Siberian Federal University

Issue

Journal of Siberian Federal University. Humanities & Social Sciences. 2026 19 (6)

Authors

Kozlova, Svetlana A.; Ferova, Irina S.

Contact information

Kozlova, Svetlana A.: Siberian Federal University (Krasnoyarsk, Russian Federation); ; ORCID: 0000-0003-0858-201X; Ferova, Irina S. : Siberian Federal University (Krasnoyarsk, Russian Federation); ORCID: 0000-0002-3359-7822

Keywords

food security; digitalization; monitoring; dynamic models; regional development; machine learning; scenario forecasting

Abstract

The aim of this study is to identify elements of international methodological approaches to food security assessment and forecasting based on digital technologies that can be used to develop a comprehensive dynamic model at the regional level. A comparative analysis of two methodological paradigms was conducted: a quantitative approach based on machine learning ensemble models and hybrid neural network architecture, and a qualitative-quantitative approach based on fuzzy structural modeling of Agriculture 4.0 drivers. The findings show that both approaches reach similar conclusions about the key role of automation as a basic condition for digital transformation in the agricultural sector and the positive impact of artificial intelligence on food security. Through the synthesis of both paradigms, three model elements were identified: a current state assessment module, a scenario forecasting module, and an uncertainty accounting module. The necessary adaptations for applying this experience to Russian conditions were determined, using an industrial-type region with spatial differentiation as an example

Pages

1202–1210

EDN

HVLWTB

Paper at repository of SibFU

https://elib.sfu-kras.ru/handle/2311/158602

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License (CC BY-NC 4.0).