Application of Artificial Intelligence Methods for Spatial Analysis of Agricultural Land Use in the Qgis Geoinformation System

The integration of artificial intelligence algorithms in agriculture has been studied to support efficient and sustainable agricultural production through the use of machine learning technologies, automated data collection, and analysis of large volumes of geospatial data to improve land resource management using geographic information systems. The article analyzes the prospects of applying artificial intelligence (AI) methods in the QGIS geographic information system for spatial analysis of agricultural land use. The effectiveness of integrating machine learning algorithms, remote sensing tools, and satellite data for improving land resource management is substantiated. The focus is placed on studying the functionality of modern QGIS plugins such as Mapflow, SCP (Semi-Automatic Classification Plugin), SentinelHub, GEE Timeseries Explorer, Structured Classification Plugin, and qgis2web, which implement AI capabilities for mapping, monitoring, and analytics in the agricultural sector. The methodology of using high-resolution satellite imagery for automatic land cover classification, identification of land use types, and assessment of vegetation condition using vegetation indices (NDVI, EVI), as well as detecting changes in agro-landscape structures, is revealed. The process of creating vector layers from satellite data, applying tools for classification quality control, and post-processing of images is described. The use of QGIS as a flexible and open-source platform for scientific and applied geospatial analysis, particularly under resource-limited conditions, is substantiated. The research results demonstrate that combining AI with GIS tools enhances the accuracy, speed, and objectivity of spatial analysis, providing a high level of detail, reducing human error, and expanding the possibilities of agricultural monitoring. This opens new horizons for effective land resource management, informed decision-making in land use, and the implementation of digital agriculture technologies.