Multi-sensor remote sensing approach for oil palm mapping and stand age detection using 38-year landsat and sentinel time series data in the google earth engine

Rapid oil-palm expansion in Southeast Asia demands accurate, up-to-date information on plantation extent and stand age, yet single-sensor approaches often misclassify mixed tropical vegetation and cannot reconstruct planting histories that underlie yield forecasts and sustainability metrics. We integrated the full 1987–2024 Landsat surface-reflectance archive (38 years) with 2024 Sentinel-2 imagery to build a cloud-native monitoring pipeline in Google Earth Engine (GEE). A Random-Forest (RF) model, trained on stratified field samples, delineated plantation extent from six Sentinel-2 bands, five vegetation/surface indices, three Sentinel-1-derived back-scatter layers, and two terrain variables. Age was retrieved inside the verified extent mask by locating the most recent year in which smoothed NDVI dropped below its 20th percentile while the Bare-Soil Index (BSI) exceeded its 80th percentile, thereby flagging the latest planting or replanting events in the Landsat record. Model skill was assessed with a 30 % hold-out set using overall accuracy, κ, precision, and recall; age estimates were validated against 234 ground plots with MAE and RMSE. The multi-sensor classifier reached an overall accuracy of 90.5 % and Kappa = 0.81, with balanced error rates (oil palm: 88.6 % precision, 92.7 % recall; non-oil palm: 92.5 % precision, 88.4 % recall). Mapped plantations covered 561 km², or 60.9 % of the study district. Age retrieval achieved an RMSE of 4.0 yr, revealing distinct replanting events that correspond to known market cycles and providing spatially explicit age strata relevant to yield and carbon-stock modelling. Combining the long Landsat record with high-resolution Sentinel data markedly outperforms single-sensor methods for both extent mapping and age estimation. The workflow relies solely on free, globally available imagery and scalable cloud computing, making it immediately transferable to government and NGO monitoring programmes. By delivering accurate maps of plantation area and stand age, the approach fills a critical information gap for sustainable palm-oil certification, carbon accounting, and land-use policy across the humid tropics.