diff --git a/2_observations.yml b/2_observations.yml index 3a2e8e2..7c7c4ad 100644 --- a/2_observations.yml +++ b/2_observations.yml @@ -12,7 +12,6 @@ targets: 2_observations: depends: - out_data/temperature_observations.csv - - out_data/flow_observations.csv # daily flow and temperature data out_data/temperature_observations.csv: @@ -21,8 +20,3 @@ targets: var = I('wtemp(C)'), in_file = 'in_data/Data - ERL paper/Forcing_attrFiles/no_dam_forcing_60__days118sites.csv') - out_data/flow_observations.csv: - command: extract_obs( - out_file = target_name, - var = I('discharge(cfs)'), - in_file = 'in_data/Data - ERL paper/Forcing_attrFiles/no_dam_forcing_60__days118sites.csv') diff --git a/3_inputs.yml b/3_inputs.yml index 9d9d213..49470c5 100644 --- a/3_inputs.yml +++ b/3_inputs.yml @@ -17,6 +17,7 @@ targets: - out_data/AT_basin_attributes.csv - out_data/weather_drivers.zip - out_data/pred_discharge.csv + - out_data/obs_discharge.csv out_data/AT_basin_attributes.csv: command: extract_AT_attributes( @@ -29,8 +30,14 @@ targets: out_data/weather_drivers.zip: command: zip_this(out_file = target_name, weather_drivers) - out_data/pred_discharge.csv: command: subset_pred_discharge( out_file = target_name, in_file = 'in_data/Data - ERL paper/Forcing_attrFiles/no_dam_forcing_60__days118sites.csv') + + out_data/obs_discharge.csv: + command: extract_obs( + out_file = target_name, + var = I('discharge(cfs)'), + in_file = 'in_data/Data - ERL paper/Forcing_attrFiles/no_dam_forcing_60__days118sites.csv') + diff --git a/in_text/text_01_spatial.yml b/in_text/text_01_spatial.yml index 0c7e1ca..f344e1b 100644 --- a/in_text/text_01_spatial.yml +++ b/in_text/text_01_spatial.yml @@ -38,23 +38,27 @@ entities: attr-def: >- Latitude of the site location. attr-defs: NA - data-min: NA - data-max: NA - data-units: NA + data-min: 30.14549 + data-max: 48.90596 + data-units: decimal degrees - attr-label: long attr-def: >- Longitude of the site location. attr-defs: NA - data-min: NA - data-max: NA - data-units: NA + data-min: -123.3299 + data-max: -70.97964 + data-units: decimal degrees data-name: GIS points of sites used in this study. data-description: Location of USGS river gages used in this study. file-format: Shapefile Data Set +process-date: 20201028 +indirect-spatial: U.S.A. +latitude-res: 0.00001 +longitude-res: 0.00001 build-environment: >- This dataset was generated using XX. diff --git a/in_text/text_02_observations.yml b/in_text/text_02_observations.yml index a88f8ed..963061c 100644 --- a/in_text/text_02_observations.yml +++ b/in_text/text_02_observations.yml @@ -3,7 +3,7 @@ title: >- abstract: >- - Mean daily temperature and discharge observations retrieved from NWIS. The temperature observations were used to train and validate all temperature models, while flow observations were used as a model input during training for a subset of the temperature models. The model training period was from 2010-10-01 to 2014-09-30, and the test period was from 2014-10-01 to 2016-09-30. + Mean daily temperature and discharge observations retrieved from NWIS. The temperature observations were used to train and validate all temperature models. The model training period was from 2010-10-01 to 2014-09-30, and the test period was from 2014-10-01 to 2016-09-30. cross-cites: - @@ -41,32 +41,13 @@ entities: data-min: NA data-max: NA data-units: degrees Celsius - - - data-name: flow_observations.csv - data-description: Observed mean daily discharge observation retrieved from NWIS for the 118 gages used in this study. Flow observations were used as a driver in the water temperature model. The data were retrieved from NWIS and are limited to the test and training period, from 2010-10-01 through 2016-09-30. - attributes: - - - attr-label: site_no - attr-def: >- - USGS unique site identifier. - attr-defs: NA - data-min: NA - data-max: NA - data-units: NA - - - attr-label: datetime - attr-def: >- - Date of temperature observation. - attr-defs: NA - data-min: NA - data-max: NA - data-units: NA - - - attr-label: discharge(cfs) - attr-def: Observed mean daily discharge - attr-defs: NA - data-min: NA - data-max: NA - data-units: degrees Celsius -file-format: comma-delimited files + +process-date: XX +indirect-spatial: U.S.A. +latitude-res: 0.00001 +longitude-res: 0.00001 +data-name: Water temperature observations +data-description: >- + Water temperature observations used to train and validate models described in Rahmani et al. 2020. +file-format: comma seperated file format (csv) diff --git a/in_text/text_03_inputs.yml b/in_text/text_03_inputs.yml index 6c506b3..02fb774 100644 --- a/in_text/text_03_inputs.yml +++ b/in_text/text_03_inputs.yml @@ -2,7 +2,7 @@ title: >- Exploring the exceptional performance of a deep learning stream temperature model and the value of streamflow data: 3 model inputs abstract: >- - Inputs to the deep learning models included daily weather forcing data, as well as river catchment attributes. + Inputs to the deep learning models included daily weather forcing data, river catchment attributes, and simulated or observed flow. cross-cites: - @@ -305,8 +305,33 @@ entities: data-min: NA data-max: NA data-units: cubic feet per second - - + - + data-name: flow_observations.csv + data-description: Observed mean daily discharge observation retrieved from NWIS for the 118 gages used in this study. Flow observations were used as a driver in the water temperature model. The data were retrieved from NWIS and are limited to the test and training period, from 2010-10-01 through 2016-09-30. + attributes: + - + attr-label: site_no + attr-def: >- + USGS unique