SEARCH · Engineering Papers

Results for “preprocessed”

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 325 records · Page 18

All sources NASA NTRS DOE OSTI

DOE OSTI2024

Streamlining Ocean Dynamics Modeling with Fourier Neural Operators: A Multiobjective Hyperparameter and Architecture Optimization Approach

Training an effective deep learning model to learn ocean processes involves careful choices of various hyperparameters. We leverage DeepHyper’s advanced search algorithms for multiobjective optimization, streamlining the development of neural networks tailored for ocean modeling. The focus is on optimizing Fourier neural operators (FNOs), a data-driven model capable of simulating complex ocean behaviors. Selecting the correct model and tuning the hyperparameters are challenging tasks, requiring much effort to ensure model accuracy. DeepHyper allows efficient exploration of hyperparameters associated with data preprocessing, FNO architecture-related hyperparameters, and various model training strategies. We aim to obtain an optimal set of hyperparameters leading to the most performant model. Moreover, on top of the commonly used mean squared error for model training, we propose adopting the negative anomaly correlation coefficient as the additional loss term to improve model performance and investigate the potential trade-off between the two terms. The numerical experiments show that the optimal set of hyperparameters enhanced model performance in single timestepping forecasting and greatly exceeded the baseline configuration in the autoregressive rollout for long-horizon forecasting up to 30 days. Utilizing DeepHyper, we demonstrate an approach to enhance the use of FNO in ocean dynamics forecasting, offering a scalable solution with improved precision.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2024

Applications of LIF to Document Natural Variability of Chlorophyll Content and Cu Uptake in Moss

Chlorophyll has long been used as a natural indicator of plant health and photosynthetic efficiency. Laser-induced fluorescence (LIF) is an emerging technique for understanding broad spectrum organic processes and has more recently been used to monitor chlorophyll response in plants. Previous work has focused on developing a LIF technique for imaging moss mats to identify metal contamination with the current focus shifting toward application to moss fronds and aiding sample collection for chemical analysis. Two laser systems (CoCoBi a Nd:YGa pulsed laser system and Chl-SL with two blue continuous semiconductor diodes) were used to collect images of moss fronds exposed to increasing levels of Cu (1, 10, and 100 nmol/cm 2 ) using a CMOS camera. The best methods for the preprocessing of images were conducted before the analysis of fluorescence signatures were compared to a control. The Chl-SL system performed better than the CoCoBi, with dynamic time warping (DTW) proving the most effective for image analysis. Manual thresholding to remove lower decimal code values improved the data distributions and proved whether using one or two fronds in an image was more advantageous. A higher DTW difference from the control correlated to lower chlorophyll a/b ratios and a higher metal content, indicating that LIF, with the aid of image processing, can be an effective technique for identifying Cu contamination shortly after an event.

59 BASIC BIOLOGICAL SCIENCES↗

DOE OSTI2024

Mapping Geothermal Indicator Minerals Using Fusion of Target Detection Algorithms

Mineral mapping from satellite images provides valuable insights into subsurface mineral alteration for geothermal exploration. In previous studies, eight fundamental algorithms were used for mineral mapping utilizing USGS spectra, a collection of reflectance spectra containing samples of minerals, rocks, and soils created by the USGS. We used an ASD FieldSpec 4 Hi-RES NG portable spectrometer to collect spectra for analyzing ASTER images of the Coso Geothermal Field. Then, we established the ground-truth information and the spectral library by analyzing 97 samples. Samples collected from the field were analyzed using the CSIRO TSG (The Spectral Geologist of the Commonwealth Scientific and Industrial Research Organization). Based on the mineralogy study, multiple high-purity spectra of geothermal alteration minerals were selected from collected data, including alunite, chalcedony, hematite, kaolinite, and opal. Eight mineral spectral target detection algorithms were applied to the preprocessed satellite data with a proposed local spectral library. We measured the highest overall accuracy of 87% for alunite, 95% for opal, 83% for chalcedony, 60% for hematite, and 96% for kaolinite out of these eight algorithms. Three, four, five, and eight algorithms were fused to extract mineral alteration with the obtained target detection results. The results prove that the fusion of algorithms gives better results than using individual ones. In conclusion, this paper discusses the significance of evaluating different mapping algorithms. It proposes a robust fusion approach to extract mineral maps as an indicator for geothermal exploration.

