In this edition we are introducing a major new feature, Batch Processing. We are also presenting Land Cover Monitoring System, a country-scale machine learning use-case built on top of Sentinel Hub services. But before going into that, good news for all of you who wanted to submit your custom script to our Contest but partied over the New Year - we have extended the deadline until the end of January, so you have three weeks left to submit your awesome scripts.
Last but not least, we wish all of you lots of successes in the new year.
We realized that the deadline immediately after the holiday season does not align best with people’s plans, so we decided to extend it until January 31st. Hand in up to three different scripts which run in Sentinel Hub EO Browser and win attractive prizes.
A new service for all of our users, who are running (or want to run) their processes on a large scale - country, continent, world. You can now do this faster, more efficiently and cheaper. In case you would like to give it a try, let us know.
Check the blog post for more details. Inside, as a New Year’s gift, you will also find a cloudless 120-meter resolution mosaic of the beautiful continent of Australia.
Sentinel Hub BYOC Tool Available
Bringing your own data to Sentinel Hub is now easier than ever!
At the end of the year we have introduced the Sentinel Hub BYOC Tool, a utility tool, available as a Docker image and Java jar, which can be used to prepare your data for use in Sentinel Hub. It converts your TIFF and JP2 files to Cloud Optimized GeoTIFFs, uploads GeoTIFFs to AWS S3 bucket and registers them in Sentinel Hub BYOC service. When complete, your data should be visible in Sentinel Hub. The same steps can be done manually and are detailed in our documentation, should you require more control over the process.
Following our blog post trilogy about land cover classification with eo-learn (part 1, part 2 and part 3), we are introducing the next level in land observation - a Land Cover Monitoring System. The system connects our latest research about land cover classification, crop type classification and change detection with data processing tools from eo-learn. This is joined with the BYOC functionality of Sentinel Hub services and with Geopedia. Finally, there is also a web application for land monitoring. Read our blog post to find out more.
Updated MODIS Data Source with Extended History
MODIS MCD43A4, being a 16-days composite, is quite a “friendly” dataset for time-lapses as there are not many clouds. You can therefore build 20-year “daily” time-lapses of your favorite places.
More MODIS products will be available in the future.
Euro Data Cube
With our partners we are fully immersed in developing new Euro Data Cube features and services. They were successfully utilized for the analysis of Land Parcel Identification System data and to amend and customize the Land Cover Classification workflow. This work was presented at the 25th MARS conference in November 2019.
Our Euro Data Cube Marketplace is now alive. It also showcases some examples on how to utilize our services. Register and try out deploying applications or running a Jupyter Notebook in our Jupyter Hub yourself. Stayed tuned, there is more to come in the next months.
To meet us in person, send us an email to email@example.com and schedule a meeting with us at the following events: