TY - JOUR
T1 - Grape leaf moisture prediction from UAVs using multimodal data fusion and machine learning
AU - Peng, Xuelian
AU - Ma, Yuxin
AU - Sun, Jun
AU - Chen, Dianyu
AU - Zhen, Jingbo
AU - Zhang, Zhitao
AU - Hu, Xiaotao
AU - Wang, Yakun
N1 - Publisher Copyright:
© The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.
PY - 2024/6/1
Y1 - 2024/6/1
N2 - To quickly and accurately obtain the moisture status of grape plants at the field scale, the treatments included three irrigation levels i.e. W3 (100%M, M as the irrigation quota), W2 (75% M) and W1 (50%M) and four fertilizer application rates i.e. F0 (0 kg/hm2), F1 (324 kg/hm2), F2 (486 kg/hm2) and F3 (648 kg/hm2). Grape leaf water content (LWC) was monitored nondestructively by an unmanned aerial vehicle (UAV) carrying multispectral (MS), visible light (RGB) and thermal infrared (TIR) cameras to extract band reflectance (BR), canopy coverage (CC) and canopy temperature (T) information, respectively. Using BR (included six bands: B, R, G, RE, NIR800, and NIR900), CC and T and their combinations as input variables brought into the partial least squares (PLS), random forest (RF), support vector machine (SVM) and extreme learning machine (ELM) algorithms. The prediction models for grape LWC were established by using four machine learning algorithms, and the optimal combination of variables was finally determined. The results represented that (1) the model built with BR + CC + T as predictor variables under different water treatments was better than other combinations of variables, with the coefficient of determination (R2) above 0.69 and the relative root mean square error (RRMSE) less than 2.5%; (2) modeling the LWC of grapes at different fertility periods based on the combination of BR + CC + T, the R2 ranged from 0.51 to 0.78 at the shoot-growing, anthesis, and fruit-inflating stages; (3) the top three important variables were T, NIR800, and NIR900 in the shoot-growing, anthesis, and fruit-inflating stages, while the top three important variables were RE, B, and T in the fruit-inflating stage. In summary, UAV multimodal data fusion has good application in predicting the LWC of grapes using RF algorithm modeling during the different growth stages. This study can supply a technical support for precise management of vineyard water regime using a UAV platform.
AB - To quickly and accurately obtain the moisture status of grape plants at the field scale, the treatments included three irrigation levels i.e. W3 (100%M, M as the irrigation quota), W2 (75% M) and W1 (50%M) and four fertilizer application rates i.e. F0 (0 kg/hm2), F1 (324 kg/hm2), F2 (486 kg/hm2) and F3 (648 kg/hm2). Grape leaf water content (LWC) was monitored nondestructively by an unmanned aerial vehicle (UAV) carrying multispectral (MS), visible light (RGB) and thermal infrared (TIR) cameras to extract band reflectance (BR), canopy coverage (CC) and canopy temperature (T) information, respectively. Using BR (included six bands: B, R, G, RE, NIR800, and NIR900), CC and T and their combinations as input variables brought into the partial least squares (PLS), random forest (RF), support vector machine (SVM) and extreme learning machine (ELM) algorithms. The prediction models for grape LWC were established by using four machine learning algorithms, and the optimal combination of variables was finally determined. The results represented that (1) the model built with BR + CC + T as predictor variables under different water treatments was better than other combinations of variables, with the coefficient of determination (R2) above 0.69 and the relative root mean square error (RRMSE) less than 2.5%; (2) modeling the LWC of grapes at different fertility periods based on the combination of BR + CC + T, the R2 ranged from 0.51 to 0.78 at the shoot-growing, anthesis, and fruit-inflating stages; (3) the top three important variables were T, NIR800, and NIR900 in the shoot-growing, anthesis, and fruit-inflating stages, while the top three important variables were RE, B, and T in the fruit-inflating stage. In summary, UAV multimodal data fusion has good application in predicting the LWC of grapes using RF algorithm modeling during the different growth stages. This study can supply a technical support for precise management of vineyard water regime using a UAV platform.
KW - Data fusion
KW - Leaf water content prediction
KW - Machine learning
KW - Multimodality
KW - UAV
UR - https://www.scopus.com/pages/publications/85188528060
U2 - 10.1007/s11119-024-10127-y
DO - 10.1007/s11119-024-10127-y
M3 - Article
AN - SCOPUS:85188528060
SN - 1385-2256
VL - 25
SP - 1609
EP - 1635
JO - Precision Agriculture
JF - Precision Agriculture
IS - 3
ER -