Artificial Neural Network to Predict Vine Water Status Spatial Variability Using Multispectral Information Obtained from an Unmanned Aerial Vehicle (UAV)

作     者：Poblete, Tomas Ortega-Farias, Samuel Angel Moreno, Miguel Bardeen, Matthew 

作者机构：Univ Talca CITRA Casilla 747 Talca 3460000 Chile Univ Talca Res Program Adaptat Agr Climate Change A2C2 Casilla 747 Talca 3460000 Chile Univ Castilla La Mancha Reg Ctr Water Res Campus Univ S-N Albacete 02071 Spain Univ Talca Fac Ingn Curico 3340000 Chile 

出 版 物：《SENSORS》 (传感器)

年 卷 期：2017年第17卷第11期

页      面：2488-2488页

核心收录：

学科分类：0710[理学-生物学] 071010[理学-生物化学与分子生物学] 0808[工学-电气工程] 07[理学] 0804[工学-仪器科学与技术] 0703[理学-化学] 

基　　金：Chilean government through the project CONICYT-PFCHA [2014-21140229] Chilean government through the project FONDECYT Universidad de Talca through the research program Adaptation of Agriculture to Climate Change (A2C2) Spanish Ministry of Education and Science (MEC) [AGL2011-30328-C02-01, AGL2014-59747-C2-1-R] FEDER 

主　　题：multispectral image processing artificial neural network UAV midday stem water potential 

摘      要：Water stress, which affects yield and wine quality, is often evaluated using the midday stem water potential ((stem)). However, this measurement is acquired on a per plant basis and does not account for the assessment of vine water status spatial variability. The use of multispectral cameras mounted on unmanned aerial vehicle (UAV) is capable to capture the variability of vine water stress in a whole field scenario. It has been reported that conventional multispectral indices (CMI) that use information between 500-800 nm, do not accurately predict plant water status since they are not sensitive to water content. The objective of this study was to develop artificial neural network (ANN) models derived from multispectral images to predict the (stem) spatial variability of a drip-irrigated Carmenere vineyard in Talca, Maule Region, Chile. The coefficient of determination (R-2) obtained between ANN outputs and ground-truth measurements of (stem) were between 0.56-0.87, with the best performance observed for the model that included the bands 550, 570, 670, 700 and 800 nm. Validation analysis indicated that the ANN model could estimate (stem) with a mean absolute error (MAE) of 0.1 MPa, root mean square error (RMSE) of 0.12 MPa, and relative error (RE) of -9.1%. For the validation of the CMI, the MAE, RMSE and RE values were between 0.26-0.27 MPa, 0.32-0.34 MPa and -24.2-25.6%, respectively.