site identifier. + attr-defs: NA + data-min: NA + data-max: NA + data-units: NA + - + attr-label: datetime + attr-def: >- + Date of temperature observation. + attr-defs: NA + data-min: NA + data-max: NA + data-units: NA + - + attr-label: discharge(cfs) + attr-def: Observed mean daily discharge + attr-defs: NA + data-min: NA + data-max: NA + data-units: degrees Celsius build-environment: Multiple computer systems were used to generate these data, including XX. The open source languages R and Python was used on all systems, as well as XX. @@ -314,5 +339,7 @@ process-date: !expr format(Sys.time(),'%Y%m%d') indirect-spatial: U.S.A. latitude-res: 0.1 longitude-res: 0.1 -data-name: weather data, river catchment metadata - +data-name: Model driver data +data-description: >- + Inputs (drivers) for the temperature models described in Rahmani et al. 2020, including weather drivers, river basin attributes, and simulated and observed river discharge. +file-format: comma seperated file format (csv) diff --git a/in_text/text_05_predictions.yml b/in_text/text_05_predictions.yml index 1b66106..b0ff52d 100644 --- a/in_text/text_05_predictions.yml +++ b/in_text/text_05_predictions.yml @@ -2,15 +2,15 @@ title: >- Exploring the exceptional performance of a deep learning stream temperature model and the value of streamflow data: 5 model prediction data abstract: >- - A deep learning model framework was used to make water temperature predictions in 118 river catchments across the U.S. All four model (LR, noQ, obsQ, and simQ) predictions are included. Additionally, a deep learning model was used to simulate discharge, which was used as inputs to the water temperature model. + A deep learning model framework was used to make water temperature predictions in 118 river catchments across the U.S. All four model (LR, noQ, obsQ, and simQ) predictions are included. cross-cites: - - authors: ['XX'] + authors: ['DP Feng', 'K Fang', "CP Shen"] title: >- - Cross cite code base? - pubdate: XX - link: XX + Enhancing streamflow forecast and extracting insights using continental-scale long-short term memory networks with data integration + pubdate: 2020 + link: https://doi.org/10.1029/2019WR026793 build-environment: >- We used XX open source XX; Any supercomputing resources used? XX @@ -46,3 +46,12 @@ entities: data-min: NA data-max: NA data-units: degrees Celsius + +process-date: !expr format(Sys.time(),'%Y%m%d') +indirect-spatial: U.S.A. +latitude-res: 0.00001 +longitude-res: 0.00001 +data-name: Model predictions +data-description: >- + Stream water temperature predictions from each model described in Rahmani et al. 2020. +file-format: comma seperated file format (csv) diff --git a/in_text/text_06_evaluation.yml b/in_text/text_06_evaluation.yml index 986bfe8..fe07cb1 100644 --- a/in_text/text_06_evaluation.yml +++ b/in_text/text_06_evaluation.yml @@ -77,3 +77,12 @@ entities: build-environment: >- We used XX open source XX. + +process-date: !expr format(Sys.time(),'%Y%m%d') +indirect-spatial: U.S.A. +latitude-res: 0.00001 +longitude-res: 0.00001 +data-name: Model evaluation metrics +data-description: >- + Evaluation metrics used to compare stream temperature models in Rahmani et al. 2020. +file-format: comma seperated file format (csv) diff --git a/in_text/text_SHARED.yml b/in_text/text_SHARED.yml index 588423a..f9cdbd7 100644 --- a/in_text/text_SHARED.yml +++ b/in_text/text_SHARED.yml @@ -53,7 +53,13 @@ funding-credits: >- process-description: >- At the core of the modeling framework is a deep learning model that uses inputs of XX. +process-date: 20201028 +latitude-res: 0.1 +longitude-res: 0.1 distro-person: Samantha K. Oliver + +build-environment: Multiple computer systems were used to generate these data, including linux, OSX. The open source languages R and Python were used on all systems. XX + liability-statement: >- 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), diff --git a/out_xml/00_parent.xml b/out_xml/00_parent.xml index a414430..bb9d695 100644 --- a/out_xml/00_parent.xml +++ b/out_xml/00_parent.xml @@ -3,7 +3,12 @@ - Samantha K. Oliver, XX + Farshid Rahmani + Kathryn Lawson + Wenyu Ouyang + Alison Appling + Samantha Oliver + Chaopeng Shen 2020 Data release: Exploring the exceptional performance of a deep learning stream temperature model and the value of streamflow data parent data item for released data products @@ -14,16 +19,21 @@ XX - TBD XX + Farshid Rahmani + Kathryn Lawson + Wenyu Ouyang + Alison Appling + Samantha Oliver + Chaopeng Shen 2020 - TBD XX + Exploring the exceptional performance of a deep learning stream temperature model and the value of streamflow data. - <p>This data release provides all data and code used in Rahmani et al. 2020. Briefly, this project used the CAMELS dataset as a test case for temperature prediction using deep learning methods. XX <br/>The data are organized into these items:</p> <ol> <li><a href="https://www.sciencebase.gov/catalog/item/5f908db182ce720ee2d0fef9">Spatial Information</a> - Basin polygons and pour points for 118 river basins used in this study</li> <li><a href="https://www.sciencebase.gov/catalog/item/5f986594d34e198cb77ff084">Observations</a> - Water temperature observations and flow observations for the 118 river reaches used in this study</li> <li><a href="https://www.sciencebase.gov/catalog/item/5f9865abd34e198cb77ff086">Model Inputs</a> - Model inputs, including basin characteristics and weather drivers. </li> <li><a href="https://www.sciencebase.gov/catalog/item/5f9865cfd34e198cb77ff088">Models</a> - Code and configuration for stream temperature models.