The Flemish Institute for Technological Research (Vlaamse Instelling voor Technologisch Onderzoek or VITO), is an independent research organisation that provides scientific advice and technological innovations that facilitate the transition to a sustainable society, and this in the areas of energy, chemistry, materials, health and land use.
In a recent blog post, VITO Remote Sensing announced that it has produced an annual interactive crop map for Belgium for the third consecutive year. The crop map shows the main crop type on each individual field cultivated in the 2020 growing season and it is publicly available via an interactive online viewer.
Just as was done for the 2018 and 2019 maps, VITO Remote Sensing deployed its automatic field boundary detection tool based on Sentinel-2 imagery and a convolutional neural network to precisely delineate the fields, followed by a recurrent neural network approach to recognize crop types based on joint time series of Sentinel-2 optical imagery and Sentinel-1 radar backscatter.
Kristof Van Tricht, VITO’s remote sensing expert in agricultural monitoring, explains more about this technology in his blog article ‘A Sentinel shake for early crop mapping’.
Says Kristof: “Multi-year detailed crop mapping experiments in a country as small as Belgium still yields a wealth of experience for global approaches such as is the case with the World Cereal project.”
Thanks to an abundance of training data gathered over the years (such as the Land Parcel Identification System), in combination with state of the art deep learning technologies, VITO specialists are able to reach accurate data levels of >90%. In addition, VITO’s classification algorithms get smarter every year as they get to see more and more variability in growing seasons and agricultural practices, making them ever more robust.
By producing a consistent crop map each year, VITO specialists say they are able to get better insights into the dynamics of the agricultural landscape, including crop rotation cycles and parcel boundary changes. And at the same time, VITO’s crop type mapping approaches can be fine tuned and applied in regions around the world.