From 78bc3cec768da37bf5e8da78529fec2093463a2e Mon Sep 17 00:00:00 2001 From: github-actions Date: Thu, 13 Jun 2024 16:01:44 +0000 Subject: [PATCH] update catalog --- .../Daily_Chlorophyll_a/collection.json | 164 +++++++++++++++ .../Daily_Chlorophyll_a/models/USGSHABs1.json | 191 ++++++++++++++++++ .../models/climatology.json | 191 ++++++++++++++++++ .../models/persistenceRW.json | 191 ++++++++++++++++++ catalog/forecasts/aquatics/collection.json | 154 ++++++++++++++ catalog/forecasts/collection.json | 29 +-- 6 files changed, 900 insertions(+), 20 deletions(-) create mode 100644 catalog/forecasts/aquatics/Daily_Chlorophyll_a/collection.json create mode 100644 catalog/forecasts/aquatics/Daily_Chlorophyll_a/models/USGSHABs1.json create mode 100644 catalog/forecasts/aquatics/Daily_Chlorophyll_a/models/climatology.json create mode 100644 catalog/forecasts/aquatics/Daily_Chlorophyll_a/models/persistenceRW.json create mode 100644 catalog/forecasts/aquatics/collection.json diff --git a/catalog/forecasts/aquatics/Daily_Chlorophyll_a/collection.json b/catalog/forecasts/aquatics/Daily_Chlorophyll_a/collection.json new file mode 100644 index 0000000000..6ad0dedc42 --- /dev/null +++ b/catalog/forecasts/aquatics/Daily_Chlorophyll_a/collection.json @@ -0,0 +1,164 @@ +{ + "id": "Daily_Chlorophyll_a", + "description": "All models for the Daily_Chlorophyll_a variable. The variable description is as follows: daily mean Chlorophyll-a (ug/L)", + "stac_version": "1.0.0", + "license": "CC0-1.0", + "stac_extensions": [ + "https://stac-extensions.github.io/scientific/v1.0.0/schema.json", + "https://stac-extensions.github.io/item-assets/v1.0.0/schema.json", + "https://stac-extensions.github.io/table/v1.2.0/schema.json" + ], + "type": "Collection", + "sci:doi": "10.1002/fee.2616", + "sci:publications": {}, + "links": [ + { + "rel": "item", + "type": "application/json", + "href": "./models/persistenceRW.json" + }, + { + "rel": "item", + "type": "application/json", + "href": "./models/USGSHABs1.json" + }, + { + "rel": "item", + "type": "application/json", + "href": "./models/climatology.json" + }, + { + "rel": "parent", + "type": "application/json", + "href": "../collection.json" + }, + { + "rel": "root", + "type": "application/json", + "href": "../collection.json" + }, + { + "rel": "self", + "type": "application/json", + "href": "collection.json" + }, + { + "rel": "cite-as", + "href": "https://doi.org/10.1002/fee.2616" + }, + { + "rel": "about", + "href": "https://projects.ecoforecast.org/usgsrc4cast-docs/", + "type": "text/html", + "title": "EFI-USGS River Chlorophyll Forecasting Challenge Documentation" + }, + { + "rel": "describedby", + "href": "https://projects.ecoforecast.org/usgsrc4cast-ci/", + "title": "EFI-USGS River Chlorophyll Forecast Challenge Dashboard", + "type": "text/html" + } + ], + "title": "Daily_Chlorophyll_a", + "extent": { + "spatial": { + "bbox": [ + [-122.6692, 39.6328, -74.7781, 45.5175] + ] + }, + "temporal": { + "interval": [ + [ + "2024-02-07T00:00:00Z", + "2024-07-17T00:00:00Z" + ] + ] + } + }, + "table:columns": [ + { + "name": "13 columns", + "type": null, + "description": {} + }, + { + "name": "datetime", + "type": "timestamp[us, tz=UTC]", + "description": "datetime of the forecasted value (ISO 8601)" + }, + { + "name": "site_id", + "type": "string", + "description": "For forecasts that are not on a spatial grid, use of a site dimension that maps to a more detailed geometry (points, polygons, etc.) is allowable. In general this would be documented in the external metadata (e.g., alook-up table that provides lon and lat)" + }, + { + "name": "prediction", + "type": "double", + "description": "predicted value for variable" + }, + { + "name": "parameter", + "type": "string", + "description": "ensemble member or distribution parameter" + }, + { + "name": "family", + "type": "string", + "description": "For ensembles: “ensemble.” Default value if unspecified for probability distributions: Name of the statistical distribution associated with the reported statistics. The “sample” distribution is synonymous with “ensemble.”For summary statistics: “summary.”" + }, + { + "name": "reference_datetime", + "type": "timestamp[us, tz=UTC]", + "description": "datetime that the forecast was initiated (horizon = 0)" + }, + { + "name": "pub_datetime", + "type": "timestamp[us, tz=UTC]", + "description": "datetime that forecast was submitted" + }, + { + "name": "date", + "type": "date32[day]", + "description": "date of the forecasted value" + }, + { + "name": "project_id", + "type": "string", + "description": "unique identifier for the forecast project" + }, + { + "name": "duration", + "type": "string", + "description": "temporal duration of forecast (hourly, daily, etc.); follows ISO 8601 duration convention" + }, + { + "name": "variable", + "type": "string", + "description": "name of forecasted variable" + }, + { + "name": "model_id", + "type": "string", + "description": "unique model identifier" + } + ], + "assets": { + "data": { + "href": "s3://anonymous@bio230014-bucket01/challenges/forecasts/parquet/project_id=usgsrc4cast/duration=P1D/variable=chla?endpoint_override=sdsc.osn.xsede.org", + "type": "application/x-parquet", + "title": "Database Access", + "roles": [ + "data" + ], + "description": "Use `arrow` for remote access to the database. This R code will return results for forecasts of the variable by the specific model .\n\n### R\n\n```{r}\n# Use code below\n\nall_results <- arrow::open_dataset(\"s3://anonymous@bio230014-bucket01/challenges/forecasts/parquet/project_id=usgsrc4cast/duration=P1D/variable=chla?endpoint_override=sdsc.osn.xsede.org\")\ndf <- all_results |> dplyr::collect()\n\n```\n \n\nYou can use dplyr operations before calling `dplyr::collect()` to `summarise`, `select` columns, and/or `filter` rows prior to pulling the data into a local `data.frame`. Reducing the data that is pulled locally will speed up the data download speed and reduce your memory usage.\n\n\n" + }, + "thumbnail": { + "href": "https://d9-wret.s3.us-west-2.amazonaws.com/assets/palladium/production/s3fs-public/thumbnails/image/Back-b.jpg", + "type": "image/JPEG", + "roles": [ + "thumbnail" + ], + "title": "Thumbnail Image" + } + } +} diff --git a/catalog/forecasts/aquatics/Daily_Chlorophyll_a/models/USGSHABs1.json b/catalog/forecasts/aquatics/Daily_Chlorophyll_a/models/USGSHABs1.json new file mode 100644 index 0000000000..7b43e7eaa1 --- /dev/null +++ b/catalog/forecasts/aquatics/Daily_Chlorophyll_a/models/USGSHABs1.json @@ -0,0 +1,191 @@ +{ + "stac_version": "1.0.0", + "stac_extensions": [ + "https://stac-extensions.github.io/table/v1.2.0/schema.json" + ], + "type": "Feature", + "id": "USGSHABs1_chla_P1D_forecast", + "bbox": [ + [-122.6692, 39.6328, -74.7781, 45.5175] + ], + "geometry": { + "type": "MultiPoint", + "coordinates": [ + [-122.6692, 45.5175], + [-122.2974, 44.7538], + [-90.6077, 39.6328], + [-122.5773, 45.3793], + [-74.7781, 40.2217], + [-89.3562, 41.1073], + [-88.984, 41.3248], + [-88.6142, 41.2999], + [-88.2515, 42.31], + [-75.0574, 41.7567] + ] + }, + "properties": { + "title": "USGSHABs1", + "description": "All forecasts for the Daily_Chlorophyll_a variable for the USGSHABs1 model. Information for the model is provided as follows: Uses the randomForest::randomForest() R package model to train site-specific models for predicting river chl-a. Uses ensemble Kalman filter to adjust predicted chl-a states..\n The model predicts this variable at the following sites: USGS-14211720, USGS-14181500, USGS-05586300, USGS-14211010, USGS-01463500, USGS-05558300, USGS-05553700, USGS-05543010, USGS-05549500, USGS-01427510.