Artificial intelligence models, photos, and data associated with the manuscript “Quantifying streambed grain sizes and hydro-biogeochemistry using YOLO and photos”

摘要: This data package is associated with the manuscript “Quantifying streambed grain sizes and hydro-biogeochemistry using YOLO and photos,” in preparation for submission to Water Resources Research (Chen et al.). 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 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; https://github.com/river-corridors-sfa/Geospatial_variables). In total, the data package includes 65 folders and 35,502 files. These files include 9,035 photos (.jpg); 17,950 photo labels and individual grain sizes and probability from AI (.txt); 8,430 grain size distribution data (.dat); and 81 CSV files for results summary and required metadata files. The summary CSV files contain 127 columns and approximately 2,200 rows that represent photo names, site locations, recording time, GPS coordinates, grains sizes, number of grains, and additional hydro-biogeochemical data such as water depth, flow velocity, Manning’s coefficient, friction …