The integration of artificial intelligence (AI) with adaptive crop monitoring has emerged as a crucial element in the environmental modeling of dynamic agricultural landscapes. AI-driven mapping has fundamentally transformed cartographic solutions across engineering, natural, and technical sciences by embedding automation into methodologies. This is particularly vital for Geographic Information Systems (GIS) where the automation of spatial data processing is critical. Given that agricultural landscapes undergo seasonal and yearly transformations, precise environmental forecasting becomes increasingly important. This study presents an overview of recent methodological advancements in three interdisciplinary areas: the environmental monitoring of agricultural landscape dynamics in soil studies, the application of AI in GIS through machine learning (ML) and deep learning (DL) techniques, and bibliometric analysis. The tools utilize the R-based libraries including Bibliometrix, Treemap, and Wordcloud, alongside the Mendeley reference system. The research explores the deployment of novel AI and ML methodologies in scalable data-driven analysis within agriculture and soil studies, addressing associated issues with their application. This review draws upon a comprehensive selection of over 100 papers from recognized databases such as Scopus, Web of Science (WoS), PubMed, and Google Scholar, providing an in-depth examination of AI applications in soil and environmental studies. Additionally, the study outlines future perspectives for AI in environmental analysis by identifying best practices for AI implementation in GIS and advocating for systematic benchmarking in remote sensing pertinent to soil studies.