Search NASA⌕ Search

SEARCH · Search NASA

Results for “Data segmentation”

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 667 records · Page 37

SU-E-T-100: Designing a QA Tool for Enhance Dynamic Wedges Based On Dynalog Files

Purpose: A robust quality assurance (QA) program for computer controlled enhanced dynamic wedge (EDW) has been designed and tested. Calculations to perform such QA test is based upon the EDW dynamic log files generated during dose delivery. Methods: Varian record and verify system generates dynamic log (dynalog) files during dynamic dose delivery. The system generated dynalog files contain information such as date and time of treatment, energy, monitor units, wedge orientation, and type of treatment. It also contains the expected calculated segmented treatment tables (STT) and the actual delivered STT for the treatment delivery as a verification record. These files can be used to assess the integrity and precision of the treatment plan delivery. The plans were delivered with a 6 MV beam from a Varian linear accelerator. For available EDW angles (10°, 15°, 20°, 25°, 30°, 45°, and 60°) Varian STT values were used to manually calculate monitor units for each segment. It can also be used to calculate the EDW factors. Independent verification of fractional MUs per segment was performed against those generated from dynalog files. The EDW factors used to calculate MUs in TPS were dosimetrically verified in solid water phantom with semiflex chamber on central axis. Results: EDW factors were generated from the STT provided by Varian and verified against practical measurements. The measurements were in agreement of the order of 1 % to the calculated EDW data. Variation between the MUs per segment obtained from dynalog files and those manually calculated was found to be less than 2%. Conclusion: An efficient and easy tool to perform routine QA procedure of EDW is suggested. The method can be easily implemented in any institution without a need for expensive QA equipment. An error of the order of ≥2% can be easily detected.

60 APPLIED LIFE SCIENCES↗

Transportation monitoring unit qualification

Transportation monitoring unit (TMU) qualification testing was performed between 3 Mar. and 14 Dec. 1989. The purpose of the testing was to qualify the TMUs to monitor and store temperature and acceleration data on redesigned solid rocket motor segments and exit cones while they are being shipped from Utah's Thiokol Corporation, Space Operations, to Kennedy Space Center. TMUs were subjected to transportation tests that concerned the structural integrity of the TMUs only, and did not involve TMU measuring capability. This testing was terminated prior to completion due to mounting plate failures, high and low temperature shutdown failures, and data collection errors. Corrective actions taken by the vendor to eliminate high temperature shutdowns were ineffective. An evaluation was performed on the TMUs to determine the TMU vibration and temperature measuring accuracy at a variety of temperatures. This test demonstrated that TMU measured shock levels are high, and that TMUs are temperature sensitive because of decreased accuracy at high and low temperatures. It was determined that modifications to the current TMU system, such that it could be qualified for use, would require a complete redesign and remanufacture. Because the cost of redesigning and remanufacturing the present TMU system exceeds the cost of procuring a new system that could be qualified without modification, it is recommended that an alternate transportation monitoring system be qualified.

