Early identification of immature rubber plantations using Landsat and Sentinel satellite images

Early identification of rubber plantations holds significant importance for both optimal plantation management and scientific studies. Even though remote sensing techniques for mapping rubber plantations have evolved considerably since the 2000s, current methods are highly effective in detecting mature rubber plantations (MRPs), which have distinctive forest characteristics, but often fail to identify immature rubber plantations (IRPs) in a timely manner. This leads to an estimated lag of at least five years in the resulting rubber plantation maps. This paper presents a novel algorithm aimed at promptly pinpointing IRPs in the early planting stage by harnessing a composite of multi-source time series satellite imagery on Google Earth Engine (GEE) platform. Twelve scenarios with different time intervals (3 months, 6 months, and 12 months) and datasets (Landsat 8, Sentinel-2, and Sentinel-1) were tested to determine the most efficient strategy for identifying IRPs using a random forest algorithm. The results demonstrate that the data cube constructed from Landsat 8, Sentinel-2, and Sentinel-1 with 3-month time intervals yields the most accurate identification accuracy. Specifically, it achieves a remarkable overall accuracy of 0.78, 0.87, and 0.93 for plantations established during the second, third, and fourth years, respectively. When implemented on Hainan Island, China's second-largest natural rubber producing base, the algorithm unveiled a significant decline trend in rubber plantation areas since 2015. Additionally, the spatial distribution exhibited pronounced heterogeneity: while the western and northern regions saw dense immature plantation clusters, the eastern coastal regions hosted only sparse plantations. These up-to-date maps of IRPs are valuable in predicting rubber production, enhancing the monitoring and management practices, and promoting the sustainable development of natural rubber industry.