Strategic Directions for Smart Agriculture Based on Deep Learning for Future Risk Management of Food Security

The paper aims to develop scientific and methodological support for the transition to the advanced development of the agricultural economy through the improvement of the risk-based approach to food security. As a result, the authors identified and systematized the risks of the future agricultural economy: disaster risks, water supply risks, land risks, biodiversity risks, import dependency risks, and food shortage risks. The authors also reviewed and assessed these risks in countries with different levels of food security (using Ireland, Russia, and Burundi as examples) in 2021. The paper proposes strategic directions for developing smart agriculture based on deep learning for risk management. The contribution of the research to the literature lies in the identification of a strategic food security perspective and opportunities to overcome the limitations of smart agriculture in food security risk management. As substantiated in the research, these opportunities and prospects are related to expanding the spectrum of the use of deep learning in agriculture, which proves the research hypothesis. The theoretical significance of the research consists in the development of scientific and methodological support for the transition to the advanced development of the agricultural economy. For this purpose, a risk-based approach to food security has been improved. © The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.