Doctoral researcher with the Global Diagnostic Modelling Research Group
Still today, many machine-learning approaches fail in encoding temporal memory effects that typically characterize dynamical natural systems. Hence, ecosystem and Earth System dynamics are often hard to model and predict. Yet, today modern deep learning approaches in the time domain (e.g., Recurrent Neural Networks) are theoretically prepared to address such issues. Specifically, the aim of this PhD project is therefore to pioneer and to scrutinize the potential of such methods and their combinations to accurately describe, understand, and predict Earth System variables considering memory effects.
Kraft, B., Jung, M., Körner, M., and Reichstein, (2020, accepted). M. Hybrid modeling: fusion of a deep learning approach and a physics-based model for global hydrological modeling. ISPRS archives.
Kraft, B., Jung, M., Körner, M., Requena Mesa, C., Cortés, J., and Reichstein, M., (2019). Identifying Dynamic Memory Effects on Vegetation State Using Recurrent Neural Networks. Frontiers in Big Data, 2, p.31.
Reichstein, M., Besnard, S., Carvalhais, N., Gans, F., Jung, M., Kraft, B., and Mahecha, M. (2018). Modelling Landsurface Time-Series with Recurrent Neural Nets. In IGARSS 2018-2018 IEEE International Geoscience and Remote Sensing Symposium (pp. 7640-7643). IEEE.
Requena-Mesa, C., Reichstein, M., Mahecha, M., Kraft, B., and Denzler, J. (2018). Predicting landscapes as seen from space from environmental conditions. In IGARSS 2018-2018 IEEE International Geoscience and Remote Sensing Symposium (pp. 1768-1771). IEEE.