Merge branch 'main' into main

berylrab · web-flow · commit b72493f52a89 · 2025-10-06T10:42:21.000-04:00
diff --git a/datasets/aws-public-blockchain.yaml b/datasets/aws-public-blockchain.yaml
@@ -13,6 +13,7 @@ Description: >
   - XRP Ledger              - SonarX  - <code>s3://aws-public-blockchain/v1.1/sonarx/xrp/</code><br>
   - Stellar(<a href="https://developers.stellar.org/docs/learn/fundamentals/data-format/xdr" rel="noopener noreferrer">XDR files</a>)              - Stellar - <code>s3://aws-public-blockchain/v1.1/stellar/</code><br>
   - The Open Network (TON)  - TON - <code>s3://aws-public-blockchain/v1.1/ton/</code><br>
+  - Cronos                  - Cronos - <code>s3://aws-public-blockchain/v1.1/cronos/</code><br>
   </br> 
 
   <h4>Become a Data Provider</h4>
@@ -24,6 +25,7 @@ Contact: aws-blockchain-data@amazon.com
 ManagedBy: "[Amazon Web Services](https://aws.amazon.com/)"
 UpdateFrequency: New data is delivered daily to the current date folders Parquet files.
 Tags:
+  - aws-pds
   - blockchain
   - web3
 License: https://github.com/aws-samples/digital-assets-examples/blob/main/LICENSE
diff --git a/datasets/clinical-ultrasound-image-data.yaml b/datasets/clinical-ultrasound-image-data.yaml
@@ -0,0 +1,20 @@
+Name: Clinical Ultrasound Image Repository
+Description: Generic Clinical Ultrasound Data from Random Subjects acquired for Clinical Reasons, to be used for Developing Artificial Intelligence Applications. This dataset is complete with 2000 studies from 2000 subjects (one third each from abdominal, cardiac, and OB/GYN cases)
+Documentation: https://clinical-ultrasound-image-repository.s3.amazonaws.com/index.html
+Contact: shuver@nvidia.com
+ManagedBy: "[MONAI Development Team](https://github.com/Project-MONAI/MONAI)"
+UpdateFrequency: This is a static dataset; however, tutorials and resources will be updated as they are developed.
+Tags:
+  - medicine
+  - medical imaging
+  - machine learning
+  - life sciences
+  - aws-pds
+License: "[CC-BY-NC 4.0](https://creativecommons.org/licenses/by-nc/4.0/)"
+Resources:
+  - Description: Clinical Ultrasound Image Repository
+    ARN: arn:aws:s3:::clinical-ultrasound-image-repository
+    Region: us-west-2
+    Type: S3 Bucket
+    Explore:
+    - "[Browse Bucket](https://clinical-ultrasound-image-repository.s3.amazonaws.com/download.html)"
diff --git a/datasets/cmas-data-warehouse.yaml b/datasets/cmas-data-warehouse.yaml
@@ -73,6 +73,12 @@ Resources:
     Type: S3 Bucket
     Explore:
     - '[Browse Bucket](https://cmaq-12us4-cracmm3-modeling-platform-2023.s3.amazonaws.com/index.html)'
+  - Description: CMAQ Model Versions 5.5 CRACMM2 Input Data (2022r1) -- 12/22/2021 - 12/31/2022 12km CONUS
+    ARN:  arn:aws:s3::::::cmaq-12us1-cracmm2-modeling-platform-2022
+    Region: us-east-1
+    Type: S3 Bucket
+    Explore:
+    - '[Browse Bucket](https://cmaq-12us1-cracmm2-modeling-platform-2022.s3.amazonaws.com/index.html)'
   - Description: EPA 2022 Modeling Platform
     ARN: arn:aws:s3:::epa-2022-modeling-platform
     Region: us-east-1
diff --git a/datasets/colorado-elevation-data.yaml b/datasets/colorado-elevation-data.yaml
@@ -2,7 +2,7 @@ Name: State of Colorado Elevation Data
 Description: The State of Colorado has gathered public historical elevation data.
