Soil Spectroscopy and Deep Learning-based modeling for decision-making in agricultural contamination
The online webinar explored how global soil spectral databases and Deep Learning-based modeling approaches support decision-making during the remediation of radiocaesium contamination in agriculture.
In particular, it focused on two pivotal topics:
- the model-centric vs. data-centric, and
- the local versus global modeling approaches in soil spectroscopy.
Biography: Franck Albinet has been providing his expertise in Data Science to a wide range of United Nations agencies since 2005, constantly driven by the desire to put technology and data science at the service of the UN’s mandate, in particular to inform decision-making during humanitarian crises or nuclear emergency responses. He is currently conducting research in the field of Deep Learning with the Food and Agriculture Organization (FAO) and the International Atomic Energy Agency (IAEA) to optimize the remediation of agricultural land in the aftermath of a large-scale nuclear accident.