Search NASA⌕ Search

SEARCH · Search NASA

Results for “Labeled Datasets”

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

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

At least 523 records · Page 29

INSURE: An Information Theory iNspired diSentanglement and pURification modEl for Domain Generalization

Domain Generalization (DG) aims to learn a generalizable model on the unseen target domain by only training on the multiple observed source domains. Although a variety of DG methods have focused on extracting domain-invariant features, the domain-specific class-relevant features have attracted attention and been argued to benefit generalization to the unseen target domain. To take into account the class-relevant domain-specific information, in this paper we propose an Information theory iNspired diSentanglement and pURification modEl (INSURE) to explicitly disentangle the latent features to obtain sufficient and compact (necessary) class-relevant feature for generalization to the unseen domain. Specifically, we first propose an information theory inspired loss function to ensure the disentangled class-relevant features contain sufficient class label information and the other disentangled auxiliary feature has sufficient domain information. Additionally, we further propose a paired purification loss function to let the auxiliary feature discard all the class-relevant information and thus the class-relevant feature will contain sufficient and compact (necessary) class-relevant information. Moreover, instead of using multiple encoders, we propose to use a learnable binary mask as our disentangler to make the disentanglement more efficient and make the disentangled features complementary to each other. We conduct extensive experiments on five widely used DG benchmark datasets including PACS, VLCS, OfficeHome, TerraIncognita, and DomainNet. The proposed INSURE achieves state-of-the-art performance. We also empirically show that domain-specific class-relevant features are beneficial for domain generalization. The code is available at https://github.com/yuxi120407/INSURE .

97 MATHEMATICS AND COMPUTING↗

Diffusion-Model-Assisted Supervised Learning of Generative Models for Density Estimation

Here, we present a supervised learning framework of training generative models for density estimation. Generative models, including generative adversarial networks (GANs), normalizing flows, and variational auto-encoders (VAEs), are usually considered as unsupervised learning models, because labeled data are usually unavailable for training. Despite the success of the generative models, there are several issues with the unsupervised training, e.g., requirement of reversible architectures, vanishing gradients, and training instability. To enable supervised learning in generative models, we utilize the score-based diffusion model to generate labeled data. Unlike existing diffusion models that train neural networks to learn the score function, we develop a training-free score estimation method. This approach uses mini-batch-based Monte Carlo estimators to directly approximate the score function at any spatial-temporal location in solving an ordinary differential equation (ODE), corresponding to the reverse-time stochastic differential equation (SDE). This approach can offer both high accuracy and substantial time savings in neural network training. Once the labeled data are generated, we can train a simple, fully connected neural network to learn the generative model in the supervised manner. Compared with existing normalizing flow models, our method does not require the use of reversible neural networks and avoids the computation of the Jacobian matrix. Compared with existing diffusion models, our method does not need to solve the reverse-time SDE to generate new samples. As a result, the sampling efficiency is significantly improved. We demonstrate the performance of our method by applying it to a set of 2D datasets as well as real data from the University of California Irvine (UCI) repository.

97 MATHEMATICS AND COMPUTING↗

Early Time-Series Classification with Reliability Guarantee

We consider the early classification of (incomplete) time-series data given a complete time series training set. The early classification problem arises naturally when test sample data is collected over time, or when costs must be incurred to collect the data. For example, for missile defense, it is important to determine the target type long before it reaches its target. A practical goal is to assign a class label as soon as enough data is available to make a good decision. This objective is formalized through the notion of reliability—the probability that a label assigned to the early, incomplete data matches that assigned to the complete data, and we propose a method to classify incomplete data only if a user-specified reliability threshold is met. Our approach models the complete data as a random variable whose distribution is dependent on the current incomplete data and the training data. The method differs from standard strategies in that our focus is on determining the reliability of the early classification decision, not only the accuracy. Proposed methods are tested on a set of open-domain time-series datasets; where the goal is to classify the time-series as early as possible while still guaranteeing that the reliability threshold is met.

