Integrating Spectral, Textural, and Morphological Data for Potato LAI Estimation from UAV Images
The Leaf Area Index (LAI) is a crucial indicator of crop photosynthetic potential, which is of great significance in farmland monitoring and precision management. This study aimed to predict potato plant LAI for potato plant growth monitoring, integrating spectral, textural, and morphological data t...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-12-01
|
| Series: | Agronomy |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4395/13/12/3070 |
| _version_ | 1797382293508063232 |
|---|---|
| author | Mingbo Bian Zhichao Chen Yiguang Fan Yanpeng Ma Yang Liu Riqiang Chen Haikuan Feng |
| author_facet | Mingbo Bian Zhichao Chen Yiguang Fan Yanpeng Ma Yang Liu Riqiang Chen Haikuan Feng |
| author_sort | Mingbo Bian |
| collection | DOAJ |
| description | The Leaf Area Index (LAI) is a crucial indicator of crop photosynthetic potential, which is of great significance in farmland monitoring and precision management. This study aimed to predict potato plant LAI for potato plant growth monitoring, integrating spectral, textural, and morphological data through UAV images and machine learning. A new texture index named VITs was established by fusing multi-channel information. Vegetation growth features (Vis and plant height Hdsm) and texture features (TIs and VITs) were obtained from drone digital images. Various feature combinations (VIs, VIs + TIs, VIs + VITs, VIs + VITs + H<sub>dsm</sub>) in three growth stages were adopted to monitor potato plant LAI using Partial Least Squares Regression (PLSR), Support Vector Regression (SVR), random forest (RF), and eXtreme gradient boosting (XGBoost), so as to find the best feature combinations and machine learning method. The performance of the newly built VITs was tested. Compared with traditional TIs, the estimation accuracy was obviously improved for all the growth stages and methods, especially in the tuber-growth stage using the RF method with 13.6% of R<sup>2</sup> increase. The performance of H<sub>dsm</sub> was verified by including it either as one input feature or not. Results showed that H<sub>dsm</sub> could raise LAI estimation accuracy in every growth stage, whichever method is used. The most significant improvement appeared in the tuber-formation stage using SVR, with an 11.3% increase of R<sup>2</sup>. Considering both the feature combinations and the monitoring methods, the combination of VIs + VITs + H<sub>dsm</sub> achieved the best results for all the growth stages and simulation methods. The best fitting of LAI in tuber-formation, tuber-growth, and starch-accumulation stages had an R<sup>2</sup> of 0.92, 0.83, and 0.93, respectively, using the XGBoost method. This study showed that the combination of different features enhanced the simulation of LAI for multiple growth stages of potato plants by improving the monitoring accuracy. The method presented in this study can provide important references for potato plant growth monitoring. |
| first_indexed | 2024-03-08T21:04:18Z |
| format | Article |
| id | doaj.art-3bf8698b4950468486c476f7468b03a1 |
| institution | Directory Open Access Journal |
| issn | 2073-4395 |
| language | English |
| last_indexed | 2024-03-08T21:04:18Z |
| publishDate | 2023-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Agronomy |
| spelling | doaj.art-3bf8698b4950468486c476f7468b03a12023-12-22T13:46:51ZengMDPI AGAgronomy2073-43952023-12-011312307010.3390/agronomy13123070Integrating Spectral, Textural, and Morphological Data for Potato LAI Estimation from UAV ImagesMingbo Bian0Zhichao Chen1Yiguang Fan2Yanpeng Ma3Yang Liu4Riqiang Chen5Haikuan Feng6School of Surveying and Land Information Engineering, Henan Polytechnic University, Jiaozuo 454000, ChinaSchool of Surveying and Land Information Engineering, Henan Polytechnic University, Jiaozuo 454000, ChinaInformation Technology Research Center, Beijing Academy of Agriculture and Forestry Sciences, Beijing 100097, ChinaSchool of Surveying and Land Information Engineering, Henan Polytechnic University, Jiaozuo 454000, ChinaInformation Technology Research Center, Beijing Academy of Agriculture and Forestry Sciences, Beijing 100097, ChinaInformation Technology Research Center, Beijing Academy of Agriculture and Forestry Sciences, Beijing 