 This paper proposes a new approach to accurately determine crop phenology using remote sensing time series data. The proposed method uses the derivative dynamic time warping, DDTW, algorithm to simultaneously extract multiple phenological stages from the sentinel 2 and DVI time series data. The results show that the RMSEs of detected phenology on the BDCH scale for corn were less than six days overall. This article was authored by Zhenyin Yi, Wenhao Bao, Chunhua Liao, and others.