Mapping the Corn Residue-Covered Types Using Multi-Scale Feature Fusion and Supervised Learning Method by Chinese GF-2 PMS Image
The management of crop residue covering is a vital part of conservation tillage, which protects black soil by reducing soil erosion and increasing soil organic carbon. Accurate and rapid classification of corn residue-covered types is significant for monitoring crop residue management. The remote se...
Main Authors: | , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Frontiers Media S.A.
2022-06-01
|
Series: | Frontiers in Plant Science |
Subjects: | |
Online Access: | https://www.frontiersin.org/articles/10.3389/fpls.2022.901042/full |
_version_ | 1811241873406164992 |
---|---|
author | Wancheng Tao Wancheng Tao Yi Dong Yi Dong Wei Su Wei Su Jiayu Li Jiayu Li Fu Xuan Fu Xuan Jianxi Huang Jianxi Huang Jianyu Yang Jianyu Yang Xuecao Li Xuecao Li Yelu Zeng Yelu Zeng Baoguo Li |
author_facet | Wancheng Tao Wancheng Tao Yi Dong Yi Dong Wei Su Wei Su Jiayu Li Jiayu Li Fu Xuan Fu Xuan Jianxi Huang Jianxi Huang Jianyu Yang Jianyu Yang Xuecao Li Xuecao Li Yelu Zeng Yelu Zeng Baoguo Li |
author_sort | Wancheng Tao |
collection | DOAJ |
description | The management of crop residue covering is a vital part of conservation tillage, which protects black soil by reducing soil erosion and increasing soil organic carbon. Accurate and rapid classification of corn residue-covered types is significant for monitoring crop residue management. The remote sensing technology using high spatial resolution images is an effective means to classify the crop residue-covered areas quickly and objectively in the regional area. Unfortunately, the classification of crop residue-covered area is tricky because there is intra-object heterogeneity, as a two-edged sword of high resolution, and spectral confusion resulting from different straw mulching ways. Therefore, this study focuses on exploring the multi-scale feature fusion method and classification method to classify the corn residue-covered areas effectively and accurately using Chinese high-resolution GF-2 PMS images in the regional area. First, the multi-scale image features are built by compressing pixel domain details with the wavelet and principal component analysis (PCA), which has been verified to effectively alleviate intra-object heterogeneity of corn residue-covered areas on GF-2 PMS images. Second, the optimal image dataset (OID) is identified by comparing model accuracy based on the fusion of different features. Third, the 1D-CNN_CA method is proposed by combining one-dimensional convolutional neural networks (1D-CNN) and attention mechanisms, which are used to classify corn residue-covered areas based on the OID. Comparison of the naive Bayesian (NB), random forest (RF), support vector machine (SVM), and 1D-CNN methods indicate that the residue-covered areas can be classified effectively using the 1D-CNN-CA method with the highest accuracy (Kappa: 96.92% and overall accuracy (OA): 97.26%). Finally, the most appropriate machine learning model and the connected domain calibration method are combined to improve the visualization, which are further used to classify the corn residue-covered areas into three covering types. In addition, the study showed the superiority of multi-scale image features by comparing the contribution of the different image features in the classification of corn residue-covered areas. |
first_indexed | 2024-04-12T13:42:42Z |
format | Article |
id | doaj.art-209718ea3bf14d92863e1a05fe8c03b6 |
institution | Directory Open Access Journal |
issn | 1664-462X |
language | English |
last_indexed | 2024-04-12T13:42:42Z |
publishDate | 2022-06-01 |
publisher | Frontiers Media S.A. |
record_format | Article |
series | Frontiers in Plant Science |
