An integrated UAV growth monitoring model of Cinnamomum camphora based on whale optimization algorithm

• Published in: PloS one Vol. 19; no. 6; p. e0299362
• Main Authors: Gong, Rongxin, Zhang, Haina, Lu, Xianghui, Wan, Haolong, Zhang, Yue, Luo, Xin, Zhang, Jie, Xie, Rongxiu
• Format: Journal Article
• Language: English
• Published: United States Public Library of Science 21.06.2024; Public Library of Science (PLoS)
• Subjects: Accuracy; Agricultural production; Algorithms; Analysis; Animals; Artificial neural networks; Back propagation networks; Biology and Life Sciences; Biomass; Cameras; Chlorophyll; Cinnamomum camphora; Cinnamomum camphora - growth & development; Coefficient of variation; Computer and Information Sciences; Drone aircraft; Engineering and Technology; Essential oils; Forestry; Growth; Indicators; Leaf area; Leaf area index; Least-Squares Analysis; Marine mammals; Mathematical optimization; Monitoring; Neural networks; Neural Networks, Computer; Nitrogen; Oils & fats; Optimization; Optimization algorithms; Petroleum industry; Phosphorus content; Physical Sciences; Plant Leaves - growth & development; Potassium; Propagation; Radial basis function; Reflectance; Remote sensing; Research and Analysis Methods; Rice; Software; Soil - chemistry; Soil analysis; Spectral reflectance; Support vector machines; Unmanned Aerial Devices; Unmanned aerial vehicles; Vegetation; Weighting methods; Wheat; China
• ISSN: 1932-6203; 1932-6203
• DOI: 10.1371/journal.pone.0299362

To explore an effective analysis model and method for estimating Cinnamomum camphora ’s ( C . camphora ’s) growth using unmanned aerial vehicle (UAV) multispectral technology, we obtained C . camphora ’s canopy spectral reflectance using a UAV-mounted multispectral camera and simultaneously measured four single-growth indicators: Soil and Plant Analyzer Development (SPAD)value, aboveground biomass (AGB), plant height (PH), and leaf area index (LAI). The coefficient of variation and equal weighting methods were used to construct the comprehensive growth monitoring indicators (CGMI) for C . camphora . A multispectral inversion model of integrated C . camphora growth was established using the multiple linear regression (MLR), partial least squares (PLS), support vector regression (SVR), random forest (RF), radial basis function neural network (RBFNN), back propagation neural network (BPNN), and whale optimization algorithm (WOA)-optimized BPNN models. The optimal model was selected based on the coefficient of determination (R 2 ), normalized root mean square error (NRMSE) and mean absolute percentage error (MAPE). Our findings indicate that apparent differences in the accuracy with different model, and the WOA–BPNN model is the best model to invert the growth potential of C . camphora , the R 2 of the model test set was 0.9020, the RMSE was 0.0722, and the MAPE was 7%. The R 2 of the WOA–BPNN model improved by 18%, the NRMSE decreased by 33%, and the MAPE decreased by 9% compared with the BPNN model. This study provides technical support for the modern field management of C . camphora essential oil and other dwarf forestry industries.