Anderson, Hyrum S.↗

MicroBooNE BNB Electron Neutrino Overlay Sample (No Wire Info)

MicroBooNE samples are provided for collaborative development in two different formats: HDF5, targeting the broadest audience, and artroot, targeting users that are familiar with the software infrastructure of Fermilab neutrino experiments and more in general of HEP experiments. The HDF5 files are stored on Zenodo, together with a list of artroot files accessible with xrootd.This sample includes simulated interactions of neutrinos from the Booster Neutrino Beam (BNB), overlaid on top of cosmic ray data. The sample is restricted to charged-current electron neutrino interactions within the argon active volume of the time projection chamber.The HDF5 files in this sample do not include the information at the wire waveform level ("NoWire" label), allowing for larger number of events to be included in the data set.More documentation, including detailed description of content, recipes, and example usage, at https://github.com/uboone/OpenSamples.Suggested text for acknowledgment is the following:We acknowledge the MicroBooNE Collaboration for making publicly available the data sets [data set DOIs] employed in this work. These data sets consist of simulated neutrino interactions from the Booster Neutrino Beamline overlaid on top of cosmic data collected with the MicroBooNE detector [2017 JINST 12 P02017].In addition, we request that software products resulting from the usage of the datasets are also made publicly available.

Abratenko, Polina↗

MicroBooNE BNB Inclusive Overlay Sample (No Wire Info)

MicroBooNE samples are provided for collaborative development in two different formats: HDF5, targeting the broadest audience, and artroot, targeting users that are familiar with the software infrastructure of Fermilab neutrino experiments and more in general of HEP experiments. The HDF5 files are stored on Zenodo, together with a list of artroot files accessible with xrootd.This sample includes simulated interactions of neutrinos from the Booster Neutrino Beam (BNB), overlaid on top of cosmic ray data. The sample is inclusive, i.e. it includes all types of neutrinos and interactions, with relative abundance matching our nominal flux and cross section models. Interactions are simulated in in the whole cryostat volume.The HDF5 files in this sample do not include the information at the wire waveform level ("NoWire" label), allowing for larger number of events to be included in the data set.More documentation, including detailed description of content, recipes, and example usage, at https://github.com/uboone/OpenSamples.Suggested text for acknowledgment is the following:We acknowledge the MicroBooNE Collaboration for making publicly available the data sets [data set DOIs] employed in this work. These data sets consist of simulated neutrino interactions from the Booster Neutrino Beamline overlaid on top of cosmic data collected with the MicroBooNE detector [2017 JINST 12 P02017].In addition, we request that software products resulting from the usage of the datasets are also made publicly available.

Abratenko, Polina↗

DeepSAT: A Deep Learning Approach to Tree-Cover Delineation in 1-m NAIP Imagery for the Continental United States

High resolution tree cover classification maps are needed to increase the accuracy of current land ecosystem and climate model outputs. Limited studies are in place that demonstrates the state-of-the-art in deriving very high resolution (VHR) tree cover products. In addition, most methods heavily rely on commercial softwares that are difficult to scale given the region of study (e.g. continents to globe). Complexities in present approaches relate to (a) scalability of the algorithm, (b) large image data processing (compute and memory intensive), (c) computational cost, (d) massively parallel architecture, and (e) machine learning automation. In addition, VHR satellite datasets are of the order of terabytes and features extracted from these datasets are of the order of petabytes. In our present study, we have acquired the National Agriculture Imagery Program (NAIP) dataset for the Continental United States at a spatial resolution of 1-m. This data comes as image tiles (a total of quarter million image scenes with ~60 million pixels) and has a total size of ~65 terabytes for a single acquisition. Features extracted from the entire dataset would amount to ~8-10 petabytes. In our proposed approach, we have implemented a novel semi-automated machine learning algorithm rooted on the principles of "deep learning" to delineate the percentage of tree cover. Using the NASA Earth Exchange (NEX) initiative, we have developed an end-to-end architecture by integrating a segmentation module based on Statistical Region Merging, a classification algorithm using Deep Belief Network and a structured prediction algorithm using Conditional Random Fields to integrate the results from the segmentation and classification modules to create per-pixel class labels. The training process is scaled up using the power of GPUs and the prediction is scaled to quarter million NAIP tiles spanning the whole of Continental United States using the NEX HPC supercomputing cluster. An initial pilot over the state of California spanning a total of 11,095 NAIP tiles covering a total geographical area of 163,696 sq. miles has produced true positive rates of around 88 percent for fragmented forests and 74 percent for urban tree cover areas, with false positive rates lower than 2 percent for both landscapes.