Cavur, Mahmut↗

DOE OSTI2026

A Centralized AI Lakehouse Framework for Brain Tumor MRI Classification and Segmentation, University KPI Forecasting, and Water Potability Prediction

In many university and healthcare projects, models are built for very different data types such as tables, institutional time series, and medical images, but they are deployed as separate applications. In this work, that separation made testing and maintenance difficult because each module had its own pipeline and runtime requirements. This paper presents an integrated AI lakehouse-style implementation that runs three model pipelines inside one containerized backend. For medical imaging, we used MRI datasets from IEEE DataPort: a four-class classification set with 7012 images (5708 train/1304 test) and a segmentation set with 3063 image–mask pairs. The classification model (ResNet50 transfer learning) is evaluated using a proper train–validation–test protocol across multiple splits (80/10/10, 70/10/20, 60/10/30, and 10/30/60), achieving a test accuracy of 99.00% under the standard 80/10/10 split. Additionally, a patient-level evaluation is conducted using an external glioma dataset to provide a more realistic assessment without data leakage. The segmentation model (DeepLabV3-ResNet50) achieved 83.09% validation mIoU and 88.79% Dice score. For university KPI forecasting, we used annual IPEDS and NSF HERD data from 2010 to 2023 for three universities (BSU, EOU, and UAB). To examine the effect of preprocessing on forecasting performance, two case studies are conducted. In the first case, linear interpolation is applied to generate semester-level data. In the second case, the original annual data is used directly without interpolation. Random Forest regression and ARIMA models are evaluated using MAE, RMSE, MAPE, and R 2 . The results showed that interpolation improved apparent forecasting performance due to smoothing, while evaluation on the original annual data provided a more realistic assessment of model behavior. To further validate the framework on a larger dataset, an additional case study is conducted using a student dropout dataset. For water potability, we trained and compared multiple tabular classifiers on a large dataset (1,048,575 samples). A Random Forest model (100 trees, max depth 10) achieved 85.86% test accuracy and high recall for unsafe samples (0.8447). All modules are served via FastAPI and deployed together using Docker, with workflow automation routing requests to the correct endpoint. System-level benchmarking indicates that the backend maintains stable throughput and latency under concurrent requests.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2023

Few-Shot Learning Enables Population-Scale Analysis of Leaf Traits in Populus trichocarpa

Plant phenotyping is typically a time-consuming and expensive endeavor, requiring large groups of researchers to meticulously measure biologically relevant plant traits, and is the main bottleneck in understanding plant adaptation and the genetic architecture underlying complex traits at population scale. In this work, we address these challenges by leveraging few-shot learning with convolutional neural networks to segment the leaf body and visible venation of 2,906 Populus trichocarpa leaf images obtained in the field. In contrast to previous methods, our approach (a) does not require experimental or image preprocessing, (b) uses the raw RGB images at full resolution, and (c) requires very few samples for training (e.g., just 8 images for vein segmentation). Traits relating to leaf morphology and vein topology are extracted from the resulting segmentations using traditional open-source image-processing tools, validated using real-world physical measurements, and used to conduct a genome-wide association study to identify genes controlling the traits. In this way, the current work is designed to provide the plant phenotyping community with (a) methods for fast and accurate image-based feature extraction that require minimal training data and (b) a new population-scale dataset, including 68 different leaf phenotypes, for domain scientists and machine learning researchers. All of the few-shot learning code, data, and results are made publicly available.

