Machine Learning

The world of Climate and Earth Observation is rapidly changing due to advances in sensor and digital technologies. Nowadays, satellites collect an unprecedented volume of data on the state of the Earth and its changes, which has led to fundamentally new ways to distribute and analyze data about our planet. Recent decades have witnessed remarkable improvements in information and communication technologies, including the Internet, cloud computing, big data analytics and storage, which have fundamentally led to new ways to collect, distribute and analyze data about our planet. This digital revolution is accompanied by rapid improvements in sensor technologies that provide an unprecedented volume of data on the state of the Earth and its changes. 
The need for practical empirical approaches for regression and classification of non-linear systems has led to Machine Learning (ML). As a broad subfield of artificial intelligence, ML is concerned with algorithms and techniques that allow computers to “learn” by example. The primary focus of ML is to extract information from data automatically by computational and statistical methods.
The CLIMERS research group focuses on developing Machine Learning models to understand the Earth system better and study the land surface processes. Examples of research interests pursued in CLIMERS are:

  • Prediction of vegetation state anomalies, agricultural yields from Earth observations
  • Enhancing Earth observation data (e.g., gap filling, downscaling, noise reduction)
  • Detangling multiple climate drivers (e.g., temperature, precipitation) of vegetation growth
  • Developing observation operators for Earth observation data assimilation
  • Data-driven modeling for fire activity:
  • Modeling the human influence on wildfires
  • Developing an integrated Fire Danger Assessment System