MultiSolSegment: EL images and masks

Sanghi, Oja; Jost, Norman; Pierce, Benjamin G.; Cooper, Emma; Deane, Isaiah; Chen, Xin; Jain, Anhubav; Schlauch, Ian M.; Bertoni, Mariana I.; Braid, Jennifer L.

doi:10.21948/2587738

Title: MultiSolSegment: EL images and masks

Dataset
Other Related Research

Abstract

This dataset was used to train MultiSolSegment, a multi-channel segmentation model for photovoltaic defect detection.

Authors:

Sanghi, Oja; Jost, Norman; Pierce, Benjamin G.; Cooper, Emma; Deane, Isaiah; Chen, Xin; Jain, Anhubav; Schlauch, Ian M.; Bertoni, Mariana I.; Braid, Jennifer L.

Sandia National Laboratories (SNL), Albuquerque, NM, and Livermore, CA (United States)
Case Western Reserve Univ., Cleveland, OH (United States)
University of Colorado, Boulder, Boulder, CO
Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States)
Florida State Univ., Tallahassee, FL (United States)
Arizona State Univ., Tempe, AZ (United States)

Publication Date:: Mon Aug 25 04:00:00 UTC 2025

DOE Contract Number:: NA0003525

Research Org.:: Sandia National Laboratories (SNL-NM), Albuquerque, NM (United States)

Sponsoring Org.:: USDOE Office of Energy Efficiency and Renewable Energy (EERE), Renewable Power Office. Solar Energy Technologies Office

Subject:: 14 SOLAR ENERGY; deep learning; electroluminescence; labeled data; multisolsegment; segmentation; solar cell defects; training data

OSTI Identifier:: 2587738

DOI:: https://doi.org/10.21948/2587738

Citation Formats


                    Sanghi, Oja, Jost, Norman, Pierce, Benjamin G., Cooper, Emma, Deane, Isaiah, Chen, Xin, Jain, Anhubav, Schlauch, Ian M., Bertoni, Mariana I., and Braid, Jennifer L. MultiSolSegment: EL images and masks.  United States: N. p., 2025. 
        Web.  doi:10.21948/2587738.

Copy to clipboard


                    Sanghi, Oja, Jost, Norman, Pierce, Benjamin G., Cooper, Emma, Deane, Isaiah, Chen, Xin, Jain, Anhubav, Schlauch, Ian M., Bertoni, Mariana I., & Braid, Jennifer L. MultiSolSegment: EL images and masks.  United States.  doi:https://doi.org/10.21948/2587738

Copy to clipboard


                    Sanghi, Oja, Jost, Norman, Pierce, Benjamin G., Cooper, Emma, Deane, Isaiah, Chen, Xin, Jain, Anhubav, Schlauch, Ian M., Bertoni, Mariana I., and Braid, Jennifer L. 2025.  
"MultiSolSegment: EL images and masks".  United States.  doi:https://doi.org/10.21948/2587738.  https://www.osti.gov/servlets/purl/2587738. Pub date:Mon Aug 25 04:00:00 UTC 2025

Copy to clipboard


                    
@article{osti_2587738,

  title        = {MultiSolSegment: EL images and masks},

  author       = {Sanghi, Oja and Jost, Norman and Pierce, Benjamin G. and Cooper, Emma and Deane, Isaiah and Chen, Xin and Jain, Anhubav and Schlauch, Ian M. and Bertoni, Mariana I. and Braid, Jennifer L.},

  abstractNote = {This dataset was used to train MultiSolSegment, a multi-channel segmentation model for photovoltaic defect detection.},

  doi          = {10.21948/2587738},

  journal      = {},

  number       = ,

  volume       = ,

  place        = {United States},

  year         = {Mon Aug 25 04:00:00 UTC 2025},

  month        = {Mon Aug 25 04:00:00 UTC 2025}

}

Copy to clipboard

Dataset:

View Dataset

DOI: https://doi.org/10.21948/2587738

Save / Share:

Export Metadata

Save to My Library

Similar records in DOE Data Explorer and OSTI.GOV collections:

DMTN-197: Streak Masking in DM Image Processing

Dataset Saunders, Clare

Streaks caused by satellites are a persistent problem in optical images, and their occurrence will likely increase in the coming years. Many Hyper Suprime-Cam images are already affected by streaks, and the same is expected for Rubin Observatory data. In the LSST Data Release Production (DRP), most streaks and other artifacts are already detected and masked by the algorithm CompareWarpAssembleCoadd. However, some streaks are not caught at this stage and can contaminate the final coadds and detection catalogs. To find and mask these, we adopt a morphologically-based method for detecting streaks, which uses the Kernel-Based Hough Transform to detect straightmore »« less
ARM: Infra-Red Sky Imager Cloud Mask in IR Range

Dataset Morris, Victor

Infra-Red Sky Imager Cloud Mask in IR Range
ARM: Infra-Red Sky Imager Cloud Mask in Visible Range

Dataset Morris, Victor

Infra-Red Sky Imager Cloud Mask in Visible Range
KAZR Hydrometeor and Insect Masks

Dataset Williams, Christopher

The Ka-band ARM zenith pointing radar (aka, KAZR) is so sensitive that it detects cloud particles and individual insects. While detecting insects with Ka-band radar is beneficial and desirable to advance radar entomology, this sensitivity can be detrimental to radar meteorology because insects could be interpreted as clouds or precipitation. For example, misclassifying insects as clouds has been a problem for the ARM Active Remote Sensing of Clouds (ARSCL) Value Added Product since its inception (Clothiaux et al. 2000). Based on cloud particle and insect radar scattering properties, an algorithm was developed that identifies clouds, raindrops, ice particles, and insectsmore »« less
AmeriFlux MX-EMg El Mogor

Dataset Cueva, Alejandro ; López-Reyes, Eulogio ; Bullock, Stephen H.

This is the AmeriFlux version of the carbon flux data for the site MX-EMg El Mogor. Site Description - The vegetation is Mediterranean-climate closed shrubland on sandy soils. Eddy flux measurements began in 2008, 20 years after the last wildfire. The site has been grazed lightly and sporadically.

Similar Records