Using long short-term memory recurrent neural network in land cover classification on Landsat and Cropland data layer time series
Using long short-term memory recurrent neural network in land cover classification on Landsat and Cropland data layer time series
复制标题
DOI：
10.1080/01431161.2018.1516313
复制
发表时间：
2018-10
影响因子：
3.4
通讯作者：
Ziheng Sun;L. Di;Hui Fang
中科院分区：
文献类型：
--
作者：
Ziheng Sun;L. Di;Hui Fang
土地覆盖图在辅助农业决策方面具有重要意义。然而，现有的土地覆盖图制作流程非常复杂，结果精度不明确。这项工作建立了一个长短期记忆（LSTM）递归神经网络（RNN）模型，以利用作物在图像时间序列中的时间模式来提高准确性并降低复杂性。提出了一个端到端的框架来训练和测试模型。Landsat场景被用作地球观测，一些实地测量数据与CDL（农田数据层）数据集一起被用作参考数据。该网络使用最先进的深度学习技术进行了彻底的训练。最后，我们在多个Landsat场景上测试了网络，以生成五级和所有级别的土地覆盖图。这些地图是可视化的，并与地面实况，CDL和SegNet CNN（卷积神经网络）的结果进行比较。实验结果表明，该方法具有良好的识别效果（五类识别精度> 97%，全类识别精度> 88%），验证了该方法的可行性。该研究为LSTM RNN在遥感图像时间序列分类中的应用开辟了一条新的途径。
ABSTRACT Land cover maps are significant in assisting agricultural decision making. However, the existing workflow of producing land cover maps is very complicated and the result accuracy is ambiguous. This work builds a long short-term memory (LSTM) recurrent neural network (RNN) model to take advantage of the temporal pattern of crops across image time series to improve the accuracy and reduce the complexity. An end-to-end framework is proposed to train and test the model. Landsat scenes are used as Earth observations, and some field-measured data together with CDL (Cropland Data Layer) datasets are used as reference data. The network is thoroughly trained using state-of-the-art techniques of deep learning. Finally, we tested the network on multiple Landsat scenes to produce five-class and all-class land cover maps. The maps are visualized and compared with ground truth, CDL, and the results of SegNet CNN (convolutional neural network). The results show a satisfactory overall accuracy (> 97% for five-class and > 88% for all-class) and validate the feasibility of the proposed method. This study paves a promising way for using LSTM RNN in the classification of remote sensing image time series.