</li> <li><a href="https://www.sciencebase.gov/catalog/item/5f9865e5d34e198cb77ff08a">Model Predictions</a> - Predictions of water temperature</li> <li><a href="https://www.sciencebase.gov/catalog/item/5f9865fbd34e198cb77ff08c">Model Evaluation</a> - Performance of models</li> <br/> <p>This research was funded by the USGS, XX.</p> - Decision support, limnological research, and fish habitat. + <p>This data release provides all data and code used in Rahmani et al. 2020. Briefly, this project used the Gages II dataset as a test case for temperature prediction using deep learning methods. XX <br/>The data are organized into these items:</p> <ol> <li><a href="https://www.sciencebase.gov/catalog/item/5f908db182ce720ee2d0fef9">Spatial Information</a> - Pour points for 118 river basins used in this study</li> <li><a href="https://www.sciencebase.gov/catalog/item/5f986594d34e198cb77ff084">Observations</a> - Water temperature observations and flow observations for the 118 river reaches used in this study</li> <li><a href="https://www.sciencebase.gov/catalog/item/5f9865abd34e198cb77ff086">Model Inputs</a> - Model inputs, including basin characteristics and weather drivers. </li> <li><a href="https://www.sciencebase.gov/catalog/item/5f9865cfd34e198cb77ff088">Models</a> - Code and configuration for stream temperature models.</li> <li><a href="https://www.sciencebase.gov/catalog/item/5f9865e5d34e198cb77ff08a">Model Predictions</a> - Predictions of stream water temperature and discharge</li> <li><a href="https://www.sciencebase.gov/catalog/item/5f9865fbd34e198cb77ff08c">Model Evaluation</a> - Performance metrics of each stream temperature model</li> <br/> <p>This research was funded by the Integrated Water Prediction Program at the US Geological Survey.</p> + Decision support, water quality research @@ -39,12 +49,12 @@ none planned - River reach polylines as defined by the XX. + Locations of sites used in the study, which are a subset of the Gages II dataset. - - - - + -123.32988684 + -70.97964444 + 48.90595739 + 30.1454932 @@ -52,12 +62,10 @@ none machine learning deep learning - hybrid modeling water temperature - reservoirs + streams modeling - XX ISO 19115 Topic Category @@ -73,6 +81,66 @@ 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 + Alabama + AL + Delaware + DE + Georgia + GA + Idaho + ID + Iowa + IA + Kansas + KS + Maine + ME + Maryland + MD + Massachusetts + MA + Michigan + MI + Mississippi + MS + Nevada + NV + New Jersey + NJ + New Mexico + NM + New York + NY + North Carolina + NC + Ohio + OH + Oklahoma + OK + Oregon + OR + Pennsylvania + PA + Rhode Island + RI + South Carolina + SC + Tennessee + TN + Texas + TX + Utah + UT + Virginia + VA + Washington + WA + West Virginia + WV + Wisconsin + WI + Wyoming + WY none @@ -80,23 +148,23 @@ - Samantha K. Oliver + Farshid Rahmani U.S. Geological Survey - Hydrologist + Graduate Research Assistant Mailing and Physical -
8505 Research Way
- Middleton - WI - 53562 +
Sackett Building, Pennsylvania State University
+ State College + PA + 16801 U.S.A. - 608-821-3824 - soliver@usgs.gov + NA + fzr5082@psu.edu - This study was funded by the Department of the Interior Northeast Climate Adaptation Science Center, the United States Geological Survey National Climate This research used resources of the Core Science Analytics and Synthesis Advanced Research Computing program at the U.S. Geological Survey. + This study was funded by the Integrated Water Prediction Program at the U.S. Geological Survey. XX. Multiple computer systems were used to generate these data, including linux, OSX. The open source languages R and Python were used on all systems. XX @@ -115,18 +183,18 @@ - At the core of the modeling framework is a coupled hydrologic-thermodynamic model that uses inputs of reach-specific properties and local meteorology to estimate flow and water temperature. Our chosen model is the open source, Precipitation Runoff Modeling System (PRMS) with the coupled Stream Network Temperature Model (SNTemp) version XX. PRMS-SNTemp is a ...XX. We used PRMS-SNTemp to simulate stream flow and temperature for the period of record...XX. - 20201027 + At the core of the modeling framework is a deep learning model that uses inputs of XX. + 20201103 U.S.A. - + Point - - + Point + 118 @@ -186,25 +254,25 @@ - 20201027 + 20201103 - Samantha K. Oliver + Farshid Rahmani U.S. Geological Survey - Hydrologist + Graduate Research Assistant Mailing and Physical -
8505 Research Way
- Middleton - WI - 53562 +
Sackett Building, Pennsylvania State University
+ State College + PA + 16801 U.S.A. - 608-821-3824 - 608-821-3817 - soliver@usgs.gov + NA + NA + fzr5082@psu.edu FGDC Content Standard for Digital Geospatial Metadata diff --git a/out_xml/01_spatial.xml b/out_xml/01_spatial.xml new file mode 100644 index 0000000..38dba4b --- /dev/null +++ b/out_xml/01_spatial.xml @@ -0,0 +1,344 @@ + + + + + + Farshid Rahmani + Kathryn Lawson + Wenyu Ouyang + Alison Appling + Samantha Oliver + Chaopeng Shen + 2020 + Exploring the exceptional performance of a deep learning stream temperature model and the value of streamflow data: 1 spatial information + Shapefile Data Set + + Online (digital release) + U.S. Geological Survey + + XX + + + Farshid Rahmani + Kathryn Lawson + Wenyu Ouyang + Alison Appling + Samantha Oliver + Chaopeng Shen + 2020 + Exploring the exceptional performance of a deep learning stream temperature model and the value of streamflow data. + + + + + + This dataset provides XX. + Decision support, water quality research + + + + + 19801001 + 20191231 + + + See publication date + + + Complete + none planned + + + Locations of