As technology advances, the possibility of using satellite data and observations to aid inagricultural activities comes closer to reality. Swedish farmers can apply for subsidies for their land in which crop management and animal grazing occurs, and every year thousands of manual follow-up checks are conducted by Svenska Jordbruksverket (Swedish Board of Agriculture) to validate the farmers’ claims to financial aid. RISE (Research Institutes of Sweden) is currently researching a replacement for the manual follow-up checks using an automated process with optical satellite observations from primarily the ESA-made satellite constellation Sentinel-2, and secondarily the radar observations of the Sentinel-1 constellation.

The optical observations from Sentinel-2 are greatly hindered by the presence of weather on the Earth’s atmosphere and lack of sunlight, but the radar-based observations of Sentinel-1 are able to penetrate any weather conditions entirely independently from sunlight. By using the optical index NDVI (Normalized Difference Vegetation Index) which is strongly correlated with plant chlorophyll, and the radar index RVI (Radar Vegetation Index), classifications on animal grazing activities are sought to be made.

Dynamic Time Warping and hierarchical clustering are used to analyse and attempt to make classifications on the two selected datasets of sizes 959 and 20 fields. Five experiments were conducted to analyse the observational data from mainly Sentinel-2, but also Sentinel-1. The results were inconclusive and were unable to perform successful classifications primarily on the 959 fields large dataset. An indication is given in one of the experiments, performed on the smaller dataset of 20 fields, that classification is indeed possible by using mean valued NDVI time series. However, it is difficult to draw conclusions due to the small size of the 20 fields large dataset. To validate any possible methods classification a larger dataset must be used.