Cook, M.↗

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

In this work, we use few-shot learning to segment the body and vein architecture of P. trichocarpa leaves from high-resolution scans obtained in the UC Davis common garden. Leaf and vein segmentation are formulated as separate tasks, in which convolutional neural networks (CNNs) are used to iteratively expand partial segmentations until reaching stopping criteria. Our leaf and vein segmentation approaches use just 50 and 8 manually traced images for training, respectively, and are applied to a set of 2,634 top and bottom leaf scans. We show that both methods achieve high segmentation accuracy, in some cases exceeding even human-level segmentation. The leaf and vein segmentations are subsequently used to extract 68 morphological traits using traditional open-source image processing tools, which are validated using real-world physical measurements. For a biological perspective, we perform a genome-wide association study using the vein density trait to discover novel genetic architectures associated with multiple physiological processes relating to leaf development and function. In addition to sharing all of the few-shot learning code (see https://github.com/jlager/few-shot-leaf-segmentation), we are releasing all images, manual segmentations, model predictions, 68 extracted leaf phenotypes, and a new set of SNPs called against the v4 P. trichocarpa genome for 1,419 genotypes. The data folder includes all images, ground truth segmentations, predicted segmentations, and extracted leaf traits. All images encode the sample ID in the file name by indicating the treatment, block, row, position, and leaf side, respectively. For example, the file, C_1_1_2_bot.jpeg, indicates the control treatment, block 1, row 1, position 2, and the bottom side of the leaf. Tabulated results include position IDs as well as the corresponding genotype IDs. The images folder includes the 2,906 high-resolution leaf scans taken in the field. The leaf_masks folder includes 50 ground truth segmentations used for training the leaf tracing algorithm. The leaf_preds folder includes the 2,906 predicted segmentations from the leaf tracing algorithm. The vein_masks folder includes 8 ground truth segmentations used for training the vein growing algorithm. The vein_preds folder includes the 1,453 predicted segmentations from the vein growing algorithm. The vein_probs folder includes the 1,453 predicted probability maps from the vein growing algorithm before thresholding. The genomes folder includes the set of SNPs called against the v4 P. trichocarpa genome for 1,419 genotypes with a README file detailing the steps taken. The results folder includes: (i) raw values of the 68 predicted leaf traits in digital_traits.tsv, (ii) manually measured values of petiole length and width in manual_traits.tsv, (iii) thin plate spline (TPS) adjusted values of the vein density trait in vein_density_tps_adj.tsv, (iv) best linear unbiased prediction (BLUP) adjusted values of the vein density trait in vein_density_blups.tsv, and (v) GWAS results for the vein density trait, including chromosome positions and corresponding P values, in gwas_results.csv.

09 BIOMASS FUELS↗

CHESS 2025: Waveform LiDAR data from NEON AOP surveys

This dataset provides Level 1 (L1) full-waveform light detection and ranging (LiDAR) data collected for the 2025 Colorado Headwaters Ecological Spectroscopy Study (CHESS). These data were acquired to enable characterization of vegetation structure and other three-dimensional features of the land surface, and to evaluate structural changes that may have occurred between a prior LiDAR acquisition in 2018 and the 2025 overflight. Waveform LiDAR data can provide more detailed information about objects on the ground than discrete point clouds typically do, and they are often used for granular target segmentation and characterization of subcanopy vegetation. The data were acquired over three study domains in the Upper Gunnison river basin: the upper East River watershed (CRBU); Almont Triangle and Taylor Canyon (ALMO); and Upper Taylor River watershed (UPTA) between 2025-06-13 and 2025-07-15. LiDAR data were acquired using the Optech Galaxy Prime Airborne LiDAR Terrain Mapper onboard the National Ecological Observatory Network (NEON) Airborne Observation Platform (AOP). These are the primary waveform LiDAR data delivered by NEON and are provided per flightline in compressed Pulsewaves format, an open-source binary file standard. A Pulsewaves object comprises a two files: a pulse (.pls) file, which stores the geographic origin, outgoing vector, and metadata for every laser pulse emitted by the scanner, and a wave file (.wvs), which stores the sequential amplitude samples of the outgoing pulse and the returning signals. The files are published here in their compressed forms (.plz, .wvz). All waveform data were processed following the theoretical workflow described in the NEON L0-to-L1 Waveform LiDAR Algorithm Theoretical Basis Document (Krause and Goulden 2022a); however, the Pulsewaves output format differs from a legacy format described in that document. Waveform amplitude samples are recorded at 1 nanosecond intervals. All coordinates are provided in meters. Horizontal coordinates are referenced in Universal Transverse Mercator (UTM) zone 13N and the World Geodetic System (WGS) 1984 ensemble datum. Elevations are referenced to Geoid12A. Waveform data for the UPTA survey area were collected without incident and the published records are complete. However, both the ALMO and CRBU collections experienced issues that resulted in incomplete data for those areas. On collection day 2018-06-16 a hardware failure caused the waveform digitizer to lose data from the eastern edge of the ALMO site (Figure 22). The waveform data for flightlines 2–20 could not be extracted from the digitizer, and the data proved unrecoverable. As a result, a portion of the site does not have coverage with waveform data. Although no hardware failure was observed during collection over the CRBU area, final waveform files generated by vendor software contained only ~25% of the expected number of return pulses. After discovery, NEON initiated troubleshooting with the vendor. The root cause of the data ablation had not been identified at the time of publication. Additional data will be published in an update to this package if further recovery proves successful. CHESS Project Description: The Colorado Headwaters Ecological Spectroscopy Study (CHESS) comprised a multi-week airborne remote sensing and field observation campaign in the Upper Gunnison Basin, Colorado, conducted in June and July of 2025. Airborne remote sensing was conducted by the National Ecological Observatory Network Airborne Observation Platform (NEON AOP), concurrent with a field campaign run by the Rocky Mountain Biological Laboratory (RMBL), the Lawrence Berkeley National Laboratory (LBNL) and SLAC National Accelerator Laboratory Watershed Function Science Focus Area (SFA), and NASA-JPL (Jet Propulsion Laboratory) Earth Surface Mineral Dust Source Investigation (EMIT) program. Between June 10 and July 18, 2025, the NEON AOP flight team collected high-resolution aerial imaging spectroscopy and Light Detection and Ranging (LiDAR) data over three domains: the Upper East River (CRBU), Almont Triangle (ALMO), and the Upper Taylor Basin (UPTA). In coordination with the flights, a field campaign acquired ground-truth observations, including observations of vegetation composition, foliar traits, forest demography, and subsurface properties in 18 core sampling areas within the domains. Additional surface water observations were taken at over 380 point locations. All CHESS campaign datasets can be found within the CHESS ESS-DIVE data portal: https://data.ess-dive.lbl.gov/portals/chess. Funding Acknowledgement: Field and remote-sensing data acquisition was performed under a grant from the National Aeronautics and Space Administration (80NSSC24K1005). This work was also supported by the Watershed Function Science Focus Area at Lawrence Berkeley National Laboratory funded by the US Department of Energy, Office of Science, Biological and Environmental Research under Contract No. DE-AC02-05CH11231.