Imagery↗

Entropy and Boundary Based Adversarial Learning for Large Scale Unsupervised Domain Adaptation

Supervised semantic segmentation methods provide state-of-the-art performance, but their performance is limited by the amount of quality labeled data they need for training. Scarcity of labeled data and non-transferablity of models, due to cross-domain discrepancy makes it a bigger challenge for remote sensing imagery analysis. In this work, we approach this problem through adversarial learning, driven by entropy and boundary of region-of-interest for unsupervised domain adaptation. This concept helps with better boundary prediction and encourages target domain entropy maps (probability/uncertainty maps) to be similar to source domains. In particular, we showed that deriving informative entropy through the adversarial learning is essential to enable the adaptation. We used a large scale cross country building extraction dataset to validate the framework. The experimental results show the usefulness of considering boundary and entropy driven adversarial learning for adaptation.

Makkar, Nikhil↗

EXSCLAIM!

Due to recent improvements in image resolution and acquisition speed, materials microscopy is experiencing an explosion of published imaging data. The standard publication format, while sufficient for traditional data ingestion scenarios where a select number of images can be critically examined and curated manually, is not conducive tolarge-scale data aggregation or analysis, hindering data sharing and reuse. Most images in publications are presented as components of a larger figure with their explicit context buried in the main body or caption text, so even if aggregated, collections of images with weak or no digitized contextual labels have limited value. To solve the problem of curating labeled microscopy data from literature, we introduce the EXSCLAIM! Python toolkit for the automatic EXtraction, Separation, and Caption-based natural Language Annotation of IMages from scientific literature. The software is implemented through a three part pipeline: the JournalScraper, which searches the web and downloads figures and captions based on a user provided query, the CaptionDistributor, which separates caption text based on the subfigure each portion of the caption refers to, and the FigueSeparator, which separates figures into component subfigures and extracts other visual information. Also included is a Django user interface for exploring the resulting dataset.

CHAN, MARIA↗

Privacy-Preserving Knowledge Transfer with Bootstrap Aggregation of Teacher Ensembles

There is a need to transfer knowledge among institutions and organizations to save effort in annotation and labeling or in enhancing task performance. However, knowledge transfer is difficult because of restrictions that are in place to ensure data security and privacy. Institutions are not allowed to exchange data or perform any activity that may expose personal information. With the leverage of a differential privacy algorithm in a high-performance computing environment, we propose a new training protocol, Bootstrap Aggregation of Teacher Ensembles (BATE), which is applicable to various types of machine learning models. The BATE algorithm is based on and provides enhancements to the PATE algorithm, maintaining competitive task performance scores on complex datasets with underrepresented class labels.We conducted a proof-of-the-concept study of the information extraction from cancer pathology report data from four cancer registries and performed comparisons between four scenarios: no collaboration, no privacy-preserving collaboration, the PATE algorithm, and the proposed BATE algorithm. The results showed that the BATE algorithm maintained competitive macro-averaged F1 scores, demonstrating that the suggested algorithm is an effective yet privacy-preserving method for machine learning and deep learning solutions.

