Benjamin Stocker

Benjamin Stocker

Group leader, Prof.

Geocomputation and Earth Observation, Institute of Geography, University of Bern

Grüezi - Hi there - Bienvenidos

This is my research group’s website. Here, you can learn about who we are, and about our research. And you can explore our open access tools for the community, and our freely accessible learning materials.

As a group, we are a collection of climate, ecosystem, and data scientists with a special interest in interactions between global environmental change and terrestrial ecology and biogeochemistry.

Our work yields insights into climate change impacts on land ecosystems and provides data-informed predictions of how forests and grasslands respond to a climatic extreme events, rising CO2 and changes in nutrient cycles. We use Earth observation data and develop process-based models that are founded on eco-evolutionary optimality principles to explain plant traits and their adaptation and acclimation to the environment. In more data-driven approaches, we apply machine learning and data assimilation techniques using diverse ecological data (ecosystem flux measurements, forest inventories, remote sensing, and manipulation experimental data, etc.). In brief, we are building models, as simple as possible and as complex as necessary to learn the most. All open access, of course.

We are motivated to gain a better understanding of issues that are becoming increasingly pressing to society and policy and that are key to creating a sustainable future.

  • Climate-biosphere interactions
  • Forecasting drought impacts
  • Monitoring the carbon cycle from space
  • Developing next-generation vegetation models
  • Model-data integration and machine-learning

Our home:


Overview of some past and ongoing research.

Featured Publications

An effective machine learning approach for predicting ecosystem CO$_textrm2$ assimilation across space and time

textlessptextgreatertextlessstrong class="journal-contentHeaderColor"textgreaterAbstract.textless/strongtextgreater Accurate predictions of environmental controls on ecosystem photosynthesis are essential for understanding the impacts of climate change and extreme events on the carbon cycle and the provisioning of ecosystem services. Using time-series measurements of ecosystem fluxes paired with measurements of meteorological variables from a network of globally distributed sites and remotely sensed vegetation indices, we train a recurrent deep neural network (Long-Short-Term Memory, LSTM), a simple deep neural network (DNN), and a mechanistic, theory-based photosynthesis model with the aim to predict ecosystem gross primary production (GPP). We test these models’ ability to spatially and temporally generalise across a wide range of environmental conditions. Both neural network models outperform the theory-based model considering leave-site-out cross-validation (LSOCV). The LSTM model performs best and achieves a mean textlessemtextgreaterRtextless/emtextgreater$^textrm2$ of 0.78 across sites in the LSOCV and an average textlessemtextgreaterRtextless/emtextgreater$^textrm2$ of 0.82 across relatively moist temperate and boreal sites. This suggests that recurrent deep neural networks provide a basis for robust data-driven ecosystem photosynthesis modelling in respective biomes. However, limits to global model upscaling are identified using cross-validation by vegetation types and by continents. In particular, our model performance is weakest at relatively arid sites where unknown vegetation exposure to water limitation limits model reliability.textless/ptextgreater

Recent Posts

Make geospatial data with a time dimension into a tidy format
The problem Geospatial data often has a time dimension. Such temporal geospatial data often comes in the form of multiple files that contain the data of a single time step - in the form of a geospatial map - or in the form of files that each contain the data of a subset of the time steps.
Understanding the growth-biomass links in mature forests
Forest demographic processes are being altered by global change. Elevated atmospheric carbon dioxide has been reported to enhance photosynthesis and tree growth rates. Different studies have reported increased tree growth globally over the last decades (Brienen et al.
Leaf Temperature’s Role in Ecosystem Modeling
An attempt to connect eco-evolutionary theory to a leaf’s energy balance to unravel the footprint of leaf temperature on ecosystem dynamics.