European Journal of Sustainable Agroecosystems

Background: Precision agriculture is moving towards using high-resolution, up-to-date data for location-based (site-specific) crop management—among the leading platforms for this is the unmanned aerial vehicle (UAV). UAVs become versatile tools for remote sensing enabling crop growth monitoring with a fresh perspective on establishing the balance between satellite images and field research.

Objective: The goal of this review is to identify the main peer-reviewed studies published from 2015 to 2025 on UAV-based remote sensing applications for crop growth monitoring with a focus on the vegetation index calculation, biomass and yield estimation, detection of diseases and weeds, examination of nutritional indicators, and assessment of obstacles to actual use.

Literature sources: The search for literature was conducted using a structured approach to search Scopus, Web of Science, PubMed, IEEE Xplore, ScienceDirect, SpringerLink, and Google Scholar, along with publications from FAO, UNDP, and national agricultural research organizations. Ultimately, thirty-four research studies met inclusion criterion as per PRISMA screening.

Essential findings: The literature indicates that the use of UAVs to derive vegetation indices shows consistent and significant correlations between aerial vegetation indices from UAV derived images and above-ground biomass and yield for cereal crops.

Gaps in research: The problems of inconsistency between studies in the calibration of sensors, lack of experiences of validation in different seasons and regions, and the low applicability of deep learning models resulted in nothing. The various regulations relating to the operation of UAVs and agricultural data processing are still unevenly implemented in different countries.

Conclusion: Remote sensing with UAVs is a well-established, but still developing technology. Future investigations should concentrate on the issues of uniform calibration standards, simultaneous processing of data from various sources, creating models that require minimal resources and could benefit other agricultural practices.