Inversion of Soybean Net Photosynthetic Rate Based on UAV Multi-Source Remote Sensing and Machine Learning
Zhen Lu,
Wenbo Yao,
Shuangkang Pei,
Yuwei Lu,
Heng Liang,
Dong Xu,
Haiyan Li,
Lejun Yu,
Yonggang Zhou,
Qian Liu
Affiliations
Zhen Lu
Key Laboratory of Biomedical Engineering of Hainan Province, School of Biomedical Engineering, Hainan University, Haikou 570228, China
Wenbo Yao
School of Breeding and Multiplication, Sanya Institute of Breeding and Multiplication, Hainan University, Sanya 572025, China
Shuangkang Pei
School of Breeding and Multiplication, Sanya Institute of Breeding and Multiplication, Hainan University, Sanya 572025, China
Yuwei Lu
Britton Chance Center for Biomedical Photonics, Wuhan National Laboratory for Optoelectronics, Huazhong University of Science and Technology, Wuhan 430074, China
Heng Liang
Key Laboratory of Biomedical Engineering of Hainan Province, School of Biomedical Engineering, Hainan University, Haikou 570228, China
Dong Xu
Key Laboratory of Biomedical Engineering of Hainan Province, School of Biomedical Engineering, Hainan University, Haikou 570228, China
Haiyan Li
School of Breeding and Multiplication, Sanya Institute of Breeding and Multiplication, Hainan University, Sanya 572025, China
Lejun Yu
Key Laboratory of Biomedical Engineering of Hainan Province, School of Biomedical Engineering, Hainan University, Haikou 570228, China
Yonggang Zhou
School of Breeding and Multiplication, Sanya Institute of Breeding and Multiplication, Hainan University, Sanya 572025, China
Qian Liu
Key Laboratory of Biomedical Engineering of Hainan Province, School of Biomedical Engineering, Hainan University, Haikou 570228, China
Net photosynthetic rate (Pn) is a common indicator used to measure the efficiency of photosynthesis and growth conditions of plants. In this study, soybeans under different moisture gradients were selected as the research objects. Fourteen vegetation indices (VIS) and five canopy structure characteristics (CSC) (plant height (PH), volume (V), canopy cover (CC), canopy length (L), and canopy width (W)) were obtained using an unmanned aerial vehicle (UAV) equipped with three different sensors (visible, multispectral, and LiDAR) at five growth stages of soybeans. Soybean Pn was simultaneously measured manually in the field. The variability of soybean Pn under different conditions and the trend change of CSC under different moisture gradients were analysed. VIS, CSC, and their combinations were used as input features, and four machine learning algorithms (multiple linear regression, random forest, Extreme gradient-boosting tree regression, and ridge regression) were used to perform soybean Pn inversion. The results showed that, compared with the inversion model using VIS or CSC as features alone, the inversion model using the combination of VIS and CSC features showed a significant improvement in the inversion accuracy at all five stages. The highest accuracy (R2 = 0.86, RMSE = 1.73 µmol m−2 s−1, RPD = 2.63) was achieved 63 days after sowing (DAS63).