\n Forecasts are the raw forecasts that includes all ensemble members or distribution parameters. Due to the size of the raw forecasts, we recommend accessing the forecast summaries or scores to analyze forecasts (unless you need the individual ensemble members)", + "start_datetime": "2024-02-13", + "end_datetime": "2024-07-14", + "providers": [ + { + "url": "jzwart@usgs.gov", + "name": "Jacob Zwart", + "roles": [ + "producer", + "processor", + "licensor" + ] + }, + { + "url": "https://www.ecoforecastprojectvt.org", + "name": "Ecoforecast Challenge", + "roles": [ + "host" + ] + } + ], + "license": "CC0-1.0", + "keywords": [ + "Forecasts", + "usgsrc4cast", + "aquatics", + "USGSHABs1", + "Chlorophyll_a", + "chla", + "Daily", + "P1D", + "USGS-14211720", + "USGS-14181500", + "USGS-05586300", + "USGS-14211010", + "USGS-01463500", + "USGS-05558300", + "USGS-05553700", + "USGS-05543010", + "USGS-05549500", + "USGS-01427510" + ], + "table:columns": [ + { + "name": "13 columns", + "type": null, + "description": {} + }, + { + "name": "datetime", + "type": "timestamp[us, tz=UTC]", + "description": "datetime of the forecasted value (ISO 8601)" + }, + { + "name": "site_id", + "type": "string", + "description": "For forecasts that are not on a spatial grid, use of a site dimension that maps to a more detailed geometry (points, polygons, etc.) is allowable. In general this would be documented in the external metadata (e.g., alook-up table that provides lon and lat)" + }, + { + "name": "prediction", + "type": "double", + "description": "predicted value for variable" + }, + { + "name": "parameter", + "type": "string", + "description": "ensemble member or distribution parameter" + }, + { + "name": "family", + "type": "string", + "description": "For ensembles: “ensemble.” Default value if unspecified for probability distributions: Name of the statistical distribution associated with the reported statistics. The “sample” distribution is synonymous with “ensemble.”For summary statistics: “summary.”" + }, + { + "name": "reference_datetime", + "type": "timestamp[us, tz=UTC]", + "description": "datetime that the forecast was initiated (horizon = 0)" + }, + { + "name": "pub_datetime", + "type": "timestamp[us, tz=UTC]", + "description": "datetime that forecast was submitted" + }, + { + "name": "date", + "type": "date32[day]", + "description": "date of the forecasted value" + }, + { + "name": "project_id", + "type": "string", + "description": "unique identifier for the forecast project" + }, + { + "name": "duration", + "type": "string", + "description": "temporal duration of forecast (hourly, daily, etc.); follows ISO 8601 duration convention" + }, + { + "name": "variable", + "type": "string", + "description": "name of forecasted variable" + }, + { + "name": "model_id", + "type": "string", + "description": "unique model identifier" + } + ] + }, + "collection": "forecasts", + "links": [ + { + "rel": "collection", + "href": "../collection.json", + "type": "application/json", + "title": "USGSHABs1" + }, + { + "rel": "root", + "href": "../../../catalog.json", + "type": "application/json", + "title": "Forecast Catalog" + }, + { + "rel": "parent", + "href": "../collection.json", + "type": "application/json", + "title": "USGSHABs1" + }, + { + "rel": "self", + "href": "USGSHABs1.json", + "type": "application/json", + "title": "Model Forecast" + }, + { + "rel": "item", + "href": "https://code.usgs.gov/wma/proxies/habs/habs-forecast-chl-usgsrc4cast/-/blob/main/2_model/src/chla_models.R?ref_type=heads", + "type": "text/html", + "title": "Link for Model Code" + } + ], + "assets": { + "1": { + "type": "application/json", + "title": "Model Metadata", + "href": "https://sdsc.osn.xsede.org/bio230014-bucket01/challenges/metadata/model_id/USGSHABs1.json", + "description": "Use `jsonlite::fromJSON()` to download the model metadata JSON file. This R code will return metadata provided during the model registration.\n \n\n### R\n\n```{r}\n# Use code below\n\nmodel_metadata <- jsonlite::fromJSON(\"https://sdsc.osn.xsede.org/bio230014-bucket01/challenges/metadata/model_id/USGSHABs1.json\")\n\n" + }, + "2": { + "type": "text/html", + "title": "Link for Model Code", + "href": "https://code.usgs.gov/wma/proxies/habs/habs-forecast-chl-usgsrc4cast/-/blob/main/2_model/src/chla_models.R?ref_type=heads", + "description": "The link to the model code provided by the model submission team" + }, + "3": { + "type": "application/x-parquet", + "title": "Database Access for Daily Chlorophyll_a", + "href": "s3://anonymous@bio230014-bucket01/challenges/forecasts/parquet/project_id=usgsrc4cast/duration=P1D/variable=chla/model_id=USGSHABs1?endpoint_override=sdsc.osn.xsede.org", + "description": "Use `arrow` for remote access to the database. This R code will return results for this variable and model combination.