporal Differential Dynamic Logic Formal Embedding

Differential dynamic logic is a formal framework to specify and reason about hybrid programs (HPs). The core of dL is a proof calculus that contains a collection of axioms and rules for the rigorous verification of properties of HPs. Recently, dL has been embedded within the theorem prover Prototype Verification System (PVS) resulting in the tool Plaidypvs2. The integration of dL into PVS expands its expressive power; user defined functions, such as trigonometric and other transcendental functions, can be used inside the dL framework, and meta-reasoning about HPs can be performed, including reasoning about entire classes of HPs, specified using dependent types in PVS. The differential temporal dynamic logic (dTL2) extends dL with temporal logic operators to reason about all the states reachable during the execution of an HP. This paper presents a work in progress focusing on embedding dTL2 in PVS as an extension of Plaidypvs. Plaidypvs is expanded with the formalization of a trace semantics for HPs, the definition of the LTL temporal operators eventually and globally, and the implementation of the proof calculus for dTL2. This new embedding has the same capabilties as Plaidypvs, which allows user defined functions and meta-reasoning of properties of HPs. To the best of the authors’ knowledge this is the first implementation of dTL2.

differential dynamic logic↗

DOE OSTI2022

Anderson Acceleration for Distributed Training of Deep Learning Models

Anderson acceleration (AA) is an extrapolation technique that has recently gained interest in the deep learning (DL) community to speed-up the sequential training of DL models. However, when performed at large scale, the DL training is exposed to a higher risk of getting trapped into steep local minima of the training loss function, and standard AA does not provide sufficient acceleration to escape from these steep local minima. This results in poor generalizability and makes AA ineffective. To restore AA’s advantage to speed-up the training of DL models on large scale computing platforms, we combine AA with an adaptive moving average procedure that boosts the training to escape from steep local minima. By monitoring the relative standard deviation between consecutive iterations, we also introduce a criterion to automatically assess whether the moving average is needed. We applied the method to the following DL instantiations for image classification: (i) ResNet50 trained on the open-source CIFAR100 dataset and (ii) ResNet50 trained on the open-source ImageNet1k dataset. Numerical results obtained using up to 1,536 NVIDIA V100 GPUs on the OLCF supercomputer Summit showed the stabilizing effect of the moving average on AA for all the problems above.

Lupo Pasini, Massimiliano↗

NASA NTRS2023

Explainable deep learning for insights in El Niño and river flows

The El Niño Southern Oscillation (ENSO) is a semi-periodic fluctuation in sea surface temperature (SST) over the tropical central and eastern Pacific Ocean that influences interannual variability in regional hydrology across the world through long-range dependence or teleconnections. Recent research has demonstrated the value of Deep Learning (DL) methods for improving ENSO prediction as well as Complex Networks (CN) for understanding teleconnections. However, gaps in predictive understanding of ENSO-driven river flows include the black box nature of DL, the use of simple ENSO indices to describe a complex phenomenon and translating DL-based ENSO predictions to river flow predictions. Here we show that eXplainable DL (XDL) methods, based on saliency maps, can extract interpretable predictive information contained in global SST and discover SST information regions and dependence structures relevant for river flows which, in tandem with climate network constructions, enable improved predictive understanding. Our results reveal additional information content in global SST beyond ENSO indices, develop understanding of how SSTs influence river flows, and generate improved river flow prediction, including uncertainty estimation. Observations, reanalysis data, and earth system model simulations are used to demonstrate the value of the XDL-CN based methods for future interannual and decadal scale climate projections.

SST↗

DOE OSTI2024

A deep learning-guided automated workflow in LipidOz for detailed characterization of fungal fatty acid unsaturation by ozonolysis

Understanding fungal lipid biology and metabolism is critical for antifungal target discovery as lipids play central roles in cellular processes. Nuances in lipid structural differences can significantly impact their functions, making it necessary to characterize lipids in detail to enable and understanding of their roles in these complex systems. In particular, lipid double bond (DB) locations are an important component of lipid structure that can only be determined using a few specialized analytical techniques. Ozone-induced dissociation mass spectrometry (OzID-MS) is one such technique that uses ozone to break lipid DBs, producing pairs of characteristic fragments that allow the determination of DB positions. In this work we apply OzID-MS and LipidOz software to analyze the complex lipids of Saccharomyces cerevisiae yeast strains transfected with different fatty acid desaturases from Histoplasma capsulatum to determine the specific unsaturated lipids produce. The automated data analysis in LipidOz made the determination of DB positions from this large dataset more practical, but manual verification for all targets was still time-consuming. The DL model reduces manual involvement in data analysis, but since it was trained using mammalian lipid extracts, the prediction accuracy on yeast-derived data was reduced. We addressed both shortcomings by retraining the DL model to act as a pre-filter to prioritize targets for automated analysis, providing confident manually verified results but requiring less computational time and manual effort. Our workflow resulted in the determination of novel DB positions and enzymatic specificity.