59 BASIC BIOLOGICAL SCIENCES↗

DOE OSTI2022

Analytical Modeling of Exoplanet Transit Spectroscopy with Dimensional Analysis and Symbolic Regression

Abstract The physical characteristics and atmospheric chemical composition of newly discovered exoplanets are often inferred from their transit spectra, which are obtained from complex numerical models of radiative transfer. Alternatively, simple analytical expressions provide insightful physical intuition into the relevant atmospheric processes. The deep-learning revolution has opened the door for deriving such analytical results directly with a computer algorithm fitting to the data. As a proof of concept, we successfully demonstrate the use of symbolic regression on synthetic data for the transit radii of generic hot-Jupiter exoplanets to derive a corresponding analytical formula. As a preprocessing step, we use dimensional analysis to identify the relevant dimensionless combinations of variables and reduce the number of independent inputs, which improves the performance of the symbolic regression. The dimensional analysis also allowed us to mathematically derive and properly parameterize the most general family of degeneracies among the input atmospheric parameters that affect the characterization of an exoplanet atmosphere through transit spectroscopy.

79 ASTRONOMY AND ASTROPHYSICS↗

DOE OSTI2026

H I Depletion Begins Well Beyond the Virial Radius: A FAST Stacking Study of 36 Galaxy Clusters to 5 × R 200

Abstract We present a stacking study of the neutral atomic hydrogen (H i ) content in and around 36 local galaxy clusters at z < 0.07, using a combination of the FAST All Sky H i survey (FASHI) and the extensive spectroscopic catalog mainly from the Dark Energy Spectroscopic Instrument (DESI). We employ spectral stacking techniques to probe the average H i mass and HI-to-stellar mass ratio ( M HI / M * ) for member galaxies down to stellar masses of M * ∼ 10 9 M ⊙ , spanning a projected cluster-centric distance of up to 5 R 200 . Our analysis reveals a pronounced environmental effect; both M HI and M HI / M * decrease steadily toward the cluster center, dropping by ∼0.5 dex on average from the outskirts to the core. Crucially, we find that M HI / M * of galaxies remain lower than the field galaxies even at the 5 R 200 . This provides direct, statistical evidence for substantial gas stripping and preprocessing in the cluster outskirts, likely occurring in infalling groups and large-scale filaments. By further splitting the sample by g − r color, we show that the H i deficiency persists at fixed galaxy color; even the bluest cluster members exhibit ∼0.5 dex lower M HI / M * than field galaxies of similar color, reflecting environmental effects on the cold gas reservoir prior to full optical transformation. The total H i mass within clusters and their outskirts agrees broadly with predictions from cosmological simulations. Our results underscore the critical role of the extended cluster environment in quenching galaxies by depleting their cold gas reservoirs well before they enter the dense cluster core.

Cheng, Cheng [Chinese Academy of Sciences South Am↗

DOE OSTI2022

Unsupervised Machine Learning for Exploratory Data Analysis of Exoplanet Transmission Spectra

Abstract Transit spectroscopy is a powerful tool for decoding the chemical compositions of the atmospheres of extrasolar planets. In this paper, we focus on unsupervised techniques for analyzing spectral data from transiting exoplanets. After cleaning and validating the data, we demonstrate methods for: (i) initial exploratory data analysis, based on summary statistics (estimates of location and variability); (ii) exploring and quantifying the existing correlations in the data; (iii) preprocessing and linearly transforming the data to its principal components; (iv) dimensionality reduction and manifold learning; (v) clustering and anomaly detection; and (vi) visualization and interpretation of the data. To illustrate the proposed unsupervised methodology, we use a well-known public benchmark data set of synthetic transit spectra. We show that there is a high degree of correlation in the spectral data, which calls for appropriate low-dimensional representations. We explore a number of different techniques for such dimensionality reduction and identify several suitable options in terms of summary statistics, principal components, etc. We uncover interesting structures in the principal component basis, namely well-defined branches corresponding to different chemical regimes of the underlying atmospheres. We demonstrate that those branches can be successfully recovered with a K-means clustering algorithm in a fully unsupervised fashion. We advocate for lower-dimensional representations of the spectroscopic data in terms of the main principal components, in order to reveal the existing structure in the data and quickly characterize the chemical class of a planet.