Yoon, Hong-Jun↗

Poster — Thur Eve — 70: Automatic lung bronchial and vessel bifurcations detection algorithm for deformable image registration assessment

Purpose: To investigate an automatic bronchial and vessel bifurcations detection algorithm for deformable image registration (DIR) assessment to improve lung cancer radiation treatment. Methods: 4DCT datasets were acquired and exported to Varian treatment planning system (TPS) EclipseTM for contouring. The lungs TPS contour was used as the prior shape for a segmentation algorithm based on hierarchical surface deformation that identifies the deformed lungs volumes of the 10 breathing phases. Hounsfield unit (HU) threshold filter was applied within the segmented lung volumes to identify blood vessels and airways. Segmented blood vessels and airways were skeletonised using a hierarchical curve-skeleton algorithm based on a generalized potential field approach. A graph representation of the computed skeleton was generated to assign one of three labels to each node: the termination node, the continuation node or the branching node. Results: 320 ± 51 bifurcations were detected in the right lung of a patient for the 10 breathing phases. The bifurcations were visually analyzed. 92 ± 10 bifurcations were found in the upper half of the lung and 228 ± 45 bifurcations were found in the lower half of the lung. Discrepancies between ten vessel trees were mainly ascribed to large deformation and in regions where the HU varies. Conclusions: We established an automatic method for DIR assessment using the morphological information of the patient anatomy. This approach allows a description of the lung's internal structure movement, which is needed to validate the DIR deformation fields for accurate 4D cancer treatment planning.

60 APPLIED LIFE SCIENCES↗

SIDDA: SInkhorn Dynamic Domain Adaptation

Modern neural networks (NNs) often do not generalize well in the presence of a "covariate shift"; that is, in situations where the training and test data distributions differ, but the conditional distribution of classification labels remains unchanged. In such cases, NN generalization can be reduced to a problem of learning more domain-invariant features. Domain adaptation (DA) methods include a range of techniques aimed at achieving this; however, these methods have struggled with the need for extensive hyperparameter tuning, which then incurs significant computational costs. In this work, we introduce SIDDA, an out-of-the-box DA training algorithm built upon the Sinkhorn divergence, that can achieve effective domain alignment with minimal hyperparameter tuning and computational overhead. We demonstrate the efficacy of our method on multiple simulated and real datasets of varying complexity, including simple shapes, handwritten digits, and real astronomical observations. SIDDA is compatible with a variety of NN architectures, and it works particularly well in improving classification accuracy and model calibration when paired with equivariant neural networks (ENNs). We find that SIDDA enhances the generalization capabilities of NNs, achieving up to a ≈40% improvement in classification accuracy on unlabeled target data. We also study the efficacy of DA on ENNs with respect to the varying group orders of the dihedral group DN, and find that the model performance improves as the degree of equivariance increases. Finally, we find that SIDDA enhances model calibration on both source and target data--achieving over an order of magnitude improvement in the ECE and Brier score. SIDDA's versatility, combined with its automated approach to domain alignment, has the potential to advance multi-dataset studies by enabling the development of highly generalizable models.

Pandya, Sneh [Northeastern U.]↗

Development and Application of NASA SPoRT’s DustTracker-AI Model for Real-Time Identification and Tracking of Dust in Geostationary Satellite Imagery