2018 NEON and 2025 CHESS Campaigns↗

Computer sizing of fighter aircraft

The computer sizing technique has been applied to a number of military mission profiles. Performance data can be determined for all segments of the selected profile, which typically include takeoff, climb, cruise, loiter, reserve and landing segments. Options are available for detailed calculation of combat performance and energy-maneuverability characteristics. Configuration changes, such as external fuel tank drop and weapon expenditure, can be included in the mission. In the sizing mode, aircraft gross weight, wing loading, and thrust-to-weight ratio are varied automatically to determine which combinations meet the design mission radius. The resulting performance data can be used to create a thumbprint plot. This plot is useful in determining the configuration size that best satisfies the mission and performance requirements. The sizing mode can also be used to perform parametric studies such as sensitivity of gross weight to alternate design conditions.

Coen, P. G.↗

Computer sizing of fighter aircraft

The computer sizing technique has been applied to a number of military mission profiles. Performance data can be determined for all segments of the selected profile, which typically include takeoff, climb, cruise, loiter, reserve and landing segments. Options are available for detailed calculation of combat performance and energy-maneuverability characteristics. Configuration changes, such as external fuel tank drop and weapon expenditure, can be included in the mission. In the sizing mode, aircraft gross weight, wing loading, and thrust-to-weight ratio are varied automatically to determine which combinations meet the design mission radius. The resulting performance data can be used to create a thumbprint plot. This plot is useful in determining the configuration size that best satisfies the mission and performance requirements. The sizing mode can also be used to perform parametric studies such as sensitivity of gross weight to alternate design conditions.

