This paper provides a framework description for movement data analysis of agricultural telematics data. The framework implements interfaces for interacting with data providers and integrates performant spatial databases for passing storage intense analysis methods on complex datasets. Preprocessing steps include methods to efficiently handle raw data to filter erroneous records and detect noisy outliers. While previously mentioned steps are described briefly, the focus is on an approach to automatically extract geographic features such as field boundaries from the filtered data. This is done using the supervised k-Nearest Neighbors classification method to determine the specific working-mode of the machine and differentiate between field work and road. To find and construct meaningful metrics leading to the required objective, a so-called Space-Time-Cube was utilized which depicts trajectories from agricultural machines in 3dimen-sional space.