Updated datasets 2024-03-27 UTC

opengeos · Mar 27, 2024 · 2094af3 · 2094af3
1 parent 88775cf
commit 2094af3
Show file tree

Hide file tree

Showing 56 changed files with 618 additions and 368 deletions.
diff --git a/aws_open_datasets.json b/aws_open_datasets.json
diff --git a/aws_open_datasets.tsv b/aws_open_datasets.tsv
diff --git a/datasets/allen-sea-ad-atlas.yaml b/datasets/allen-sea-ad-atlas.yaml
@@ -6,6 +6,7 @@ Contact: [email protected]
 ManagedBy: "[Allen Institute](http://www.alleninstitute.org/)"
 UpdateFrequency: Annually
 Tags: 
+  - aws-pds
   - biology
   - cell biology
   - cell imaging

diff --git a/datasets/asem-project.yaml b/datasets/asem-project.yaml
@@ -5,6 +5,7 @@ Contact: [email protected]
 ManagedBy: Kirchhausen Lab at Harvard Medical School
 UpdateFrequency: Data is added as it becomes available
 Tags:
+  - aws-pds
   - biology
   - cell biology
   - segmentation

diff --git a/datasets/binding-db.yaml b/datasets/binding-db.yaml
@@ -5,6 +5,7 @@ Contact: https://github.com/aws-samples/data-lake-as-code/issues
 ManagedBy: "[Amazon Web Services](https://aws.amazon.com/)"
 UpdateFrequency: Within 2 months after an new BindingDB release.
 Tags:  
+  - aws-pds
   - chemistry
   - genetic
   - genomic

diff --git a/datasets/blended-tropomi-gosat-methane.yaml b/datasets/blended-tropomi-gosat-methane.yaml
@@ -5,6 +5,7 @@ Contact: [email protected]
 ManagedBy: Nicholas Balasus
 UpdateFrequency: Monthly
 Tags:
+  - aws-pds
   - climate
   - environmental
   - satellite imagery

diff --git a/datasets/catalyst-cooperative-pudl.yaml b/datasets/catalyst-cooperative-pudl.yaml
@@ -26,6 +26,7 @@ UpdateFrequency: |
   The federal agencies that publish the raw data PUDL processes release new data, monthly, quarterly and yearly. 
   PUDL is continuously improving the data and tries to release new versions of the data monthly.
 Tags:
+  - aws-pds
   - climate
   - climate model
   - energy

diff --git a/datasets/cellpainting-gallery.yaml b/datasets/cellpainting-gallery.yaml
@@ -10,6 +10,7 @@ Contact: [email protected]
 ManagedBy: Carpenter-Singh and Cimini Labs at the Broad Institute
 UpdateFrequency: Typically when an associated publication is posted on biorxiv
 Tags:
+  - aws-pds
   - bioinformatics
   - biology
   - cancer

diff --git a/datasets/census-2010-dhc-nmf.yaml b/datasets/census-2010-dhc-nmf.yaml
@@ -13,6 +13,7 @@ Contact: [email protected]
 ManagedBy: "[United States Census Bureau](http://www.census.gov/)"
 UpdateFrequency: Not Updated
 Tags:
+  - aws-pds
   - census
   - differential privacy
   - disclosure avoidance

diff --git a/datasets/census-2010-pl94-nmf.yaml b/datasets/census-2010-pl94-nmf.yaml
@@ -16,6 +16,7 @@ Contact: [email protected]
 ManagedBy: "[United States Census Bureau](http://www.census.gov/)"
 UpdateFrequency: "Last updated November 10, 2023: Modifications to identifiers within the parquet metadata used to support internal tracking of source data."
 Tags:
+  - aws-pds
   - census
   - differential privacy
   - disclosure avoidance

diff --git a/datasets/census-2020-dhc-nmf.yaml b/datasets/census-2020-dhc-nmf.yaml
@@ -17,6 +17,7 @@ Contact: [email protected]
 ManagedBy: "[United States Census Bureau](http://www.census.gov/)"
 UpdateFrequency: Not Updated
 Tags:
+  - aws-pds
   - census
   - differential privacy
   - disclosure avoidance

