AUTHOR=Wang Hengbin , Chang Wanqiu , Yao Yu , Yao Zhiying , Zhao Yuanyuan , Li Shaoming , Liu Zhe , Zhang Xiaodong 

TITLE=Cropformer: A new generalized deep learning classification approach for multi-scenario crop classification

JOURNAL=Frontiers in Plant Science

VOLUME=Volume 14 - 2023

YEAR=2023

URL=https://www.frontiersin.org/journals/plant-science/articles/10.3389/fpls.2023.1130659

DOI=10.3389/fpls.2023.1130659

ISSN=1664-462X

ABSTRACT=Accurate and efficient crop classification using remotely sensed data can provide fundamental and important information for crop yield estimation. Existing crop classification approaches are usually designed to be strong in some specific scenarios but not for multi-scenario crop classification. Developing a generalized model for crop classification in multiple scenarios is greatly essential. In this study, we proposed a new deep learning approach for multi-scenario crop classification, named Cropformer. Cropformer is a two-step classification approach, where the first step is self-supervised pre-training to accumulate knowledge of crop growth, and the second step is a fine-tuned supervised classification based on the weights from the first step. The unlabeled time series and the labeled time series are used as input for the first and second steps respectively. Multi-scenario crop classification experiments including full-season crop classification, in-season crop classification, few-sample crop classification, and transfer of classification models were conducted in five study areas with complex crop types and compared with several existing competitive approaches. Cropformer produced an overall accuracy (OA) of 83.5% in the full-season experiment and more than 14 crops can be classified in July with the equivalent F1 score as when classifying full-season crops. In the few-sample crop classification, using only 1% of the total samples obtained an OA of 82.3% compared to that using total samples (84.6%); an average accuracy (AA) of 69.63% was obtained when using no more than 100 samples per class, exceeding that of AA using all samples (66.4%). Compared to other approaches, the classification performance of Cropformer during model transfer and the efficiency of the classification were outstanding. The results showed that Cropformer could build up a priori knowledge using unlabeled data and learn generalized features using labeled data, making it applicable to crop classification in multiple scenarios.