 Documentation: https://docs.google.com/document/d/1HMO-d4cCrBvFa2F6-N3lhP6rkezlvBmSUFA5S8t_ekQ/edit?usp=sharing
 Contact: oit_gis@state.co.us
-ManagedBy: State of Colorado Governor's Office of Information Technology (OIT) GIS team
+ManagedBy: State of Colorado Governors Office of Information Technology OIT GIS team
 UpdateFrequency: Periodically
 Tags:
   - aws-pds
diff --git a/datasets/colorado-imagery.yaml b/datasets/colorado-imagery.yaml
@@ -2,7 +2,7 @@ Name: State of Colorado Imagery
 Description: The State of Colorado has gathered public historical imagery ranging from 2005 to 2021.
 Documentation: https://docs.google.com/document/d/1YDHignUj9lQTMw2J-SqA96MTP8KmJYtk2ZKKC2ZYuPE/edit?usp=sharing
 Contact: oit_gis@state.co.us
-ManagedBy: State of Colorado Governor's Office of Information Technology (OIT) GIS team
+ManagedBy: State of Colorado Governors Office of Information Technology OIT GIS team
 UpdateFrequency: Periodically
 Collabs:
   ASDI:
diff --git a/datasets/deepdrug-dpeb.yaml b/datasets/deepdrug-dpeb.yaml
@@ -0,0 +1,38 @@
+Name: DeepDrug Protein Embeddings Bank (DPEB)
+Description: DPEB is a multimodal database of human protein embeddings integrating four biologically complementary representations—AlphaFold2, BioEmbeddings, ESM-2, and ProtVec—designed for enhanced protein-protein interaction prediction and functional classification.
+Documentation: https://github.com/deepdrugai/DPEB
+Contact: https://github.com/deepdrugai/DPEB/issues
+ManagedBy: "Louisiana State University"
+UpdateFrequency: Initial release; maintained for at least 2 years with updates planned based on new embedding models and protein coverage.
+Tags:
+  - bioinformatics
+  - protein
+  - structural biology
+  - machine learning
+  - life sciences
+  - aws-pds
+License: MIT
+Citation: "Sajol MSI et al. DeepDrug Protein Embeddings Bank (DPEB) was accessed on [DATE] at https://registry.opendata.aws/dpeb"
+Resources:
+  - Description: Multimodal human protein embeddings (AlphaFold2, BioEmbeddings, ESM-2, ProtVec) with JSONL-formatted metadata containing FASTA, UniProt IDs, and embeddings.
+    ARN: arn:aws:s3:::deepdrug-dpeb
+    Region: us-west-2
+    Type: S3 Bucket
+DataAtWork:
+  Tutorials:
+    - Title: Aggregating and Clustering AlphaFold2 Embeddings from DPEB
+      URL: https://github.com/deepdrugai/DPEB/tree/main
+      AuthorName: Md. Saiful Islam Sajol
+      AuthorURL: https://github.com/deepdrugai
+  Tools & Applications:
+    - Title: DPEB Explorer Tool
+      URL: https://github.com/deepdrugai/DPEB
+      AuthorName: DeepDrug Lab
+      AuthorURL: https://github.com/deepdrugai
+  Publications:
+    - Title: A Multimodal Human Protein Embeddings Database - DeepDrug Protein Embeddings Bank (DPEB)
+      URL: https://doi.org/10.XXXX/nar.dpeb2025
+      AuthorName: Sajol MSI, Rajasekaran M, Bess A, Alvin C, Mukhopadhyay S
+      AuthorURL: https://github.com/deepdrugai/DPEB
+ADXCategories:
+  - Healthcare & Life Sciences Data
diff --git a/datasets/dmi-danra-05.yaml b/datasets/dmi-danra-05.yaml
@@ -0,0 +1,50 @@
+Name: Danish Meteorological Institute (DMI) Reanalysis dataset v0.5
+Description: DANRA is a high-resolution meteorological reanalysis dataset for Denmark and Northwestern Europe covering the period September 1990 to December 2023
+Documentation: https://dmidk.github.io/danradocs/intro.html
+Contact: https://www.dmi.dk/kontakt
+ManagedBy: "[Danish Meteorological Institute](https://www.dmi.dk/)"
+UpdateFrequency: Not updated
+Collabs:
+  ASDI:
+    Tags:
+      - climate
+      - weather
+Tags:
+  - aws-pds
+  - air temperature
+  - atmosphere
+  - geospatial
+  - global
+  - land
+  - meteorological
+  - near-surface air temperature
+  - near-surface relative humidity
+  - near-surface specific humidity
+  - model
+  - water
+  - weather
