The research is about the methods that can be used to estimate the moisture content most effectively, and which are the optimal settings that can be used to achieve the most accurate results.
Using artificial intelligence (AI), researchers from the Faculty of Science and Technology of the University of Debrecen (DE) are developing a methodology for predicting soil moisture content. The new method, carried out using multispectral and thermal cameras mounted on unmanned aerial vehicles, can make yield optimization more efficient and is planned to be available to farmers.
According to the university’s press release, the research was based on the GINOP project related to precision agriculture, in the framework of which the natural geography and geoinformatics department of the faculty worked with industry players in 2019 on how to effectively determine the moisture content of the soil in fields.
As part of the project, tests were carried out on a corn field and its fallow area on the border of Hajdúböszörmény, by installing a thermal camera on the department’s industrial category drones and creating so-called thermal orthophoto mosaics, a kind of heat map. Using different data processing combinations, they investigated how the moisture content of the soil can be determined, for which it was necessary to know the actual extent of the distribution of soil moisture at the time of the investigation – assistant professor László Bertalan reported on the details of the research.
The specialists involved in the research collected soil samples, in which the moisture content of the soil at the given points was determined under laboratory conditions. At the same time, drone data collection was also carried out, on the one hand with a thermal camera, and on the other hand with so-called multispectral mapping, when differences in the soil surface were detected based on reflected solar radiation in different ranges of the electromagnetic spectrum, and then the values measured by different methods were compared.
The study is about the methods we can use to estimate the moisture content most effectively. If, for example, the soil surface is 35 degrees on the drone heat map, but next to it the moisture content is 20 percent in the case of the given soil sample, then with the help of artificial intelligence, including machine learning, we can determine a statistical correlation from the combinations of the data if there are enough soil samples – explained the specialist, noting , to present the optimal settings in the publication, with which the most accurate results can be achieved.