Coen, P. G.↗

The Analysis of the Patterns of Radiation-Induced DNA Damage Foci by a Stochastic Monte Carlo Model of DNA Double Strand Breaks Induction by Heavy Ions and Image Segmentation Software

To create a generalized mechanistic model of DNA damage in human cells that will generate analytical and image data corresponding to experimentally observed DNA damage foci and will help to improve the experimental foci yields by simulating spatial foci patterns and resolving problems with quantitative image analysis. Material and Methods: The analysis of patterns of RIFs (radiation-induced foci) produced by low- and high-LET (linear energy transfer) radiation was conducted by using a Monte Carlo model that combines the heavy ion track structure with characteristics of the human genome on the level of chromosomes. The foci patterns were also simulated in the maximum projection plane for flat nuclei. Some data analysis was done with the help of image segmentation software that identifies individual classes of RIFs and colocolized RIFs, which is of importance to some experimental assays that assign DNA damage a dual phosphorescent signal. Results: The model predicts the spatial and genomic distributions of DNA DSBs (double strand breaks) and associated RIFs in a human cell nucleus for a particular dose of either low- or high-LET radiation. We used the model to do analyses for different irradiation scenarios. In the beam-parallel-to-the-disk-of-a-flattened-nucleus scenario we found that the foci appeared to be merged due to their high density, while, in the perpendicular-beam scenario, the foci appeared as one bright spot per hit. The statistics and spatial distribution of regions of densely arranged foci, termed DNA foci chains, were predicted numerically using this model. Another analysis was done to evaluate the number of ion hits per nucleus, which were visible from streaks of closely located foci. In another analysis, our image segmentaiton software determined foci yields directly from images with single-class or colocolized foci. Conclusions: We showed that DSB clustering needs to be taken into account to determine the true DNA damage foci yield, which helps to determine the DSB yield. Using the model analysis, a researcher can refine the DSB yield per nucleus per particle. We showed that purely geometric artifacts, present in the experimental images, can be analytically resolved with the model, and that the quantization of track hits and DSB yields can be provided to the experimentalists who use enumeration of radiation-induced foci in immunofluorescence experiments using proteins that detect DNA damage. An automated image segmentaiton software can prove useful in a faster and more precise object counting for colocolized foci images.

Ponomarev, Artem↗

Apodization Specific Fitting for Improved Resolution, Charge Measurement, and Data Analysis Speed in Charge Detection Mass Spectrometry

Short-time Fourier transforms with short segment lengths are typically used to analyze single ion charge detection mass spectrometry (CDMS) data either to overcome effects of frequency shifts that may occur during the trapping period or to more precisely determine the time at which an ion changes mass or charge, or enters an unstable orbit. The short segment lengths can lead to scalloping loss unless a large number of zero-fills are used, making computational time a significant factor in real-time analysis of data. Apodization specific fitting leads to a 9-fold reduction in computation time compared to zero-filling to a similar extent of accuracy. This makes possible real-time data analysis using a standard desktop computer. Rectangular apodization leads to higher resolution than the more commonly used Gaussian or Hann apodization and makes it possible to separate ions with similar frequencies, a significant advantage for experiments in which the masses of many individual ions are measured simultaneously. Equally important is a >20% increase in S/N obtained with rectangular apodization compared to Gaussian or Hann, which directly translates to a corresponding improvement in accuracy of both charge measurements and ion energy measurements that rely on the amplitudes of the fundamental and harmonic frequencies. Finally, combined with computing the fast Fourier transform in a lower-level language, this fitting procedure eliminates computational barriers and should enable real-time processing of CDMS data on a laptop computer.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

An Analysis of U.S. Civil Rotorcraft Accidents by Cost and Injury (1990-1996)

A study of rotorcraft accidents was conducted to identify safety issues and research areas that might lead to a reduction in rotorcraft accidents and fatalities. The primary source of data was summaries of National Transportation Safety Board (NTSB) accident reports. From 1990 to 1996, the NTSB documented 1396 civil rotorcraft accidents in the United States in which 491 people were killed. The rotorcraft data were compared to airline and general aviation data to determine the relative safety of rotorcraft compared to other segments of the aviation industry. In depth analysis of the rotorcraft data addressed demographics, mission, and operational factors. Rotorcraft were found to have an accident rate about ten times that of commercial airliners and about the same as that of general aviation. The likelihood that an accident would be fatal was about equal for all three classes of operation. The most dramatic division in rotorcraft accidents is between flights flown by private pilots versus professional pilots. Private pilots, flying low cost aircraft in benign environments, have accidents that are due, in large part, to their own errors. Professional pilots, in contrast, are more likely to have accidents that are a result of exacting missions or use of specialized equipment. For both groups judgement error is more likely to lead to a fatal accident than are other types of causes. Several approaches to improving the rotorcraft accident rate are recommended. These mostly address improvement in the training of new pilots and improving the safety awareness of private pilots.