diff --git a/datasets/census-2020-pl94-nmf.yaml b/datasets/census-2020-pl94-nmf.yaml
@@ -16,6 +16,7 @@ Contact: [email protected]
 ManagedBy: "[United States Census Bureau](http://www.census.gov/)"
 UpdateFrequency: Not Updated
 Tags:
+  - aws-pds
   - census
   - differential privacy
   - disclosure avoidance

diff --git a/datasets/citrus-farm.yaml b/datasets/citrus-farm.yaml
@@ -10,6 +10,7 @@ Contact: Hanzhe Teng ([email protected]), Konstantinos Karydis ([email protected].
 ManagedBy: "[Autonomous Robots and Control Systems Lab](https://sites.google.com/view/arcs-lab)"
 UpdateFrequency: NA
 Tags:
+  - aws-pds
   - robotics
   - computer vision
   - agriculture

diff --git a/datasets/cord-19.yaml b/datasets/cord-19.yaml
@@ -5,6 +5,7 @@ Contact: [email protected]
 ManagedBy: Allen Institute for AI
 UpdateFrequency: Weekly
 Tags:
+  - aws-pds
   - COVID-19
   - coronavirus
   - life sciences

diff --git a/datasets/czi-cellxgene-census.yaml b/datasets/czi-cellxgene-census.yaml
@@ -9,6 +9,7 @@ Contact: [email protected]
 ManagedBy: "[Chan Zuckerberg Initiative Foundation](http://www.chanzuckerberg.com/)"
 UpdateFrequency: New releases are published weekly. Long-term supported (LTS) releases are published every 6 months.
 Tags:
+  - aws-pds
   - single-cell transcriptomics
   - transcriptomics
   - cell biology

diff --git a/datasets/ecmwf-forecasts.yaml b/datasets/ecmwf-forecasts.yaml
@@ -6,6 +6,7 @@ Contact: https://confluence.ecmwf.int/site/support
 ManagedBy: "[European Centre for Medium-Range Weather Forecasts](https://www.ecmwf.int/)"
 UpdateFrequency: "The data are released 1 hour after the [real-time dissemination schedule](https://confluence.ecmwf.int/display/DAC/Dissemination+schedule)."
 Tags:
+  - aws-pds
   - air temperature
   - atmosphere
   - meteorological

diff --git a/datasets/emearth.yaml b/datasets/emearth.yaml
@@ -5,6 +5,7 @@ Contact: [email protected]
 ManagedBy: "[Computational Hydrology at the University of Saskatchewan](https://uofs-comphyd.github.io/)"
 UpdateFrequency: N/A
 Tags:
+  - aws-pds
   - atmosphere
   - netcdf
   - near-surface air temperature

diff --git a/datasets/euro-cordex.yaml b/datasets/euro-cordex.yaml
@@ -12,6 +12,7 @@ Collabs:
     Tags:
       - climate
 Tags:
+  - aws-pds
   - climate
   - model
   - climate model

