Janet Barclay Yingda Fan Lauren Koenig Runlong Yu Yiming Sun Yiqun Xie Xiaowei Jia Alison Appling 20250305 Vector digital data Online (digital release) U.S. Geological Survey data release https://doi.org/10.5066/P1UP5DXN <p>This model archive component contains model inputs used in the methods experiments of Fan et al. (2025b).</p> <p>The parent model archive (<a href="https://www.sciencebase.gov/catalog/item/66787f3ed34efbe36238c80a">Fan et al. 2025a</a>) provides all data, code, and model outputs used in the corresponding manuscript (Fan et al. 2025b) to test machine learning (ML) methods for downscaling and multi-scale modeling of stream temperature to combine an ML model and/or input data at coarse spatial resolution with an ML model and/or input data at fine spatial resolution to predict stream temperatures at fine spatial resolution in a watershed.</p> <p>The data are organized into these child items: <li><a href="https://www.sciencebase.gov/catalog/item/6682f4f8d34e57e93663d655"> 1. Geospatial Information </a>- Stream reach and catchment shapefiles </li> <li><a href="https://www.sciencebase.gov/catalog/item/6682f50bd34e57e93663d65a"> [THIS ITEM] 2. Model Inputs </a> - Meteorological data, river network matrices, and stream temperature observations </li> <li><a href="https://www.sciencebase.gov/catalog/item/6682f522d34e57e93663d65e"> 3. Model Code </a>- Python files and README for reproducing model training and evaluation </li> <li><a href="https://www.sciencebase.gov/catalog/item/6682f545d34e57e93663d665"> 4. Coarse Model </a>- Trained coarse stream temperature model to be downscaled </li> <li><a href="https://www.sciencebase.gov/catalog/item/6682f556d34e57e93663d668"> 5. Model Outputs </a>- Model simulation outputs and evaluation metrics </li> </p> <p>The publication associated with this model archive is: Fan, Yingda, Runlong Yu, Janet R. Barclay, Alison P. Appling, Yiming Sun, Yiqun Xie, and Xiaowei Jia. 2025. "Multi-Scale Graph Learning for Anti-Sparse Downscaling." In Proceedings of the AAAI Conference on Artificial Intelligence. Vol. 39. Washington, DC, USA: AAAI Press.</p> <p>This data compilation was supported by the U.S. Department of Energy, Office of Science, Office of Biological and Environmental Research, Environmental System Science Data Management Program, as part of the ExaSheds project, under Award Number 89243021SSC000068. Work was also supported by the U.S. Geological Survey, Water Availability and Use Science Program.</p> Water quality modeling methods development 19791001 20210930 See publication date Complete None planned -76.3879905924101 -74.380785128688 42.4544544671721 38.7894548062558 none machine learning deep learning water resources water temperature streams modeling downscaling mathematical simulation ISO 19115 Topic Category environment inlandWaters USGS Metadata Identifier USGS:6682f50bd34e57e93663d65a Department of Commerce, 1995, Countries, Dependencies, Areas of Special Sovereignty, and Their Principal Administrative Divisions, Federal Information Processing Standard (FIPS) 10-4, Washington, D.C., National Institute of Standards and Technology United States US U.S. Department of Commerce, 1987, Codes for the identification of the States, the District of Columbia and the outlying areas of the United States, and associated areas (Federal Information Processing Standard 5-2): Washington, D. C., NIST Delaware DE Maryland MD New Jersey NJ New York NY Pennsylvania PA none None, but see "Distribution Liability"/"distliab" below. Users are advised to read the associated publication thoroughly to understand appropriate use and data limitations. Janet Barclay U.S. Geological Survey Research Hydrologist Mailing and Physical

U.S. Geological Survey

