Authors

Forecasting of crop yields using the quasi-linear equation of n-factor autoregression

Both in Russia and in other countries, scientists note the need development of artificial intelligence methods for precision farming. However, the software nowadays used for this purpose is only developing and sometimes not released for sale, and the methods stated in individual articles use standard approaches, which leads to significant errors. Another reason is a non-trivial way of obtaining initial data, in particular, as a result of the analysis of satellite images, which is a rather laborious work and is possible only if there is a database of the objects under study with their specified geographical coordinates. The article discusses the development of a system for predicting the yield of agricultural land using satellite images. The system includes both classical methods (for example, the parabolic regression discussed in the article) and approaches developed by the authors to identify the parameters of the quasi-linear equation of n-factor autoregression. Despite the presence on the market of a fairly large number of software products for precision farming, many of the existing software and approaches are not intended to provide data for further analysis by specialists who are not employees of the developer company. As for our system, the collection and subsequent analysis of aerial photography data is carried out, which consists in building a model of the dynamics of the vegetation index, which is subsequently used to predict the yield of the field in the following periods. The proposed system is extensible, i. e., it allows connecting additional modules for analysis and inclusion in the analysis of additional factors that affect the indicator under study. The article describes the data presentation method, the process of calculating vegetation indices for a certain date, and also provides mathematical approaches to modeling the vegetation process using high-quality deterministic mathematical models and predicting the next season’s crop yield and production costs. Read more...