A transformer-based model for detecting land surface phenology from the irregular harmonized Landsat and Sentinel-2 time series across the United States

作者：Khuong H. Tran, Xiaoyang Zhang, Hankui K. Zhang, Yu Shen, Yongchang Ye, Yuxia Liu, Shuai Gao, Shuai An · 发表于：Remote Sensing of Environment · 年份：2025 · DOI：10.1016/j.rse.2025.114656 · 被引用次数：13 · 研究领域：Remote Sensing in Agriculture、Species Distribution and Climate Change、Remote Sensing and LiDAR Applications

Land surface phenology (LSP) has been widely generated using traditional methods of fitting satellite-based time series of vegetation indices over the past two decades. However, these methods are highly vulnerable to the presence of temporal gaps and the use of specific smoothing or gap-filling algorithms. Several attempts have recently used Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) to detect phenology, which produce an uncertainty of larger than three weeks and as large as two months. Further, these deep learning methods cannot handle missing data in time series and still need temporal gap-filling, which results in low to moderate accuracy in phenology detection. This study proposed a novel Transformer-based model to detect 30 m phenological events across the United States for the years 2019 and 2020. Specifically, we adapted the Transformer architecture to handle irregular time series and capture long-range relationships among all high-quality observations in the satellite time series. The Transformer-based model was trained using reference time series samples extracted from the high-quality LSP product, which was recently produced by fusing the HLS (Harmonized Landsat and Sentinel-2) observations with near-surface PhenoCam time series (HLS-PhenoCam LSP). The accuracy of the Transformer-based model for LSP detection using the two-band Enhanced Vegetation Index (EVI2) was investigated and compared with the most widely used Hybrid Piecewise Log...