The NASA Short-term Prediction Research and Transition (SPoRT) Center developed the DustTracker-AI model for identifying and tracking dust in NASA/NOAA Geostationary Operational Environmental Satellite (GOES) imagery in a real-time framework. A training dataset consisting of day and night dust cases was gathered over the southwestern consisting of 115 distinct images and over a million dust pixels and 256 million no dust pixels. The dataset was separated into training (60%), testing (20%), and validation (20%). A simple random forest machine learning model was developed originally to overcome the problem of night-time dust detection and has been expanded to a comprehensive day/night model for dust identification and tracking. This physically-based machine-learning approach uses NASA/NOAA GOES-16 Advanced Baseline Imager infrared imagery as inputs to the model. The model probability of dust output achieves an Area-Under-Curve (AUC) of 0.97 with a standard deviation of 0.04 for dust cases. For images with dust present, the model correctly labels 85% of dust pixels for all dust images in the validation data set. In conjunction with developing the machine-learning model, the NASA Short-term Prediction Research and Transition Center (SPoRT) partnered with NOAA National Weather Service forecast offices to evaluate the model for utility in weather forecasting operations during the 2021 and 2023 late winter-spring seasons. Preliminary evaluation has indicated the majority of forecasters described the DustTracker-AI probabilities as having added confidence to interpreting the Dust RGB and other satellite products to objectively assess the dust extent and trends and increased the amount of time the dust plume could be tracked into the night as compared to use of the Dust RGB. More recently, SPoRT tested small scale events associated with thunderstorm outflow and burn scars to determine the model’s ability to capture local events. This presentation highlights design of the model, validation/evaluation of model performance, and example cases collected during end user product assessments.

Connor H Welch↗

Total Dissolved Nitrogen and Ammonia Data for the East River Watershed, Colorado (2015-2025)

This data package contains mean values for total dissolved nitrogen (TDN) and ammonia concentrations for water samples taken from the East River Watershed in Colorado. The East River is part of the Watershed Function Scientific Focus Area (WFSFA) located in the Upper Colorado River Basin, United States. TDN was analyzed using a Shimadzu Total Nitrogen Module (TNM-1) combined with the TOC-VCSH analyzer (Shimadzu Corporation, Japan). TNM-1 is a non-specific measurement of total nitrogen (TN). All nitrogen species in samples are combusted to nitrogen monoxide and nitrogen dioxide, then reacted with ozone to form an excited state of nitrogen dioxide. Upon returning to ground state, light energy is emitted. Then, TDN is measured using a chemiluminescence detector. Ammonia was determined using a Lachat's QuikChem 8500 Series 2 Flow Injection Analysis System (LACHAT Instruments, QuckChem 8500 series 2, Automated Ion Analyzer, Loveland, Colorado). When ammonia in water samples is heated (60 degrees C) with salicylate and hypochlorite in an alkaline phosphate buffer, an emerald green color is produced which is proportional to the ammonia concentration. The color is intensified by the addition of nitroprusside. Ethylenediaminetetraacetic acid (EDTA) is added to the buffer to prevent the interference of metal ions (Ca, Mg, and Fe etc.). Ammonia-N is then determined by LACHAT flow injection and a colorimetric assay at an absorbance wavelength 660 nm. (Reference: LACHAT Instruments: QuickChem Method 90-107-06-3-A, Determination of Ammonia by Flow Injection Analysis (High Throughput, Salicylate Method/DCIC) (Multi Matrix method). Written by Lynn Egan (Application group), February 08, 2011.) All files are labeled by location and variable, and data reported are the mean values upon replicate measurements. All samples were analyzed under a rigorous quality assurance and quality control (QA/QC) process as detailed in the methods. This data package contains (1) a