Iseler, Laura↗

Depth-resolved soil data from DOE-LM Riverton Wyoming site, April-September 2017

Averaged (from 3 to 5 replicates) and QA/QC:d data for soil cores taken roughly every month in the period April 5 to September 13 in 2017 at a location close to DOE Legacy Management well 855 at the Riverton, Wyoming floodplain site. The groundwater at this site exhibits persistent U, Mo, and sulfate plumes and is one of the field sites in focus for the SLAC Groundwater Quality SFA program. Cores were separated into 5-20 cm segments based on soil horizonation and each segment was subsampled for microbial analyses (data available at the NCBI Single Read Archive (SRA) Database, https://www.ncbi.nlm.nih.gov/sra/, BioProject ID# PRJNA626616) in addition to the soil analyses included in this dataset. The soil analyses dataset includes aerobic and anaerobic respiration rate estimates (MicroResp method), water content estimates (on collected samples, not in situ), total C, N, S, Ca, K, Mg, Na, Fe, As, Mo, U, and organic-C concentrations, water extractable concentrations of the same elements, and HCl-extractable Fe(II) concentrations.There are four files included in this data package: metadataFile.csv, avgDataFile.csv, methodFile.csv, and RVT2017soilData.xlsx. The excel file contains the same information as the individual csv-files (in separate tabs).

54 ENVIRONMENTAL SCIENCES↗

Comparison of temporal resolution selection approaches in energy systems models

Capacity expansion models for the power sector are used to project future decisions over the coming decades by simulating investment and operation decisions for the use of electricity. Due to model performance constraints, these models typically do not explicitly simulate every hour within a year, but instead simulate representative time segments (groups of hours). This paper evaluates different approaches for selecting time segments across three methods: sequential, categorical, and clustering, across a wide range of time-segment quantities, for a total of 204 temporal profiles. To measure the performance of each profile's ability to accurately represent data, the root-mean-square-error of each profile's time segments are compared to the data's original hourly data. The temporal alignment across regions is also measured (i.e., how often windy days align across regions). Different spatial resolutions were applied for a subset of the temporal selection methods to investigate the impact spatial resolution has on performance. This paper provides a framework for measuring the value of different temporal selection methods and of adding more granular data to energy system models. Overall, multi-criteria clustering yields the lowest root-mean-square-error across all datasets evaluated and provides a holistic view of the intertwined relationships between renewable generation and electricity demand.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗

Poster — Thur Eve — 71: A 4D Multimodal Lung Phantom for Regmentation Evaluation

Segmentation and registration of medical imaging data are two processes that can be integrated (a process termed regmentation) to iteratively reinforce each other, potentially improving efficiency and overall accuracy. A significant challenge is presented when attempting to validate the joint process particularly with regards to minimizing geometric uncertainties associated with the ground truth while maintaining anatomical realism. This work demonstrates a 4D MRI, PET, and CT compatible tissue phantom with a known ground truth for evaluating registration and segmentation accuracy. The phantom consists of a preserved swine lung connected to an air pump via a PVC tube for inflation. Mock tumors were constructed from sea sponges contained within two vacuum-sealed compartments with catheters running into each one for injection of radiotracer solution. The phantom was scanned using a GE Discovery-ST PET/CT scanner and a 0.23T Phillips MRI, and resulted in anatomically realistic images. A bifurcation tracking algorithm was implemented to provide a ground truth for evaluating registration accuracy. This algorithm was validated using known deformations of up to 7.8 cm using a separate CT scan of a human thorax. Using the known deformation vectors to compare against, 76 bifurcation points were selected. The tracking accuracy was found to have maximum mean errors of −0.94, 0.79 and −0.57 voxels in the left-right, anterior-posterior and inferior-superior directions, respectively. A pneumatic control system is under development to match the respiratory profile of the lungs to a breathing trace from an individual patient.