diff --git a/datasets/geoglows-v2.yaml b/datasets/geoglows-v2.yaml
@@ -1,17 +1,21 @@
-Name: GEOGloWS Hydrologic Model Version 2
+Name: GEOGLOWS Hydrologic Model Version 2
 Description: |
-  The GEOGloWS Hydrologic Model provides a global simulation of river discharge. The model simulates river discharge at 
+  The GEOGLOWS Hydrologic Model provides a global simulation of river discharge. The model simulates river discharge at 
   7 million river segments over a period of more than 80 years beginning on 1 January 1940. The retrospective simulation 
   is updated weekly to monthly keeping the lag time small. The model is also used to produce daily forecasts which are 
   not archived in this repository. The model is based on the ERA5 reanalysis climate data and forecasts are derived from 
   the ECMWF Integrated Forecast System (IFS). The stream network is derived from the TDX-Hydro streams and basins data 
   produced by the United State's National Geospatial Intelligence Agency. The model simulations are computed daily at 
   the ECMWF super computing facility in Bologna, Italy.<br><br>
-  This repository contains: (1) model configuration files used to generate the simulations, (2) the model retrospective 
-  outputs in zarr format optimized for time series queries of up to a few hundred rivers on demand, (3) the model output 
-  in netCDF format best for bulk downloading large volumes of data, (4) estimated return period flows for all 7 million 
-  rivers in netCDF format, (5) the GIS streams datasets used by the model, (6) the GIS streams datasets optimized for 
-  visualizations used by Esri's Living Atlas layer.
+  The geoglows-v2 bucket contains: (1) model configuration files used to generate the simulations, (2) the GIS streams 
+  datasets used by the model, (3) the GIS streams datasets optimized for visualizations used by Esri's Living Atlas 
+  layer, (4) several supporting table of metadata including country names, river names, hydrologic properties used for
+  modeling.<br><br>
+  The geoglows-v2-retrospective bucket contains: (1) the model retrospective outputs in (1a) zarr format optimized for 
+  time series queries of up to a few hundred rivers on demand as well as (1b) in netCDF format best for bulk downloading 
+  the dataset, (2) estimated return period flows for all 7 million million rivers (2a) in zarr format optimized for 
+  reading subsets of the dataset as well as (2b) in netCDF format best for bulk downloading. (3) The initialization files 
+  produced at the end of each incremental simulation useful for restarting the model from a specific date.<br><br>
 Documentation: https://data.geoglows.org
 Contact: https://groups.google.com/g/geoglows
 ManagedBy: Riley Hales
@@ -27,19 +31,25 @@ Tags:
 License: "[Creative Commons BY 4 (CC BY 4.0)](https://creativecommons.org/licenses/by/4.0/)"
 Citation: https://doi.org/10.1111/jfr3.12859
 Resources:
-  - Description: GEOGloWS Hydrologic Model Version 2
+  - Description: GEOGLOWS Version 2
     ARN: arn:aws:s3:::geoglows-v2
     Region: us-west-2
     Type: S3 Bucket
     Explore:
     - '[Browse Bucket](http://geoglows-v2.s3-website-us-west-2.amazonaws.com)'
+  - Description: GEOGLOWS Version 2 Retrospective Simulation
+    ARN: arn:aws:s3:::geoglows-v2-retrospective
+    Region: us-west-2
+    Type: S3 Bucket
+    Explore:
+    - '[Browse Bucket](http://geoglows-v2-retrospective.s3-website-us-west-2.amazonaws.com)'
 DataAtWork:
   Tutorials:
-    - Title: GEOGloWS V2 Tutorials
+    - Title: GEOGLOWS V2 Tutorials
       URL: https://data.geoglows.org
       AuthorName: Riley Hales
       AuthorURL: https://hales.app
-    - Title: Finding River Numbers 
+    - Title: Finding River Numbers
       URL: https://data.geoglows.org/tutorials/finding-river-numbers
       AuthorName: Riley Hales
       AuthorURL: https://hales.app
@@ -58,7 +68,7 @@ DataAtWork:
       Services:
         - S3
   Tools & Applications:
-    - Title: GEOGloWS Hydroviewer
+    - Title: GEOGLOWS Hydroviewer
       URL: https://apps.geoglows.org/apps/geoglows-hydroviewer
       AuthorName: Riley Hales
       AuthorURL: https://hales.app

diff --git a/datasets/glo-30-hand.yaml b/datasets/glo-30-hand.yaml
@@ -12,6 +12,7 @@ UpdateFrequency: >
   None, except HAND may be updated if the[ Copernicus GLO-30 Public](https://registry.opendata.aws/copernicus-dem/)
   dataset is updated.
 Tags:
+  - aws-pds
   - elevation
   - hydrology
   - agriculture

diff --git a/datasets/global-drought-flood-catalogue.yaml b/datasets/global-drought-flood-catalogue.yaml
@@ -6,6 +6,7 @@ Contact: For any questions regrading dataset, email Professor Xiaogang He at hex
 ManagedBy: "[PREP-NexT Lab](https://github.com/PREP-NexT)"
 UpdateFrequency: No future updates planned.
 Tags:
+  - aws-pds
   - floods
   - global
   - netcdf

diff --git a/datasets/intelinair_agriculture_vision.yaml b/datasets/intelinair_agriculture_vision.yaml
@@ -16,6 +16,7 @@ Collabs:
     Tags:
       - agriculture
 Tags:
+  - aws-pds
   - aerial imagery
   - agriculture
   - computer vision

diff --git a/datasets/intelinair_corn_kernel_counting.yaml b/datasets/intelinair_corn_kernel_counting.yaml
@@ -5,6 +5,7 @@ Contact: [email protected]
 ManagedBy: Intelinair, Inc.
 UpdateFrequency: Periodically
 Tags:
+  - aws-pds
   - agriculture
   - computer vision
   - machine learning

