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 ( R2=0.84R^{2} = 0.84 and RMSE = 0.76) when compared to the LSTM estimation ( R2=0.83R^{2} = 0.83 and RMSE = 0.82) and LAI products ( R2<0.68R^{2} < 0.68 and RMSE > 1). Furthermore, our proposed method provided smoother and more continuous temporal profiles of LAI than other retrieval approaches.

中文翻译：

---

使用多个卫星产品进行时间序列叶面积指数估计的 Bi-LSTM 模型


时间序列叶面积指数（LAI）对于研究植被动态和气候变化至关重要。当前状态的LAI可以看作是先前状态的LAI的累积结果。尽管深度学习（DL）算法、长短期记忆（LSTM）可以从连续卫星数据中捕获长期依赖性以进行时间序列LAI估计，但它仅使用先前状态的信息，而忽略了当前植被的向后传播更改信息。因此，基于 LSTM 的 LAI 质量可能会受到限制。在这封信中，提出了双向 LSTM (Bi-LSTM) 方法来整合过去和未来的多个卫星产品的信息，以进行时间 LAI 检索。 2014-2015年全球陆面卫星（GLASS）、中分辨率成像光谱仪（MODIS）和可见红外成像辐射仪（VIIRS）LAI产品的融合值以及MODIS反射率作为输出响应和输入Bi-LSTM 训练。然后，我们将 Bi-LSTM 预测与 LSTM、融合 LAI 以及 2016 年使用独立验证数据集的三个产品的对应预测进行比较。结果表明，我们提出的 Bi-LSTM 方法以更高的准确度实现了更好的性能（R2=0.84R） ^{2} = 0.84 和 RMSE = 0.76) 与 LSTM 估计（ R2=0.83R^{2} = 0.83 和 RMSE = 0.82）和 LAI 产品（ R2<0 id=0> 1）相比。此外，我们提出的方法比其他检索方法提供了更平滑、更连续的 LAI 时间剖面。