60 APPLIED LIFE SCIENCES↗

Geometric correction process for the Landsat-4 Thematic Mapper

The processing approaches which form the basis of the Landsat-4 Thematic Mapper (TM) geometric correction system are summarized. The correction is accomplished in two phases. In the first phase, correction data are generated. The spacecraft position, TM frame attitude, TM scanning mirror position, and detector sampling are found as a function of time through a combination of flight segment measurements, ground segment modeling, and control point information. The data, along with the earth position and geoid model, are used to determine the earth location for each TM image sample. Then, using map projections, correction data can be generated which define the location of each TM image sample on the output coordinate system. In the second phase, the correction data are used to resample TM detector samples onto the output coordinate system.

Beyer, E. P.↗

Segmentation-free empirical beam hardening correction for CT

Purpose: The polychromatic nature of the x-ray beams and their effects on the reconstructed image are often disregarded during standard image reconstruction. This leads to cupping and beam hardening artifacts inside the reconstructed volume. To correct for a general cupping, methods like water precorrection exist. They correct the hardening of the spectrum during the penetration of the measured object only for the major tissue class. In contrast, more complex artifacts like streaks between dense objects need other techniques of correction. If using only the information of one single energy scan, there are two types of corrections. The first one is a physical approach. Thereby, artifacts can be reproduced and corrected within the original reconstruction by using assumptions in a polychromatic forward projector. These assumptions could be the used spectrum, the detector response, the physical attenuation and scatter properties of the intersected materials. A second method is an empirical approach, which does not rely on much prior knowledge. This so-called empirical beam hardening correction (EBHC) and the previously mentioned physical-based technique are both relying on a segmentation of the present tissues inside the patient. The difficulty thereby is that beam hardening by itself, scatter, and other effects, which diminish the image quality also disturb the correct tissue classification and thereby reduce the accuracy of the two known classes of correction techniques. The herein proposed method works similar to the empirical beam hardening correction but does not require a tissue segmentation and therefore shows improvements on image data, which are highly degraded by noise and artifacts. Furthermore, the new algorithm is designed in a way that no additional calibration or parameter fitting is needed. Methods: To overcome the segmentation of tissues, the authors propose a histogram deformation of their primary reconstructed CT image. This step is essential for the proposed algorithm to be segmentation-free (sf). This deformation leads to a nonlinear accentuation of higher CT-values. The original volume and the gray value deformed volume are monochromatically forward projected. The two projection sets are then monomially combined and reconstructed to generate sets of basis volumes which are used for correction. This is done by maximization of the image flatness due to adding additionally a weighted sum of these basis images. sfEBHC is evaluated on polychromatic simulations, phantom measurements, and patient data. The raw data sets were acquired by a dual source spiral CT scanner, a digital volume tomograph, and a dual source micro CT. Different phantom and patient data were used to illustrate the performance and wide range of usability of sfEBHC across different scanning scenarios. The artifact correction capabilities are compared to EBHC. Results: All investigated cases show equal or improved image quality compared to the standard EBHC approach. The artifact correction is capable of correcting beam hardening artifacts for different scan parameters and scan scenarios. Conclusions: sfEBHC generates beam hardening-reduced images and is furthermore capable of dealing with images which are affected by high noise and strong artifacts. The algorithm can be used to recover structures which are hardly visible inside the beam hardening-affected regions.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

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↗

ClimateNet: an expert-labeled open dataset and deep learning architecture for enabling high-precision analyses of extreme weather

