Аналіз методів і особливостей цифровізації даних польових досліджень як бази для управління рослинництвом

Abstract

The purpose of the study. The topic of crop management, which is largely determined by modern digitalization processes, is relevant and is in the center of attention of both specialists and experts in the field of agriculture and in the field of computer technology, because the production of products of the agricultural sector plays a vital role in the world economy. Considering that traditional field data processing methods are unable to meet the ever-growing needs of agricultural producers at the new stage of agricultural development and are a serious obstacle to obtaining the necessary information, the purpose of the article is to conduct a critical review and analysis of publications on the digitization of field research databases in order to develop and adopt effective management decisions in crop production. Research methods. Research was conducted using generally accepted scientific methods: abstract-logical; analysis and synthesis; induction and deduction; expert evaluations. Research results. The conducted analysis made it possible to determine that the level of development of agricultural enterprises currently largely depends on modern digital technologies, the implementation of which involves a change in the general paradigm of production process management and allows commodity producers to act accordingly to increase production volumes. It has been proven that along with updating the material and technical component, the priority of production is the intellectualization of production and management activities based on digitization. Conclusion. In order to benefit from the ever-increasing amount of data that comes from numerous sources of digital transformation, despite the fact that the vast majority of farmers and agricultural producers are not experts in this field and are unable to fully understand the basic laws of the algorithms being created, the scientific and methodological approach to increase the effectiveness of machine learning for automatic recognition of agricultural crops, detection of diseases and weeds, forecasting of yield and quality of the crop, management of water resources and soil can be useful for agricultural enterprises of many countries of the world. Key words: machine learning, precision farming, productivity, soil conditions, water resources.