Implementation of Artificial Intelligence in Agriculture to Optimize Irrigation

• Published in: Agricultural Machinery and Technologies Vol. 16; no. 4; pp. 45 - 53
• Main Authors: Fedosov, A. Yu, Menshikh, A. M.
• Format: Journal Article
• Language: English; Russian
• Published: Federal Scientific Agroengineering Centre VIM 13.12.2022
• Subjects: crop irrigation optimization; digitalization; machine learning; mobile application; precision irrigation; smart agriculture; web application
• ISSN: 2073-7599
• DOI: 10.22314/2073-7599-2022-16-4-45-53

The relevance of artificial intelligence in agriculture is substantiated for irrigation optimization. (Research purpose) To report on the progress made over the past few years in the application of artificial intelligence to optimize crop irrigation. (Materials and methods) The review focuses on the most salient facts and important scientific information on the application of artificial intelligence in crop production. The review is based on Various databases (Google Scholar, PubMed, Science Direct, SciFinder, Web of Science, RSCI) and online sources (Research Gate, Springer Nature Open Access, Wiley Online Library). It is shown how the integration of machine learning models can provide intelligent irrigation management. The review reports on the research trends and applicability of machine learning methods, as well as the deployment of developed machine learning models for sustainable irrigation management. (Results and discussion) Mobile and web platforms are shown to be able to facilitate intelligent irrigation management. Machine learning proves to be one of the central areas of artificial intelligence helping researchers to work more creatively and efficiently. The review notes the problems of introducing artificial intelligence in crop production and specifies the future research areas in the machine learning implementation and digital farming solutions. (Conclusions) The relevance of the intelligent system in irrigation and water management is proved for sustainable agriculture. It is revealed that, despite the extensive literature available, machine learning modeling for crop irrigation management is still in its infancy. The countries leading in this area are China, the United States and Australia.