+  - zarr
+License: DMI Reanalysis dataset v0.5 is distributed under the [Creative Commons License CC BY 4.0](https://creativecommons.org/licenses/by/4.0/legalcode.en)
+Resources:
+  - Description: DMI Reanalysis dataset v0.5
+    ARN: arn:aws:s3:::dmi-danra-05
+    Region: eu-north-1
+    Type: S3 Bucket
+DataAtWork:
+  Tutorials:
+    - Title: Looking at distributions
+      URL: https://dmidk.github.io/danradocs/notebooks/distributions.html
+      NotebookURL: https://dmidk.github.io/danradocs/_sources/notebooks/distributions.ipynb
+      AuthorName: Danish Meteorological Institute
+      AuthorURL: https://www.dmi.dk/
+      Services:
+        - Amazon S3
+    - Title: DANRA figures
+      URL: https://dmidk.github.io/danradocs/notebooks/paper-figures.html
+      NotebookURL: https://dmidk.github.io/danradocs/_sources/notebooks/paper-figures.ipynb
+      AuthorName: Danish Meteorological Institute
+      AuthorURL: https://www.dmi.dk/
+      Services:
+        - Amazon S3
+ADXCategories:
+  - Environmental Data
diff --git a/datasets/e11bio-prism.yaml b/datasets/e11bio-prism.yaml
@@ -0,0 +1,62 @@
+Name: E11bio PRISM
+Description: |
+  This dataset was generated using E11.bio's PRISM technology (Protein Reconstruction and Identification through Multiplexing),
+  a platform that combines viral barcoding, expansion microscopy, and iterative immunolabeling for large-scale neuronal reconstruction.
+
+  Neurons in the mouse hippocampal CA3 were transduced with a library of adeno-associated viruses (AAVs)
+  encoding diverse “protein bits”—small epitope tags that act as combinatorial barcodes. 
+  Tissue was then processed with an expansion microscopy protocol, physically enlarging the sample ~5×
+  to achieve an effective voxel size of ~35 × 35 × 80 nm.
+  Across multiple cycles of staining, imaging, and antibody stripping, the same expanded tissue was repeatedly labeled,
+  enabling iterative immunostaining for dozens of molecular targets.
+
+  The dataset includes:
+  1) Light microscopy data of multiplexed brain tissue
+  2) Segmentations of cell morphology and protein expression in the tissue
+  3) Files for faster visualization of the data (e.g. precomputed format)
+  4) Additional supporting files (e.g. model predictions, manual annotations etc.)
+Documentation: https://github.com/e11bio/e11-open-data
+Contact: hello@e11.bio
+ManagedBy: "[E11.bio](https://e11.bio)"
+UpdateFrequency: As required
+Tags:
+  - bioinformatics
+  - biology
+  - brain images
+  - cell imaging
+  - computer vision
+  - fluorescence imaging
+  - high-throughput imaging
+  - image processing
+  - imaging
+  - ion channels
+  - life sciences
+  - machine learning
+  - microscopy
+  - morphological reconstructions
+  - Mus musculus
+  - neurobiology
+  - neuroimaging
+  - neuroscience
+  - protein
+  - segmentation
+  - zarr
+  - aws-pds
+License: https://e11.bio/terms-of-use
+Resources:
+  - Description: Data files in a public bucket
+    ARN: arn:aws:s3:::e11bio-prism
+    Region: us-east-1
+    Type: S3 Bucket
+DataAtWork:
+  Tutorials:
+    - Title: E11.Bio PRISM OpenData
+      URL: https://github.com/e11bio/e11-open-data
+      NotebookURL:
+      AuthorName: Arlo Sheridan & Johan Winnubst
+      AuthorURL: https://e11.bio/team
+  Tools & Applications:
+    - Title: Volara 
+      URL: https://github.com/e11bio/volara
+      AuthorName: Arlo Sheridan & Will Patton
+      AuthorURL: https://e11.bio/team
diff --git a/datasets/ecmwf-era5.yaml b/datasets/ecmwf-era5.yaml
@@ -1,5 +1,6 @@
 Deprecated: True
-DeprecatedNotice: The provider of this dataset will no longer maintain this dataset.  We are open to talking with anyone else who might be willing to provide this dataset to the community.  Contact <a href="mailto:opendata@amazon.com">opendata@amazon.com</a>.
