Integrating Unmanned Aerial Vehicle-Derived Vegetation and Texture Indices for the Estimation of Leaf Nitrogen Concentration in Drip-Irrigated Cotton under Reduced Nitrogen Treatment and Different Plant Densities
The accurate assessment of nitrogen (N) status is important for N management and yield improvement. The N status in plants is affected by plant densities and N application rates, while the methods for assessing the N status in drip-irrigated cotton under reduced nitrogen treatment and different plan...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-01-01
|
| Series: | Agronomy |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4395/14/1/120 |
| _version_ | 1827372944207118336 |
|---|---|
| author | Minghua Li Yang Liu Xi Lu Jiale Jiang Xuehua Ma Ming Wen Fuyu Ma |
| author_facet | Minghua Li Yang Liu Xi Lu Jiale Jiang Xuehua Ma Ming Wen Fuyu Ma |
| author_sort | Minghua Li |
| collection | DOAJ |
| description | The accurate assessment of nitrogen (N) status is important for N management and yield improvement. The N status in plants is affected by plant densities and N application rates, while the methods for assessing the N status in drip-irrigated cotton under reduced nitrogen treatment and different plant densities are lacking. Therefore, this study was conducted with four different N treatments (195.5, 299, 402.5, and 506 kg N ha<sup>−1</sup>) and three sowing densities (6.9 × 10<sup>4</sup>, 13.8 × 10<sup>4</sup>, and 24 × 10<sup>4</sup> plants ha<sup>−1</sup>) by using a low-cost Unmanned Aerial Vehicle (UAV) system to acquire RGB imagery at a 10 m flight altitude at cotton main growth stages. We evaluated the performance of different ground resolutions (1.3, 2.6, 5.2, 10.4, 20.8, 41.6, 83.2, and 166.4 cm) for image textures, vegetation indices (VIs), and their combination for leaf N concentration (LNC) estimation using four regression methods (stepwise multiple linear regression, SMLR; support vector regression, SVR; extreme learning machine, ELM; random forest, RF). The results showed that combining VIs (ExGR, GRVI, GBRI, GRRI, MGRVI, RGBVI) and textures (VAR, HOM, CON, DIS) yielded higher estimation accuracy than using either alone. Specifically, the RF regression models had a higher accuracy and stability than SMLR and the other two machine learning algorithms. The best accuracy (R<sup>2</sup> = 0.87, RMSE = 3.14 g kg<sup>−1</sup>, rRMSE = 7.00%) was obtained when RF was applied in combination with VIs and texture. Thus, the combination of VIs and textures from UAV images using RF could improve the estimation accuracy of drip-irrigated cotton LNC and may have a potential contribution in the rapid and non-destructive nutrition monitoring and diagnosis of other crops or other growth parameters. |
| first_indexed | 2024-03-08T11:08:37Z |
| format | Article |
| id | doaj.art-9576afabe11847f69ce3df211e744e6c |
| institution | Directory Open Access Journal |
| issn | 2073-4395 |
| language | English |
| last_indexed | 2024-03-08T11:08:37Z |
| publishDate | 2024-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Agronomy |
| spelling | doaj.art-9576afabe11847f69ce3df211e744e6c2024-01-26T14:25:04ZengMDPI AGAgronomy2073-43952024-01-0114112010.3390/agronomy14010120Integrating Unmanned Aerial Vehicle-Derived Vegetation and Texture Indices for the Estimation of Leaf Nitrogen Concentration in Drip-Irrigated Cotton under Reduced Nitrogen Treatment and Different Plant DensitiesMinghua Li0Yang Liu1Xi Lu2Jiale Jiang3Xuehua Ma4Ming Wen5Fuyu Ma6School of Agriculture, Shihezi University, Shihezi 843000, ChinaSchool of Agriculture, Shihezi University, Shihezi 843000, ChinaSchool of Agriculture, Shihezi University, Shihezi 843000, ChinaSchool of Agriculture, Shihezi University, Shihezi 843000, ChinaSchool of Agriculture, Shihezi University, Shihezi 843000, ChinaSchool of Agriculture, Gansu Agriculture University, Lanzhou 730070, ChinaSchool of Agriculture, Shihezi University, Shihezi 843000, ChinaThe accurate assessment of nitrogen (N) status is important for N management and yield improvement. The N status in plants is affected by plant densities and N application rates, while the methods for assessing the N status in drip-irrigated cotton under reduced nitrogen treatment and different plant densities are lacking. Therefore, this study was conducted with four different N treatments (195.5, 299, 402.5, and 506 kg N ha<sup>−1</sup>) and three sowing densities (6.9 × 10<sup>4</sup>, 13.8 × 10<sup>4</sup>, and 24 × 10<sup>4</sup> plants ha<sup>−1</sup>) by using a low-cost Unmanned Aerial Vehicle (UAV) system to acquire RGB imagery at a 