Identify Tea Plantations Using Multidimensional Features Based on Multisource Remote Sensing Data: A Case Study of the Northwest Mountainous Area of Hubei Province

Accurate identification of tea plantation distribution is critical for optimizing agricultural practices, informing land-use policies, and preserving ecological balance. However, challenges persist in mountainous regions with persistent cloud cover and heterogeneous vegetation, where conventional methods relying on single-source remote sensing features face limitations due to spectral confusion and information redundancy. This study proposes a novel framework integrating multisource remote sensing data and feature optimization to address these challenges. Leveraging the Google Earth Engine (GEE) cloud platform, this study synthesized 108 spectral, textural, phenological, and topographic features from Sentinel-1 SAR and Sentinel-2 optical data. SVM-RFE (support vector machine recursive feature elimination) was employed to identify the optimal feature subset, prioritizing spectral indices, radar texture metrics, and terrain parameters. Comparative analysis of three classifiers, namely random forest (RF), support vector machine (SVM), and decision tree (DT), revealed that RF achieved the highest accuracy, with an overall accuracy (OA) of 95.03%, a kappa coefficient of 0.95. The resultant 10 m resolution spatial distribution map of tea plantations in Shiyan City (2023) demonstrates robust performance in distinguishing plantations from forests and farmlands, particularly in cloud-prone mountainous terrain. This methodology not only mitigates dimensionality challenges through feature optimization but also provides a scalable solution for large-scale agricultural monitoring, offering critical insights for sustainable land management and policy formulation in subtropical mountainous regions.