Reston VA 20192 U.S.A. NA jbarclay@usgs.gov This data compilation was supported by the U.S. Department of Energy, Office of Science, Office of Biological and Environmental Research, Environmental System Science Data Management Program, as part of the ExaSheds project, under Award Number 89243021SSC000068. Work was also supported by the U.S. Geological Survey, Water Availability and Use Science Program. These code files were tested on high performance computing systems and laptops at the University of Pittsburgh and the United State Geological Survey. Operating systems included Windows, linux, and OSX. The open source languages R and Python were used on all systems. Fan, Yingda Runlong Yu Janet Barclay Alison Appling Yiming Sun Yiqun Xie Xiaowei Jia 2025 http://doi.org/TBD/TBD No formal attribute accuracy tests were conducted. Not applicable Not applicable A formal accuracy assessment of the horizontal positional information in the dataset was not conducted. Bock, A.R Santiago, M. Wieczorek, M.E. Foks, S.S. Norton, P.A. Lombard, M.A. 2020 https://doi.org/10.5066/P971JAGF online 2020 publication date Bock et al. (2020) Stream reach polylines for the contiguous United States (CONUS) as used by the National Hydrologic Model (NHM) and defined in the National Hydro-Geospatial Fabric version 1.1 (NHGFv1.1) McKay, L. Bondelid, T. Dewald, T. Johnston, J. Moore, R. Rea, A. 2012 https://www.epa.gov/waterdata/nhdplus-national-hydrography-dataset-plus online 2012 publication date McKay et al. (2012) Stream reach polylines for the contiguous United States (CONUS) as defined in the National Hydrography Dataset Plus version 2.1 Oliver, S.K. Sleckman, M.J. Appling, A.P. Corson-Dosch, H.R. Zwart, J.A. Thompson, T.P. Koenig, L. White, E. Watkins, D. Platt, L.R. Padilla, J.A. Sadler, J.M. 2022 https://doi.org/10.5066/P9GUHX1U online 2022 publication date Oliver et al. (2022) Compiled temperature observations and model driver data for the Delaware River Basin at the resolution of the NHM Terry, N. Briggs, M.A Kushner, D. Dickerson, H. Baldwin, A. Trottier, B. Haynes, A. Besteder, C. Glas, R. Doctor, D. Gazoorian, C. Odom, W. Benton, J. 2023 https://doi.org/10.5066/P9R3TYOZ online 2023 publication date Terry et al. (2022) Raw temperature observations for the Neversink watershed U.S. Geological Survey 2024 http://dx.doi.org/10.5066/F7P55KJN online 2024 publication date NWIS NWIS station data (stream width measurements) Abatzoglou, J.T. 2013 https://doi.org/10.5066/P9R3TYOZ online 2013 publication date Abatzoglou (2013) Gridded meteorological data Datasets were compiled that represent 1) river distances among flow-connected stream reaches, 2) a crosswalk between the NHD (McKay et al. 2012) and NHM (Bock et al. 2021) river networks, 3) observed water temperatures, and 4) model driver data, including daily climate variables. (1) The river adjacency matrices contain the river distances among flow-connected reaches within a network (NHD or NHM). River distances were calculated along a directed graph network created using the network routing and reach length attributes from McKay et al. (2012). Negative values indicate upstream distances and positive values indicate downstream distances. (2) A crosswalk between the NHD and NHM was created by first identifying the NHD flowline reaches that overlay each NHM segment, using spatial intersection. From the intersecting ("on_nhm") NHD reaches, the most-downstream NHD reach was identified by COMID, and network routing attributes from McKay et al. (2012) were used to identify any NHD reaches that would drain to that most-downstream NHD reach of each NHM segment and that were not already contributing to another most-downstream NHM reach (i.e., were not within the set of reaches that overlay the NHM network). (3) Water temperature data were taken from two sources: a previous compilation of observed stream temperature data in the Delaware River Basin (Oliver et al. 2022, "unaggregated_temperature_observations_drb.zip") and stream temperature data from the Neversink sub-basin (Terry et al. 2022, "WTmatrix.csv"). Where possible, monitoring point locations from either temperature data source were mapped to the nearest NHD flowline reach. Sites were preferentially matched to the nearest reach outlet (i.e., downstream vertex), which sometimes resulted in sites being matched to reaches immediately upstream of a co-located reach. The DRB data from Oliver et al. (2022) were further processed to reduce site-dates with multiple sub-locations representing different parts of the stream, retaining data from the sub-location with the greatest number of