Establishing future land-use management strategies is essential for mitigating climate change. To mitigate climate change, it is important to lower concentrations of atmospheric carbon. Lowering atmospheric carbon concentrations can be realised by enhancing the carbon that is stored in the soil. It is understood that the total carbon stock in the soil is 2 to 3 times bigger than the atmospheric carbon stock. Furthermore, enhancing soil carbon stocks is of immense importance in climate adaption to extreme meteorological weather events like periods of droughts or flooding.
Enhancing soil carbon stocks is of immense importance and this can be realised by integrating specific interventions in land-use management strategies called nature-based solutions. However, this decisions for the landscape are often made without data and without an ex-ante evaluation of interventions like nature-based solutions. In addition, there are currently datasets available, but these datasets have grown to sizes in which machine learning is required for analysis.
This research is filling up that knowledge gap by offering a rapid methodology in which soil carbon and land-use datasets can be analysed and used by machine learning. This research comes with an integrated model which is key for future land-use management strategies in which nature-based solutions and the brand-new climate scenarios from the Royal Dutch Meteorological Institute (KNMI) are implemented. The results of this research are essential for a societal dialogue between decision makers, society, and land-use planners.
The main objective of the research is setting up an integrated modelling approach for future land-use management strategies which can effectively be used by stakeholders for climate adapted land-use management strategies.
The main research question is: How can soil carbon and land-use datasets be combined using an integrative modelling approach to predict future land-use planning for a productive societal dialogue while incorporating climate adaptation measures.