An NDVI Retrieval Method Based on a Double-Attention Recurrent Neural Network for Cloudy Regions

Remote Sensing

Wenji Zhao¹  Fuzhou Duan²  Fengxian Lu³  Miao Zhang³  Ran Jing⁴ 

[1] College of Resource Environment and Tourism, Capital Normal University, Beijing 100048, China;Engineering Research Center of Spatial Information Technology, MOE, Beijing 100048, China;Henan Engineering Research Center of Environmental Laser Remote Sensing Technology and Application, Nanyang 473061, China;School of Geosciences, Yangtze University, Wuhan 430100, China;

关键词: SAR;    multispectral imagery;    double-attention mechanism;    RNN;    deep learning;   

DOI  :  10.3390/rs14071632

来源: DOAJ

【 摘 要 】

NDVI is an important parameter for environmental assessment and precision agriculture that well-describes the status of vegetation. Nevertheless, the clouds in optical images often result in the absence of NDVI information at key growth stages. The integration of SAR and optical image features will likely address this issue. Although the mapping of different data sources is complex, the prosperity of deep learning technology provides an alternative approach. In this study, the double-attention RNN architecture based on the recurrent neural network (RNN) and attention mechanism is proposed to retrieve NDVI data of cloudy regions. Overall, the NDVI is retrieved by the proposed model from two aspects: the temporal domain and the pixel neighbor domain. The performance of the double-attention RNN is validated through different cloud coverage conditions, input ablation, and comparative experiments with various methods. The results conclude that a high retrieval accuracy is guaranteed by the proposed model, even under high cloud coverage conditions (R² = 0.856, RMSE = 0.124). Using SAR images independently results in poor NDVI retrieval results (R² = 0.728, RMSE = 0.141) with considerable artifacts, which need to be addressed with auxiliary data, such as IDM features. Temporal and pixel neighbor features play an important role in improving the accuracy of NDVI retrieval (R² = 0.894, RMSE = 0.096). For the missing values of NDVI data caused by cloud coverage, the double-attention RNN proposed in this study provides a potential solution for information recovery.

【 授权许可】

Unknown