Timeseries Unlabeled and Labeled Photos, Modeled Stream Elevation, and (Meta)Data of Variably Inundated Streams Across The Yakima River Basin, Washington, United States (v2)
Abstract
This dataset is associated with the “River Monitoring Photos” (RMP) study and subsequent manuscript (Bao et al. 2025. Monitoring river flow status using low-cost wildlife camera and image segmentation artificial intelligence doi: 10.1016/j.envsoft.2025.106715). Game camera timeseries photos were collected to evaluate stream variable inundation via changes in width. A subset of photos was labeled for training the YOLOv8 and Mask2Former models and used to segment water surface fractions from all the game camera photos.This data package was originally published in March 2024. It was updated in October 2025 (v2) to add additional photos and files associated with the manuscript (i.e., processed data, labeled photos, and trained models). For details on how to navigate data packages generated by this project, see https://data.ess-dive.lbl.gov/portals/PNNLRiverCorridorSFA/About.In addition to a readme, this data package also includes two file-level metadata (FLMD) files that describes each file and two data dictionaries (DD) that describe all column/row headers and variable definitions. This dataset is comprised of (1) file-level metadata; (2) data dictionary; (3) readme; (4) field metadata; and (5) folders containing game camera photos and manuscript-associated files. Each Yakima River Basin site has a folder that contains subfolders for each month photos were collected. There is also a foldermore »
- Authors:
-
- Pacific Northwest National Laboratory
- Publication Date:
- DOE Contract Number:
- AC02-05CH11231
- Research Org.:
- River Corridor Hydro-biogeochemistry from Molecular to Multi-Basin Scales SFA
- Sponsoring Org.:
- U.S. DOE > Office of Science > Biological and Environmental Research (BER)
- Subject:
- 54 ENVIRONMENTAL SCIENCES; AI image segmentation; Artificial intelligence; Biogeochemistry; EARTH SCIENCE > TERRESTRIAL HYDROSPHERE > SURFACE WATER > SURFACE WATER PROCESSES/MEASUREMENTS > WATER DEPTH; ESS-DIVE CSV File Formatting Guidelines Reporting Format; ESS-DIVE File Level Metadata Reporting Format; Freshwater; Hydrologic exchange; Hydrology; Hyporheic zone; Intermittent; Labeled photos; Non-perennial; River; River corridor; Stream; Surface water; Time series photos; Variable inundation; Water surface fraction; Watershed; Width
- OSTI Identifier:
- 2319247
- DOI:
- https://doi.org/10.15485/2319247
Citation Formats
Renteria, Lupita, Bao, Jie, Chen, Yunxiang, Forbes, Brieanne, Goldman, Amy E., McKever, Sophia A., Powers-McCormack, Beck, Barnes, Morgan, and Stegen, James C. Timeseries Unlabeled and Labeled Photos, Modeled Stream Elevation, and (Meta)Data of Variably Inundated Streams Across The Yakima River Basin, Washington, United States (v2). United States: N. p., 2024.
Web. doi:10.15485/2319247.
Renteria, Lupita, Bao, Jie, Chen, Yunxiang, Forbes, Brieanne, Goldman, Amy E., McKever, Sophia A., Powers-McCormack, Beck, Barnes, Morgan, & Stegen, James C. Timeseries Unlabeled and Labeled Photos, Modeled Stream Elevation, and (Meta)Data of Variably Inundated Streams Across The Yakima River Basin, Washington, United States (v2). United States. doi:https://doi.org/10.15485/2319247
Renteria, Lupita, Bao, Jie, Chen, Yunxiang, Forbes, Brieanne, Goldman, Amy E., McKever, Sophia A., Powers-McCormack, Beck, Barnes, Morgan, and Stegen, James C. 2024.
"Timeseries Unlabeled and Labeled Photos, Modeled Stream Elevation, and (Meta)Data of Variably Inundated Streams Across The Yakima River Basin, Washington, United States (v2)". United States. doi:https://doi.org/10.15485/2319247. https://www.osti.gov/servlets/purl/2319247. Pub date:Tue Feb 27 04:00:00 UTC 2024
@article{osti_2319247,
title = {Timeseries Unlabeled and Labeled Photos, Modeled Stream Elevation, and (Meta)Data of Variably Inundated Streams Across The Yakima River Basin, Washington, United States (v2)},
author = {Renteria, Lupita and Bao, Jie and Chen, Yunxiang and Forbes, Brieanne and Goldman, Amy E. and McKever, Sophia A. and Powers-McCormack, Beck and Barnes, Morgan and Stegen, James C.},
abstractNote = {This dataset is associated with the “River Monitoring Photos” (RMP) study and subsequent manuscript (Bao et al. 2025. Monitoring river flow status using low-cost wildlife camera and image segmentation artificial intelligence doi: 10.1016/j.envsoft.2025.106715). Game camera timeseries photos were collected to evaluate stream variable inundation via changes in width. A subset of photos was labeled for training the YOLOv8 and Mask2Former models and used to segment water surface fractions from all the game camera photos.This data package was originally published in March 2024. It was updated in October 2025 (v2) to add additional photos and files associated with the manuscript (i.e., processed data, labeled photos, and trained models). For details on how to navigate data packages generated by this project, see https://data.ess-dive.lbl.gov/portals/PNNLRiverCorridorSFA/About.In addition to a readme, this data package also includes two file-level metadata (FLMD) files that describes each file and two data dictionaries (DD) that describe all column/row headers and variable definitions. This dataset is comprised of (1) file-level metadata; (2) data dictionary; (3) readme; (4) field metadata; and (5) folders containing game camera photos and manuscript-associated files. Each Yakima River Basin site has a folder that contains subfolders for each month photos were collected. There is also a folder for files associated with the manuscript which has subfolders for labeled data, trained models, Yakima River Basin site water surface fractions, and USGS site water surface fractions. All files are .csv, .json, .txt, .yaml, .pth, .pt, or .pdf. 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.},
doi = {10.15485/2319247},
journal = {},
number = ,
volume = ,
place = {United States},
year = {Tue Feb 27 04:00:00 UTC 2024},
month = {Tue Feb 27 04:00:00 UTC 2024}
}
