Gap Filling for Historical Landsat NDVI Time Series by Integrating Climate Data

High-quality Normalized Difference Vegetation Index (NDVI) time series are essential in studying vegetation phenology, dynamic monitoring, and global change. Gap filling is the most important issue reconstructing NDVI from satellites with high spatial resolution, e.g., Landsat Chinese GaoFen-1/6 series. Due to sparse revisit frequencies of high-resolution satellites, traditional reconstruction approaches face challenge dealing large gaps raw data. In this paper, a climate incorporated gap-filling (CGF) method proposed for historical The CGF model considers relationship conditions between two adjacent years. Climate variables, including downward solar shortwave radiation, precipitation, temperature, used characterize constrain factors growth. Radial basis function networks (RBFNs) link years variabilities climatic conditions. An RBFN predicted background target year, observed values year were adjust Finally, recursively reconstructed 2018 1986. experiments performed heterogeneous region Qilian Mountains. results demonstrate that can accurately reconstruct generate continuous 30 m 8-day using observations. outperforms methods (e.g., harmonic analysis (HANTS) Savitzky-Golay (SG) filter methods) when contaminated gaps, which widely exist images.