observations. The data were then aggregated to daily minimum, mean, and maximum values, combined with the daily average stream temperature data from Terry et al. (2022), and further summarized to one daily mean value for each NHD reach (i.e., COMID) and date. (4) Model driver data were compiled to represent river reach characteristics and daily climate variables. Daily climate information was retrieved from Abatzoglou (2013), spanning the temporal range of 1979-01-01 to 2022-04-04 and the spatial extent represented by the NHD catchments within the basin. For each NHD catchment, daily climate variables were summarized to an area-weighted mean value. Daily climate data were combined with a set of static attributes that were repeated for each date, including reach slope and minimum elevation from (McKay et al. 2012). For each NHD reach, mean river width was estimated based on empirical relationships between the mean measured width at a monitoring location (NWIS) and the NHD reach arbolate sum (McKay et al. 2012). To suppport the various models and modeling experiments reported by Fan et al. 2025b, the above datasets were subset to different scopes and extents; see the entity descriptions below for details. 20250304 U.S.A. Vector String 456 1e-06 1e-06 Decimal degrees WGS84 WGS_1984 6378137.0 298.257 2_inputs_file_dictionary.csv Comma-separated values description of the files in this model archive component (inputs to the models). Describes the format, contents, and source of each file within the zip files of this model archive component. This study file-name File path relative to this model archive component. e.g., "NHM/dist_matrix.npz" refers to a file within NHM.zip. When unpacked, NHM.zip will yield a top-level folder called "NHM" and a file at NHM/dist_matrix.npz. This data release NA NA NA file-type File type, given as file extension or "folder" for directory This data release NA NA NA description Description of the file contents This data release NA NA NA file-source File source This data release NA NA NA allNHD.zip Zip archive of input files on all NHD reaches used to train and test the modeling methods that include both on- and off-network reaches (section D.2 in the appendix of the manuscript). Users will need to unzip/decompress .zip file to view contents. Files are described in file_dictionary.csv and also as metadata attributes as follows. This study allNHD/nhgfv11_nhdv2_crosswalk.csv Comma-separated values: A crosswalk between the coarse and fine resolution reach identifiers for all fine resolution reaches [both overlapping and non-overlapping] This model archive NA NA NA allNHD/nhdv2_distance_matrix.npz NumPy compressed file: A distance matrix for all fine resolution reaches [both overlapping and non-overlapping] This model archive NA NA NA allNHD/nhdv2_inputs_io.zarr Directory: A compressed archive of model inputs for all fine resolution reaches [both overlapping and non-overlapping] This model archive NA NA NA allNHD/nhdv2_temp_observations.zarr Directory: A compressed archive of temperature observations for all fine resolution reaches [both overlapping and non-overlapping] This model archive NA NA NA Neversink_allNHD_masked.zip Zip archive of masked (simulated data sparsity) input files on all NHD reaches used to train and test the modeling methods that include both on- and off-network reaches (section D.2 in the appendix of the manuscript). Users will need to unzip/decompress .zip file to view contents. Files are described in file_dictionary.csv and also as metadata attributes as follows. This study Neversink_allNHD_masked/seed71 Directory: A directory of masked model inputs for all reaches [overlapping and non-overlapping] in the Neversink basin This model archive NA NA NA Neversink_allNHD_masked/seed61 Directory: A directory of masked model inputs for all reaches [overlapping and non-overlapping] in the Neversink basin This model archive NA NA NA Neversink_allNHD_masked/seed42 Directory: A directory of masked model inputs for all reaches [overlapping and non-overlapping] in the Neversink basin This model archive NA NA NA NHD_on_NHM_masked.zip Zip archive of masked (simulated data sparsity) input files on all