Level-2 News
Launches secured for five Sentinel satellites [link]
A recently signed contract between ESA and Arianespace ensures the launches of 5 Copernicus Sentinels: Sentinel-1D, Sentinel-2C, Sentinel-3C, and the Copernicus Anthropogenic Carbon Dioxide-A and -B satellites.
Successful launch of The Meteosat Third Generation Imager (MTG-I1) satellite [link]
On 13 December, ESA’s and Eumetsat’s MTG-I1 lifted off Europe’s Spaceport in French Guiana. It is the first of a new generation of satellites, set to revolutionize storm prediction, enhance weather forecasts, extend climate records, and provide a wide range of essential observations. [link]
Blue Marble Now 50 Years On [YouTube]
“To celebrate the 50th Anniversary of the Apollo 17 photograph the ‘Blue Marble’, Living Earth Orchestra presents a reflection on what our space-view means for understanding the changes on the Earth that have been taking place in the last 50 years.”
Developer’s Orbit
SpaceNet 8: A Closer Look at the Winning Approaches [link]
Follow this medium story to learn more about the winning entries in the SpaceNet 8 Challenge; “Flood Detection Challenge Using Multiclass Segmentation”.
This competition challenged participants to develop a multiclass feature extraction and characterization solution for flood detection, leveraging data and algorithms from previous challenges as well as a new dataset and baseline.
GitHub repo containing a baseline model: https://github.com/SpaceNetChallenge/SpaceNet8
Artificial Intelligence for Geospatial Analysis with Pytorch’s TorchGeo
Check out this 3-part series, written by Dr. Maurício Cordeiro, on how to use PyTorch and TorchGeo to train deep learning model for a segmentation task — surface water mapping!
The series covers data visualization and normalization, extending the input data by adding spectral indices, training a DeepLabV3 model and evaluating its performance.
Part 1 [link]
Part 2 [link]
Part 3 [link]
Related: Earlier this month, the author of this series defended his PhD titled:
“Use of Data Science Tools for Assessing Inland Water Surface and Quality Through High-Resolution Sentinel-2 Remote Sensing Images”.
You can find the video of his presentation here.
As part of his work, he published the paper “Automatic water detection from multidimensional hierarchical clustering for Sentinel-2 images and a comparison with Level 2A processors” [link].
You can find the implementation of that method at his Github repo.
Global shoreline mapping tool from satellite imagery [Github]
“CoastSat is an open-source software toolkit written in Python that enables users to obtain time-series of shoreline position at any coastline worldwide from 30+ years (and growing) of publicly available satellite imagery.”
Check the example Jupyter notebook for how to use CoastSat! [link]
Interesting read
Worst Drought on Record Parches Horn of Africa [link]
People in the Horn of Africa face a food security crisis due to severe drought, as several factors have contributed to the unprecedented number of four consecutive dry seasons in the region. The article describes how teams at the Climate Hazards Center (CHC) at the University of California, FEWS NET and NASA’ s FLDAS use different datasets to provide forecasts of precipitation and model water supply deficits related to agricultural drought and food insecurity.
Learning
SAR Handbook: Comprehensive Methodologies for Forest Monitoring and Biomass Estimation [link]
“The SAR Handbook: Comprehensive Methodologies for Forest Monitoring and Biomass Estimation is the culmination of a two-year collaboration between NASA SERVIR and SilvaCarbon. Five trainings, led by six SAR subject matter experts, were held at hubs throughout the SERVIR network. The topics of these trainings included SAR basics, SAR for forest change detection, forest height estimation, biomass estimation, mangrove monitoring, and sampling design. Each of these training topics are covered in a SAR Handbook chapter, which includes the theoretical basics and applied exercises.”