\n\n### R\n\n```{r}\n# Use code below\n\nall_results <- arrow::open_dataset(\"s3://anonymous@bio230014-bucket01/challenges/forecasts/parquet/project_id=usgsrc4cast/duration=P1D/variable=chla/model_id=USGSHABs1?endpoint_override=sdsc.osn.xsede.org\")\ndf <- all_results |> dplyr::collect()\n\n```\n \n\nYou can use dplyr operations before calling `dplyr::collect()` to `summarise`, `select` columns, and/or `filter` rows prior to pulling the data into a local `data.frame`. Reducing the data that is pulled locally will speed up the data download speed and reduce your memory usage.\n\n\n" + } + } +} diff --git a/catalog/forecasts/aquatics/Daily_Chlorophyll_a/models/climatology.json b/catalog/forecasts/aquatics/Daily_Chlorophyll_a/models/climatology.json new file mode 100644 index 0000000000..b18956577e --- /dev/null +++ b/catalog/forecasts/aquatics/Daily_Chlorophyll_a/models/climatology.json @@ -0,0 +1,191 @@ +{ + "stac_version": "1.0.0", + "stac_extensions": [ + "https://stac-extensions.github.io/table/v1.2.0/schema.json" + ], + "type": "Feature", + "id": "climatology_chla_P1D_forecast", + "bbox": [ + [-122.6692, 39.6328, -74.7781, 45.5175] + ], + "geometry": { + "type": "MultiPoint", + "coordinates": [ + [-75.0574, 41.7567], + [-74.7781, 40.2217], + [-88.6142, 41.2999], + [-88.2515, 42.31], + [-88.984, 41.3248], + [-89.3562, 41.1073], + [-90.6077, 39.6328], + [-122.2974, 44.7538], + [-122.5773, 45.3793], + [-122.6692, 45.5175] + ] + }, + "properties": { + "title": "climatology", + "description": "All forecasts for the Daily_Chlorophyll_a variable for the climatology model. Information for the model is provided as follows: Forecasts stream chlorophyll-a based on the historic average and standard deviation for that given site and day-of-year..\n The model predicts this variable at the following sites: USGS-01427510, USGS-01463500, USGS-05543010, USGS-05549500, USGS-05553700, USGS-05558300, USGS-05586300, USGS-14181500, USGS-14211010, USGS-14211720.\n Forecasts are the raw forecasts that includes all ensemble members or distribution parameters. Due to the size of the raw forecasts, we recommend accessing the forecast summaries or scores to analyze forecasts (unless you need the individual ensemble members)", + "start_datetime": "2024-02-07", + "end_datetime": "2024-07-17", + "providers": [ + { + "url": "jzwart@usgs.gov", + "name": "Jacob Zwart", + "roles": [ + "producer", + "processor", + "licensor" + ] + }, + { + "url": "https://www.ecoforecastprojectvt.org", + "name": "Ecoforecast Challenge", + "roles": [ + "host" + ] + } + ], + "license": "CC0-1.0", + "keywords": [ + "Forecasts", + "usgsrc4cast", + "aquatics", + "climatology", + "Chlorophyll_a", + "chla", + "Daily", + "P1D", + "USGS-01427510", + "USGS-01463500", + "USGS-05543010", + "USGS-05549500", + "USGS-05553700", + "USGS-05558300", + "USGS-05586300", + "USGS-14181500", + "USGS-14211010", + "USGS-14211720" + ], + "table:columns": [ + { + "name": "13 columns", + "type": null, + "description": {} + }, + { + "name": "datetime", + "type": "timestamp[us, tz=UTC]", + "description": "datetime of the forecasted value (ISO 8601)" + }, + { + "name": "site_id", + "type": "string", + "description": "For forecasts that are not on a spatial grid, use of a site dimension that maps to a more detailed geometry (points, polygons, etc.) is allowable. In general this would be documented in the external metadata (e.g., alook-up table that provides lon and lat)" + }, + { + "name": "prediction", + "type": "double", + "description": "predicted value for variable" + }, + { + "name": "parameter", + "type": "string", + "description": "ensemble member or distribution parameter" + }, + { + "name": "family", + "type": "string", + "description": "For ensembles: “ensemble.” Default value if unspecified for probability distributions: Name of the statistical distribution associated with the reported statistics. The “sample” distribution is synonymous with “ensemble.”For summary statistics: “summary.”" + }, + { + "name": "reference_datetime", + "type": "timestamp[us, tz=UTC]", + "description": "datetime that the forecast was initiated (horizon = 0)" + }, + { + "name": "pub_datetime", + "type": "timestamp[us, tz=UTC]", + "description": "datetime that forecast was submitted" + }, + { + "name": "date", + "type": "date32[day]", + "description": "date of the forecasted value" + }, + { + "name": "project_id", + "type": "string", + "description": "unique identifier for the forecast project" + }, + { + "name": "duration", + "type": "string", + "description": "temporal duration of forecast (hourly, daily, etc.); follows ISO 8601 duration convention" + }, + { + "name": "variable", + "type": "string", + "description": "name of forecasted variable" + }, + { + "name": "model_id", + "type": "string", + "description": "unique model identifier" + } + ] + }, + "collection": "forecasts", + "links": [ + { + "rel": "collection", + "href": "../collection.json", + "type": "application/json", + "title": "climatology" + }, + { + "rel": "root", + "href": "../../../catalog.json", + "type": "application/json", + "title": "Forecast Catalog" + }, + { + "rel": "parent", + "href": "../collection.json", + "type": "application/json", + "title": "climatology" + }, + { + "rel": "self", + "href": "climatology.json", + "type": "application/json", + "title": "Model Forecast" + }, + { + "rel": "item", + "href": "https://github.com/eco4cast/usgsrc4cast-ci/blob/main/baseline_models/models/aquatics_climatology.R", + "type": "text/html", + "title": "Link for Model Code" + } + ], + "assets": { + "1": { + "type": "application/json", + "title": "Model Metadata", + "href": "https://sdsc.osn.xsede.org/bio230014-bucket01/challenges/metadata/model_id/climatology.json", + "description": "Use `jsonlite::fromJSON()` to download the model metadata JSON file. This R code will return metadata provided during the model registration.\n \n\n### R\n\n```{r}\n# Use code below\n\nmodel_metadata <- jsonlite::fromJSON(\"https://sdsc.osn.xsede.org/bio230014-bucket01/challenges/metadata/model_id/climatology.json\")\n\n" + }, + "2": { + "type": "text/html", + "title": "Link for Model Code", + "href": "https://github.com/eco4cast/usgsrc4cast-ci/blob/main/baseline_models/models/aquatics_climatology.R", + "description": "The link to the model code provided by the model submission team" + }, + "3": { + "type": "application/x-parquet", + "title": "Database Access for Daily Chlorophyll_a", + "href": "s3://anonymous@bio230014-bucket01/challenges/forecasts/parquet/project_id=usgsrc4cast/duration=P1D/variable=chla/model_id=climatology?endpoint_override=sdsc.osn.xsede.org", + "description": "Use `arrow` for remote access to the database. This R code will return results for this variable and model combination.\n\n### R\n\n```{r}\n# Use code below\n\nall_results <- arrow::open_dataset(\"s3://anonymous@bio230014-bucket01/challenges/forecasts/parquet/project_id=usgsrc4cast/duration=P1D/variable=chla/model_id=climatology?endpoint_override=sdsc.osn.xsede.org\")\ndf <- all_results |> dplyr::collect()\n\n```\n \n\nYou can use dplyr operations before calling `dplyr::collect()` to `summarise`, `select` columns, and/or `filter` rows prior to pulling the data into a local `data.frame`. Reducing the data that is pulled locally will speed up the data download speed and reduce your memory usage.\n\n\n" + } + } +} diff --git a/catalog/forecasts/aquatics/Daily_Chlorophyll_a/models/persistenceRW.json b/catalog/forecasts/aquatics/Daily_Chlorophyll_a/models/persistenceRW.json new file mode 100644 index 0000000000..4d74c91fc8 --- /dev/null +++ b/catalog/forecasts/aquatics/Daily_Chlorophyll_a/models/persistenceRW.json @@ -0,0 +1,191 @@ +{ + "stac_version": "1.0.0", + "stac_extensions": [ + "https://stac-extensions.github.io/table/v1.2.0/schema.json" + ], + "type": "Feature", + "id": "persistenceRW_chla_P1D_forecast", + "bbox": [ + [-122.6692, 39.6328, -74.7781, 45.5175] + ], + "geometry": { + "type": "MultiPoint", + "coordinates": [ + [-122.6692, 45.5175], + [-75.0574, 41.7567], + [-74.7781, 40.2217], + [-88.6142, 41.2999], + [-88.2515, 42.31], + [-88.984, 41.3248], + [-89.3562, 41.1073], + [-90.6077, 39.6328], + [-122.2974, 44.7538], + [-122.5773, 45.3793] + ] + }, + "properties": { + "title": "persistenceRW", + "description": "All forecasts for the Daily_Chlorophyll_a variable for the persistenceRW model. Information for the model is provided as follows: Random walk model based on most recent stream chl-a observations using the fable::RW() model..\n The model predicts this variable at the following sites: USGS-14211720, USGS-01427510, USGS-01463500, USGS-05543010, USGS-05549500, USGS-05553700, USGS-05558300, USGS-05586300, USGS-14181500, USGS-14211010.\n Forecasts are the raw forecasts that includes all ensemble members or distribution parameters. Due to the size of the raw forecasts, we recommend accessing the forecast summaries or scores to analyze forecasts (unless you need the individual ensemble members)", + "start_datetime": "2024-02-07", + "end_datetime": "2024-07-16", + "providers": [ + { + "url": "jzwart@usgs.gov", + "name": "Jacob Zwart", + "roles": [ + "producer", + "processor", + "licensor" + ] + }, + { + "url": "https://www.ecoforecastprojectvt.org", + "name": "Ecoforecast Challenge", + "roles": [ + "host" + ] + } + ], + "license": "CC0-1.0", + "keywords": [ + "Forecasts", + "usgsrc4cast", + "aquatics", + "persistenceRW", + "Chlorophyll_a", + "chla", + "Daily", + "P1D", + "USGS-14211720", + "USGS-01427510", + "USGS-01463500", + "USGS-05543010", + "USGS-05549500", + "USGS-05553700", + "USGS-05558300", + "USGS-05586300", + "USGS-14181500", + "USGS-14211010" + ], + "table:columns": [ + { + "name": "13 columns", + "type": null, + "description": {} + }, + { + "name": "datetime", + "type": "timestamp[us, tz=UTC]", + "description": "datetime of the forecasted value (ISO 8601)" + }, + { + "name": "site_id", + "type": "string", + "description": "For forecasts that are not on a spatial grid, use of a site dimension that maps to a more detailed geometry (points, polygons, etc.) is allowable. In general this would be documented in the external metadata (e.g., alook-up table that provides lon and lat)" + }, + { + "name": "prediction", + "type": "double", + "description": "predicted value for variable" + }, + { + "name": "parameter", + "type": "string", + "description": "ensemble member or distribution parameter" + }, + { + "name": "family", + "type": "string", + "description": "For ensembles: “ensemble.” Default value if unspecified for probability distributions: Name of the statistical distribution associated with the reported statistics. The “sample” distribution is synonymous with “ensemble.”For summary statistics: “summary.”" + }, + { + "name": "reference_datetime", + "type": "timestamp[us, tz=UTC]", + "description": "datetime that the forecast was initiated (horizon = 0)" + }, + { + "name": "pub_datetime", + "type": "timestamp[us, tz=UTC]", + "description": "datetime that forecast was submitted" + }, + { + "name": "date", + "type": "date32[day]", + "description": "date of the forecasted value" + }, + { + "name": "project_id", + "type": "string", + "description": "unique identifier for the forecast project" + }, + { + "name": "duration", + "type": "string", + "description": "temporal duration of forecast (hourly, daily, etc.); follows ISO 8601 duration convention" + }, + { + "name": "variable", + "type": "string", + "description": "name of forecasted variable" + }, + { + "name": "model_id", + "type": "string", + "description": "unique model identifier" + } + ] + }, + "collection": "forecasts", + "links": [ + { + "rel": "collection", + "href": "../collection.json", + "type": "application/json", + "title": "persistenceRW" + }, + { + "rel": "root", + "href": "../../../catalog.json", + "type": "application/json", + "title": "Forecast Catalog" + }, + { + "rel": "parent", + "href": "../collection.json", + "type": "application/json", + "title": "persistenceRW" + }, + { + "rel": "self", + "href": "persistenceRW.json", + "type": "application/json", + "title": "Model Forecast" + }, + { + "rel": "item", + "href": "https://github.com/eco4cast/usgsrc4cast-ci/blob/main/baseline_models/models/aquatics_persistenceRW.R", + "type": "text/html", + "title": "Link for Model Code" + } + ], + "assets": { + "1": { + "type": "application/json", + "title": "Model Metadata", + "href": "https://sdsc.osn.xsede.org/bio230014-bucket01/challenges/metadata/model_id/persistenceRW.json", + "description": "Use `jsonlite::fromJSON()` to download the model metadata JSON file. This R code will return metadata provided during the model registration.