diff --git a/datasets/intelinair_longitudinal_nutrient_deficiency.yaml b/datasets/intelinair_longitudinal_nutrient_deficiency.yaml
@@ -5,6 +5,7 @@ Contact: [email protected]
 ManagedBy: Intelinair, Inc.
 UpdateFrequency: Periodically
 Tags:
+  - aws-pds
   - aerial imagery
   - agriculture
   - computer vision

diff --git a/datasets/klarna_productpage_dataset.yaml b/datasets/klarna_productpage_dataset.yaml
@@ -7,6 +7,7 @@ Contact: https://github.com/klarna/product-page-dataset/issues, stefan.magureanu
 ManagedBy: Web Automation Research, Klarna
 UpdateFrequency: The dataset is not expected to update frequently.
 Tags:
+  - aws-pds
   - internet
   - natural language processing
   - computer vision

diff --git a/datasets/kyfromabove.yaml b/datasets/kyfromabove.yaml
@@ -5,6 +5,7 @@ Contact: More information regarding the KyFromAbove program can be found at http
 ManagedBy: "[Kentucky Division of Geographic Information](https://kygeonet.ky.gov)"
 UpdateFrequency: KyFromAbove data is typically updated on an annual basis. Each year, a portion of the state is acquired with an overall update cycle of every three to four years. This update cadance is determined by both funding and the length of leaf-off conditions in a given year. This catalog currently includes imagery and LiDAR data from 2010 through 2022 for most products.
 Tags:
+  - aws-pds
   - earth observation
   - aerial imagery
   - geospatial

diff --git a/datasets/m3ed.yaml b/datasets/m3ed.yaml
@@ -5,6 +5,7 @@ Contact: https://m3ed.io/contact-us/
 ManagedBy: "[Daniilidis Group](https://www.grasp.upenn.edu/people/kostas-daniilidis/), [KumarRobotics](https://www.kumarrobotics.org/)"
 UpdateFrequency: The dataset will be uploaded sporadically, when bugs are found and new features are implemented (see [updates](https://m3ed.io/#updates)).
 Tags:
+  - aws-pds
   - autonomous vehicles
   - computer vision
   - deep learning

diff --git a/datasets/maf-genome.yaml b/datasets/maf-genome.yaml
@@ -6,6 +6,7 @@ Contact: [email protected]
 ManagedBy: "[Morris Animal Foundation](https://www.morrisanimalfoundation.org/)"
 UpdateFrequency: Static
 Tags:
+  - aws-pds
   - genome
   - genotyping
   - golden retriever lifetime study

diff --git a/datasets/maxar-open-data.yaml b/datasets/maxar-open-data.yaml
@@ -12,6 +12,7 @@ Collabs:
     Tags:
       - disaster response
 Tags:
+  - aws-pds
   - earth observation
   - disaster response
   - geospatial

diff --git a/datasets/modis-astraea.yaml b/datasets/modis-astraea.yaml
@@ -19,6 +19,7 @@ Collabs:
     Tags:
       - satellite imagery
 Tags:
+  - aws-pds
   - agriculture
   - geospatial
   - satellite imagery

diff --git a/datasets/nasa-heasarc.yaml b/datasets/nasa-heasarc.yaml
@@ -17,6 +17,7 @@ ManagedBy: The [HEASARC](https://heasarc.gsfc.nasa.gov/)
 UpdateFrequency: Various.
 
 Tags:
+  - aws-pds
   - astronomy
   - archives
   - datacenter

diff --git a/datasets/nasa-lambda.yaml b/datasets/nasa-lambda.yaml
@@ -14,6 +14,7 @@ ManagedBy: "[LAMBDA](https://lambda.gsfc.nasa.gov/)"
 UpdateFrequency: "Various."
 
