How do ecosystems respond to changing weather patterns, rising temperatures and increasing carbon dioxide concentrations? Is the effect of precipitation more important than that of temperature? Or are ecosystem dynamics more strongly affected by nutrient availability? What is the role of extreme events in shaping biogeochemical cycles? To find out the answers we need to understand the interactions among three complex systems: climate, vegetation, and soil. Thus, we combine experiments and in-situ long-term observation with Earth Observations gathered by aircraft and satellites across a range of spatial scales, and embrace data-driven machine learning and theory-driven mechanistic modelling. With our research, we try to understand how the terrestrial biosphere reacts to and exerts feedbacks on ongoing environmental change and variation in atmospheric conditions.
Latest publications
Poehls, J., Alonso, L., Koirala, S., Carvalhais, N., & Reichstein, M. (2025). Downscaling soil moisture to sub-km resolutions with simple machine learning ensembles. Journal of Hydrology,652: 132624. doi:10.1016/j.jhydrol.2024.132624. // Figure 4: Prediction regime for the Dense, Prob, and WDL ensembles. Each ensemble member (cube) is trained on samples weighted against imbalances in a static variable. These predictions are then averaged to provide an ensemble prediction.
Poehls, J., Alonso, L., Koirala, S., Carvalhais, N., & Reichstein, M. (2025). Downscaling soil moisture to sub-km resolutions with simple machine learning ensembles. Journal of Hydrology,652: 132624. doi:10.1016/j.jhydrol.2024.132624. // Figure 4: Prediction regime for the Dense, Prob, and WDL ensembles. Each ensemble member (cube) is trained on samples weighted against imbalances in a static variable. These predictions are then averaged to provide an ensemble prediction.
Lee, H. T.; Jung, M.; Carvalhais, N.; Reichstein, M.; Forkel, M.; Bloom, A. A.; Pacheco-Labrador, J.; Koirala, S.: Spatial attribution of temporal variability in global land-atmosphere CO2 exchange using a model-data integration framework. ESS Open Archive (2025)
Qin, X.; Tian, H.; Canadell, J. G.; Shi, Y.; Pan, S.; Bastos, A.; Ciais, P.; Crippa, M.; Pan, N.; Patra, P. K.et al.; Poulter, B.; Saunois, M.; Sitch, S.: Greenhouse gas budgets of Central and West Asia (2000– 2020): A significant net source to the atmosphere. Global Biogeochemical Cycles 39 (3), e2024GB008370 (2025)
Chang, Y.; Winkler, A.; Noori, A.; Knyazikhin, Y.; Myneni, R.: Precipitation leads the long-term vegetation increase in the conterminous United States drylands. Environmental Research Letters (accepted)
Benson, V.; Bastos, A.; Reimers, C.; Winkler, A.; Yang, F.; Reichstein, M.: Atmospheric transport modeling of CO2 with neural networks. Journal of Advances in Modeling Earth Systems 17 (2), e2024MS004655 (2025)
Cattry, M.; Zhao, W.; Nathaniel, J.; Qiu, J.; Zhang, Y.; Gentine, P.: EcoPro-LSTMv0: A memory-based machine learning approach to predicting ecosystem dynamics across time scales in mediterranean environments. EGUsphere (2025)
