Land cover guides better gap filling in modis satellite images
LC-TSRNet: A Land-Cover-Guided Two-Stage Network for Annual MODIS Surface Reflectance Time Series Reconstruction
Computer Vision and Pattern Recognition
Summary
MODIS satellite images often have missing or cloudy parts, which makes it hard to study Earth’s surface over time. The authors created LC-TSRNet, a two-step method that uses land cover maps to help fill these missing gaps more accurately. First, it uses the fact that similar land types reflect light in comparable ways to guess missing data. Then, it combines information from nearby times and places to improve the results further. This method works better than others and helps with tasks like monitoring vegetation.
What this means in practice
- •For environmental monitoring teams: Improve the accuracy of vegetation and land surface studies by filling gaps in MODIS satellite time series using land-cover guided reconstructions.
- •For agriculture technology developers: Enhance crop monitoring systems by providing more complete annual reflectance data from MODIS satellites for large-scale and long-term analyses.
Authors
Wenjuan Zhang, Xuesong Ma, Zhen Li, Meixiang Wang, Caimeng Yi, Jie Pan, Nan Su, Bing Zhang
Abstract
MODIS surface reflectance (SR) products often suffer from data gaps due to cloud contamination and sensor malfunctions, limiting their applications in long-term and large-scale studies. Most existing methods rely on cloud-free observations from optical time series or introduce SAR time series as auxiliary information. However, due to the coarse spatial resolution of MODIS, cloud-free reference images are difficult to obtain, and SAR imagery is not well matched to the spatial resolution of MODIS, making it difficult to provide effective prior constraints. To address these issues, this study proposes LC-TSRNet for seamless reconstruction of annual MODIS SR products. In the first stage, an annual land cover map is introduced as prior knowledge, and CSPM is designed by leveraging the spectral similarity within identical land cover types, thereby providing prior spectral constraints for missing regions. In the second stage, to address large-area, persistent, and overlapping gaps in MODIS imagery, SMRM is designed to adaptively exploit and integrate multi-scale spatiotemporal contextual information. Meanwhile, to address the limited collaborative utilization of spatio-temporal-spectral information, 3DAM is designed to impose cross-dimensional joint constraints. Considering the lack of publicly available MODIS sample datasets, this study constructs the AIRMOD-TSR dataset. Extensive experimental results show that LC-TSRNet outperforms the comparison methods and achieves better reconstruction accuracy and spectral fidelity. Under the spatially adjacent scenario, LC-TSRNet improves PSNR by 0.56 dB and reduces SAM by 0.13°. The vegetation monitoring application further verifies the practical value of the reconstructed SR time series.