zip file (tdn_ammonia_data_2015-2025.zip) containing a total of 299 files: 298 data files of ammonia and TDN data from across the Lawrence Berkeley National Laboratory (LBNL) Watershed Function Scientific Focus Area (SFA) which is reported in .csv files per location and a locations.csv (1 file) with latitude and longitude for each location; (2) a file-level metadata (v7_20260901_flmd.csv) file that lists each file contained in the dataset with associated metadata; (3) a data dictionary (v7_20260901_dd.csv) file that contains terms/column_headers used throughout the files along with a definition, units, and data type; (4) PDF and docx files for the determination of Method Detection Limits (MDLs) for TDN data, which has been updated in 2026-08; and (5) PDF and docx files for the detemination of Method Detection Limits (MDLs) for Ammonia and the Interferences by LACHAT Flow Injection Analysis. Missing values within the anion data files are noted as either "-9999" or "0.0" for not detectable (N.D.) data. There are a total of 105 locations containing TDN and Ammonia-N data. Update 2020-10-07: Updated the data files to remove times from the timestamps, so that only dates remain. The data values have not changed. Update 2021-04-11: Added Determination of Method Detection Limits (MDLs) for DIC, NPOC and TDN Analyses and Determination of Method Detection Limit for Ammonia and the Interferences by LACHAT Flow Injection Analysis documents, which can be accessed as PDFs or with Microsoft Word.Update on 6/10/2022: versioned updates to this dataset was made along with these changes: (1) updated total dissolved nitrogen and ammonia data for all locations up to 2021-12-31, (2) removal of units from column headers in datafiles, (3) added row underneath headers to contain units of variables, (4) restructure of units to comply with CSV reporting format requirements, (5) added -9999 for empty numerical cells, and (6) the addition of the file-level metadata (flmd.csv) and data dictionary (dd.csv) were added to comply with the File-Level Metadata Reporting Format. Update on 2022-09-09: Updates were made to reporting format specific files (file-level metadata and data dictionary) to correct swapped file names, add additional details on metadata descriptions on both files, add a header_row column to enable parsing, and add version number and date to file names (v2_20220909_flmd.csv and v2_20220909_dd.csv). Update on 2022-12-20: Updates were made to both the data files and reporting format specific files. Units were listed incorrectly, but have been fixed to reflect correct units (ug/L). File level metadata (flmd) and data dictionary (dd) files were updated to reflect the updated versions of these files. Available data was added up until 2022-06-01. Update on 2023-08-08: Updates were made to both the data files and reporting format specific files. New available anion data was added, up until 2023-01-05. The file level metadata and data dictionary files were updated to reflect the additional data added. Update on 2024-03-11: Updates were made to both the data files and reporting format specific files. New available anion data was added, up until 2023-10-27. Further, revisions to the data files were made to remove incorrect data points (from 1970 and 2001). The reporting format specific files were updated to reflect the additional data added. Revised versions of the PDF and docx files for determination of MDLs for TDN were added to replace previous versions. Update on 2025-05-15: Updates were made to both the data files and reporting format specific files. New available TDN and Ammonia-N data was added, up until the end of WY2024 (September 30, 2024). International Generic Sample Numbers (IGSNs), when registered, were added to the data files. The reporting format specific files were updated to reflect the additional data added. Update on 2026-09-01: Updates were made to both the data files and reporting format specific files. New available TDN and Ammonia-N data was added, up until the end of WY2025 (September 30, 2025). Updated versions, as of 2026-08-10, of the PDF and docx files for determination of MDLs for TDN data were added to this dataset.