Matchev, Konstantin T. (ORCID:0000000341829096)↗

DOE OSTI2021

Inpainting radar missing data regions with deep learning

Abstract. Missing and low-quality data regions are a frequent problem for weather radars. They stem from a variety of sources: beam blockage, instrument failure, near-ground blind zones, and many others. Filling in missing data regions is often useful for estimating local atmospheric properties and the application of high-level data processing schemes without the need for preprocessing and error-handling steps – feature detection and tracking, for instance. Interpolation schemes are typically used for this task, though they tend to produce unrealistically spatially smoothed results that are not representative of the atmospheric turbulence and variability that are usually resolved by weather radars. Recently, generative adversarial networks (GANs) have achieved impressive results in the area of photo inpainting. Here, they are demonstrated as a tool for infilling radar missing data regions. These neural networks are capable of extending large-scale cloud and precipitation features that border missing data regions into the regions while hallucinating plausible small-scale variability. In other words, they can inpaint missing data with accurate large-scale features and plausible local small-scale features. This method is demonstrated on a scanning C-band and vertically pointing Ka-band radar that were deployed as part of the Cloud Aerosol and Complex Terrain Interactions (CACTI) field campaign. Three missing data scenarios are explored: infilling low-level blind zones and short outage periods for the Ka-band radar and infilling beam blockage areas for the C-band radar. Two deep-learning-based approaches are tested, a convolutional neural network (CNN) and a GAN that optimize pixel-level error or combined pixel-level error and adversarial loss respectively. Both deep-learning approaches significantly outperform traditional inpainting schemes under several pixel-level and perceptual quality metrics.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2020

Improving climate model coupling through a complete mesh representation: a case study with E3SM (v1) and MOAB (v5.x)

One of the fundamental factors contributing to the spatiotemporal inaccuracy in climate modeling is the mapping of solution field data between different discretizations and numerical grids used in the coupled component models. The typical climate computational workflow involves evaluation and serialization of the remapping weights during the preprocessing step, which is then consumed by the coupled driver infrastructure during simulation to compute field projections. Tools like Earth System Modeling Framework (ESMF) and TempestRemap offer capability to generate conservative remapping weights, while the Model Coupling Toolkit (MCT) that is utilized in many production climate models exposes functionality to make use of the operators to solve the coupled problem. However, such multistep processes present several hurdles in terms of the scientific workflow and impede research productivity. In order to overcome these limitations, we present a fully integrated infrastructure based on the Mesh Oriented datABase (MOAB) library, which allows for a complete description of the numerical grids and solution data used in each submodel. Through a scalable advancing-front intersection algorithm, the supermesh of the source and target grids are computed, which is then used to assemble the high-order, conservative, and monotonicity-preserving remapping weights between discretization specifications. The Fortran-compatible interfaces in MOAB are utilized to directly link the submodels in the Energy Exascale Earth System Model (E3SM) to enable online remapping strategies in order to simplify the coupled workflow process. We demonstrate the superior computational efficiency of the remapping algorithms in comparison with other state-of-the-science tools and present strong scaling results on large-scale machines for computing remapping weights between the spectral element atmosphere and finite volume discretizations on the polygonal ocean grids.

58 GEOSCIENCES↗

DOE OSTI2020

Janus: A Python Package for Agent-Based Modeling of Land Use and Land Cover Change

Janus is an open source Python package for agent-based modeling (ABM) of land use and land cover change (LULCC). Many ABMs of LULCC have been created across platforms, some of which are not ideal for large scale, high resolution scenarios. This model provides a simple object-oriented framework for creating ABMs specific to LULCC. The organizational philosophy of the modeling framework is to create software objects (agents) that are associated with specific and contextual attributes which are isolated from where those agents exist in the spatial setting of the model, yet provide clear linkages between the agent, their environment, and other agents in the simulation. In this way, the framework allows for assembly of LULCC ABMs with low (programmatic) overhead, making the models extensible and providing clear mechanisms for integrating them with process-oriented biophysical models. Provided with Janus is a suite of geospatial data preprocessing tools that can use arbitrary land cover products as an input. Crop choice decisions are based on potential crop prices, these can be created synthetically, or drawn from integrated human-Earth systems models such as the GCAM. Janus is publicly accessible through GitHub and provides an example dataset for testing.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2025

