A local model based on environmental variables clustering for estimating foliar phosphorus of rubber trees with vis-NIR spectroscopic data

Guo，Peng Tao1,2,3,4; Zhu，A. Xing5,6,7,8; Cha，Zheng Zao1,2,3,4; Li，Mao Fen9,10; Luo，Wei1,2,3,4

2022-06-01

10.1016/j.heliyon.2022.e09795

Heliyon   Impact Factor & Quartile

2405-8440

2405-8440

Existing local models based on multiple environmental variables clustering (LM-MEVC) treat the influences of environmental factors on leaf phosphorus concentration (LPC) of rubber trees (Hevea brasiliensis) equally when grouping samples. In fact, the effects that environmental factors assert on LPC are different. So, environmental factors need to be treated differently so that the different effects can be taken into consideration when dividing samples into clusters or groups. According to this basic idea, a local model based on weighted environmental variables clustering (LM-WEVC) was developed. This approach consists of four steps. Firstly, the most important environmental variables that influence LPC were selected. Then, the weights of the selected environmental variables were determined. In the following, the selected environmental variables were weighted and used as clustering variables to group samples. Finally, within each cluster or group of samples, an estimation model was established. In order to verify its effectiveness in predicting LPC of rubber trees, the proposed method was applied to a case study in Hainan Island, China. Rubber tree (cultivar CATAS-7-33-97) leaf samples were collected from three different sampling periods. Spectral reflectance of the collected leaf samples was measured using an ASD spectroradiometer, FieldSpec 3. Leaf samples collected from the three different sampling periods were used separately to test LM-WEVC. Coefficient of determination (R), root mean squared error (RMSE), and ratio of prediction deviation (RPD) were employed as evaluation criterion. Performance of LM-WEVC was compared with that of the existing LM-MEVC. Results indicated that for the three sampling periods, the prediction accuracies of LM-WEVC were always higher than those of LM-MEVC. The values of R and RPD for LM-WEVC were increased by 8.15%–36.68%, and by 11.33%–59.40% respectively, while values of RMSE were reduced by 9.09%–37.5%, compared with those for LM-MEVC. These results demonstrate that LM-WEVC was effective in estimating LPC of rubber trees, and also confirmed our hypothesis that environmental factors unequally influenced LPC of rubber trees.

Environmental factors Hyperspectral reflectance K-means clustering Partial least squares regression Regional scale

SCI

English

Corresponding

Hainan Provincial Natural Science Foundation of China[321RC656] ; National Natural Science Foundation of China[41871300] ; Opening Project Fund of Key Lab-oratory of Rubber Biology and Genetic Resource Utilization, Ministry of Agriculture and Rural Affairs[RRI-KLOF201803] ; National Technical System of Natural Rubber Industry[CARS-33-ZP-2]

Science & Technology - Other Topics

Multidisciplinary Sciences

WOS:000830142600001

ELSEVIER SCI LTD

2-s2.0-85133597173

Scopus

1.Rubber Research Institute,Chinese Academy of Tropical Agriculture Sciences,Haikou,Hainan,571101,China
2.Key Laboratory of Biology and Genetic Resources of Rubber Tree,Ministry of Agriculture and Rural Affairs,Haikou,Hainan,571101,China
3.State Key Laboratory Incubation Base for Cultivation & Physiology of Tropical Crops,Haikou,Hainan,571101,China
4.Soil and Fertilizer Research Center,Chinese Academy of Tropical Agriculture Sciences,Haikou,Hainan,571101,China
5.School of Geography Science,Nanjing Normal University,Nanjing,1 Wenyuan Road,210023,China
6.Department of Geography,University of Wisconsin-Madison,Madison,550 North Park Street,53706,United States
7.State Key Laboratory of Resources and Environmental Information System,Institute of Geographical Sciences and Natural Resources Research,Chinese Academy of Science,Beijing,11A Datun Road,100101,China
8.Center for Social Sciences,Southern University of Science and Technology,Shenzhen,China
9.Institute of Scientific and Technical Information,Chinese Academy of Tropical Agriculture Sciences,Haikou,Hainan,571101,China
10.Hainan Provincial Key Laboratory of Practical Research on Tropical Crops Information Technology,China

Guo，Peng Tao,Zhu，A. Xing,Cha，Zheng Zao,et al. A local model based on environmental variables clustering for estimating foliar phosphorus of rubber trees with vis-NIR spectroscopic data[J]. Heliyon,2022,8(6).

Guo，Peng Tao,Zhu，A. Xing,Cha，Zheng Zao,Li，Mao Fen,&Luo，Wei.(2022).A local model based on environmental variables clustering for estimating foliar phosphorus of rubber trees with vis-NIR spectroscopic data.Heliyon,8(6).

Guo，Peng Tao,et al."A local model based on environmental variables clustering for estimating foliar phosphorus of rubber trees with vis-NIR spectroscopic data".Heliyon 8.6(2022).