54 ENVIRONMENTAL SCIENCES↗

Artificial intelligence models, photos, and data associated with the manuscript “Quantifying Streambed Grain Size, Uncertainty, and Hydrobiogeochemical Parameters Using Machine Learning Model YOLO” (v2)

This data package is associated with the manuscript “Quantifying Streambed Grain Size, Uncertainty, and Hydrobiogeochemical Parameters Using Machine Learning Model YOLO” published in Water Resources Research (Chen et al., 2024). This data package includes the training, validation, testing, and prediction data used by the artificial intelligence (AI) model for automated grain size and hydro-biogeochemistry quantification using streambed photos. The grain size data are extracted for each photo using You Look Only Once (YOLO), a pre-trained object detection model. This data package was originally published in October 2023. It was updated August 2025 (v2; new and modified files). File and folder names were not revised to indicate changes. See the change history section in the readme for more details. Please see flmd.csv for a list of all files contained in this data package and descriptions for each. Please see dd.csv for a data dictionary that defines the column headers of .csv files in the data package. This dataset is comprised of one data folder containing (1) file-level metadata; (2) data dictionary; (3) readme; and (4) six subfolders. Subfolders 1 to 4 include the training, validation, testing, and prediction data. Subfolder 5_Summary includes the summary results of different combinations of training, validation, testing, and prediction data. Subfolder 6_SupplementalData includes additional data downloaded from public sources (Kaufman et al., 2023a; Kaufman et al., 2023b; Garefalakis et al., 2023; Mair et al., 2024; https://github.com/river-corridors-sfa/Geospatial_variables). In total, the data package includes 110 folders and 44,283 files. These files include 9,047 .jpg photos, 1 .png photo, 3 .tif photos; 26,639 photo labels and individual grain sizes and probability from AI (.txt); 8,447 grain size distribution data (.dat); and 126 CSV files for results summary, and 14 required metadata files (.xlsx). The summary CSV files contain 68 columns and approximately 2,200 rows that represent photo names, site locations, recording time, GPS coordinates, grains sizes (D10, D50, D60, and D84), number of grains, and additional hydro-biogeochemical data such as water depth, flow velocity, Manning’s coefficient, friction factor, hydraulic conductivity, permeability, streambed interstitial velocity magnitude, mass transfer rate, and nitrate uptake velocity. The photos were obtained from 75 sites in the Yakima River Basin and the Columbia River shorelines, and other associated data from samples and sensors obtained when the photos were taken are publicly available (Fulton et al. 2022; Grieger et al. 2023). All files are .csv, .txt, .dat, .jpg, or .pdf. We acknowledge the Yakama Nation as owners and caretakers of the lands where we collected some of these data. We thank the Confederated Tribes and Bands of the Yakama Nation Tribal Council and Yakama Nation Fisheries for working with us to facilitate sample collection and optimization of data usage according to their values and worldview.

54 ENVIRONMENTAL SCIENCES↗

Residual tissue repositories as a resource for population-based cancer proteomic studies

Background: Mass spectrometry-based proteomics has become a powerful tool for the identification and quantification of proteins from a wide variety of biological specimens. To date, the majority of studies utilizing tissue samples have been carried out on prospectively collected fresh frozen or optimal cutting temperature (OCT) embedded specimens. However, such specimens are often difficult to obtain, in limited in supply, and clinical information and outcomes on patients are inherently delayed as compared to banked samples. Annotated formalin fixed, paraffin embedded (FFPE) tumor tissue specimens are available for research use from a variety of tissue banks, such as from the surveillance, epidemiology and end results (SEER) registries’ residual tissue repositories. Given the wealth of outcomes information associated with such samples, the reuse of archived FFPE blocks for deep proteomic characterization with mass spectrometry technologies would provide a valuable resource for population-based cancer studies. Further, due to the widespread availability of FFPE specimens, validation of specimen integrity opens the possibility for thousands of studies that can be conducted worldwide. Methods: To examine the suitability of the SEER repository tissues for proteomic and phosphoproteomic analysis, we analyzed 60 SEER patient samples, with time in storage ranging from 7 to 32 years; 60 samples with expression proteomics and 18 with phosphoproteomics, using isobaric labeling. Linear modeling and gene set enrichment analysis was used to evaluate the impacts of collection site and storage time. Results: All samples, regardless of age, yielded suitable protein mass after extraction for expression analysis and 18 samples yielded sufficient mass for phosphopeptide analysis. Although peptide, protein, and phosphopeptide identifications were reduced by 50, 20 and 76% respectively, from comparable OCT specimens, we found no statistically significant differences in protein quantitation correlating with collection site or specimen age. GSEA analysis of GOterm level measurements of protein abundance differences between FFPE and OCT embedded specimens suggest that the formalin fixation process may alter representation of protein categories in the resulting dataset. Conclusions: These studies demonstrate that residual FFPE tissue specimens, of varying age and collection site, are a promising source of protein for proteomic investigations if paired with rigorously verified mass spectrometry workflows.

