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

Abstract

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

Reconstruction of Sentinel-2 Time Series Using Robust Gaussian Mixture Models -- Application to the Detection of Anomalous Crop Development in wheat and rapeseed crops

“…Hence, our results confirm the interest of using outlier detection techniques as standard preprocessing steps in remote sensing, as also recommended for instance in [43] for the classification of land cover. Note that the obtained results are coherent with the literature: an MAE of 0.0281 was obtained in [63] for the reconstruction of NDVI in crop vegetation, an MAE of 0.038 was obtained in [21] for the reconstruction of NDVI for grassland parcels and MAE varying from 0.035 to 0.042 (depending on the region analyzed) was obtained in [22] for agricultural parcels. While these results provide quantitative values for comparison purposes, important differences have to be highlighted: existing studies generally focus on NDVI time series acquired at the pixel-level and do not analyze crops at the parcel level, as proposed in this paper.…”

“…Gap filling methods (linear interpolation, spline interpolation and Whittaker smoother) [8] perform overall poorly compared to the methods investigated in this paper, which is mainly due to the sparsity of S2 acquisitions, confirming the results found in [63]. Moreover, when applied to the detection of abnormal crop development, smoothing methods tend to decrease the accuracy of the detection results.…”

“…In particular, the automatic classification of the different anomalies could be considered as in León-López et al [31]. Finally, adding external information such as climate data could also be relevant to reconstruct more efficiently the various VI, since interesting results were obtained for the reconstruction of NDVI time series [59,63].…”

Temporal and Spatial Changes in Vegetation Ecological Quality and Driving Mechanism in Kökyar Project Area from 2000 to 2021

“…Secondly, only using temperature and precipitation to quantify climate change increases the uncertainty of the study. In fact, in addition to temperature and precipitation, other climatic factors also affect the vegetation ecological status, such as the vapor pressure deficit (VPD) [46,47], atmospheric pressure [48,49], shortwave radiation [50,51], and wind speed [52,53]. However, in the current state, it is still unrealistic to thoroughly reveal the driving mechanism of the vegetation ecological parameters of Kökyar.…”

Estimating Evapotranspiration over Heterogeneous Surface with Sentinel-2 and Sentinel-3 Data: A Case Study in Heihe River Basin

“…However, widespread contamination (due to aerosols, clouds, etc.) and the long revisit period of these high-resolution satellites induce large gaps in the NDVI time series data and limit their application in related studies [73].…”