NLR HPC Kestrel Jobs Data

Overview: Anonymized job-level records from the Kestrel HPC system at the National Laboratory of the Rockies (NLR). Each record represents a Slurm batch job with scheduling metadata, resource requests, utilization, energy estimates, and efficiency metrics. Sensitive fields (user, account, job name, submit line, working directory, submit script, and job type) are replaced with 7-character cryptographic hashes. System & Timeframe: Kestrel is located at the NLR campus. Standard compute nodes have 104 cores and 256 GB RAM; bigmem nodes have 2,000 GB. GPU nodes (gpu-h100 partition) use NVIDIA H100 GPUs. Data covers jobs submitted August 2023 through December 2025. Funding provided by the U.S. Department of Energy, EERE. Files: esif.hpc.kestrel.job-anon.zip — Anonymized job records (Hive-partitioned Parquet) datacard.md — Full dataset documentation ~11 million rows, 50 variables. Readable with PyArrow, pandas, DuckDB, Apache Spark, or any Parquet-compatible tool. Data Collection: Jobs collected via sacct with timezone-aware export (SLURM_TIME_FORMAT="%Y-%m-%dT%H:%M:%S%z"), loaded into PostgreSQL. Calculated columns updated via database triggers and batch functions. All timestamps use timestamptz and correctly handle DST transitions. Preprocessing: Anonymization of name, user, account, submit_line, work_dir, submit_script, and job_type via 7-char hex hashes Derived columns: queue_wait, cpu_eff, max/min/avg_mem_eff, energy estimates Simplified job state mapping (e.g., "CANCELLED by 132357" → "CANCELLED") Boolean flags: python_job, reframe_job Temporal decomposition: year, month, day, day_of_week, hour, minute from submit_time Shared node tracking: shared_job_count, nodes_shared, jobs_shared Key Variables: Scheduling: job_id, partition, state_simple, submit_time, start_time, end_time, queue_wait Resources: nodes_req/used, processors_req/used, memory_req, wallclock_req/used, gpus_requested Efficiency: cpu_eff, max/min/avg_mem_eff Energy: cpu_energy_tdp_estimated_max/used_watt_hours, consumed_energy_raw_joules, consumed_energy_raw_watt_hours Sharing: shared_job_count, nodes_shared, jobs_shared Partitions: short, standard, debug, gpu-h100 Job States: CANCELLED, COMPLETED, FAILED, PENDING, RUNNING QoS Levels: normal, high Important Notes: Timestamps include timezone offsets; DST transitions are handled correctly, though adding intervals across DST boundaries requires offset adjustment shared_job_count reflects physical node co-residency, not use of the shared partition Job step records and raw Slurm JSONB fields are excluded Do not attempt to re-identify individuals from hashed fields