+DeprecatedNotice: |
+  <h3>The provider of this dataset will no longer maintain it, but has instead worked with NSF NCAR to rehost the dataset here: <a href=https://registry.opendata.aws/nsf-ncar-era5/>https://registry.opendata.aws/nsf-ncar-era5/</a> </h3>
 Name: ECMWF ERA5 Reanalysis
 Description: |
   ERA5 is the fifth generation of ECMWF atmospheric reanalyses of the global climate, and the first reanalysis produced as an operational service. It utilizes the best available observation data from satellites and in-situ stations, which are assimilated and processed using ECMWF's Integrated Forecast System (IFS) Cycle 41r2.
diff --git a/datasets/fvcom_gom3.yaml b/datasets/fvcom_gom3.yaml
@@ -0,0 +1,28 @@
+Name: UMASSD-FVCOM-GOM3-Hindcast
+Description: The Finite Volume Community Ocean Model (FVCOM) was used to simulate ocean water levels, velocity, temperature and salinity over a multi-decadal period (1984-present) in the waters of the Northeast US including the Gulf of Maine.  The model was configured and run by the Dr. Changshen Chen, Director of the Marine Ecosystems Dynamics Modeling Laboratory in the School for Marine Science & Technology at the University of Massachusetts Dartmouth.  The triangular mesh has a varying horizontal resolution from several hundred meters inshore to several kilometers offshore, and 45 terrain-following vertical layers.  The model output was saved at hourly intervals from 2009-08-21 to 2022-06-17. 
+Documentation: https://en.wikipedia.org/wiki/Finite_Volume_Community_Ocean_Model
+Contact: rich@opensciencecomputing.com
+ManagedBy: Open Science Computing, LLC
+UpdateFrequency: None
+Citation: https://web.archive.org/web/20161229211546id_/http://fvcom.smast.umassd.edu/wp-content/uploads/2013/11/MITSG_12-25.pdf
+Tags:
+  - aws-pds
+  - oceans
+License: CC0
+Resources:
+  - Description: A collection of NetCDF files, kerchunk-generated Parquet reference files, and an Intake catalog
+    ARN: arn:aws:s3:::fvcom-gom3
+    Region: us-east-1
+    Type: S3 Bucket
+DataAtWork:
+  Tutorials:
+    - Title: FVCOM Explorer Notebook
+      URL: https://github.com/opensciencecomputing/fvcom
+      NotebookURL: https://github.com/opensciencecomputing/umassd-fvcom/blob/main/fvcom_gom3_explore.ipynb
+      AuthorName: Rich Signell
+      AuthorURL: https://about.me/rich.signell
+      Services:
+  Publications:
+    - Title: An Unstructured Grid, Finite Volume, Three Dimensional, Primitive Equations Ocean Model with Application to Coastal Ocean and Estuaries
+      URL: https://doi.org/10.1175/1520-0426(2003)020%3C0159:AUGFVT%3E2.0.CO;2
+      AuthorName: Changsheng Chen, Hedong Liu, and Robert C. Beardsley
diff --git a/datasets/humancellatlas.yaml b/datasets/humancellatlas.yaml
@@ -12,7 +12,7 @@ Documentation: https://data.humancellatlas.org/
 
 Contact: https://data.humancellatlas.org/contact
 
-ManagedBy: UC Santa Cruz Genomics Institute, University of California, Santa Cruz (UCSC)
+ManagedBy: UC Santa Cruz Genomics Institute, University of California, Santa Cruz, UCSC
 
 UpdateFrequency: Monthly
 
@@ -95,4 +95,4 @@ DataAtWork:
       AuthorName: "Various authors"
 