Abstract. Identifying, detecting, and localizing extreme weather events is a crucial first step in understanding how they may vary under different climate change scenarios. Pattern recognition tasks such as classification, object detection, and segmentation (i.e., pixel-level classification) have remained challenging problems in the weather and climate sciences. While there exist many empirical heuristics for detecting extreme events, the disparities between the output of these different methods even for a single event are large and often difficult to reconcile. Given the success of deep learning (DL) in tackling similar problems in computer vision, we advocate a DL-based approach. DL, however, works best in the context of supervised learning – when labeled datasets are readily available. Reliable labeled training data for extreme weather and climate events is scarce. We create “ClimateNet” – an open, community-sourced human-expert-labeled curated dataset that captures tropical cyclones (TCs) and atmospheric rivers (ARs) in high-resolution climate model output from a simulation of a recent historical period. We use the curated ClimateNet dataset to train a state-of-the-art DL model for pixel-level identification – i.e., segmentation – of TCs and ARs. We then apply the trained DL model to historical and climate change scenarios simulated by the Community Atmospheric Model (CAM5.1) and show that the DL model accurately segments the data into TCs, ARs, or “the background” at a pixel level. Further, we show how the segmentation results can be used to conduct spatially and temporally precise analytics by quantifying distributions of extreme precipitation conditioned on event types (TC or AR) at regional scales. The key contribution of this work is that it paves the way for DL-based automated, high-fidelity, and highly precise analytics of climate data using a curated expert-labeled dataset – ClimateNet. ClimateNet and the DL-based segmentation method provide several unique capabilities: (i) they can be used to calculate a variety of TC and AR statistics at a fine-grained level; (ii) they can be applied to different climate scenarios and different datasets without tuning as they do not rely on threshold conditions; and (iii) the proposed DL method is suitable for rapidly analyzing large amounts of climate model output. While our study has been conducted for two important extreme weather patterns (TCs and ARs) in simulation datasets, we believe that this methodology can be applied to a much broader class of patterns and applied to observational and reanalysis data products via transfer learning.

54 ENVIRONMENTAL SCIENCES↗

The Analysis of Image Segmentation Hierarchies with a Graph-based Knowledge Discovery System

Currently available pixel-based analysis techniques do not effectively extract the information content from the increasingly available high spatial resolution remotely sensed imagery data. A general consensus is that object-based image analysis (OBIA) is required to effectively analyze this type of data. OBIA is usually a two-stage process; image segmentation followed by an analysis of the segmented objects. We are exploring an approach to OBIA in which hierarchical image segmentations provided by the Recursive Hierarchical Segmentation (RHSEG) software developed at NASA GSFC are analyzed by the Subdue graph-based knowledge discovery system developed by a team at Washington State University. In this paper we discuss out initial approach to representing the RHSEG-produced hierarchical image segmentations in a graphical form understandable by Subdue, and provide results on real and simulated data. We also discuss planned improvements designed to more effectively and completely convey the hierarchical segmentation information to Subdue and to improve processing efficiency.

Tilton, James C.↗

Coadding Techniques for Image-based Wavefront Sensing for Segmented-mirror Telescopes

Image-based wavefront sensing algorithms are being used to characterize optical performance for a variety of current and planned astronomical telescopes. Phase retrieval recovers the optical wavefront that correlates to a series of diversity-defocused point-spread functions (PSFs), where multiple frames can be acquired at each defocus setting. Multiple frames of data can be coadded in different ways; two extremes are in "image-plane space," to average the frames for each defocused PSF and use phase retrieval once on the averaged images, or in "pupil-plane space," to use phase retrieval on every set of PSFs individually and average the resulting wavefronts. The choice of coadd methodology is particularly noteworthy for segmented-mirror telescopes that are subject to noise that causes uncorrelated motions between groups of segments. Using data collected on and simulations of the James Webb Space Telescope Testbed Telescope (TBT) commissioned at Ball Aerospace, we show how different sources of noise (uncorrelated segment jitter, turbulence, and common-mode noise) and different parts of the optical wavefront, segment and global aberrations, contribute to choosing the coadd method. Of particular interest, segment piston is more accurately recovered in "image-plane space" coadding, while segment tip/tilt is recovered in "pupil-plane space" coadding.

Smith, Scott↗