Spatially continuous data in biogeosciences are urgently requested to assess patterns and trends in ecosystem dynamics. Remote sensing is a powerful tool to provide such data and methods for its application to estimate ecosystem variables evolved rapidly during the recent years. New sensors deliver large hyperspectral, LiDAR and Radar datasets requesting new approaches to dealing with Big Data. In this context, machine learning algorithms are frequently used to link large remote sensing data to ecosystem variables. In this session, we welcome contributions which present novel approaches of mapping, monitoring and modelling ecosystem characteristics combining machine learning with remotely sensed data with a special focus on products to estimate ecosystem processes, functions and services.

Convener: Lukas Lehnert | Co-conveners: Hanna Meyer, Elias Symeonakis
| Attendance Wed, 10 Apr, 10:45–12:30
Hall A

Attendance time: Wednesday, 10 April 2019, 10:45–12:30 | Hall A

A.351 |
Thilo Wellmann, Sebastian Scheuer, Angela Lausch, and Dagmar Haase
A.352 |
Bora Lee, Eunsook Kim, Keunchang Jang, Nang Hyun Cho, Wookyung Song, Goeun Park, Chanwoo Park, and Jong-Hwan Lim
A.353 |
Zhipeng Tang, Janne Heiskanen, Hari Adhikari, and Petri Pellikka
A.354 |
Reyhan Akyol, Danika van Proosdij, Greg Baker, and Jennifer Graham
A.355 |
Ana-Ioana Breaban, Ersilia Oniga, and Florian Statescu
A.356 |
Aleksandra Radecka, Katarzyna Osińska-Skotak, Wojciech Ostrowski, Jakub Charyton, Krzysztof Bakuła, Łukasz Jełowicki, Dorota Michalska-Hejduk, Adam Kania, Jan Niedzielko, Łukasz Sławik, and Jaromir Borzuchowski
A.357 |
Marvin Ludwig, Theunis Morgenthal, Florian Detsch, Thomas Higginbottom, Maite Lezama Valdes, Thomas Nauß, and Hanna Meyer
A.358 |
Evyatar Erell, Bin Zhou, Ian Hough, and Itai Kloog
A.360 |
A deep-learning approach for multi-temporal savannah woody vegetation density assessment with Earth Observation data
Elias Symeonakis, Antonis Korkofigkas, Giorgos Vamvoukakis, and Giorgos Stamou