Radiant MLHub

Tutorials

• Explore wind speed images from Amazon Sustainability Data Initiative (ASDI) hosted on S3 using SageMaker Studio Lab (SMSL) by Frank Rubino
  
  Amazon SageMaker Studio Lab
• How to access Radiant MLHub Data by Radiant Earth
  
• Radiant MLHub Tutorials with Jupyter Notebooks by Kevin Booth
  

Tools & Applications

• Challenge on Computer Vision for Crop Detection from Satellite Imagery by Radiant Earth
  
• Radiant MLHub Dataset Registry by Radiant Earth
  

Publications

• A Guide for Collecting and Sharing Ground Reference Data for Machine Learning Applications by Yonah Bromberg Gaber
  
• Creating a Machine Learning Commons for Global Development by Hamed Alemohammad
  
• Geo-Diverse Open Training Data as a Global Public Good by Hamed Alemohammad
  

RarePlanes

Tutorials

• Announcing YOLTv4: Improved Satellite Imagery Object Detection by Adam Van Etten
  
• Automatically compress and archive satellite imagery for Amazon S3 by Newel Hirst, Joseph Fahimi, and Justin Downes
  Amazon S3Amazon S3 GlacierAWS LambdaAmazon ECR
• Getting Started with YOLTv4 for Object Detection in Imagery: Getting Training Data by Sophia Parafina
  
• Notebook for training and testing YOLYv4 by Adam Van Etten
  

Tools & Applications

• RarePlanes Codebase by Thomas Hossler and Jacob Shermeyer
  

Publications

• RarePlanes: Synthetic Data Takes Flight by Jacob Shermeyer, Thomas Hossler, Adam Van Etten, Daniel Hogan, Ryan Lewis, Daeil Kim
  

High resolution, annual cropland and landcover maps for selected African countries

Tutorials

• Accessing and downloading data by Rahebe Abedi
  

Publications

• A super-ensemble approach to map land cover types with high resolution over data-sparse African savanna landscapes by Song et al. (2023)
  
• Final report-Phase 1: Creating open agricultural maps and ground truth data to better deliver farm extension services by Estes et al (2022)
  
• Final report-Phase 2: Creating next generation field boundary and crop type maps: Rigorous multi-scale groundtruth provides sustainable extension services for smallholders by Wussah et al (2022)
  
• High resolution, annual maps of field boundaries for smallholder-dominated croplands at national scales by Estes et al. (2022)
  

A region-wide, multi-year set of crop field boundary labels for Africa

Tutorials

• Instructions on data access and label-making demonstration notebook by Lyndon Estes
  
  

Publications

• A platform for crowdsourcing the creation of representative, accurate landcover maps by Estes et al. (2016)
  
• A region-wide, multi-year set of crop field boundary labels for Africa by Estes et al. (2024)
  
• A region-wide, multi-year set of crop field boundary labels for Africa by Wussah et al. (2023)
  
• Generalization enhancement strategies to enable cross-year cropland mapping with convolutional neural networks trained using historical samples by Khallaghi et al. (2025)
  
• High resolution, annual maps of field boundaries for smallholder-dominated croplands at national scales by Estes et al. (2022)
  
• Technical report on label develop and processing by Wussah et al. (2023)
  

PD12M

Tutorials

• Downloading Images by Spawning
  
• Working with the Metadata by Spawning
  

Tools & Applications

• Hugging Face Dataset by Spawning
  
• Source.Plus by Spawning
  

Publications

• Datasheet by Spawning
  
• PD12M: A Large-Scale Image Captioning Dataset by Jordan Meyer, Nick Padgett, Laura Exline, Cullen Miller
  

Sophos/ReversingLabs 20 Million malware detection dataset

Tutorials

• SOREL-20M quickstart by Richard Harang
  Amazon S3Amazon EC2

Tools & Applications

• SOREL-20M dataset interface code by Richard Harang and Ethan M Rudd
  

Publications

• SOREL-20M: A Large Scale Benchmark Dataset for Malicious PE Detection by Richard Harang and Ethan M Rudd
  

Consented Activities of People

Tools & Applications

• OpenFAD - Open Fine Grained Activity Detection Challenge by Visym Labs & NIST
  
• Visym Collector by Visym Labs & Systems & Technology Research
  

Emory Knee Radiograph (MRKR) dataset

Tutorials

• Example Notebook by Emory-HITI
  

Publications

• Emory Knee Radiograph Dataset by Brandon Price, Jason Adleberg, Kaesha Thomas, Zach Zaiman, Aawez Mansuri, Beatrice Brown-Mulry, Chima Okecheukwu, Judy Gichoya, Hari Trivedi.
  

Orcasound - bioacoustic data for marine conservation

Tools & Applications

• Github for our open source projects by Orcasound open source community
  

RSNA Abdominal Trauma Detection (RSNA-ABT)

Publications

• The RSNA Abdominal Traumatic Injury CT (RATIC) Dataset by Rudie, Jeffrey D.
  

RSNA Cervical Spine Fracture Detection (RSNA-CSF) Dataset

Publications

• The RSNA Cervical Spine Fracture CT Dataset by Ming, Hui Lin
  

RSNA Intracranial Hemorrhage Detection

Publications

• Construction of a Machine Learning Dataset through Collaboration: The RSNA 2019 Brain CT Hemorrhage Challenge by Rudie, Jeffrey D.
  

RSNA Pulmonary Embolism Detection

Publications

• The RSNA Pulmonary Embolism CT Dataset by Colak, Errol
  

YouTube 8 Million - Data Lakehouse Ready

Tutorials

• Data Lake as Code Deployment Guide by AWS Industry Blueprints Team
  Amazon AthenaAWS GlueAWS Lake Formation

Publications

• YouTube 8 Million by Google Research