In this month’s ML4EO market news, explore new public data available on Radiant MLHub, Maxar, and Mapbox, ML applications that detect transformers in agricultural fields, tutorials, and, more highlights from the EO community’s continued contributions to the pandemic response, including NASA’s Earth Data’s COVID-19 Dashboard.
Geo-COVID19 Updates
- Satellites provide crucial data on crops during COVID-19
- NASA’s Earth Data releases COVID-19 Dashboard. It can be used to investigate how social distancing measures and regional shelter-in-place guidelines have affected Earth’s air, land, and water.
- Mapping Canada’s mask-mandatory businesses with Google Maps
- Tracking cases of COVID-19 to predict peak outbreaks in India
- Ghana Health Service receives support in software from Sambus Geospatial on COVID-19
- EU Space Data for Sustainable Farming platform and COVID-19
- COVID-19 impact is seen by satellite data on ESA’s RACE platform
- WeRobotics announce the Flying Labs that have won microgrants to tackle COVID-19
- COVID-19 lessons applied to forestry, climate change
Methodologies & Applications
- Development Seed updated ML Enabler, including an on-demand machine learning predictions for mapping tools
- An urban water extraction method combining deep learning and Google Earth Engine
- Learning super-resolution for Sentinel-2 images with real ground truth data from a reference satellite
- Machine learning methods for landslide susceptibility studies: A comparative overview of algorithm performance
- Detection of unregistered electric distribution transformers in agricultural fields with the aid of Sentinel-1 SAR images by machine learning approaches
- CosmiQWorks introduced SpaceNet Change and Object Tracking (SCOT) metric
- Sentinel Hub now supports data fusion, allowing you to combine satellite datasets to unlock new possibilities
- Mapping crop types using Sentinel-2 satellite data
Data Access & Validation
- “Western USA Live Fuel Moisture” training data is now available on Radiant MLHub!
- The SpaceNet 7 Multi-Temporal Urban Development Challenge: Dataset Release
- High-resolution imagery (15 cm) in France is live on Mapbox
- Open data response to the wildfires in California and Colorado by Maxar
- GroundWork Update: Announcing Validation, Magic Wand & More
Standards Research & Innovation
- OGC seeks public comment on new OGC API for Environmental Data Retrieval
- Join the ‘Cloud Native Geospatial’ Outreach Day and Sprint on Sept 8
- You can now easily browse through all (CORS-enabled) STAC catalogs and APIs submitted to STAC Index
- Released sat-search 0.3.0, a Python library and CLI, for use with any STAC compliant endpoint
- STAC Node Validator 0.4 has been released and can now validate even more STAC catalogs, API and extensions
Tutorials, Webinars (recorded) & Resources
- Sentinel Hub Custom Script Contest. Submit your script by October 31, 2020
- TUTORIAL – Towards large-scale tree mortality studies in cities with deep learning and street view images
- TUTORIAL – Clustering geospatial data: Plot machine learning & deep learning clustering with interactive maps
- TUTORIAL – Solaris Model Deployment: From Start to Finish. Demystifying geospatial deep learning with In-Q-Tel CosmiQ Works’ Solaris
- EU’s Global Wildfire Information System aims to support operational wildfire management from national to global scales.
- TUTORIAL – Test out the SpaceNet 7 Multi-Temporal Urban Development Challenge Algorithmic Baseline
- TUTORIAL – Visualizing geospatial data with pydeck and Earth Engine
Data Challenges & Conferences
- Tackling Climate Change with Machine Learning Workshop at NeurIPS conference, Dec 11 or 12
- AI for Earth Sciences Workshop at NeurIPS conference, Dec 11 or 12
- IGARSS 2020 Technical Program is now available online
- AI for Social Good – AAAI Fall Symposium 2020, Nov 13-14
What are we missing? Contact Louisa@radiant.earth