MACLEAN 2020
MAChine Learning for EArth ObservatioN Workshop 2020

Table of Contents

Summary: There were 17 papers submitted for peer-review to this workshop. Out of these, 9 papers were accepted for this volume, 7 as regular papers and 2 as short papers.

Session 1: Semi-Supervised and (Inter)active Learning

• Interactive Learning for Semantic Segmentation in Earth Observation
  Gaston Lenczner, Adrien Chan-Hon-Tong, Nicola Luminari, Bertrand Le Saux, Guy Le Besnerais
• Deep Active Learning in Remote Sensing for data efficient Change Detection
  Vit Ruzicka, Stefano D'Aronco, Jan Dirk Wegner, Konrad Schindler
• On Auxiliary Losses for Semi-Supervised Semantic Segmentation
  Javiera Castillo-Navarro, Bertrand Le Saux, Alexandre Boulch, Sébastien Lefèvre

Session 2: Physical event characterization

• Comparing Machine Learning Methods for Predicting Seismic P-wave Velocity on Global Scale
  Yousef Razeghi, Wilhelm Hasselbring, Christian Berndt, Ines Dumke
• Multi-modal deep learning models for ocean wind speed estimation
  Clémentin Boittiaux, Paul Nguyen Hong Duc, Nicolas Longépé, Sara Pensieri, Roberto Bozzano, Dorian Cazau
• Joint Learning for Cyclone Track Nowcasting
  Abhijit Mukherjee, Pabitra Mitra

Session 3: Multi-spectral and Colorization

• Dual Color-Image Discriminators Adversarial Networks for Generating Artificial-SAR Colorized Images from SENTINEL-1 Images
  Youssef Mourchid, Marc Donias, Yannick Berthoumieu
• Tri-Band Assessment of Multi-Spectral Satellite Data for Flood Detection
  Pallavi Jain, Bianca Schoen-Phelan, Robert Ross
• Clustering Sargassum Mats from Earth Observation Data
  Estèle Glize, Marie-José Huguet, Gilles Tredan, Marc Lucas, Marion Sutton