Sugarcane Biomass Prediction with Multi-Mode Remote Sensing Data Using Deep Archetypal Analysis and Integrated Learning
The use of multi-mode remote sensing data for biomass prediction is of potential value to aid planting management and yield maximization. In this study, an advanced biomass estimation approach for sugarcane fields is proposed based on multi-source remote sensing data. Since feature interpretability...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-10-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/14/19/4944 |
| _version_ | 1797477096522514432 |
|---|---|
| author | Zhuowei Wang Yusheng Lu Genping Zhao Chuanliang Sun Fuhua Zhang Su He |
| author_facet | Zhuowei Wang Yusheng Lu Genping Zhao Chuanliang Sun Fuhua Zhang Su He |
| author_sort | Zhuowei Wang |
| collection | DOAJ |
| description | The use of multi-mode remote sensing data for biomass prediction is of potential value to aid planting management and yield maximization. In this study, an advanced biomass estimation approach for sugarcane fields is proposed based on multi-source remote sensing data. Since feature interpretability in agricultural data mining is significant, a feature extraction method of deep archetypal analysis (DAA) that has good model interpretability is introduced and aided by principal component analysis (PCA) for feature mining from the multi-mode multispectral and light detection and ranging (LiDAR) remote sensing data pertaining to sugarcane. In addition, an integrated regression model integrating random forest regression, support vector regression, K-nearest neighbor regression and deep network regression is developed after feature extraction by DAA to precisely predict biomass of sugarcane. In this study, the biomass prediction performance achieved using the proposed integrated learning approach is found to be predominantly better than that achieved by using conventional linear methods in all the time periods of plant growth. Of more significance, according to model interpretability of DAA, only a small set of informative features maintaining their physical meanings (four informative spectral indices and four key LiDAR metrics) can be extracted which eliminates the redundancy of multi-mode data and plays a vital role in accurate biomass prediction. Therefore, the findings in this study provide hands-on experience to planters with indications of the key or informative spectral or LiDAR metrics relevant to the biomass to adjust the corresponding planting management design. |
| first_indexed | 2024-03-09T21:12:50Z |
| format | Article |
| id | doaj.art-3abd3a4e1d0349f9b1e82c2d207b0c2f |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-09T21:12:50Z |
| publishDate | 2022-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-3abd3a4e1d0349f9b1e82c2d207b0c2f2023-11-23T21:41:17ZengMDPI AGRemote Sensing2072-42922022-10-011419494410.3390/rs14194944Sugarcane Biomass Prediction with Multi-Mode Remote Sensing Data Using Deep Archetypal Analysis and Integrated LearningZhuowei Wang0Yusheng Lu1Genping Zhao2Chuanliang Sun3Fuhua Zhang4Su He5School of Computer Science and Technology, Guangdong University and Technology, Guangzhou 510006, ChinaSchool of Computer Science and Technology, Guangdong University and Technology, Guangzhou 510006, ChinaSchool of Computer Science and Technology, Guangdong University and Technology, Guangzhou 510006, ChinaInstitute of Agricultural Information, Jiangsu Academy of Agricultural Science, Nanjing 210014, ChinaBeijing Aerospace TITAN Technology Co., Ltd., Beijing 100070, ChinaCollege of Mechanical and Electrical Engineering, Inner Mongolia Agricultural University, Hohhot 010018, ChinaThe use of multi-mode remote sensing data for biomass prediction is of potential value to aid planting management and yield maximization. In this study, an advanced biomass estimation approach for sugarcane fields is proposed based on multi-source remote sensing data. Since feature interpretability in agricultural data mining is significant, a feature extraction method of deep archetypal analysis (DAA) that has good model interpretability is introduced and aided by principal component analysis (PCA) for feature mining from the multi-mode multispectral and light detection and ranging (LiDAR) remote sensing data pertaining to sugarcane. In addition, an integrated regression model integrating random forest regression, support vector regression, K-nearest neighbor regression and deep network regression is developed after feature extraction by DAA to precisely predict biomass of sugarcane. In this study, the biomass prediction performance achieved using the proposed integrated learning approach is found to be predominantly better than that achieved by using conventional linear methods in all the time periods of plant growth. Of more significance, according to model interpretability of DAA, only a small set of informative features maintaining their physical meanings (four informative spectral indices and four key LiDAR metrics) can be extracted which eliminates the redundancy of multi-mode data and plays a vital role in accurate biomass prediction. Therefore, the findings in this study provide hands-on experience to planters with indications of the key or informative spectral or LiDAR metrics relevant to the biomass to adjust the corresponding planting management design.https://www.mdpi.com/2072-4292/14/19/4944biomass predictionmulti-mode remote sensing datadeep archetypal analysisintegrated learning |
| spellingShingle | Zhuowei Wang Yusheng Lu Genping Zhao Chuanliang Sun Fuhua Zhang Su He Sugarcane Biomass Prediction with Multi-Mode Remote Sensing Data Using Deep Archetypal Analysis and Integrated Learning Remote Sensing biomass prediction multi-mode remote sensing data deep archetypal analysis integrated learning |
| title | Sugarcane Biomass Prediction with Multi-Mode Remote Sensing Data Using Deep Archetypal Analysis and Integrated Learning |
| title_full | Sugarcane Biomass Prediction with Multi-Mode Remote Sensing Data Using Deep Archetypal Analysis and Integrated Learning |
| title_fullStr | Sugarcane Biomass Prediction with Multi-Mode Remote Sensing Data Using Deep Archetypal Analysis and Integrated Learning |
| title_full_unstemmed | Sugarcane Biomass Prediction with Multi-Mode Remote Sensing Data Using Deep Archetypal Analysis and Integrated Learning |
| title_short | Sugarcane Biomass Prediction with Multi-Mode Remote Sensing Data Using Deep Archetypal Analysis and Integrated Learning |
| title_sort | sugarcane biomass prediction with multi mode remote sensing data using deep archetypal analysis and integrated learning |
| topic | biomass prediction multi-mode remote sensing data deep archetypal analysis integrated learning |
| url | https://www.mdpi.com/2072-4292/14/19/4944 |
| work_keys_str_mv | AT zhuoweiwang sugarcanebiomasspredictionwithmultimoderemotesensingdatausingdeeparchetypalanalysisandintegratedlearning AT yushenglu sugarcanebiomasspredictionwithmultimoderemotesensingdatausingdeeparchetypalanalysisandintegratedlearning AT genpingzhao sugarcanebiomasspredictionwithmultimoderemotesensingdatausingdeeparchetypalanalysisandintegratedlearning AT chuanliangsun sugarcanebiomasspredictionwithmultimoderemotesensingdatausingdeeparchetypalanalysisandintegratedlearning AT fuhuazhang sugarcanebiomasspredictionwithmultimoderemotesensingdatausingdeeparchetypalanalysisandintegratedlearning AT suhe sugarcanebiomasspredictionwithmultimoderemotesensingdatausingdeeparchetypalanalysisandintegratedlearning |