Datasets to reproduce the exploratory Bayesian network developed in USGS SIR 2018-5053 for estimating water-quality parameters at streamgage 03374100 White River at Hazleton, Indiana, 1973-2016

This U.S. Geological Survey (USGS) data release contains the data used in the USGS Scientific Investigations Report 2018-5053 entitled "An exploratory Bayesian network for estimating the magnitudes and uncertainties of selected water-quality parameters at streamgage 03374100 White River at Hazleton, Indiana, from partially observed data." The four datasets, which contain only ASCII characters in a column-oriented format, are: (1) sel_qw_parm_full_time_series.csv: A comma-delimited file containing an irregular time series of 713 rows of discrete water-quality measurements that start on February 21, 1973 and end on September 14, 2016. (2) baye_network_initialize.cas: This tab-delimited file can be used to initialize a Bayesian network for the water quality parameters analyzed in the subject report. (3) baye_network_training.cas: This tab-delimited file was used to identify the structure (directed acyclic graph) and the conditional probability tables used for estimation in the Bayesian network. (4) baye_network_testing.cas: This tab-delimited file has the same format as the training data set, but includes 117 rows of data that were reserved for testing the accuracy of the Bayesian network. This data release supports the following publication: Holtschlag, D.J., 2018, An exploratory Bayesian network for estimating the magnitudes and uncertainties of selected water-quality parameters at streamgage 03374100 White River at Hazleton, Indiana, from partially observed data: U.S. Geological Survey Scientific Investigations Report 2018-5053, 30 p., https://doi.org/10.3133/sir20185053.

                                            [
  "010:12"
]
                                        

                                            {
  "fn": "David J. Holtschlag",
  "@type": "vcard:Contact",
  "hasEmail": "mailto:dholtschlag@usgs.gov"
}
                                        

                                            [
  {
    "@type": "dcat:Distribution",
    "title": "Digital Data",
    "format": "XML",
    "accessURL": "https://doi.org/10.5066/P9JJYKWD",
    "mediaType": "application/http",
    "description": "Landing page for access to the data"
  },
  {
    "@type": "dcat:Distribution",
    "title": "Original Metadata",
    "format": "XML",
    "mediaType": "text/xml",
    "description": "The metadata original format",
    "downloadURL": "https://data.usgs.gov/datacatalog/metadata/USGS.5afd9d5be4b0da30c1bdb2d2.xml"
  }
]
                                        

                                            [
  "Bayesian",
  "Bayesian network",
  "Hazleton",
  "Indiana",
  "USGS:5afd9d5be4b0da30c1bdb2d2",
  "White River",
  "conditional probability",
  "d-separation (directional separation)",
  "directed acyclic graph (DAG)",
  "stream-gage measurement",
  "streamflow",
  "surface water (non-marine)",
  "surface water quality",
  "water quality"
]
                                        

                                            {
  "name": "U.S. Geological Survey",
  "@type": "org:Organization"
}
                                        

                                            [
  "Geospatial"
]