Cropformer: A new generalized deep learning classification approach for multi-scenario crop classification
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. In t...
Main Authors: | , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Frontiers Media S.A.
2023-03-01
|
Series: | Frontiers in Plant Science |
Subjects: | |
Online Access: | https://www.frontiersin.org/articles/10.3389/fpls.2023.1130659/full |
_version_ | 1811161601399586816 |
---|---|
author | Hengbin Wang Wanqiu Chang Yu Yao Zhiying Yao Yuanyuan Zhao Yuanyuan Zhao Shaoming Li Shaoming Li Zhe Liu Zhe Liu Xiaodong Zhang Xiaodong Zhang |
author_facet | Hengbin Wang Wanqiu Chang Yu Yao Zhiying Yao Yuanyuan Zhao Yuanyuan Zhao Shaoming Li Shaoming Li Zhe Liu Zhe Liu Xiaodong Zhang Xiaodong Zhang |
author_sort | Hengbin Wang |
collection | DOAJ |
description | 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. In this study, we proposed a new deep learning approach for multi-scenario crop classification, named Cropformer. Cropformer can extract global features and local features, to solve the problem that current crop classification methods extract a single feature. Specifically, 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. Experimental results showed that Cropformer can not only obtain a very significant accuracy advantage in crop classification, but also can obtain higher accuracy with fewer samples. 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. |
first_indexed | 2024-04-10T06:17:01Z |
format | Article |
id | doaj.art-1a7040dc3ac541f88ec404634302ffb9 |
institution | Directory Open Access Journal |
issn | 1664-462X |
language | English |
last_indexed | 2024-04-10T06:17:01Z |
publishDate | 2023-03-01 |
publisher | Frontiers Media S.A. |
record_format | Article |
series | Frontiers in Plant Science |
spelling | doaj.art-1a7040dc3ac541f88ec404634302ffb92023-03-02T06:06:10ZengFrontiers Media S.A.Frontiers in Plant Science1664-462X2023-03-011410.3389/fpls.2023.11306591130659Cropformer: A new generalized deep learning classification approach for multi-scenario crop classificationHengbin Wang0Wanqiu Chang1Yu Yao2Zhiying Yao3Yuanyuan Zhao4Yuanyuan Zhao5Shaoming Li6Shaoming Li7Zhe Liu8Zhe Liu9Xiaodong Zhang10Xiaodong Zhang11College of Land Science and Technology, China Agricultural University, Beijing, ChinaCollege of Land Science and Technology, China Agricultural University, Beijing, ChinaCollege of Land Science and Technology, China Agricultural University, Beijing, ChinaCollege of Land Science and Technology, China Agricultural University, Beijing, ChinaCollege of Land Science and Technology, China Agricultural University, Beijing, ChinaKey Laboratory of Remote Sensing for Agri-Hazards, Ministry of Agriculture and Rural Affairs, Beijing, ChinaCollege of Land Science and Technology, China Agricultural University, Beijing, ChinaKey Laboratory of Remote Sensing for Agri-Hazards, Ministry of Agriculture and Rural Affairs, Beijing, ChinaCollege of Land Science and Technology, China Agricultural University, Beijing, ChinaKey Laboratory of Remote Sensing for Agri-Hazards, Ministry of Agriculture and Rural Affairs, Beijing, ChinaCollege of Land Science and Technology, China Agricultural University, Beijing, ChinaKey Laboratory of Remote Sensing for Agri-Hazards, Ministry of Agriculture and Rural Affairs, Beijing, ChinaAccurate 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. In this study, we proposed a new deep learning approach for multi-scenario crop classification, named Cropformer. Cropformer can extract global features and local features, to solve the problem that current crop classification methods extract a single feature. Specifically, 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. Experimental results showed that Cropformer can not only obtain a very significant accuracy advantage in crop classification, but also can obtain higher accuracy with fewer samples. 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.https://www.frontiersin.org/articles/10.3389/fpls.2023.1130659/fullmulti-scenario crop classificationtime seriesdeep learningpre-trainingCropformer |
spellingShingle | Hengbin Wang Wanqiu Chang Yu Yao Zhiying Yao Yuanyuan Zhao Yuanyuan Zhao Shaoming Li Shaoming Li Zhe Liu Zhe Liu Xiaodong Zhang Xiaodong Zhang Cropformer: A new generalized deep learning classification approach for multi-scenario crop classification Frontiers in Plant Science multi-scenario crop classification time series deep learning pre-training Cropformer |
title | Cropformer: A new generalized deep learning classification approach for multi-scenario crop classification |
title_full | Cropformer: A new generalized deep learning classification approach for multi-scenario crop classification |
title_fullStr | Cropformer: A new generalized deep learning classification approach for multi-scenario crop classification |
title_full_unstemmed | Cropformer: A new generalized deep learning classification approach for multi-scenario crop classification |
title_short | Cropformer: A new generalized deep learning classification approach for multi-scenario crop classification |
title_sort | cropformer a new generalized deep learning classification approach for multi scenario crop classification |
topic | multi-scenario crop classification time series deep learning pre-training Cropformer |
url | https://www.frontiersin.org/articles/10.3389/fpls.2023.1130659/full |
work_keys_str_mv | AT hengbinwang cropformeranewgeneralizeddeeplearningclassificationapproachformultiscenariocropclassification AT wanqiuchang cropformeranewgeneralizeddeeplearningclassificationapproachformultiscenariocropclassification AT yuyao cropformeranewgeneralizeddeeplearningclassificationapproachformultiscenariocropclassification AT zhiyingyao cropformeranewgeneralizeddeeplearningclassificationapproachformultiscenariocropclassification AT yuanyuanzhao cropformeranewgeneralizeddeeplearningclassificationapproachformultiscenariocropclassification AT yuanyuanzhao cropformeranewgeneralizeddeeplearningclassificationapproachformultiscenariocropclassification AT shaomingli cropformeranewgeneralizeddeeplearningclassificationapproachformultiscenariocropclassification AT shaomingli cropformeranewgeneralizeddeeplearningclassificationapproachformultiscenariocropclassification AT zheliu cropformeranewgeneralizeddeeplearningclassificationapproachformultiscenariocropclassification AT zheliu cropformeranewgeneralizeddeeplearningclassificationapproachformultiscenariocropclassification AT xiaodongzhang cropformeranewgeneralizeddeeplearningclassificationapproachformultiscenariocropclassification AT xiaodongzhang cropformeranewgeneralizeddeeplearningclassificationapproachformultiscenariocropclassification |