Hui Chen;Yuean Qiu;Dameng Yin;Jin Chen;Xuehong Chen;Shuaijun Liu;Licong li

State Key Laboratory of Remote Sensing Science, Institute of Remote Sensing Science and Engineering, Faculty of Geographical Science, Beijing Normal University, Beijing 100875, Chin;State Key Laboratory of Remote Sensing Science, Institute of Remote Sensing Science and Engineering, Faculty of Geographical Science, Beijing Normal University, Beijing 100875, China;Institute of Crop Sciences, Chinese Academy of Agricultural Sciences, Beijing 100081, China

Crop classification;Convolutional neural network;Handcrafted feature;Stacked spectral feature space patch;Spectral informatio

Spectral and spatial features in remotely sensed data play an irreplaceable role in classifying crop types for precision agriculture. Despite the thriving establishment of the handcrafted features, designing or selecting such features valid for specific crop types requires prior knowledge and thus remains an open challenge. Convolutional neural networks (CNNs) can effectively overcome this issue with their advanced ability to generate high-level features automatically but are still inadequate in mining spectral features compared to mining spatial features. This study proposed an enhanced spectral feature called Stacked Spectral Feature Space Patch (SSFSP) for CNN-based crop classification. SSFSP is a stack of two-dimensional (2D) gridded spectral feature images that record various crop types' spatial and intensity distribution characteristics in a 2D feature space consisting of two spectral bands. SSFSP can be input into 2D-CNNs to support the simultaneous mining of spectral and spatial features, as the spectral features are successfully converted to 2D images that can be processed by CNN. We tested the performance of SSFSP by using it as the input to seven CNN models and one multilayer perceptron model for crop type classi-fication compared to using conventional spectral features as input. Using high spatial resolution hyper -spectral datasets at three sites, the comparative study demonstrated that SSFSP outperforms conventional spectral features regarding classification accuracy, robustness, and training efficiency. The theoretical analysis summarizes three reasons for its excellent performance. First, SSFSP mines the spec-tral interrelationship with feature generality, which reduces the required number of training samples. Second, the intra-class variance can be largely reduced by grid partitioning. Third, SSFSP is a highly sparse feature, which reduces the dependence on the CNN model structure and enables early and fast conver-gence in model training. In conclusion, SSFSP has great potential for practical crop classification in pre-cision agriculture.(c) 2022 2022 Crop Science Society of China and Institute of Crop Science, CAAS. Production and hosting by Elsevier B.V. on behalf of KeAi Communications Co., Ltd. This is an open access article under the CC BY-NC -ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).