 ADXCategories:
-  - Healthcare & Life Sciences Data
+  - Healthcare & Life Sciences Data
diff --git a/datasets/ideam-radares.yaml b/datasets/ideam-radares.yaml
@@ -29,9 +29,9 @@ DataAtWork:
     - Title: Read and plot Sigmet files available on AWS using Xradar
       URL: https://docs.openradarscience.org/projects/xradar/en/stable/notebooks/Read-plot-Sigmet-data-from-AWS.html
       AuthorName: Alfonso Ladino
-    - Title: Taller de datos científicos con Python y R - AtmosCol 2023
-      URL: https://projectpythia.org/AtmosCol-2023/notebooks/2.acceso-datos/2.2.Radares.html
+    - Title: Ciencia de Datos Hidrometeorológicos con Python
+      URL: https://projectpythia.org/AtmosCol-2023/radares
       AuthorName: Alfonso Ladino, Nicole Rivera, Max Grover
     - Title: Specific Differential Phase (KDP) retrieval methods comparison
-      URL: https://projectpythia.org/radar-cookbook/notebooks/example-workflows/kdp-comparison.html
+      URL: https://projectpythia.org/radar-cookbook/notebooks/example-workflows/kdp-comparison/
       AuthorName: Alfonso Ladino, Max Grover
diff --git a/datasets/noaa-ocs-hydrodata.yaml b/datasets/noaa-ocs-hydrodata.yaml
@@ -28,6 +28,8 @@ Resources:
     Type: S3 Bucket
     Explore:
       - '[Browse Bucket](https://noaa-ocs-hydrodata-pds.s3.amazonaws.com/index.html)'
+      - '[STAC Catalog](https://noaa-ocs-hydrodata-pds.s3.amazonaws.com/catalog.json)'
+      - '[STAC Browser](https://radiantearth.github.io/stac-browser/#/external/noaa-ocs-hydrodata-pds.s3.amazonaws.com/catalog.json?.language=en)'
   - Description: NOAA Office of Coast Survey Hydrographic Survey Data New Object Notification
     ARN: arn:aws:sns:us-east-1:709902155096:NewOCSHYDROObject
     Region: us-east-1
diff --git a/datasets/noaa-wod.yaml b/datasets/noaa-wod.yaml
@@ -3,8 +3,8 @@ Description: >
   The World Ocean Database (WOD) is the largest uniformly formatted, quality-controlled, publicly available historical subsurface ocean profile database. From Captain Cook's second voyage in 1772 to today's automated Argo floats, global aggregation of ocean variable information including temperature, salinity, oxygen, nutrients, and others vs. depth allow for study and understanding of the changing physical, chemical, and to some extent biological state of the World's Oceans. Browse the bucket via the AWS S3 explorer: https://noaa-wod-pds.s3.amazonaws.com/index.html
 Documentation: https://www.nodc.noaa.gov/OC5/WOD/pr_wod.html
 Contact: |
-  For any questions regarding data delivery not associated with this platform or any general questions regarding the NOAA Big Data Program, email noaa.bdp@noaa.gov.
-  <br /> We also seek to identify case studies on how NOAA data is being used and will be featuring those stories in joint publications and in upcoming events. If you are interested in seeing your story highlighted, please share it with the NOAA BDP team here: noaa.bdp@noaa.gov
+  For any questions regarding data delivery not associated with this platform or any general questions regarding the NOAA Open Data Dissemination (NODD) Program, email the NODD Team at nodd@noaa.gov.