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2025

NLR HPC Eagle Jobs Data and Additional Energy Metrics

Overview: Anonymized job-level records from the Eagle high-performance computing (HPC) system at the National Laboratory of the Rockies (NLR). Each record represents a Slurm batch job with scheduling metadata, resource requests, resource utilization, CPU/GPU energy consumption, and efficiency metrics. Sensitive fields (user, account, job name) are replaced with cryptographic hashes. System & Timeframe: Eagle was a 2,000-node, 8-petaflop system operated at NLR from 2019–2024. Data covers the full operational lifetime of the system. Slurm data was processed nightly; timestamps are in Mountain Time. Funding provided by the U.S. Department of Energy, EERE. Files: esif.hpc.eagle.job-anon.zip — Core anonymized job records (Hive-partitioned Parquet) esif.hpc.eagle.job-anon-energy-metrics.zip — Same records with additional iLO and Ganglia energy metrics datacard.md — Full dataset documentation ~13.8 million rows, 62 variables. Readable with PyArrow, pandas, DuckDB, Apache Spark, or any Parquet-compatible tool. Data Collection: Jobs collected via sacct through a pipeline: Eagle Jobs API → Redpanda → StreamSets → HPCMON API → PostgreSQL. Node-level power from iLO (HP Integrated Lights-Out); GPU power from Ganglia monitoring, joined to jobs via node lists and time ranges. Preprocessing: Anonymization of name, user, and account fields via cryptographic hashing Derived columns: queue_wait, cpu_eff, max_mem_eff Simplified job state mapping (e.g., "CANCELLED BY 12345" → "CANCELLED") QoS accounting rules (buy-in, standby, or Slurm QoS value) CPU energy estimated from TDP (200W, Intel Xeon Gold 6154, 18 cores) Timezone-aware columns (_tz) sourced from LEX accounting database to correctly handle DST transitions Key Variables: Scheduling: job_id, partition, state_simple, submit_time_tz, start_time_tz, end_time_tz, queue_waitResources: nodes_req/used, processors_req/used, memory_req, wallclock_req/used, gpus_requested Efficiency: cpu_eff, max_mem_eff Energy: cpu_energy_tdp_estimated_max/used_watt_hours, node_energy_total_watt_hours (iLO), gpu0/1_energy_total_watt_hours (Ganglia) Partitions: bigmem, bigmem-8600, bigscratch, csc, dav, ddn, debug, gpu, haswell, long, mono, short, standard Job States: CANCELLED, COMPLETED, FAILED, NODE_FAIL, OUT_OF_MEMORY, PENDING, RUNNING, TIMEOUT QoS Levels: Unknown, normal, buy-in, debug, penalty, high, standby Important Notes: Non-_tz timestamp columns may be off by one hour across DST boundaries; use _tz columns for time difference calculations Energy fields are null for jobs without monitoring coverage Job step records and raw Slurm JSONB fields are excluded from this extract Do not attempt to re-identify individuals from hashed fields

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2020

On Performance Prediction of Big Data Transfer in High-performance Networks

Big data generated by large-scale scientific and industrial applications need to be transferred between different geographical locations for remote storage, processing, and analysis. High-speed dedicated connections provisioned in High-performance Networks (HPNs) are increasingly utilized to carry out such big data transfer. HPN management highly relies on an important capability of performance (mainly throughput) prediction to reserve sufficient bandwidth and meanwhile avoid over-provisioning that may result in unnecessary resource waste. This capability is critical to improving the resource (mainly bandwidth) utilization of dedicated connections and meeting various user requests for data transfer. Conventional methods conduct performance prediction by fitting prior observed transfer history with predefined loss functions, without considering unobservable latent factors such as competing loads on end hosts. Such latent factors also have a significant impact on the application-level data transfer performance, which may result in an inaccurate prediction model. In this paper, we first investigate the impact of latent factors and propose a clustering-based method to eliminate their negative impact on performance prediction. We then develop a robust machine learning-based performance predictor by: i) incorporating the proposed latent factor elimination method into data preprocessing, and ii) adopting a customized domain guided loss function. Extensive experimental results show that our predictor achieves significantly higher prediction accuracy than several other state-of-the-art methods.

Liu, Wuji↗

DOE OSTI2020

Performance Prediction of Big Data Transfer Through Experimental Analysis and Machine Learning

