As an earth system scientist and ecologist, Koen models ecosystem processes, such as vegetation growth or drought/disturbance resistance, using various (retrospective) proxy measurements in a model data fusion approach. Throughout his career his work has always been interdisciplinary, borrowing heavily from fields outside of ecology, such as image vision processing (computer science), remote sensing & engineering to assist in either field measurements &/or model driven analysis.

Most of Koen’s work is aimed at predicting rhythmical changes in vegetation growth, i.e. vegetation phenology. He has been putting automated cameras on weather towers and other elevated platforms to study the the seasonal timing of changes in plants, shrubs, & trees – called 'phenology'. Because this timing of when plants leaf, flower, & fruit is very sensitive to changes in weather, plant phenology alerts us to changing climate patterns. Koen contributed a lot to a network of about 300 cameras ('PhenoCams') that takes pictures of vegetated landscapes every half hour, every day, all year round - that’s a lot of pictures! With the data from these images he can figure the relationships between plant phenology & local weather & then predict the effects of future climate using models.