Corn Phenology Detection Using the Derivative Dynamic Time Warping Method and Sentinel-2 Time Series

Accurate determination of crop phenology information is essential for effective field management and decision-making processes. Remote sensing time series analyses are widely employed to extract the phenological stages. Each crop’s stage has its unique characteristic on plant, while satellite-derived refers some key transition dates in satellite observations. Current techniques primarily estimate specific stages by detecting points with distinctive features remote curve. But these may be different from Biologische Bundesanstalt, Bundessortenamt CHemical Industry (BBCH) scale, which commonly used identify development crops. Moreover, when aiming various concurrently, it becomes necessary adjust extraction strategy each feature. This need distinct strategies at heightens complexity simultaneous extraction. In this study, we utilize Sentinel-2 Normalized Difference Vegetation Index (NDVI) data propose a framework based Derivative Dynamic Time Warping (DDTW) algorithm. method capable simultaneously extracting complete stages, results demonstrate that Root Mean Square Errors (RMSEs, days) detected BBCH scale corn were less than 6 days overall.