100097, ChinaInformation Technology Research Center, Beijing Academy of Agriculture and Forestry Sciences, Beijing 100097, ChinaThe Leaf Area Index (LAI) is a crucial indicator of crop photosynthetic potential, which is of great significance in farmland monitoring and precision management. This study aimed to predict potato plant LAI for potato plant growth monitoring, integrating spectral, textural, and morphological data through UAV images and machine learning. A new texture index named VITs was established by fusing multi-channel information. Vegetation growth features (Vis and plant height Hdsm) and texture features (TIs and VITs) were obtained from drone digital images. Various feature combinations (VIs, VIs + TIs, VIs + VITs, VIs + VITs + H<sub>dsm</sub>) in three growth stages were adopted to monitor potato plant LAI using Partial Least Squares Regression (PLSR), Support Vector Regression (SVR), random forest (RF), and eXtreme gradient boosting (XGBoost), so as to find the best feature combinations and machine learning method. The performance of the newly built VITs was tested. Compared with traditional TIs, the estimation accuracy was obviously improved for all the growth stages and methods, especially in the tuber-growth stage using the RF method with 13.6% of R<sup>2</sup> increase. The performance of H<sub>dsm</sub> was verified by including it either as one input feature or not. Results showed that H<sub>dsm</sub> could raise LAI estimation accuracy in every growth stage, whichever method is used. The most significant improvement appeared in the tuber-formation stage using SVR, with an 11.3% increase of R<sup>2</sup>. Considering both the feature combinations and the monitoring methods, the combination of VIs + VITs + H<sub>dsm</sub> achieved the best results for all the growth stages and simulation methods. The best fitting of LAI in tuber-formation, tuber-growth, and starch-accumulation stages had an R<sup>2</sup> of 0.92, 0.83, and 0.93, respectively, using the XGBoost method. This study showed that the combination of different features enhanced the simulation of LAI for multiple growth stages of potato plants by improving the monitoring accuracy. The method presented in this study can provide important references for potato plant growth monitoring.https://www.mdpi.com/2073-4395/13/12/3070Leaf Area IndexUnmanned Aerial Vehiclepotatooptimized texture features indexfused feature modelmachine learning |
| spellingShingle | Mingbo Bian Zhichao Chen Yiguang Fan Yanpeng Ma Yang Liu Riqiang Chen Haikuan Feng Integrating Spectral, Textural, and Morphological Data for Potato LAI Estimation from UAV Images Agronomy Leaf Area Index Unmanned Aerial Vehicle potato optimized texture features index fused feature model machine learning |
| title | Integrating Spectral, Textural, and Morphological Data for Potato LAI Estimation from UAV Images |
| title_full | Integrating Spectral, Textural, and Morphological Data for Potato LAI Estimation from UAV Images |
| title_fullStr | Integrating Spectral, Textural, and Morphological Data for Potato LAI Estimation from UAV Images |
| title_full_unstemmed | Integrating Spectral, Textural, and Morphological Data for Potato LAI Estimation from UAV Images |
| title_short | Integrating Spectral, Textural, and Morphological Data for Potato LAI Estimation from UAV Images |
| title_sort | integrating spectral textural and morphological data for potato lai estimation from uav images |
| topic | Leaf Area Index Unmanned Aerial Vehicle potato optimized texture features index fused feature model machine learning |
| url | https://www.mdpi.com/2073-4395/13/12/3070 |
| work_keys_str_mv | AT mingbobian integratingspectraltexturalandmorphologicaldataforpotatolaiestimationfromuavimages AT zhichaochen integratingspectraltexturalandmorphologicaldataforpotatolaiestimationfromuavimages AT yiguangfan integratingspectraltexturalandmorphologicaldataforpotatolaiestimationfromuavimages AT yanpengma integratingspectraltexturalandmorphologicaldataforpotatolaiestimationfromuavimages AT yangliu integratingspectraltexturalandmorphologicaldataforpotatolaiestimationfromuavimages AT riqiangchen integratingspectraltexturalandmorphologicaldataforpotatolaiestimationfromuavimages AT haikuanfeng integratingspectraltexturalandmorphologicaldataforpotatolaiestimationfromuavimages |