Coffee Extraction from Remote Sensing Imagery Based on Multiple Features: A Case Study of Pu'er City, China

Qianrui Huang¹Xianfeng Cheng¹Yu Chen^2,3,4Huicong Jia^2,3,4*Xinyi Ding^2,3,4,5*

• ¹Yunnan Land and Resources Vocational College, Kunming, China
• ²Chinese Academy of Sciences International Research Center of Big Data for Sustainable Development Goals, Beijing, China
• ³Chinese Academy of Sciences Key Laboratory of Digital Earth Science, Beijing, China
• ⁴Chenjiang Laboratory, Chenzhou, China
• ⁵University of Chinese Academy of Sciences, Beijing, China

Coffee, a vital beverage and cultural symbol, significantly influences global economic and cultural development. Due to the characteristics of agricultural production activities, such as areas, significant differences, and relatively low economic benefits per unit area, Traditional ground surveys often fail to accurately capture coffee crop distribution due to the large-scale, regionally varied, and economically modest nature of agricultural production. Remote sensing offers a promising alternative but faces challenges in distinguishing coffee from vegetation with similar spectral characteristics, especially in areas with complex land cover and dense canopies. This study focuses on Pu'er City in Yunnan Province, China, renowned as the 'golden belt' of global coffee cultivation. Using Sentinel-2 remote sensing imagery, we analyzed key phenological features through time-series curves of the Normalized Difference Vegetation Index (NDVI), Ratio Vegetation Index (RVI), and Difference Vegetation Index (DVI). To ensure a balanced and representative dataset, interpretation keys were established from 1,617 field-measured sampling points, yielding a total of 4,000 coffee and non-coffee samples. Employing the Random Forest (RF) algorithm, we constructed a refined coffee crop extraction model incorporating spectral, texture, terrain, and regional pattern features. The findings indicate: (1) Incorporating administrative division features and using a larger texture window size (5× 5) enhances model accuracy, achieving an overall accuracy (OA) of 93.92% and a Kappa coefficient of 0.8783. (2) The four-period segmentation approach significantly improved accuracy, with the highest OA reaching 94.80%, identifying October to December (coffee fruiting season) as the most critical period for classification. (3) Administrative Division Features (ID), Topographical features (SLOPE) and vegetation indices (NDVI and DVI) were the most crucial for coffee classification, while texture features, except for Sum Average (SAVG), generally had lower importance. This study validates the effectiveness of remote sensing in monitoring and mapping coffee cultivation. The This is a provisional file, not the final typeset article proposed feature input strategy shows strong potential for application in other regions with similar agro-ecological conditions, supporting precision agricultural management and promoting sustainable coffee farming practices.