10 m flight altitude at cotton main growth stages. We evaluated the performance of different ground resolutions (1.3, 2.6, 5.2, 10.4, 20.8, 41.6, 83.2, and 166.4 cm) for image textures, vegetation indices (VIs), and their combination for leaf N concentration (LNC) estimation using four regression methods (stepwise multiple linear regression, SMLR; support vector regression, SVR; extreme learning machine, ELM; random forest, RF). The results showed that combining VIs (ExGR, GRVI, GBRI, GRRI, MGRVI, RGBVI) and textures (VAR, HOM, CON, DIS) yielded higher estimation accuracy than using either alone. Specifically, the RF regression models had a higher accuracy and stability than SMLR and the other two machine learning algorithms. The best accuracy (R<sup>2</sup> = 0.87, RMSE = 3.14 g kg<sup>−1</sup>, rRMSE = 7.00%) was obtained when RF was applied in combination with VIs and texture. Thus, the combination of VIs and textures from UAV images using RF could improve the estimation accuracy of drip-irrigated cotton LNC and may have a potential contribution in the rapid and non-destructive nutrition monitoring and diagnosis of other crops or other growth parameters.https://www.mdpi.com/2073-4395/14/1/120leaf nitrogen concentrationmachine learning algorithmsUAVtexturevegetation index |
| spellingShingle | Minghua Li Yang Liu Xi Lu Jiale Jiang Xuehua Ma Ming Wen Fuyu Ma Integrating Unmanned Aerial Vehicle-Derived Vegetation and Texture Indices for the Estimation of Leaf Nitrogen Concentration in Drip-Irrigated Cotton under Reduced Nitrogen Treatment and Different Plant Densities Agronomy leaf nitrogen concentration machine learning algorithms UAV texture vegetation index |
| title | Integrating Unmanned Aerial Vehicle-Derived Vegetation and Texture Indices for the Estimation of Leaf Nitrogen Concentration in Drip-Irrigated Cotton under Reduced Nitrogen Treatment and Different Plant Densities |
| title_full | Integrating Unmanned Aerial Vehicle-Derived Vegetation and Texture Indices for the Estimation of Leaf Nitrogen Concentration in Drip-Irrigated Cotton under Reduced Nitrogen Treatment and Different Plant Densities |
| title_fullStr | Integrating Unmanned Aerial Vehicle-Derived Vegetation and Texture Indices for the Estimation of Leaf Nitrogen Concentration in Drip-Irrigated Cotton under Reduced Nitrogen Treatment and Different Plant Densities |
| title_full_unstemmed | Integrating Unmanned Aerial Vehicle-Derived Vegetation and Texture Indices for the Estimation of Leaf Nitrogen Concentration in Drip-Irrigated Cotton under Reduced Nitrogen Treatment and Different Plant Densities |
| title_short | Integrating Unmanned Aerial Vehicle-Derived Vegetation and Texture Indices for the Estimation of Leaf Nitrogen Concentration in Drip-Irrigated Cotton under Reduced Nitrogen Treatment and Different Plant Densities |
| title_sort | integrating unmanned aerial vehicle derived vegetation and texture indices for the estimation of leaf nitrogen concentration in drip irrigated cotton under reduced nitrogen treatment and different plant densities |
| topic | leaf nitrogen concentration machine learning algorithms UAV texture vegetation index |
| url | https://www.mdpi.com/2073-4395/14/1/120 |
| work_keys_str_mv | AT minghuali integratingunmannedaerialvehiclederivedvegetationandtextureindicesfortheestimationofleafnitrogenconcentrationindripirrigatedcottonunderreducednitrogentreatmentanddifferentplantdensities AT yangliu integratingunmannedaerialvehiclederivedvegetationandtextureindicesfortheestimationofleafnitrogenconcentrationindripirrigatedcottonunderreducednitrogentreatmentanddifferentplantdensities AT xilu integratingunmannedaerialvehiclederivedvegetationandtextureindicesfortheestimationofleafnitrogenconcentrationindripirrigatedcottonunderreducednitrogentreatmentanddifferentplantdensities AT jialejiang integratingunmannedaerialvehiclederivedvegetationandtextureindicesfortheestimationofleafnitrogenconcentrationindripirrigatedcottonunderreducednitrogentreatmentanddifferentplantdensities AT xuehuama integratingunmannedaerialvehiclederivedvegetationandtextureindicesfortheestimationofleafnitrogenconcentrationindripirrigatedcottonunderreducednitrogentreatmentanddifferentplantdensities AT mingwen integratingunmannedaerialvehiclederivedvegetationandtextureindicesfortheestimationofleafnitrogenconcentrationindripirrigatedcottonunderreducednitrogentreatmentanddifferentplantdensities AT fuyuma integratingunmannedaerialvehiclederivedvegetationandtextureindicesfortheestimationofleafnitrogenconcentrationindripirrigatedcottonunderreducednitrogentreatmentanddifferentplantdensities |