spelling | doaj.art-209718ea3bf14d92863e1a05fe8c03b62022-12-22T03:30:47ZengFrontiers Media S.A.Frontiers in Plant Science1664-462X2022-06-011310.3389/fpls.2022.901042901042Mapping the Corn Residue-Covered Types Using Multi-Scale Feature Fusion and Supervised Learning Method by Chinese GF-2 PMS ImageWancheng Tao0Wancheng Tao1Yi Dong2Yi Dong3Wei Su4Wei Su5Jiayu Li6Jiayu Li7Fu Xuan8Fu Xuan9Jianxi Huang10Jianxi Huang11Jianyu Yang12Jianyu Yang13Xuecao Li14Xuecao Li15Yelu Zeng16Yelu Zeng17Baoguo Li18College of Land Science and Technology, China Agricultural University, Beijing, ChinaKey Laboratory of Remote Sensing for Agri-Hazards, Ministry of Agriculture, Beijing, ChinaCollege of Land Science and Technology, China Agricultural University, Beijing, ChinaKey Laboratory of Remote Sensing for Agri-Hazards, Ministry of Agriculture, Beijing, ChinaCollege of Land Science and Technology, China Agricultural University, Beijing, ChinaKey Laboratory of Remote Sensing for Agri-Hazards, Ministry of Agriculture, Beijing, ChinaCollege of Land Science and Technology, China Agricultural University, Beijing, ChinaKey Laboratory of Remote Sensing for Agri-Hazards, Ministry of Agriculture, Beijing, ChinaCollege of Land Science and Technology, China Agricultural University, Beijing, ChinaKey Laboratory of Remote Sensing for Agri-Hazards, Ministry of Agriculture, Beijing, ChinaCollege of Land Science and Technology, China Agricultural University, Beijing, ChinaKey Laboratory of Remote Sensing for Agri-Hazards, Ministry of Agriculture, Beijing, ChinaCollege of Land Science and Technology, China Agricultural University, Beijing, ChinaKey Laboratory of Remote Sensing for Agri-Hazards, Ministry of Agriculture, Beijing, ChinaCollege of Land Science and Technology, China Agricultural University, Beijing, ChinaKey Laboratory of Remote Sensing for Agri-Hazards, Ministry of Agriculture, Beijing, ChinaCollege of Land Science and Technology, China Agricultural University, Beijing, ChinaKey Laboratory of Remote Sensing for Agri-Hazards, Ministry of Agriculture, Beijing, ChinaCollege of Land Science and Technology, China Agricultural University, Beijing, ChinaThe management of crop residue covering is a vital part of conservation tillage, which protects black soil by reducing soil erosion and increasing soil organic carbon. Accurate and rapid classification of corn residue-covered types is significant for monitoring crop residue management. The remote sensing technology using high spatial resolution images is an effective means to classify the crop residue-covered areas quickly and objectively in the regional area. Unfortunately, the classification of crop residue-covered area is tricky because there is intra-object heterogeneity, as a two-edged sword of high resolution, and spectral confusion resulting from different straw mulching ways. Therefore, this study focuses on exploring the multi-scale feature fusion method and classification method to classify the corn residue-covered areas effectively and accurately using Chinese high-resolution GF-2 PMS images in the regional area. First, the multi-scale image features are built by compressing pixel domain details with the wavelet and principal component analysis (PCA), which has been verified to effectively alleviate intra-object heterogeneity of corn residue-covered areas on GF-2 PMS images. Second, the optimal image dataset (OID) is identified by comparing model accuracy based on the fusion of different features. Third, the 1D-CNN_CA method is proposed by combining one-dimensional convolutional neural networks (1D-CNN) and attention mechanisms, which are used to classify corn residue-covered areas based on the OID. Comparison of the naive Bayesian (NB), random forest (RF), support vector machine (SVM), and 1D-CNN methods indicate that the residue-covered areas can be classified effectively using the 1D-CNN-CA method with the highest accuracy (Kappa: 96.92% and overall accuracy (OA): 97.26%). Finally, the most appropriate machine learning model and the connected domain calibration method are combined to improve the visualization, which are further used to classify the corn residue-covered areas into three covering types. In addition, the study showed the superiority of multi-scale image features by comparing the contribution of the different image features in the classification of corn residue-covered areas.https://www.frontiersin.org/articles/10.3389/fpls.2022.901042/fullcrop residue coveringmulti-scale image featuresmachine learningGF-2 PMS imagehigh spatial resolution remote sensing |