NHD reaches used to train and test the modeling methods focused on the fine-resolution reaches that are coincident with the coarse resolution network (NHM) (main manuscript and section D.1 in the appendix). Users will need to unzip/decompress .zip file to view contents. Files are described in file_dictionary.csv and also as metadata attributes as follows. This study NHD_on_NHM_masked/seed71 Directory: A directory of masked model inputs for fine resolution reaches that overlap the coarse resolution model This model archive NA NA NA NHD_on_NHM_masked/seed61 Directory: A directory of masked model inputs for fine resolution reaches that overlap the coarse resolution model This model archive NA NA NA NHD_on_NHM_masked/seed42 Directory: A directory of masked model inputs for fine resolution reaches that overlap the coarse resolution model This model archive NA NA NA NHD_on_NHM.zip Zip archive of input files on all NHD reaches used to train and test the modeling methods focused on the fine-resolution reaches that are coincident with the coarse resolution network (NHM) (main manuscript and section D.1 in the appendix). Users will need to unzip/decompress .zip file to view contents. Files are described in file_dictionary.csv and also as metadata attributes as follows. This study NHD_on_NHM/dist_matrix.npz NumPy compressed file: A distance matrix for the fine resolution reaches that overlap the coarse resolution model This model archive NA NA NA NHD_on_NHM/obs_temp_flow.tar Tar archive: A compressed archive of observed temperatures and streamflows for the fine resolution reaches that overlap the coarse resolution model This model archive NA NA NA NHD_on_NHM/sntemp_input_output.tar Tar archive: A compressed archive of model inputs for the fine resolution reaches that overlap the coarse resolution model This model archive NA NA NA NHD_on_NHM/NHD_on_NHM_crosswalk.csv Comma-separated values: A crosswalk between the coarse and fine resolution reach identifiers for the fine resolution reaches that overlap the coarse resolution model This model archive NA NA NA NHM.zip Zip archive of input files on all NHM reaches used to train and test the coarse regional model describe in section D.1 of the appendix. Users will need to unzip/decompress .zip file to view contents. Files are described in file_dictionary.csv and also as metadata attributes as follows. This study NHM/dist_matrix.npz NumPy compressed file: A distance matrix for the coarse resolution model https://doi.org/10.5066/P9GUHX1U NA NA NA NHM/obs_temp_flow.tar Tar archive: A compressed archive of observed temperatures and streamflows for the coarse resolution model https://doi.org/10.5066/P9GUHX1U NA NA NA NHM/sntemp_input_output.tar Tar archive: A compressed archive of model inputs for the coarse resolution model https://doi.org/10.5066/P9GUHX1U NA NA NA U.S. Geological Survey GS ScienceBase mailing address

Denver Federal Center, Building 810, Mail Stop 302

Denver CO 80255 United States 1-888-275-8747 sciencebase@usgs.gov Unless otherwise stated, all data, metadata and related materials are considered to satisfy the quality standards relative to the purpose for which the data were collected. Although these data and associated metadata have been reviewed for accuracy and completeness and approved for release by the U.S. Geological Survey (USGS), no warranty expressed or implied is made regarding the display or utility of the data on any other system or for general or scientific purposes, nor shall the act of distribution constitute any such warranty. Any use of trade, product, or firm names is for descriptive purposes only and does not imply endorsement by the U.S. Government. Model input files are archived within 6 zipfiles, each with inputs for a different extent / scope of model. Contents of zip files are described in the metadata file (2_inputs.xml) and also in the comma-separated-values file 2_inputs_file_dictionary.csv. https://doi.org/10.5066/P1UP5DXN None 20250305 Alison Appling U.S. Geological Survey Ecologist Mailing and Physical

U.S. Geological Survey

Reston VA 20192 U.S.A. NA NA aappling@usgs.gov FGDC Content Standard for Digital Geospatial Metadata FGDC-STD-001-1998