sites used in the study, which are a subset of the Gages II dataset. + + -123.32988684 + -70.97964444 + 48.90595739 + 30.1454932 + + + + + none + machine learning + deep learning + water + temperature + streams + modeling + + + ISO 19115 Topic Category + environment + inlandWaters + 007 + 012 + + + 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 + Alabama + AL + Delaware + DE + Georgia + GA + Idaho + ID + Iowa + IA + Kansas + KS + Maine + ME + Maryland + MD + Massachusetts + MA + Michigan + MI + Mississippi + MS + Nevada + NV + New Jersey + NJ + New Mexico + NM + New York + NY + North Carolina + NC + Ohio + OH + Oklahoma + OK + Oregon + OR + Pennsylvania + PA + Rhode Island + RI + South Carolina + SC + Tennessee + TN + Texas + TX + Utah + UT + Virginia + VA + Washington + WA + West Virginia + WV + Wisconsin + WI + Wyoming + WY + + + none + These data are subject to change and are not citable until reviewed and approved for official publication by the USGS + + + + Farshid Rahmani + U.S. Geological Survey + + Graduate Research Assistant + + Mailing and Physical +
Sackett Building, Pennsylvania State University
+ State College + PA + 16801 + U.S.A. + + NA + fzr5082@psu.edu + + + This study was funded by the Integrated Water Prediction Program at the U.S. Geological Survey. XX. + This dataset was generated using XX. + + + J.A. Falcone + 2011 + GAGES-II: Geospatial attributes of gages for evaluating streamflow + https://doi.org/10.3133/70046617 + + + + + + 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. + + + A formal accuracy assessment of the vertical positional information in the dataset was not conducted. + + + + + At the core of the modeling framework is a deep learning model that uses inputs of XX. + 20201028 + + + + + U.S.A. + Point + + + Point + 118 + + + + + + + 1e-05 + 1e-05 + Decimal degrees + + + WGS84 + WGS_1984 + 6378137.0 + 298.257 + + + + + + + 01_gage_locations.zip + GIS point locations for the 118 river catchments included in this study. These sites are a subset from the Gages II dataset. + U.S. Geological Survey + + + site_no + USGS unique site identifier. + NA + + + NA + NA + NA + + + + + site_name + Name of the site, which often includes river name. + NA + + + NA + NA + NA + + + + + lat + Latitude of the site location. + NA + + + 30.14549 + 48.90596 + decimal degrees + + + + + long + Longitude of the site location. + NA + + + -123.3299 + -70.97964 + decimal degrees + + + + + + + + + + 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. + + + + Shapefile Data Set + + + + + + XX + + + + + + None + + + + 20201103 + + + + Farshid Rahmani + U.S. Geological Survey + + Graduate Research Assistant + + Mailing and Physical +
Sackett Building, Pennsylvania State University
+ State College + PA + 16801 + U.S.A. + + NA + NA + fzr5082@psu.edu + + + FGDC Content Standard for Digital Geospatial Metadata + FGDC-STD-001-1998 + + diff --git a/out_xml/02_observations.xml b/out_xml/02_observations.xml new file mode 100644 index 0000000..d1c7553 --- /dev/null +++ b/out_xml/02_observations.xml @@ -0,0 +1,332 @@ + + + + + + Farshid Rahmani + Kathryn Lawson + Wenyu Ouyang + Alison Appling + Samantha Oliver + Chaopeng Shen + 2020 + Exploring the exceptional performance of a deep learning stream temperature model and the value of streamflow data: 2 observations + comma seperated file format (csv) + + Online (digital release) + U.S. Geological Survey + + XX + + + Farshid Rahmani + Kathryn Lawson + Wenyu Ouyang + Alison Appling + Samantha Oliver + Chaopeng Shen + 2020 + Exploring the exceptional performance of a deep learning stream temperature model and the value of streamflow data. + + + + + + Mean daily temperature and discharge observations retrieved from NWIS. The temperature observations were used to train and validate all temperature models. The model training period was from 2010-10-01 to 2014-09-30, and the test period was from 2014-10-01 to 2016-09-30. + Decision support, water quality research + + + + + 19801001 + 20191231 + + + See publication date + + + Complete + none planned + + + Locations of sites used in the study, which are a subset of the Gages II dataset. + + -123.32988684 + -70.97964444 + 48.90595739 + 30.1454932 + + + + + none + machine learning + deep learning + water + temperature + streams + modeling + + + ISO 19115 Topic Category + environment + inlandWaters + 007 + 012 + + + 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 + Alabama + AL + Delaware + DE + Georgia + GA + Idaho + ID + Iowa + IA + Kansas + KS + Maine + ME + Maryland + MD + Massachusetts + MA + Michigan + MI + Mississippi + MS + Nevada + NV + New Jersey + NJ + New Mexico + NM + New York + NY + North Carolina + NC + Ohio + OH + Oklahoma + OK + Oregon + OR + Pennsylvania + PA + Rhode Island + RI + South Carolina + SC + Tennessee + TN + Texas + TX + Utah + UT + Virginia + VA + Washington + WA + West Virginia + WV + Wisconsin + WI + Wyoming + WY + + + none + These data are subject to change and are not citable until reviewed and approved for official publication by the USGS + + + + Farshid Rahmani + U.S. Geological Survey + + Graduate Research Assistant + + Mailing and Physical +
Sackett Building, Pennsylvania State University