Big data transfer in next-generation scientific applications is now commonly carried out over connections with guaranteed bandwidth provisioned in High-performance Networks (HPNs) through advance bandwidth reservation. To use HPN resources efficiently, provisioning agents need to carefully schedule data transfer requests and allocate appropriate bandwidths. Such reserved bandwidths, if not fully utilized by the requesting user, could be simply wasted or cause extra overhead and complexity in management due to exclusive access. This calls for the capability of performance prediction to reserve bandwidth resources that match actual needs. Towards this goal, we employ machine learning algorithms to predict big data transfer performance based on extensive performance measurements, which are collected over a span of several years from a large number of data transfer tests using different protocols and toolkits between various end sites on several real-life physical or emulated HPN testbeds. We first identify a comprehensive list of attributes involved in a typical big data transfer process, including end host system configurations, network connection properties, and control parameters of data transfer methods. We then conduct an in-depth exploratory analysis of their impacts on application-level throughput, which provides insights into big data transfer performance and motivates the use of machine learning. We also investigate the applicability of machine learning algorithms and derive their general performance bounds for performance prediction of big data transfer in HPNs. Experimental results show that, with appropriate data preprocessing, the proposed machine learning-based approach achieves 95% or higher prediction accuracy in up to 90% of the cases with very noisy real-life performance measurements.

Yun, Daqing↗

DOE OSTI2020

Optical array for high-quality imaging in harsh environments

Methods and apparatus are disclosed for producing high quality images in uncontrolled or impaired environments. In some examples of the disclosed technology, groups of cameras for high dynamic range (HDR), polarization diversity, and optional other diversity modes are arranged to concurrently image a common scene. For example, in a vehicle checkpoint application, HDR provides discernment of dark objects inside a vehicle, while polarization diversity aids in rejecting glare. Spectral diversity, infrared imaging, and active illumination can be applied for better imaging through a windshield. Preprocessed single-camera images are registered and fused. Faces or other features of interest can be detected in the fused image and identified in a library. Impairments can include weather, insufficient or interfering lighting, shadows, reflections, window glass, occlusions, or moving objects.

42 ENGINEERING↗

DOE OSTI2020

Anatomical Fraction segmentation in the biomass bales

The U.S. Department of Energy Bioenergy Technologies Office (BETO) is committed to the development of sustainable, nationwide, commercial biofuel production to displace petroleum-derived fuels, increase domestic energy production, and encourage the creation of a domestic bioenergy and bioproducts industry. Operating a commercial-scale bioenergy operation requires significant technological advancements for determining biomass feedstock quality during the preprocessing stage. Usage of non-food feedstocks- e.g., corn-stover, pine residue, and forest residue - at the biorefineries reduces strain on the food supply chain. But the non-food feedstock heterogeneity- physical size, shape, and chemical composition-poses a significant challenge during milling, conveyance, feeding, and biofuel conversion processes. 3D X-Ray imaging (CT) is capable of distinguishing material features by detecting density and compositional differences. But the inherent complexity introduced during harvesting and bailing makes the reconstruction and interpretation of baled biomass materials from x-ray data time consuming, laborious, and expensive. Feedstocks are low-density materials that produce small contrast differences in the x-ray images. This paper focuses on using the shape and texture properties, using 3D image processing techniques like 3D skeletonization, directional statistics to characterize and extract volumetric content of the different tissue samples in the biomass bales.

09 BIOMASS FUELS↗

DOE OSTI2020

FLEET: Flexible Efficient Ensemble Training for Heterogeneous Deep Neural Networks

Parallel training of an ensemble of Deep Neural Networks (DNN) on a cluster of nodes is an effective approach to shorten the process of neural network architecture search and hyper-parameter tuning for a given learning task. Prior efforts have shown that data sharing, where the common preprocessing operation is shared across the DNN training pipelines, saves computational resources and improves pipeline efficiency. Data sharing strategy, however, performs poorly for a heterogeneous set of DNNs where each DNN has varying computational needs and thus different training rate and convergence speed. This paper proposes FLEET, a flexible ensemble DNN training framework for efficiently training a heterogeneous set of DNNs. We build FLEET via several technical innovations. We theoretically prove that an optimal resource allocation is NP-hard and propose a greedy algorithm to efficiently allocate resources for training each DNN with data sharing. We integrate data-parallel DNN training into ensemble training to mitigate the differences in training rates and introduce checkpointing into this context to address the issue of different convergence speeds. Experiments show that FLEET significantly improves the training efficiency of DNN ensembles without compromising the quality of the result.

Guan, Hui↗