Dual Activation Function-Based Extreme Learning Machine (ELM) for Estimating Grapevine Berry Yield and Quality

Abstract

Reliable assessment of grapevine productivity is a destructive and time-consuming process. In addition, the mixed effects of grapevine water status and scion-rootstock interactions on grapevine productivity are not always linear. Despite the potential opportunity of applying remote sensing and machine learning techniques to predict plant traits, there are still limitations to previously studied techniques for vine productivity due to the complexity of the system not being adequately modeled. During the 2014 and 2015 growing seasons, hyperspectral reflectance spectra were collected using a handheld spectroradiometer in a vineyard designed to investigate the effects of irrigation level (0%, 50%, and 100%) and rootstocks (1103 Paulsen, 3309 Couderc, SO4 and Chambourcin) on vine productivity. To assess vine productivity, it is necessary to measure factors related to fruit ripeness and not just yield, as an over cropped vine may produce high-yield but poor-quality fruit. Therefore, yield, Total Soluble Solids (TSS), Titratable Acidity (TA) and the ratio TSS/TA (maturation index, IMAD) were measured. A total of 20 vegetation indices were calculated from hyperspectral data and used as input for predictive model calibration. Prediction performance of linear/nonlinear multiple regression methods and Weighted Regularized Extreme Learning Machine (WRELM) were compared with our newly developed WRELM-TanhRe. The developed method is based on two activation functions: hyperbolic tangent (Tanh) and rectified linear unit (ReLU). The results revealed that WRELM and WRELM-TanhRe outperformed the widely used multiple regression methods when model performance was tested with an independent validation dataset. WRELM-TanhRe produced the highest prediction accuracy for all the berry yield and quality parameters (R2 of 0.522–0.682 and RMSE of 2–15%), except for TA, which was predicted best with WRELM (R2 of 0.545 and RMSE of 6%). The results demonstrate the value of combining hyperspectral remote sensing and machine learning methods for improving of berry yield and quality prediction.

Early Detection of Plant Viral Disease Using Hyperspectral Imaging and Deep Learning

“…PSRI is closely related to carotenoid and mesophyll cell structures [ 63 , 82 ], Ant Gitelson (values of 550, 700, and 780 nm) is closely related to anthocyanin [ 52 ], and WSCT (values of 850 and 970 nm) is closely related to the canopy water content and temperature [ 77 ]. Previous studies also showed that the NPQI was important for early detection of Xylella fastidiosa (Xf)-affected olive trees [ 83 ], that FRI 1 was important for identification of water-stressed soybean plants [ 84 ] and to estimate grapevine berry yield and quality [ 36 ], that PSRI was critically needed to characterize the spectra of peanut leaf spot disease [ 85 ], that Ant Gitelson was necessary for identifying tomato spotted wilt virus (TSWV) in capsicum plants [ 86 ], and that water-related indices were essential for more accurate detection of citrus canker disease [ 26 ].…”

“…To reduce spectral data to manageable low-dimensional data, the most widely used approaches are spectral band selection and data transforms. The former approach is used to choose a discrete number of key wavelengths at various positions in the spectrum to calculate representative indices (e.g., vegetation Indices) [ 21 , 35 , 36 ]. As the band selection approach preserve as much spectral information as possible, the data transform approach utilizes a transformation to compact the data into a new optimal size.…”

Combination of an Automated 3D Field Phenotyping Workflow and Predictive Modelling for High-Throughput and Non-Invasive Phenotyping of Grape Bunches

“…Thus, it is reasonable to compare different regression models. In various disciplines, there are examples where the comparison of different regression models revealed wider or only slighter differences between models [56][57][58][59].…”

Sentinel-2 Validation for Spatial Variability Assessment in Overhead Trellis System Viticulture Versus UAV and Agronomic Data

“…The knowledge of spatial and temporal variability improves all aspects of vineyard management such as ground sampling, vines status monitoring, fertilizer distribution, phytosanitary treatments, weed control, and quality-selective harvesting [2,[11][12][13]. In the last three decades, advances in proximal and remote sensing technologies have provided useful and cost-effective solutions to better characterize in-field variability [14][15][16][17][18][19].…”