The operation mode determines the optimal settings for different parameters of agricultural vehicles. A classification of road mode and field mode is essential for adapting settings, e.g. the automatic adjustment of tire inflation during transport on road and operational field work. This study focuses on the development and application of algorithms for automatically detecting the operation mode of agricultural vehicles based on GNSS data. The approach is solely based on the parameters speed, COG and derived values such as acceleration, curve radius and angular speed. Known field boundaries and the current position of the vehicle have been neglected to increase the flexibility and applicability of the algorithm. For this purpose the GNSS data were collected with two GNSS receivers differing with respect to model and correction data source (EGNOS and RTK). Speed, time, heading and derived parameters were included in the development of a decision tree based model to classify the operating mode using the rpart package in RStudio. The prediction of operating mode was carried out with the predict package in RStudio. A confusion matrix was introduced to validate the performance of different models. The algorithms derived from the two training datasets (EGNOS and the RTK dataset) show convincing results in the detection of road and field mode. Both algorithms demonstrated an accuracy of more than 90%. The prediction performance was improved when training and validation data were derived from the same dataset (either EGNOS or RTK dataset). The comparison of two algorithms based on EGNOS and RTK data reveal the advantage of models based on RTK data. It is of great importance that the number of wrong decisions regarding the detection of the operating mode on the road are minimized since road safety plays an important role and the potential harm caused by a wrong decision is substantially higher than in the field. The method reveals a large potential for other applications where the operating mode is relevant.