+ State College + PA + 16801 + U.S.A. + + NA + fzr5082@psu.edu + + + This study was funded by the Integrated Water Prediction Program at the U.S. Geological Survey. XX. + Multiple computer systems were used to generate these data, including linux, OSX. The open source languages R and Python were used on all systems. XX + + + U.S. Geological Survey + Accessed on XX + National Water Information System data available on the World Wide Web (USGS Water Data for the Nation) + http://dx.doi.org/10.5066/F7P55KJN + + + + + + 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. + + + A formal accuracy assessment of the vertical positional information in the dataset was not conducted. + + + + + At the core of the modeling framework is a deep learning model that uses inputs of XX. + XX + + + + + U.S.A. + Point + + + Point + 118 + + + + + + + 1e-05 + 1e-05 + Decimal degrees + + + WGS84 + WGS_1984 + 6378137.0 + 298.257 + + + + + + + temperature_observations.csv + Water temperature observation data from 118 catchments used in this study. The observations were retrieved from NWIS and are limited to the test and training period, from 2010-10-01 through 2016-09-30. + U.S. Geological Survey + + + site_no + USGS unique site identifier. + NA + + + NA + NA + NA + + + + + datetime + Date of temperature observation. + NA + + + NA + NA + NA + + + + + wtemp(C) + Observed mean daily water temperature + NA + + + NA + NA + degrees Celsius + + + + + + + + + + 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. + + + + comma seperated file format (csv) + + + + + + XX + + + + + + None + + + + 20201103 + + + + Farshid Rahmani + U.S. Geological Survey + + Graduate Research Assistant + + Mailing and Physical +
Sackett Building, Pennsylvania State University
+ State College + PA + 16801 + U.S.A. + + NA + NA + fzr5082@psu.edu + + + FGDC Content Standard for Digital Geospatial Metadata + FGDC-STD-001-1998 + + diff --git a/out_xml/03_inputs.xml b/out_xml/03_inputs.xml new file mode 100644 index 0000000..070ea6d --- /dev/null +++ b/out_xml/03_inputs.xml @@ -0,0 +1,775 @@ + + + + + + Farshid Rahmani + Kathryn Lawson + Wenyu Ouyang + Alison Appling + Samantha Oliver + Chaopeng Shen + 2020 + Exploring the exceptional performance of a deep learning stream temperature model and the value of streamflow data: 3 model inputs + comma seperated file format (csv) + + Online (digital release) + U.S. Geological Survey + + XX + + + Farshid Rahmani + Kathryn Lawson + Wenyu Ouyang + Alison Appling + Samantha Oliver + Chaopeng Shen + 2020 + Exploring the exceptional performance of a deep learning stream temperature model and the value of streamflow data. + + + + + + Inputs to the deep learning models included daily weather forcing data, river catchment attributes, and simulated or observed flow. + Decision support, water quality research + + + + + 19801001 + 20191231 + + + See publication date + + + Complete + none planned + + + Locations of sites used in the study, which are a subset of the Gages II dataset. + + -123.32988684 + -70.97964444 + 48.90595739 + 30.1454932 + + + + + none + machine learning + deep learning + water + temperature + streams + modeling + + + ISO 19115 Topic Category + environment + inlandWaters + 007 + 012 + + + 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 + Alabama + AL + Delaware + DE + Georgia + GA + Idaho + ID + Iowa + IA + Kansas + KS + Maine + ME + Maryland + MD + Massachusetts + MA + Michigan + MI + Mississippi + MS + Nevada + NV + New Jersey + NJ + New Mexico + NM + New York + NY + North Carolina + NC + Ohio + OH + Oklahoma + OK + Oregon + OR + Pennsylvania + PA + Rhode Island + RI + South Carolina + SC + Tennessee + TN + Texas + TX + Utah + UT + Virginia + VA + Washington + WA + West Virginia + WV + Wisconsin + WI + Wyoming + WY + + + none + These data are subject to change and are not citable until reviewed and approved for official publication by the USGS + + + + Farshid Rahmani + U.S. Geological Survey + + Graduate Research Assistant + + Mailing and Physical +
Sackett Building, Pennsylvania State University
+ State College + PA + 16801 + U.S.A. + + NA + fzr5082@psu.edu + + + This study was funded by the Integrated Water Prediction Program at the U.S. Geological Survey. XX. + Multiple computer systems were used to generate these data, including XX. The open source languages R and Python was used on all systems, as well as XX. + + + P.E. Thornton + M.M. Thornton + B.W. Mayer + Y. Wei + R. Devarakonda + R.S. Vose + R.B. Cook + 2018 + Daymet: Daily Surface Weather Data on a 1-km Grid for North America, Version 3 + https://doi.org/10.3334/ORNLDAAC/1328 + + + + + J.A. Falcone + 2011 + GAGES-II: Geospatial attributes of gages for evaluating streamflow + https://doi.org/10.3133/70046617 + + + + + + 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. + + + A formal accuracy assessment of the vertical positional information in the dataset was not conducted. + + + + + At the core of the modeling framework is a deep learning model that uses inputs of XX. + 20201103 + + + + + U.S.A. + Point + + + Point + 118 + + + + + + + 0.1 + 0.1 + Decimal degrees + + + WGS84 + WGS_1984 + 6378137.0 + 298.257 + + + + + + + weather_drivers.csv + Daily weather driver data that was used to drive both the temperature and flow models. Data were obtained from Daymet and interpolated over each basin from the period 2004 to 2016. + U.S. Geological Survey + + + site_no + The unique site identifier, which is also the USGS gage site ID. + NA + + + NA + NA + NA + + + + + dayls(s) + Duration of the daylight period in seconds per day. This calculation is based on the period of the day during which the sun is above a hypothetical flat horizon. + NA + + + NA + NA + seconds per day + + + + + prcp(mm/day) + Daily total precipitation in millimeters per day, sum of all forms converted to water-equivalent. Precipitation occurrence on any given day may be ascertained. + NA + + + NA + NA + millimeters per day + + + + + srad(W/m2) + Incident shortwave radiation