spellingShingle | Wancheng Tao Wancheng Tao Yi Dong Yi Dong Wei Su Wei Su Jiayu Li Jiayu Li Fu Xuan Fu Xuan Jianxi Huang Jianxi Huang Jianyu Yang Jianyu Yang Xuecao Li Xuecao Li Yelu Zeng Yelu Zeng Baoguo Li Mapping the Corn Residue-Covered Types Using Multi-Scale Feature Fusion and Supervised Learning Method by Chinese GF-2 PMS Image Frontiers in Plant Science crop residue covering multi-scale image features machine learning GF-2 PMS image high spatial resolution remote sensing |
title | Mapping the Corn Residue-Covered Types Using Multi-Scale Feature Fusion and Supervised Learning Method by Chinese GF-2 PMS Image |
title_full | Mapping the Corn Residue-Covered Types Using Multi-Scale Feature Fusion and Supervised Learning Method by Chinese GF-2 PMS Image |
title_fullStr | Mapping the Corn Residue-Covered Types Using Multi-Scale Feature Fusion and Supervised Learning Method by Chinese GF-2 PMS Image |
title_full_unstemmed | Mapping the Corn Residue-Covered Types Using Multi-Scale Feature Fusion and Supervised Learning Method by Chinese GF-2 PMS Image |
title_short | Mapping the Corn Residue-Covered Types Using Multi-Scale Feature Fusion and Supervised Learning Method by Chinese GF-2 PMS Image |
title_sort | mapping the corn residue covered types using multi scale feature fusion and supervised learning method by chinese gf 2 pms image |
topic | crop residue covering multi-scale image features machine learning GF-2 PMS image high spatial resolution remote sensing |
url | https://www.frontiersin.org/articles/10.3389/fpls.2022.901042/full |
work_keys_str_mv | AT wanchengtao mappingthecornresiduecoveredtypesusingmultiscalefeaturefusionandsupervisedlearningmethodbychinesegf2pmsimage AT wanchengtao mappingthecornresiduecoveredtypesusingmultiscalefeaturefusionandsupervisedlearningmethodbychinesegf2pmsimage AT yidong mappingthecornresiduecoveredtypesusingmultiscalefeaturefusionandsupervisedlearningmethodbychinesegf2pmsimage AT yidong mappingthecornresiduecoveredtypesusingmultiscalefeaturefusionandsupervisedlearningmethodbychinesegf2pmsimage AT weisu mappingthecornresiduecoveredtypesusingmultiscalefeaturefusionandsupervisedlearningmethodbychinesegf2pmsimage AT weisu mappingthecornresiduecoveredtypesusingmultiscalefeaturefusionandsupervisedlearningmethodbychinesegf2pmsimage AT jiayuli mappingthecornresiduecoveredtypesusingmultiscalefeaturefusionandsupervisedlearningmethodbychinesegf2pmsimage AT jiayuli mappingthecornresiduecoveredtypesusingmultiscalefeaturefusionandsupervisedlearningmethodbychinesegf2pmsimage AT fuxuan mappingthecornresiduecoveredtypesusingmultiscalefeaturefusionandsupervisedlearningmethodbychinesegf2pmsimage AT fuxuan mappingthecornresiduecoveredtypesusingmultiscalefeaturefusionandsupervisedlearningmethodbychinesegf2pmsimage AT jianxihuang mappingthecornresiduecoveredtypesusingmultiscalefeaturefusionandsupervisedlearningmethodbychinesegf2pmsimage AT jianxihuang mappingthecornresiduecoveredtypesusingmultiscalefeaturefusionandsupervisedlearningmethodbychinesegf2pmsimage AT jianyuyang mappingthecornresiduecoveredtypesusingmultiscalefeaturefusionandsupervisedlearningmethodbychinesegf2pmsimage AT jianyuyang mappingthecornresiduecoveredtypesusingmultiscalefeaturefusionandsupervisedlearningmethodbychinesegf2pmsimage AT xuecaoli mappingthecornresiduecoveredtypesusingmultiscalefeaturefusionandsupervisedlearningmethodbychinesegf2pmsimage AT xuecaoli mappingthecornresiduecoveredtypesusingmultiscalefeaturefusionandsupervisedlearningmethodbychinesegf2pmsimage AT yeluzeng mappingthecornresiduecoveredtypesusingmultiscalefeaturefusionandsupervisedlearningmethodbychinesegf2pmsimage AT yeluzeng mappingthecornresiduecoveredtypesusingmultiscalefeaturefusionandsupervisedlearningmethodbychinesegf2pmsimage AT baoguoli mappingthecornresiduecoveredtypesusingmultiscalefeaturefusionandsupervisedlearningmethodbychinesegf2pmsimage |