Bi-LSTM Model for Time Series Leaf Area Index Estimation Using Multiple Satellite Products

Time series leaf area index (LAI) is essential to studying vegetation dynamics and climate changes. The LAI at current status can be regarded as the accumulative consequence of the counterpart at prior times. Although the deep learning (DL) algorithm, long short-term memory (LSTM), can capture long-time dependencies from sequential satellite data for time series LAI estimation, it only uses the information at prior statuses and neglects the backward propagation of current vegetation change information. Thus, the LSTM-based LAI quality might be limited. In this letter, the bidirectional LSTM (Bi-LSTM) approach was proposed to integrate the information of multiple satellite products from both the past and future for temporal LAI retrieval. The fused values from Global Land Surface Satellite (GLASS), moderate-resolution imaging spectroradiometer (MODIS), and visible infrared imaging radiometer (VIIRS) LAI products, as well as MODIS reflectance in 2014-2015, serve as the output response and input for the Bi-LSTM training. Then, we compared the Bi-LSTM predictions with the counterparts from the LSTM, the fused LAI, and three products using independent validation datasets in 2016. Results illustrated that our proposed Bi-LSTM method achieved better performance with higher accuracy (R-2 = 0.84 and RMSE = 0.76) when compared to the LSTM estimation (R-2 = 0.83 and RMSE = 0.82) and LAI products (R-2 < 0.68 and RMSE > 1). Furthermore, our proposed method provided smoother and more continuous temporal profiles of LAI than other retrieval approaches.

Automated summary

This study proposes a bidirectional LSTM (Bi-LSTM) approach to improve the estimation of time series leaf area index (LAI). By integrating information from multiple satellite products, including Global Land Surface Satellite (GLASS), moderate-resolution imaging spectroradiometer (MODIS), and visible infrared imaging radiometer (VIIRS) LAI products, as well as MODIS reflectance, the Bi-LSTM method achieves better accuracy and smoother temporal profiles than other retrieval approaches.