mass spectrometry, deep learning, Lipidomics, doub↗

DOE OSTI2024

A Dataset of CFD Simulated Industrial Furnace Images for Conditional Automatic Generation with GANs

The steel industry is constantly looking for ways to automate processes and improve efficiency. A standard practice in industry is to simulate how complex systems will operate before they are actually used. Some complex systems, including steel industry processes such as blast furnaces, require complex physics-based simulations utilizing computational fluid dynamics (CFD). These CFD physics-based simulations are very accurate but can take significant time and computational resources to process, resulting in challenges for the implementation of the models in real-world operational environments. In recent years, deep learning (DL) has been considered as a substitute for these CFD models. DL models can be trained on validated CFD simulation data and then used for industrial process inference. Previous DL-based solutions have made great contributions for industrial automation but are currently missing the additional visualization component that CFD simulations also provide. In this paper, we propose a dataset for simple DL generative approaches that can help to address this issue. The dataset and methodology under development to approach this prediction are discussed in this work.

Calix, Ricardo↗

DOE OSTI2019

Effect of Plastic Deformation on Passivation Characteristics of Type 304 Stainless Steel

Electrochemical response of Type 304 stainless steel, with different levels of plastic deformation, was investigated in solutions containing different amounts of H{sub 2}SO{sub 4} and KSCN at room temperature. Potentiodynamic polarization and double-loop electrochemical potentiokinetic reactivation (DL-EPR) techniques were used to characterize different levels of plastic deformation. The results have indicated that DL-EPR values and passivation current density increased with increase in plastic deformation. The DL-EPR values were correlated well with hardness and fraction of strain-induced martensite. Attack during DL-EPR tests occurred on strain regions within the matrix such as dislocations in austenite and martensite and/or interface between austenite and martensite. No well-defined correlation was observed between the levels of plastic deformation and potentiodynamic polarization behavior.

36 MATERIALS SCIENCE↗

DOE OSTI2018

Relationship between serum trimethylamine N-oxide and exposure to dioxin-like pollutants

Highlights: • TMAO has been linked to cardiovascular disease risk in human studies and animal models. • TMAO was positively associated with 22 indexes of dioxin-like pollutant exposures in ACHS-II. • Associations with TMAO were significant among females (except at high BMIs) but not among males. • The dioxin TEQ: TMAO association was unaltered by adjustment for independent covariates of TMAO. Trimethylamine N-oxide (TMAO) is a diet and gut microbiota-derived metabolite that has been linked to cardiovascular disease risk in human studies and animal models. TMAO levels show wide inter and intra individual variability in humans that can likely be accounted for by multiple factors including diet, the gut microbiota, levels of the TMAO generating liver enzyme Flavin-containing monooxygenase 3 (FMO3) and kidney function. We recently found that dioxin-like (DL) environmental pollutants increased FMO3 expression to elevate circulating diet-derived TMAO in mice, suggesting that exposure to this class of pollutants might also contribute to inter-individual variability in circulating TMAO levels in humans. To begin to explore this possibility we examined the relationship between body burden of DL pollutants (reported by serum lipid concentrations) and serum TMAO levels (n = 340) in the Anniston, AL cohort, which was highly exposed to polychlorinated biphenyls (PCBs). TMAO concentrations in archived serum samples from the Anniston Community Health Survey (ACHS-II) were measured, and associations of TMAO with 28 indices of pollutant body burden, including total dioxins toxic equivalent (TEQ), were quantified. Twenty-three (22 after adjustment for multiple comparisons) of the 28 indices were significantly positively associated with TMAO. Although the design of ACHS-II does not enable quantitative assessment of the contributions of previously known determinants of TMAO variability to this relationship, limited multivariate modeling revealed that total dioxins TEQ was significantly associated with TMAO among females (except at high BMIs) but not among males. Our results from this cross-sectional study indicate that exposure to DL pollutants may contribute to elevated serum TMAO levels. Prospective longitudinal studies will be required to assess the joint relationship between DL pollutant exposures, other determinants of TMAO, and health outcomes.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2021

Deep learning inversion of gravity data for detection of CO 2 plumes in overlying aquifers