flux density in watts per square meter, taken as an average over the daylight period of the day. NOTE: Daily total radiation (MJ/m2/day) can be calculated as follows: ((srad (W/m2) * dayl (s/day)) / l,000,000). + NA + + + NA + NA + watts per square meter + + + + + swe(mm) + Snow water equivalent in kilograms per square meter. The amount of water contained within the snowpack. + NA + + + NA + NA + kilograms per square meter + + + + + tmax(C) + Daily maximum 2-meter air temperature in degrees Celsius. + NA + + + NA + NA + degrees Celsius + + + + + tmin(C) + Daily minimum 2-meter air temperature in degrees Celsius. + NA + + + NA + NA + degrees Celsius + + + + + vp(Pa) + Water vapor pressure in pascals. Daily average partial pressure of water vapor. + NA + + + NA + NA + pascals + + + + + datetime + Date of observation + NA + + + NA + NA + NA + + + + + + + AT_basin_attributes.csv + River basin characteristics used as inputs to the water temperature model. Basin characteristics are from the Gages II dataset. + U.S. Geological Survey + + + site_no + The unique site identifier, which is also the USGS gage site ID. + NA + + + NA + NA + NA + + + + + DRAIN_SQKM + Watershed drainage area. + NA + + + NA + NA + Square kilometer + + + + + STREAMS_KM_SQ_KM + Stream density (length of streams per area of watershed). + NA + + + NA + NA + kilometer per square kilometer + + + + + STOR_NID_2009 + Dam storage in watershed per watershed area. + NA + + + NA + NA + Megalitre per square kilometer + + + + + FORESTNLCD06 + Watershed percent forest. + NA + + + NA + NA + percent + + + + + PLANTNLCD06 + Watershed percent agriculture (plant). + NA + + + NA + NA + percent + + + + + SLOPE_PCT + Mean watershed slope. + NA + + + NA + NA + percent + + + + + RAW_DIS_NEAREST_MAJ_DAM + Raw straight line distance of gage location to nearest major dam in watershed. + NA + + + NA + NA + kilometer + + + + + PERDUN + Dunne overland flow as percentage of total streamflow. + NA + + + NA + NA + percentage + + + + + RAW_DIS_NEAREST_DAM + Raw straight line distance of gage location to nearest dam in watershed. + NA + + + NA + NA + kilometer + + + + + RAW_AVG_DIS_ALL_MAJ_DAMS + Raw average straight line distance of gage location to all major dams in watershed. + NA + + + NA + NA + kilometer + + + + + T_MIN_BASIN + Average of minimum monthly air temperature for 1971-2000. + NA + + + NA + NA + degrees Celsius + + + + + T_MINSTD_BASIN + Standard deviation of minimum monthly air temperature for 1971-2000. + NA + + + NA + NA + degrees Celsius + + + + + RH_BASIN + Watershed average relative humidity. + NA + + + NA + NA + percent + + + + + RAW_AVG_DIS_ALLDAMS + Raw average straight line distance of gage location to all dams in watershed. + NA + + + NA + NA + kilometer + + + + + PPTAVG_BASIN + Mean annual precipitation for watershed for 1971-2000. + NA + + + NA + NA + centimeter + + + + + HIRES_LENTIC_PCT + Percent of watershed area covered by lake/pond/reservoir. + NA + + + NA + NA + percent + + + + + T_AVG_BASIN + Average annual air temperature for the watershed. + NA + + + NA + NA + degrees Celsius + + + + + T_MAX_BASIN + Average of maximum monthly air temperature for 1971-2000. + NA + + + NA + NA + degrees Celsius + + + + + T_MAXSTD_BASIN + Standard deviation of maximum monthly air temperature for 1971-2000. + NA + + + NA + NA + degrees Celsius + + + + + NDAMS_2009 + Number of dams in watershed. + NA + + + NA + NA + NA + + + + + ELEV_MEAN_M_BASIN + Mean watershed elevation. + NA + + + NA + NA + meters + + + + + + + pred_discharge.csv + Simulated discharge that was used as an input to the water temperature models. Simulated discharge was only used during the test period (water years 2014-2016). + U.S. Geological Survey + + + site_no + U.S. Geological Survey site number. + NA + + + NA + NA + NA + + + + + datetime + Date of prediction. + NA + + + NA + NA + NA + + + + + sim_discharge(cfs) + Stream discharge as predicted by the discharge model. + NA + + + NA + NA + cubic feet per second + + + + + + + flow_observations.csv + Observed mean daily discharge observation retrieved from NWIS for the 118 gages used in this study. Flow observations were used as a driver in the water temperature model. The data were retrieved from NWIS and are limited to the test and training period, from 2010-10-01 through 2016-09-30. + U.S. Geological Survey + + + site_no + USGS unique site identifier. + NA + + + NA + NA + NA + + + + + datetime + Date of temperature observation. + NA + + + NA + NA + NA + + + + + discharge(cfs) + Observed mean daily discharge + NA + + + NA + NA + degrees Celsius + + + + + + + + + + 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. + + + + comma seperated file format (csv) + + + + + + XX + + + + + + None + + + + 20201103 + + + + Farshid Rahmani + U.S. Geological Survey + + Graduate Research Assistant + + Mailing and Physical +
Sackett Building, Pennsylvania State University