\n \n\n### R\n\n```{r}\n# Use code below\n\nmodel_metadata <- jsonlite::fromJSON(\"https://sdsc.osn.xsede.org/bio230014-bucket01/challenges/metadata/model_id/persistenceRW.json\")\n\n" + }, + "2": { + "type": "text/html", + "title": "Link for Model Code", + "href": "https://github.com/eco4cast/usgsrc4cast-ci/blob/main/baseline_models/models/aquatics_persistenceRW.R", + "description": "The link to the model code provided by the model submission team" + }, + "3": { + "type": "application/x-parquet", + "title": "Database Access for Daily Chlorophyll_a", + "href": "s3://anonymous@bio230014-bucket01/challenges/forecasts/parquet/project_id=usgsrc4cast/duration=P1D/variable=chla/model_id=persistenceRW?endpoint_override=sdsc.osn.xsede.org", + "description": "Use `arrow` for remote access to the database. This R code will return results for this variable and model combination.\n\n### R\n\n```{r}\n# Use code below\n\nall_results <- arrow::open_dataset(\"s3://anonymous@bio230014-bucket01/challenges/forecasts/parquet/project_id=usgsrc4cast/duration=P1D/variable=chla/model_id=persistenceRW?endpoint_override=sdsc.osn.xsede.org\")\ndf <- all_results |> dplyr::collect()\n\n```\n \n\nYou can use dplyr operations before calling `dplyr::collect()` to `summarise`, `select` columns, and/or `filter` rows prior to pulling the data into a local `data.frame`. Reducing the data that is pulled locally will speed up the data download speed and reduce your memory usage.\n\n\n" + } + } +} diff --git a/catalog/forecasts/aquatics/collection.json b/catalog/forecasts/aquatics/collection.json new file mode 100644 index 0000000000..f6903db816 --- /dev/null +++ b/catalog/forecasts/aquatics/collection.json @@ -0,0 +1,154 @@ +{ + "id": "aquatics", + "description": "All variables for the aquatics group.", + "stac_version": "1.0.0", + "license": "CC0-1.0", + "stac_extensions": [ + "https://stac-extensions.github.io/scientific/v1.0.0/schema.json", + "https://stac-extensions.github.io/item-assets/v1.0.0/schema.json", + "https://stac-extensions.github.io/table/v1.2.0/schema.json" + ], + "type": "Collection", + "sci:doi": "10.1002/fee.2616", + "sci:publications": {}, + "links": [ + { + "rel": "child", + "type": "application/json", + "href": "Daily_Chlorophyll_a/collection.json" + }, + { + "rel": "parent", + "type": "application/json", + "href": "../collection.json" + }, + { + "rel": "root", + "type": "application/json", + "href": "../collection.json" + }, + { + "rel": "self", + "type": "application/json", + "href": "collection.json" + }, + { + "rel": "cite-as", + "href": "https://doi.org/10.1002/fee.2616" + }, + { + "rel": "about", + "href": "https://projects.ecoforecast.org/usgsrc4cast-docs/", + "type": "text/html", + "title": "EFI-USGS River Chlorophyll Forecasting Challenge Documentation" + }, + { + "rel": "describedby", + "href": "https://projects.ecoforecast.org/usgsrc4cast-ci/", + "title": "EFI-USGS River Chlorophyll Forecast Challenge Dashboard", + "type": "text/html" + } + ], + "title": "aquatics", + "extent": { + "spatial": { + "bbox": [ + [-122.6692, 39.6328, -74.7781, 45.5175] + ] + }, + "temporal": { + "interval": [ + [ + "2024-02-07T00:00:00Z", + "2024-07-17T00:00:00Z" + ] + ] + } + }, + "table:columns": [ + { + "name": "13 columns", + "type": null, + "description": {} + }, + { + "name": "datetime", + "type": "timestamp[us, tz=UTC]", + "description": "datetime of the forecasted value (ISO 8601)" + }, + { + "name": "site_id", + "type": "string", + "description": "For forecasts that are not on a spatial grid, use of a site dimension that maps to a more detailed geometry (points, polygons, etc.) is allowable. In general this would be documented in the external metadata (e.g., alook-up table that provides lon and lat)" + }, + { + "name": "prediction", + "type": "double", + "description": "predicted value for variable" + }, + { + "name": "parameter", + "type": "string", + "description": "ensemble member or distribution parameter" + }, + { + "name": "family", + "type": "string", + "description": "For ensembles: “ensemble.” Default value if unspecified for probability distributions: Name of the statistical distribution associated with the reported statistics. The “sample” distribution is synonymous with “ensemble.”For summary statistics: “summary.”" + }, + { + "name": "reference_datetime", + "type": "timestamp[us, tz=UTC]", + "description": "datetime that the forecast was initiated (horizon = 0)" + }, + { + "name": "pub_datetime", + "type": "timestamp[us, tz=UTC]", + "description": "datetime that forecast was submitted" + }, + { + "name": "date", + "type": "date32[day]", + "description": "date of the forecasted value" + }, + { + "name": "project_id", + "type": "string", + "description": "unique identifier for the forecast project" + }, + { + "name": "duration", + "type": "string", + "description": "temporal duration of forecast (hourly, daily, etc.); follows ISO 8601 duration convention" + }, + { + "name": "variable", + "type": "string", + "description": "name of forecasted variable" + }, + { + "name": "model_id", + "type": "string", + "description": "unique model identifier" + } + ], + "assets": { + "data": { + "href": "s3://anonymous@bio230014-bucket01/challenges/scores/parquet/?endpoint_override=sdsc.osn.xsede.org", + "type": "application/x-parquet", + "title": "Database Access", + "roles": [ + "data" + ], + "description": "Use `arrow` for remote access to the database. This R code will return results for the NEON Ecological Forecasting Aquatics theme.\n\n### R\n\n```{r}\n# Use code below\n\nall_results <- arrow::open_dataset(\"s3://anonymous@bio230014-bucket01/challenges/scores/parquet/?endpoint_override=sdsc.osn.xsede.org\")\ndf <- all_results |>\n dplyr::filter(variable %in% c(\"chla\")) |>\n dplyr::collect()\n\n```\n \n\nYou can use dplyr operations before calling `dplyr::collect()` to `summarise`, `select` columns, and/or `filter` rows prior to pulling the data into a local `data.frame`. Reducing the data that is pulled locally will speed up the data download speed and reduce your memory usage.\n\n\n" + }, + "thumbnail": { + "href": "https://d9-wret.s3.us-west-2.amazonaws.com/assets/palladium/production/s3fs-public/thumbnails/image/Back-b.jpg", + "type": "image/JPEG", + "roles": [ + "thumbnail" + ], + "title": "USGS Streamgage" + } + } +} diff --git a/catalog/forecasts/collection.json b/catalog/forecasts/collection.json index 2db3638831..7b663313b1 100644 --- a/catalog/forecasts/collection.json +++ b/catalog/forecasts/collection.json @@ -16,12 +16,6 @@ "href": "aquatics/collection.json", "title": "aquatics" }, - { - "rel": "child", - "type": "application/json", - "href": "models/collection.json", - "title": "group item" - }, { "rel": "parent", "type": "application/json", @@ -49,7 +43,7 @@ }, { "rel": "describedby", - "href": "https://projects.ecoforecast.org/usgsrc4cast-docs/", + "href": "https://projects.ecoforecast.org/usgsrc4cast-ci/", "title": "EFI-USGS River Chlorophyll Forecast Challenge Dashboard", "type": "text/html" } @@ -58,24 +52,24 @@ "extent": { "spatial": { "bbox": [ - [ - -122.6692, - 39.6327, - -74.7781, - 45.5175 - ] + [-122.6692, 39.6328, -74.7781, 45.5175] ] }, "temporal": { "interval": [ [ "2024-02-07T00:00:00Z", - "2024-06-03T00:00:00Z" + "2024-07-17T00:00:00Z" ] ] } }, "table:columns": [ + { + "name": "13 columns", + "type": null, + "description": {} + }, { "name": "datetime", "type": "timestamp[us, tz=UTC]", @@ -114,7 +108,7 @@ { "name": "date", "type": "date32[day]", - "description": {} + "description": "date of the forecasted value" }, { "name": "project_id", @@ -135,11 +129,6 @@ "name": "model_id", "type": "string", "description": "unique model identifier" - }, - { - "name": "reference_date", - "type": "string", - "description": "date that the forecast was initiated" } ], "assets": {