 Tags:
+  - aws-pds
   - astronomy
   - archives
   - datacenter

diff --git a/datasets/nex-gddp-cmip6.yaml b/datasets/nex-gddp-cmip6.yaml
@@ -23,6 +23,7 @@ Collabs:
     Tags:
       - climate
 Tags:
+  - aws-pds
   - CMIP6
   - climate
   - climate model

diff --git a/datasets/oida.yaml b/datasets/oida.yaml
@@ -5,6 +5,7 @@ Contact: [email protected]
 ManagedBy: Johns Hopkins University
 UpdateFrequency: monthly
 Tags:
+  - aws-pds
   - archives
   - text analysis
   - txt

diff --git a/datasets/ons-opendata-portal.yaml b/datasets/ons-opendata-portal.yaml
@@ -6,6 +6,7 @@ ManagedBy: "[ONS - National Electric System Operator](https://www.ons.org.br/)"
 UpdateFrequency: diary
 Citation: Portuguese
 Tags:  
+    - aws-pds
     - electricity
     - hydrography
     - energy

diff --git a/datasets/openaq.yaml b/datasets/openaq.yaml
@@ -9,6 +9,7 @@ Collabs:
     Tags:
       - air quality
 Tags:
+  - aws-pds
   - air quality
   - cities
   - environmental

diff --git a/datasets/orcasound.yaml b/datasets/orcasound.yaml
@@ -9,6 +9,7 @@ Collabs:
     Tags:
       - biodiversity
 Tags:
+  - aws-pds
   - biodiversity
   - biology
   - coastal

diff --git a/datasets/palsar-2-scansar-flooding-in-bangladesh.yaml b/datasets/palsar-2-scansar-flooding-in-bangladesh.yaml
@@ -6,6 +6,7 @@ Documentation: https://www.eorc.jaxa.jp/ALOS/en/dataset/alos_open_and_free_e.htm
 ManagedBy: "[JAXA](https://www.jaxa.jp/)"
 Contact: [email protected]
 Tags:
+  - aws-pds
   - agriculture
   - cog
   - disaster response

diff --git a/datasets/palsar-2-scansar-flooding-in-rwanda.yaml b/datasets/palsar-2-scansar-flooding-in-rwanda.yaml
@@ -6,6 +6,7 @@ Documentation: https://www.eorc.jaxa.jp/ALOS/en/dataset/alos_open_and_free_e.htm
 ManagedBy: "[JAXA](https://www.jaxa.jp/)"
 Contact: [email protected]
 Tags:
+  - aws-pds
   - agriculture
   - cog
   - deafrica

diff --git a/datasets/panstarrs.yaml b/datasets/panstarrs.yaml
@@ -7,6 +7,7 @@ ManagedBy: "[Space Telescope Science Institute](http://www.stsci.edu/)"
 Citation: Please see the documentation for full citation instructions.
 UpdateFrequency: Never
 Tags:
+  - aws-pds
   - astronomy
 License: STScI hereby grants the non-exclusive, royalty-free, non-transferable, worldwide right and license to use, reproduce, and publicly display in all media data from the PS1 surveys.
 Resources:

diff --git a/datasets/racecar-dataset.yaml b/datasets/racecar-dataset.yaml
@@ -5,6 +5,7 @@ Contact: Prof. Madhur Behl ([email protected])
 ManagedBy: Amar Kulkarni ([email protected])
 UpdateFrequency: This dataset was constructed during a single racing season (2021-22). Future seasons may potentially be added.
 Tags:
+  - aws-pds
   - autonomous vehicles
   - autonomous racing
   - robotics

diff --git a/datasets/serratus-lovelywater.yaml b/datasets/serratus-lovelywater.yaml
@@ -5,6 +5,7 @@ Contact: https://github.com/ababaian/serratus/issues
 ManagedBy: Serratus / UBC Cloud Innovation Centre
 UpdateFrequency: Quarterly
 Tags:
+  - aws-pds
   - life sciences
   - genetic
   - genomic

diff --git a/datasets/singlecellhumanbloodatlas.yaml b/datasets/singlecellhumanbloodatlas.yaml
@@ -5,6 +5,7 @@ Contact: [email protected]
 ManagedBy: Sage Bionetworks
 UpdateFrequency: Never
 Tags:
+  - aws-pds
   - protein
   - single-cell transcriptomics
 License: '[CC BY]'

diff --git a/datasets/spitzer-seip.yaml b/datasets/spitzer-seip.yaml
@@ -5,6 +5,7 @@ Contact: https://irsa.ipac.caltech.edu/docs/help_desk.html
 ManagedBy: "NASA/IPAC Infrared Science Archive ([IRSA](https://irsa.ipac.caltech.edu)) at Caltech"
 UpdateFrequency: This data set may be updated once or twice in the future.
 Tags:
+  - aws-pds
   - astronomy
   - imaging
   - satellite imagery