+ State College + PA + 16801 + U.S.A. + + NA + NA + fzr5082@psu.edu + + + FGDC Content Standard for Digital Geospatial Metadata + FGDC-STD-001-1998 + + diff --git a/out_xml/05_predictions.xml b/out_xml/05_predictions.xml new file mode 100644 index 0000000..86b2879 --- /dev/null +++ b/out_xml/05_predictions.xml @@ -0,0 +1,334 @@ + + + + + + Farshid Rahmani + Kathryn Lawson + Wenyu Ouyang + Alison Appling + Samantha Oliver + Chaopeng Shen + 2020 + Exploring the exceptional performance of a deep learning stream temperature model and the value of streamflow data: 5 model prediction data + comma seperated file format (csv) + + Online (digital release) + U.S. Geological Survey + + XX + + + Farshid Rahmani + Kathryn Lawson + Wenyu Ouyang + Alison Appling + Samantha Oliver + Chaopeng Shen + 2020 + Exploring the exceptional performance of a deep learning stream temperature model and the value of streamflow data. + + + + + + A deep learning model framework was used to make water temperature predictions in 118 river catchments across the U.S. All four model (LR, noQ, obsQ, and simQ) predictions are included. + Decision support, water quality research + + + + + 19801001 + 20191231 + + + See publication date + + + Complete + none planned + + + Locations of sites used in the study, which are a subset of the Gages II dataset. + + -123.32988684 + -70.97964444 + 48.90595739 + 30.1454932 + + + + + none + machine learning + deep learning + water + temperature + streams + modeling + + + ISO 19115 Topic Category + environment + inlandWaters + 007 + 012 + + + 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 + Alabama + AL + Delaware + DE + Georgia + GA + Idaho + ID + Iowa + IA + Kansas + KS + Maine + ME + Maryland + MD + Massachusetts + MA + Michigan + MI + Mississippi + MS + Nevada + NV + New Jersey + NJ + New Mexico + NM + New York + NY + North Carolina + NC + Ohio + OH + Oklahoma + OK + Oregon + OR + Pennsylvania + PA + Rhode Island + RI + South Carolina + SC + Tennessee + TN + Texas + TX + Utah + UT + Virginia + VA + Washington + WA + West Virginia + WV + Wisconsin + WI + Wyoming + WY + + + none + These data are subject to change and are not citable until reviewed and approved for official publication by the USGS + + + + Farshid Rahmani + U.S. Geological Survey + + Graduate Research Assistant + + Mailing and Physical +
Sackett Building, Pennsylvania State University
+ State College + PA + 16801 + U.S.A. + + NA + fzr5082@psu.edu + + + This study was funded by the Integrated Water Prediction Program at the U.S. Geological Survey. XX. + We used XX open source XX; Any supercomputing resources used? XX + + + DP Feng + K Fang + CP Shen + 2020 + Enhancing streamflow forecast and extracting insights using continental-scale long-short term memory networks with data integration + https://doi.org/10.1029/2019WR026793 + + + + + + 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. + + + A formal accuracy assessment of the vertical positional information in the dataset was not conducted. + + + + + At the core of the modeling framework is a deep learning model that uses inputs of XX. + 20201103 + + + + + U.S.A. + Point + + + Point + 118 + + + + + + + 1e-05 + 1e-05 + Decimal degrees + + + WGS84 + WGS_1984 + 6378137.0 + 298.257 + + + + + + + model_{}_predictions.csv + The water temperature predictions from each stream temperature model described in Rahmani et al. 2020. Each file represents a different stream temperature model, where model names are contained in the filename (modabbrev). Model abbreviation "lr" refers the locally-fitted linear regression model, "obsq" to the model trained with observed discharge, "simq" to the model trained with simulated discharge, and "noq" to the model trained with no discharge information. + U.S. Geological Survey + + + site_no + Unique USGS site identifier. + NA + + + NA + NA + NA + + + + + datetime + Date of prediction. + NA + + + NA + NA + NA + + + + + sim_wtemp(C) + Simulated water temperature. + NA + + + NA + NA + degrees Celsius + + + + + + + + + + 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. + + + + comma seperated file format (csv) + + + + + + XX + + + + + + None + + + + 20201103 + + + + Farshid Rahmani + U.S. Geological Survey + + Graduate Research Assistant + + Mailing and Physical +
Sackett Building, Pennsylvania State University
+ State College + PA + 16801 + U.S.A. + + NA + NA + fzr5082@psu.edu + + + FGDC Content Standard for Digital Geospatial Metadata + FGDC-STD-001-1998 + + diff --git a/out_xml/06_evaluation.xml b/out_xml/06_evaluation.xml new file mode 100644 index 0000000..167a917 --- /dev/null +++ b/out_xml/06_evaluation.xml @@ -0,0 +1,380 @@ + + + + + + Farshid Rahmani + Kathryn Lawson + Wenyu Ouyang + Alison Appling + Samantha Oliver + Chaopeng Shen + 2020 + Exploring the exceptional performance of a deep learning stream temperature model and the value of streamflow data: 6 model evaluation + comma seperated file format (csv) + + Online (digital release) + U.S. Geological Survey + + XX + + + Farshid Rahmani + Kathryn Lawson + Wenyu Ouyang + Alison Appling + Samantha Oliver + Chaopeng Shen + 2020 + Exploring the exceptional performance of a deep learning stream temperature model and the value of streamflow data. + + + + + + Several evaluation metrics were used to assess the predictive performance of each stream temperature model. For further description, see the metric calculations in the supplement of Rahmani et al. 2020. Each file correspond to a different model, but the structure of the files is the same across all models. + Decision support, water quality research + + + + + 19801001 + 20191231 + + + See publication date + + + Complete + none planned + + + Locations of sites used in the study, which are a subset of the Gages II dataset. + + -123.32988684 + -70.97964444 + 48.90595739 + 30.1454932 + + + + + none + machine learning + deep learning + water + temperature + streams + modeling + + + ISO 19115 Topic Category + environment + inlandWaters + 007 + 012 + + + 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 + Alabama + AL + Delaware + DE + Georgia + GA + Idaho + ID + Iowa + IA + Kansas + KS + Maine + ME + Maryland + MD + Massachusetts + MA + Michigan + MI + Mississippi + MS + Nevada + NV + New Jersey + NJ + New Mexico + NM + New York + NY + North Carolina + NC + Ohio + OH + Oklahoma + OK + Oregon + OR + Pennsylvania + PA + Rhode Island + RI + South Carolina + SC + Tennessee + TN + Texas + TX + Utah + UT + Virginia + VA + Washington + WA + West Virginia + WV + Wisconsin + WI + Wyoming + WY + + + none + These data are subject to change and are not citable until reviewed and approved for official publication by the USGS + + + + Farshid Rahmani + U.S. Geological Survey + + Graduate Research Assistant + + Mailing and Physical +