60 APPLIED LIFE SCIENCES↗

Snow Depth and Density at End-of-Winter for NGEE Areas A, B, C and D, Utqiagvik (Barrow), Alaska, 2012-2014

End-of-winter snow depth and average snow density from area A, B, C and D, which include 1000's of point depth measurement located between ~20 and ~50 cm apart. The data was originally provided in excel workbooks, these files have been preserved within the zip Original_Files. The files were transformed for archiving with images pulled out into jpegs and data preserved as csv files. Some functions, features, and formatting was lost during the transformation. Missing data was defined with blank cells. Additional documentation can be found in files labelled with readme.csv and information.csv file endings.The Next-Generation Ecosystem Experiments: Arctic (NGEE Arctic), was a research effort to reduce uncertainty in Earth System Models by developing a predictive understanding of carbon-rich Arctic ecosystems and feedbacks to climate. NGEE Arctic was supported by the Department of Energy's Office of Biological and Environmental Research.The NGEE Arctic project had two field research sites: 1) located within the Arctic polygonal tundra coastal region on the Barrow Environmental Observatory (BEO) and the North Slope near Utqiagvik (Barrow), Alaska and 2) multiple areas on the discontinuous permafrost region of the Seward Peninsula north of Nome, Alaska.Through observations, experiments, and synthesis with existing datasets, NGEE Arctic provided an enhanced knowledge base for multi-scale modeling and contributed to improved process representation at global pan-Arctic scales within the Department of Energy's Earth system Model (the Energy Exascale Earth System Model, or E3SM), and specifically within the E3SM Land Model component (ELM).

54 ENVIRONMENTAL SCIENCES↗

Integrating Natural Language Processing and Machine Learning Algorithms to Categorize Oncologic Response in Radiology Reports

A significant volume of medical data remains unstructured. Natural language processing (NLP) and machine learning (ML) techniques have shown to successfully extract insights from radiology reports. However, the codependent effects of NLP and ML in this context have not been well-studied. Between April 1, 2015 and November 1, 2016, 9418 cross-sectional abdomen/pelvis CT and MR examinations containing our internal structured reporting element for cancer were separated into four categories: Progression, Stable Disease, Improvement, or No Cancer. We combined each of three NLP techniques with five ML algorithms to predict the assigned label using the unstructured report text and compared the performance of each combination. The three NLP algorithms included term frequency-inverse document frequency (TF-IDF), term frequency weighting (TF), and 16-bit feature hashing. The ML algorithms included logistic regression (LR), random decision forest (RDF), one-vs-all support vector machine (SVM), one-vs-all Bayes point machine (BPM), and fully connected neural network (NN). The best-performing NLP model consisted of tokenized unigrams and bigrams with TF-IDF. Increasing N-gram length yielded little to no added benefit for most ML algorithms. With all parameters optimized, SVM had the best performance on the test dataset, with 90.6 average accuracy and F score of 0.813. The interplay between ML and NLP algorithms and their effect on interpretation accuracy is complex. The best accuracy is achieved when both algorithms are optimized concurrently.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

ICAT: The Interactive Corpus Analysis Tool

The Interactive Corpus Analysis Tool (ICAT) is a Python library for creating dashboards to explore textual datasets and build simple binary classification models to help filter through them and focus on entries of interest. This tool uses a form of interactive machine learning (IML), a paradigm of “machine teaching” (Simard et al., 2017) that sits at the intersection of the fields of human computer interaction (HCI), visual analytics, and machine learning. The intent of ICAT is to allow subject matter experts (SME) with limited to no experience in machine learning to benefit from an iterative human-in-the-loop (HITL) approach to building their own model without needing to understand the details of the underlying algorithm. This interactivity is achieved by allowing the user to create features, label data points, and visually manipulate a representation of the features to manually cluster and investigate data, while a model is trained on the fly based on these actions. ICAT is built on top of the Panel (Holoviz, 2018) library, using a combination of Vega, a custom IPyWidget using D3, and ipyvuetify, and is intended to be used inside of a Jupyter environment.

Martindale, Nathan [Oak Ridge National Laboratory ↗