In this work, we developed an effective U-Net based deep learning (DL) model for inversion of surface gravity data on a rectangular grid to predict 2-D high-resolution subsurface CO 2 distribution along a vertical cross-section due to CO 2 leakage through a wellbore within a deep CO 2 storage reservoir. We used synthetic data to model two types of CO 2 leakage scenarios: one CO 2 plume in a shallow aquifer (single plume case), and two plumes present at different depths (double plume case). The 3-D synthetic plume samples were created by sampling among predetermined CO 2 plume depths, saturations, and volumes. The corresponding surface gravity data on a rectangular grid were generated by a 3-D forward model. The U-Net model detected 72% of single-plume samples, and one or both plumes in 75% of double-plume samples. Most of the undetected single plumes have small gravity field strengths below the typical noise level of 5 μGal. This model generated reproducible, reliable predictions with acceptable errors and demonstrated improved spatial resolution over the conventional least-squares inversion. In contrast to the conventional least-squares inversion, which often overestimates the size of its target and underestimates its density, this U-Net model accurately delineated the boundary of a target. Furthermore, this DL inversion detected deep, small, or low saturation CO 2 plumes that are often more difficult to resolve with conventional gravity inversion methods. We note the limitations of this feasibility study, including the use of synthetic data with regular CO 2 plume shapes, and the prediction of a 2-D plume cross-section rather than the full 3-D plume, as well, we recognize the lower detection fraction for double-plume scenarios. Nevertheless, this study demonstrates that DL gravity inversion is a promising and potentially superior method to conventional least-squares inversion. Our U-Net based deep learning inversion approach may be adapted for inversion of other types of geophysical data. DL inversion can facilitate near real-time monitoring of geologic carbon sequestration to provide site operators with prompt information about subsurface CO 2 distribution for risk management and mitigation.

58 GEOSCIENCES↗

DOE OSTI2022

Towards multi-fidelity deep learning of wind turbine wakes

We report engineering wake models that accurately predict wake in a computationally efficient manner are very important for tasks such as layout optimization and control of wind farms. In this paper, we explore an application of deep learning (DL) to learn the wake model from hierarchies of physics-based approaches ranging from analytical models to an approximate form of the Reynolds-averaged Navier-Stokes equations. We first illustrate the application of principal component analysis to obtain a lower-dimensional representation that allows a computationally tractable training and deployment of DL models. Then, the DL model is trained to learn the mapping from input parameter space to the principal components, which are then used to reconstruct the three-dimensional flow field. Additionally, we investigate a composite framework consisting of two neural networks to learn the correlation between low- and high-fidelity data with Gauss and curl models treated as proxies for low- and high-fidelity models, respectively. The prediction from both DL models matches well with the high-fidelity data with a maximum relative percentage error for the kinetic energy flux of <1%. This work opens up possibilities for data-efficient construction of surrogate models for wake prediction that can be used to study the influence of wind speed and yaw angles on wind farm power production.

17 WIND ENERGY↗

DOE OSTI2022

The Data Synergy Effects of Time-Series Deep Learning Models in Hydrology

When fitting statistical models to variables in geoscientific disciplines such as hydrology, it is a customary practice to stratify a large domain into multiple regions (or regimes) and study each region separately. Traditional wisdom suggests that models built for each region separately will have higher performance because of homogeneity within each region. However, each stratified model has access to fewer and less diverse data points. Here, through two hydrologic examples (soil moisture and streamflow), we show that conventional wisdom may no longer hold in the era of big data and deep learning (DL). We systematically examined an effect we call data synergy, where the results of the DL models improved when data were pooled together from characteristically different regions. The performance of the DL models benefited from modest diversity in the training data compared to a homogeneous training set, even with similar data quantity. Moreover, allowing heterogeneous training data makes eligible much larger training datasets, which is an inherent advantage of DL. A large, diverse data set is advantageous in terms of representing extreme events and future scenarios, which has strong implications for climate change impact assessment. The results here suggest the research community should place greater emphasis on data sharing.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2024

Use of Satellite, Surface Observations and Numerical Weather Prediction Model Data to Improve Cloud Base Height and Cloud Base Vertical Velocity Estimation

Cloud base height (CBH) and cloud base vertical velocity (CBVV) are important variables that impact the overall climate in a region as they influence the formulation, longevity, and evolution of clouds. Retrieval of both parameters have long used ground instrumentation (e.g., Doppler lidar (DL), ground base radar); however, retrieving CBH from satellites is particularly challenging given that space-based instruments only observe cloud tops. In this manuscript, CBH is retrieved using a multi-linear regression equation, while CBVV used a random forests model. Both retrievals combine satellite and numerical weather prediction data. The satellite data used are the Visible Infrared Imaging Radiometer Suite imagery, while measurements of CBH and CBVV include DL and radiosonde data at the Southern Great Plains (SGP) Atmospheric Radiation Measurement observatory. Data from 83 summer days (May-August) in 2018–2021 featuring cumulus clouds forced by solar heating were examined and used to train the models, with years 2022–2023 used for validation. Various spatial domains were defined with one large (2.4° longitude by 2.0° latitude) SGP domain being split into smaller sections (smallest being 0.99° and 0.61° longitude and latitude respectably). CBH and CBVV values obtained from the DL as compared to the models show root mean square errors between 150 and 200 m, with CBVV values between 0.45 and 1 ms -1 . Finally, it was found that the CBH formulation performs well over all domains, while the CBVV retrievals become less accurate due to more turbulence being introduced into the observations as the number of DL stations decreases in the smaller domains.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2023

Explainable deep learning for insights in El Niño and river flows

54 ENVIRONMENTAL SCIENCES↗