Automatic Crop Classification Based on Optimized Spectral and Textural Indexes Considering Spatial Heterogeneity
Crop recognition with high accuracy at a large scale is hampered by the spatial heterogeneity of crop growth characteristics under the complex influence of environmental conditions. With the aim to automatically realize large-scale crop classification with high accuracy, this study proposes an autom...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-11-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/15/23/5550 |
| _version_ | 1797399667807354880 |
|---|---|
| author | Xiaomi Wang Jiuhong Liu Peng Peng Yiyun Chen Shan He Kang Yang |
| author_facet | Xiaomi Wang Jiuhong Liu Peng Peng Yiyun Chen Shan He Kang Yang |
| author_sort | Xiaomi Wang |
| collection | DOAJ |
| description | Crop recognition with high accuracy at a large scale is hampered by the spatial heterogeneity of crop growth characteristics under the complex influence of environmental conditions. With the aim to automatically realize large-scale crop classification with high accuracy, this study proposes an automatic crop classification strategy considering spatial heterogeneity (ACCSH) by combining the geographic detector technique, random forest average accuracy model, and random forest classification model. In ACCSH, spectral and textural indexes that can quantify crop growth characteristics and environmental variables with potential driving effects are first calculated. Next, an adaptive spatial heterogeneity mining method based on the geographic detector technique is proposed to mine spatial homogeneous zones adaptively with significant differentiation of crop growth characteristics. Subsequently, in view of the differences in crop growth characteristics and key classification indexes between spatial homogeneous zones, correlation analysis, and random forest average accuracy are combined to optimize classification indexes independently within each zone. Finally, random forest is used to classify the target crop in each spatial homogeneous zone separately. The proposed ACCSH is applied to automatically recognize crop types, specifically wheat and corn, in northern France. Results show that kappa coefficients of wheat and corn using ACCSH are 15% and 26% higher than those of classifications at the global scale, respectively. In addition, the index optimization strategy in ACCSH shows apparent superiority. Kappa coefficients of wheat and corn are 5–18% and 9–42% higher than those of classifications based on non-optimized indexes, respectively. In general, ACCSH can automatically realize crop classification with a high precision that suggests its reliability. |
| first_indexed | 2024-03-09T01:43:26Z |
| format | Article |
| id | doaj.art-d33ea048f4114906be00300b76b03d4d |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-09T01:43:26Z |
| publishDate | 2023-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-d33ea048f4114906be00300b76b03d4d2023-12-08T15:24:59ZengMDPI AGRemote Sensing2072-42922023-11-011523555010.3390/rs15235550Automatic Crop Classification Based on Optimized Spectral and Textural Indexes Considering Spatial HeterogeneityXiaomi Wang0Jiuhong Liu1Peng Peng2Yiyun Chen3Shan He4Kang Yang5School of Geographic Sciences, Hunan Normal University, 36 Lushan Road, Changsha 410081, ChinaSchool of Geographic Sciences, Hunan Normal University, 36 Lushan Road, Changsha 410081, ChinaSchool of Geographic Sciences, Hunan Normal University, 36 Lushan Road, Changsha 410081, ChinaSchool of Resource and Environment Science, Wuhan University, 129 Luoyu Road, Wuhan 430079, ChinaSchool of Geographic Sciences, Hunan Normal University, 36 Lushan Road, Changsha 410081, ChinaGuizhou Zhiyuan Engineering Technology Consulting Co., Ltd., Xingzhu West Road, Guiyang 550081, ChinaCrop recognition with high accuracy at a large scale is hampered by the spatial heterogeneity of crop growth characteristics under the complex influence of environmental conditions. With the aim to automatically realize large-scale crop classification with high accuracy, this study proposes an automatic crop classification strategy considering spatial heterogeneity (ACCSH) by combining the geographic detector technique, random forest average accuracy model, and random forest classification model. In ACCSH, spectral and textural indexes that can quantify crop growth characteristics and environmental variables with potential driving effects are first calculated. Next, an adaptive spatial heterogeneity mining method based on the geographic detector technique is proposed to mine spatial homogeneous zones adaptively with significant differentiation of crop growth characteristics. Subsequently, in view of the differences in crop growth characteristics and key classification indexes between spatial homogeneous zones, correlation analysis, and random forest average accuracy are combined to optimize classification indexes independently within each zone. Finally, random forest is used to classify the target crop in each spatial homogeneous zone separately. The proposed ACCSH is applied to automatically recognize crop types, specifically wheat and corn, in northern France. Results show that kappa coefficients of wheat and corn using ACCSH are 15% and 26% higher than those of classifications at the global scale, respectively. In addition, the index optimization strategy in ACCSH shows apparent superiority. Kappa coefficients of wheat and corn are 5–18% and 9–42% higher than those of classifications based on non-optimized indexes, respectively. In general, ACCSH can automatically realize crop classification with a high precision that suggests its reliability.https://www.mdpi.com/2072-4292/15/23/5550crop classificationspatial heterogeneityautomaticspectral indexestextural indexes |
| spellingShingle | Xiaomi Wang Jiuhong Liu Peng Peng Yiyun Chen Shan He Kang Yang Automatic Crop Classification Based on Optimized Spectral and Textural Indexes Considering Spatial Heterogeneity Remote Sensing crop classification spatial heterogeneity automatic spectral indexes textural indexes |
| title | Automatic Crop Classification Based on Optimized Spectral and Textural Indexes Considering Spatial Heterogeneity |
| title_full | Automatic Crop Classification Based on Optimized Spectral and Textural Indexes Considering Spatial Heterogeneity |
| title_fullStr | Automatic Crop Classification Based on Optimized Spectral and Textural Indexes Considering Spatial Heterogeneity |
| title_full_unstemmed | Automatic Crop Classification Based on Optimized Spectral and Textural Indexes Considering Spatial Heterogeneity |
| title_short | Automatic Crop Classification Based on Optimized Spectral and Textural Indexes Considering Spatial Heterogeneity |
| title_sort | automatic crop classification based on optimized spectral and textural indexes considering spatial heterogeneity |
| topic | crop classification spatial heterogeneity automatic spectral indexes textural indexes |
| url | https://www.mdpi.com/2072-4292/15/23/5550 |
| work_keys_str_mv | AT xiaomiwang automaticcropclassificationbasedonoptimizedspectralandtexturalindexesconsideringspatialheterogeneity AT jiuhongliu automaticcropclassificationbasedonoptimizedspectralandtexturalindexesconsideringspatialheterogeneity AT pengpeng automaticcropclassificationbasedonoptimizedspectralandtexturalindexesconsideringspatialheterogeneity AT yiyunchen automaticcropclassificationbasedonoptimizedspectralandtexturalindexesconsideringspatialheterogeneity AT shanhe automaticcropclassificationbasedonoptimizedspectralandtexturalindexesconsideringspatialheterogeneity AT kangyang automaticcropclassificationbasedonoptimizedspectralandtexturalindexesconsideringspatialheterogeneity |