Sackett Building, Pennsylvania State University
+ State College + PA + 16801 + U.S.A. + + NA + fzr5082@psu.edu + + + This study was funded by the Integrated Water Prediction Program at the U.S. Geological Survey. XX. + We used XX open source XX. + + + XX + XX + Cross cite code base? + XX + + + + + + 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. + + + A formal accuracy assessment of the vertical positional information in the dataset was not conducted. + + + + + At the core of the modeling framework is a deep learning model that uses inputs of XX. + 20201103 + + + + + U.S.A. + Point + + + Point + 118 + + + + + + + 1e-05 + 1e-05 + Decimal degrees + + + WGS84 + WGS_1984 + 6378137.0 + 298.257 + + + + + + + model_{modabbrev}_evaluation.csv + The performance metrics of each stream temperature model assessed in Rahmani et al. 2020. Each file represents a different stream temperature model, where model names are contained in the filename (modabbrev). Model abbreviation "lr" refers the locally-fitted linear regression model, "obsq" to the model trained with observed discharge, "simq" to the model trained with simulated discharge, and "noq" to the model trained with no discharge information. + U.S. Geological Survey + + + site_no + Unique USGS site identifier. + NA + + + NA + NA + NA + + + + + Bias + mean error (bias) + NA + + + NA + NA + degrees Celsius + + + + + RMSE + root mean squared error + NA + + + NA + NA + degrees Celsius + + + + + ubRMSE + Unbiased root mean squared error (RMSE), which is calculated as RMSE minus the mean bias. + NA + + + NA + NA + degrees Celsius + + + + + NSE + Nash-Sutcliffe efficiency + NA + + + NA + NA + NA + + + + + NSE_res + Residual Nash-Sutcliffe efficiency (NSE), where NSE is calculated on the residual between stream and air temperature. + NA + + + NA + NA + NA + + + + + Corr_res + Pearson's correlation coefficient, calculated on the residual between stream and air temperature. + NA + + + 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. + + + + comma seperated file format (csv) + + + + + + XX + + + + + + None + + + + 20201103 + + + + Farshid Rahmani + U.S. Geological Survey + + Graduate Research Assistant + + Mailing and Physical +
Sackett Building, Pennsylvania State University
+ State College + PA + 16801 + U.S.A. + + NA + NA + fzr5082@psu.edu + + + FGDC Content Standard for Digital Geospatial Metadata + FGDC-STD-001-1998 + + diff --git a/remake.yml b/remake.yml index 9071195..4766b3f 100644 --- a/remake.yml +++ b/remake.yml @@ -40,12 +40,43 @@ targets: - 05_predictions_sb_data - 06_evaluation_sb_data - 06_evaluation_sb_xml + - out_xml/00_parent.xml + - out_xml/01_spatial.xml + - out_xml/02_observations.xml + - out_xml/03_inputs.xml + - out_xml/05_predictions.xml + - out_xml/06_evaluation.xml out_xml/00_parent.xml: command: render(filename = target_name, "in_text/text_SHARED.yml", - "in_text/text_00_parent.yml") + "in_text/text_00_parent.yml", spatial_metadata) + + out_xml/01_spatial.xml: + command: render(filename = target_name, + "in_text/text_SHARED.yml", + "in_text/text_01_spatial.yml", spatial_metadata) + + out_xml/02_observations.xml: + command: render(filename = target_name, + "in_text/text_SHARED.yml", + "in_text/text_02_observations.yml", spatial_metadata) + + out_xml/03_inputs.xml: + command: render(filename = target_name, + "in_text/text_SHARED.yml", + "in_text/text_03_inputs.yml", spatial_metadata) + + out_xml/05_predictions.xml: + command: render(filename = target_name, + "in_text/text_SHARED.yml", + "in_text/text_05_predictions.yml", spatial_metadata) + + out_xml/06_evaluation.xml: + command: render(filename = target_name, + "in_text/text_SHARED.yml", + "in_text/text_06_evaluation.yml", spatial_metadata) 00_parent_sb_xml: command: sb_render_post_xml(sbid_00_parent, @@ -53,7 +84,6 @@ targets: "in_text/text_00_parent.yml", spatial_metadata) - 01_spatial_sb_xml: command: sb_render_post_xml(sbid_01_spatial, "in_text/text_SHARED.yml", @@ -66,7 +96,7 @@ targets: 02_observations_sb_data: command: sb_replace_files(sbid_02_observations, - "out_data/temperature_observations.csv", "out_data/flow_observations.csv") + "out_data/temperature_observations.csv") 02_observations_sb_xml: command: sb_render_post_xml(sbid_02_observations, @@ -83,7 +113,7 @@ targets: command: sb_replace_files(sbid_03_inputs, "out_data/weather_drivers.zip", "out_data/AT_basin_attributes.csv", - "out_data/pred_discharge.csv") + "out_data/pred_discharge.csv", "out_data/obs_discharge.csv") 05_predictions_sb_xml: command: sb_render_post_xml(sbid_05_predictions, diff --git a/src/munge_functions.R b/src/munge_functions.R index d6c745e..e02f01f 100644 --- a/src/munge_functions.R +++ b/src/munge_functions.R @@ -22,7 +22,7 @@ extract_AQ_attributes <- function(out_file, in_file) { subset_pred_discharge <- function(out_file, in_file){ dat <- readr::read_csv(in_file) %>% select(site_no, datetime, `sim_discharge(cfs)` = combine_discharge) %>% - filter(datetime >= as.Date('2013-09-30')) # predicted Q only in test period + filter(datetime > as.Date('2014-09-30')) # predicted Q only in test period readr::write_csv(dat, out_file) }