+  We also seek to identify case studies on how NOAA data is being used and will be featuring those stories in joint publications and in upcoming events. If you are interested in seeing your story highlighted, please share it with the NODD team by emailing nodd@noaa.gov
 ManagedBy: "[NOAA](http://www.noaa.gov/)"
 UpdateFrequency: Data is update on a quarterly basis
 Collabs:
@@ -34,3 +34,4 @@ DataAtWork:
     - Title: The World Ocean Database User's Manual
       URL: https://data.nodc.noaa.gov/woa/WOD/DOC/wodreadme.pdf
       AuthorName: Hernan E. Garcia, Tim P. Boyer, Ricardo A. Locarnini, Olga K. Baranova, Melissa M. Zweng
+  
diff --git a/datasets/oceanomics.yaml b/datasets/oceanomics.yaml
@@ -2,7 +2,7 @@ Name: OceanOmics
 Description: "Minderoo Foundation OceanOmics aims to establish environmental DNA (eDNA) as a tool to measure, understand, and protect oceans. OceanOmics mainly generates two types of data: eDNA sequencing data (metabarcoding, metagenomics), and genome assembly data (marine vertebrates)."
 Documentation: https://edna.minderoo.org
 Contact: oceanomics@minderoo.org
-ManagedBy: Minderoo Foundation OceanOmics (Dr Shannon Corrigan, Dr Philipp Bayer)
+ManagedBy: Minderoo Foundation OceanOmics, Dr Shannon Corrigan, Dr Philipp Bayer
 UpdateFrequency: Data will be continually updated as it is generated.
 Collabs:
   ASDI:
diff --git a/datasets/proteingym.yaml b/datasets/proteingym.yaml
@@ -3,7 +3,7 @@ Description: |
   ProteinGym is a benchmark suite for assessing the performance of protein fitness prediction and design models. It comprises a large curated collection of 200+ high-throughput experimental assays (~3M mutated sequences), as well as clinical annotations from experts about the pathogenicity of mutants in over 3k human genes.
 Documentation: https://github.com/OATML-Markslab/ProteinGym/blob/main/README.md
 Contact: pascal_notin@hms.harvard.edu
-ManagedBy: "Harvard Medical School; University of Oxford"
+ManagedBy: "Harvard Medical School, University of Oxford"
 UpdateFrequency: Quarterly
 Tags:
   - aws-pds
diff --git a/datasets/st-open-data.yaml b/datasets/st-open-data.yaml
@@ -0,0 +1,33 @@
+Name: SpaceEye-T VVHR EO Open Data
+Description: |
+  SpaceEye-T satellite collects the highest resolution optical imagery among the commercial satellites, 25 cm resolution. The Open Data features various satellite images around the world for end users to experience the power of VVHR optical data.
+Documentation: https://www.si-imaging.com/page/72?sca=SpaceEye-T
+Contact: https://www.si-imaging.com
+UpdateFrequency: The dataset is frequently updated. The frequent updates include the time-series data for regular monitoring, and the data for disaster management. SI Imaging wants to provide the user expierence on what is possible with VVHR optical satellite data. If you have a suggestion for a new location, feedback on the dataset, or any questions, contact us.
+Tags:
+  - aws-pds
+  - satellite imagery
+  - earth observation
+  - disaster response
+  - geospatial
+  - image processing
+License: Creative Commons Attribution-NonCommercial 4.0 International
+ManagedBy: "[SI Imaging Services](https://www.si-imaging.com/)"
+Resources:
+  - Description: SpaceEye-T Imagery Collection
+    ARN: arn:aws:s3:::st-vvhr-opendata
+    Region: us-west-2
+    Type: S3 Bucket
+    Explore:
+    - '[Browse Bucket](http://st-vvhr-opendata.s3-website.us-west-2.amazonaws.com/)'
+  - Description: Notifications for new SpaceEye-T VVHR EO Open data
+    ARN: arn:aws:sns:us-west-2:348881531141:st-vvhr-opendata-object_created
+    Region: us-west-2
+    Type: SNS Topic
+DataAtWork:
+  Publications:
+    - Title: "SpaceEye-T Data Manual"
+      URL: https://www.si-imaging.com/page/72?sca=SpaceEye-T
+      AuthorName: SI-Imaging Services
+ADXCategories: 
+  - Resources Data
diff --git a/datasets/ucsf-rmac.yaml b/datasets/ucsf-rmac.yaml
