Poblete Tomas, Ortega-Farías Samuel, Moreno Miguel Angel, Bardeen Matthew
Centro de Investigación y Transferencia en Riego y Agroclimatología (CITRA), Universidad de Talca, Casilla 747, Talca 3460000, Chile.
Research program on Adaptation of Agriculture to Climate Change (A2C2), Universidad de Talca, Casilla 747, Talca 3460000, Chile.
Sensors (Basel). 2017 Oct 30;17(11):2488. doi: 10.3390/s17112488.
Water stress, which affects yield and wine quality, is often evaluated using the midday stem water potential (Ψ). 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 Ψ spatial variability of a drip-irrigated Carménère vineyard in Talca, Maule Region, Chile. The coefficient of determination (R²) obtained between ANN outputs and ground-truth measurements of Ψ 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 Ψ 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.
水分胁迫会影响产量和葡萄酒品质，通常使用午间茎水势（Ψ）进行评估。然而，这种测量是基于单株植物进行的，并未考虑葡萄藤水分状况空间变异性的评估。使用安装在无人机（UAV）上的多光谱相机能够在整个田间场景中捕捉葡萄藤水分胁迫的变异性。据报道，使用500 - 800 nm之间信息的传统多光谱指数（CMI）不能准确预测植物水分状况，因为它们对含水量不敏感。本研究的目的是开发基于多光谱图像的人工神经网络（ANN）模型，以预测智利马乌莱地区塔尔卡一个滴灌佳美娜葡萄园的Ψ空间变异性。ANN输出与Ψ地面真值测量之间获得的决定系数（R²）在0.56 - 0.87之间，包含550、570、670、700和800 nm波段的模型表现最佳。验证分析表明，ANN模型能够以平均绝对误差（MAE）0.1 MPa、均方根误差（RMSE）0.12 MPa和相对误差（RE）-9.1%来估计Ψ。对于CMI的验证，MAE、RMSE和RE值分别在0.26 - 0.27 MPa、0.32 - 0.34 MPa和-24.2 - 25.6%之间。
