Using long short-term memory recurrent neural network in land cover classification on Landsat and Cropland data layer time series

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.

Acknowledgments

We sincerely thank the authors and copyright holders of all the datasets and software used to accomplish this research, and the editor and anonymous reviewers for their careful reading of our manuscript and thoughtful comments. This study was partially supported in part by NSF EarthCube under grants #1740693.

Disclosure statement

No potential conflict of interest was reported by the authors.

Supplemental material

Supplemental data for this article can be accessed here.

Additional information

Funding

This work was supported by grants from National Science Foundation (Grant number: ICER-1440294, AGS-1740693; PI: Dr. Liping Di).

Notes on contributors

Ziheng Sun

Dr. Ziheng Sun is a research assistant professor in Center for Spatial Information Science and Systems, George Mason University.

Liping Di

Dr. Liping Di is a professor of Geography and Geoinformation Science, George Mason University and the director of Center for Spatial Information Science and Systems, George Mason University.

Hui Fang

Hui Fang receives her M.Sc degree from State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University.