Progress and Trends in UAV-Based Soil Moisture Inversion: A Comparative Knowledge Mapping Analysis of CNKI and Web of Science

Soil moisture critically governs terrestrial energy and water cycles. Precise monitoring of soil water content is essential for precision agriculture, drought early warning, and water resource management. Ground-based observations offer limited spatial coverage, and satellite remote sensing generally lacks high spatial resolution. Unmanned aerial vehicle (UAV) remote sensing, which provides centimeter-level spatial detail, can effectively address this gap and has therefore attracted considerable attention in soil moisture inversion research. Using CiteSpace, we performed a bibliometric analysis of 97 Chinese papers from the China National Knowledge Infrastructure (CNKI) and 321 English papers from the Web of Science Core Collection (2014–2025). The field has expanded rapidly since 2018, with China occupying a leading role. Domestically, Northwest A&F University represents a major research cluster, while the Chinese Academy of Sciences leads internationally. Key research topics include UAVs, soil moisture, machine learning, hyperspectral sensing, canopy temperature, and precision agriculture. Research themes have progressed from reliance on vegetation indices and temperature data toward the integration of hyperspectral and thermal infrared measurements, and toward the use of machine learning approaches to improve inversion models and achieve more accurate estimations. This study delineates the classification and developmental context of a knowledge system for soil moisture inversion using UAV remote sensing. Current work concentrates on integrating multi-sensor data with machine learning, while future efforts will emphasize coupling physical mechanisms with deep learning. These findings offer researchers a clear view of the field’s frontiers and a basis for planning future studies.