Journal Articles

Permanent URI for this collectionhttps://mro.massey.ac.nz/handle/10179/7915

Browse

Author: search.filters.author.Sandoval EHas files: Yes

Search Results

Now showing 1 - 9 of 9
  • Thumbnail Image
    Item
    Synthetic hyperspectral reflectance data augmentation by generative adversarial network to enhance grape maturity determination
    (Elsevier B V, 2025-08) Lyu H; Grafton M; Ramilan T; Irwin M; Sandoval E
    Non-destructive and rapid grape maturity detection is important for the wine industry. The ongoing development of hyperspectral imaging techniques and deep learning methods has greatly helped in non-destructive assessing of grape quality and maturity, but the performance of deep learning methods depends on the volume and the quality of labeled data for training. Building non-destructive grape quality or maturity testing datasets requires damaging grapes for chemical analysis to produce labels which are time consuming and resource intensive. To solve this problem, this study proposed a conditional Wasserstain Generative Adversarial Network (WGAN) with the gradient penalty data augmentation technique to generate synthetic hyperspectral reflectance data of two grape maturity categories (ripe and unripe) and different Total Soluble Solids (TSS) values. The conditional WGAN with the gradient penalty was trained for a range of epochs: 500, 1000, 2000, 8000, 10,000, and 20,000. After training of 10,000 epochs, synthetic hyperspectral reflectance data were very similar to real spectra for each maturity category and different TSS values. Thereafter, contextual deep three-dimensional CNN (3D-CNN), Spatial Residual Network (SSRN) and Support Vector Machine (SVM) are trained on original training and syn- thetic + original training datasets to classify grape maturity. The synthetic hyperspectral reflectance data, incrementally added to the original training set in steps of 250, 500, 1000, 1500, and 2000 samples, consistently resulted in higher model performance compared to training solely on the original dataset. The best results were achieved by augmenting the training dataset with 2000 synthetic samples and training with a 3D-CNN, yielding a classification accuracy of 91 % on the testing set. To better assess the effectiveness of GAN-based data augmentation methods, two widely used regression models: Partial Least Squares Regression (PLSR) and one-dimensional CNN (1D-CNN) were used based on same data augmentation method. The best result was achieved by adding 250 synthetic samples to the original training set when training 1D-CNN model, yielding an R2 of 0.78, RMSE of 0.63 ◦Brix, and RPIQ of 3.36 on the testing set. This study indicated that deep learning models combined with conditional WGAN with the gradient penalty data augmentation technique had a good application prospect in the grape maturity assessment.
  • Thumbnail Image
    Item
    Non-destructive and on-site estimation of grape total soluble solids by field spectroscopy and stack ensemble learning
    (Elsevier, 2025-02-20) Lyu H; Grafton M; Ramilan T; Irwin M; Sandoval E
  • Thumbnail Image
    Item
    Assessing the Leaf Blade Nutrient Status of Pinot Noir Using Hyperspectral Reflectance and Machine Learning Models
    (MDPI (Basel, Switzerland), 2023-03-08) Lyu H; Grafton M; Ramilan T; Irwin M; Sandoval E; Díaz-Varela RA
    Monitoring grape nutrient status, from flowering to veraison, is important for viticulturists when implementing vineyard management strategies, in order to produce quality wines. However, traditional methods for measuring nutrient elements incur high labour costs. The aim of this study is to explore the potential of predicting grapevine leaf blade nutrient concentration based on hyperspectral data. Leaf blades were collected at two Pinot Noir commercial vineyards at Martinborough, New Zealand. The leaf blade spectral data were obtained with a handheld spectroradiometer, to evaluate surface reflectance and derivative spectra in the spectrum range between 400 and 2400 nm. Afterwards, leaf blades nutrient concentrations (N, P, K, Ca, and Mg) were measured, and their relationships with the hyperspectral data were modelled by machine learning models; partial least squares regression (PLSR), random forest regression (RFR), and support vector regression (SVR) were used. Pearson correlation and recursive feature elimination, based on cross-validation, were used as feature selection methods for RFR and SVR, to improve the model’s performance. The variable importance score of PLSR, and permutation variable importance of RFR and SVR, were used to determine the most sensitive wavelengths, or spectral regions related to each biochemical variable. The results showed that the best predictive performance for leaf blade N concentration was based on PLSR to raw reflectance data (R2 = 0.66; RMSE = 0.15%). The combination of support vector regression with the Pearson correlation selected method and second derivative reflectance provided a high accuracy for K and Ca modelling (R2 = 0.7; RMSE = 0.06%; R2 = 0.62; RMSE = 0.11%, respectively). However, the modelling performance for P and Mg, by different feature groups and variable selection methods, was poor (R2 = 0.15; RMSE = 0.02%; R2 = 0.43; RMSE = 0.43%, respectively). Thus, a larger dataset is needed for improving the prediction of P and Mg. The results indicated that for Pinot Noir leaf blades, raw reflectance data had potential for the prediction of N concentration, while the second-derivative spectra were more suitable to predict K and Ca. This study led to the provision of rapid and non-destructive measurements of grapevine leaf nutrient status.
  • Thumbnail Image
    Item
    Using Remote and Proximal Sensing Data and Vine Vigor Parameters for Non-Destructive and Rapid Prediction of Grape Quality
    (MDPI (Basel, Switzerland), 2023-11-19) Lyu H; Grafton M; Ramilan T; Irwin M; Wei H-E; Sandoval E; Zhang C; Liu D
    The traditional method for determining wine grape total soluble solid (TSS) is destructive laboratory analysis, which is time consuming and expensive. In this study, we explore the potential of using different predictor variables from various advanced techniques to predict the grape TSS in a non-destructive and rapid way. Calculating Pearson’s correlation coefficient between the vegetation indices (VIs) obtained from UAV multispectral imagery and grape TSS resulted in a strong correlation between OSAVI and grape TSS with a coefficient of 0.64. Additionally, seven machine learning models including ridge regression and lasso regression, k-Nearest neighbor (KNN), support vector regression (SVR), random forest regression (RFR), extreme gradient boosting (XGBoost), and artificial neural network (ANN) are used to build the prediction models. The predictor variables include the unmanned aerial vehicles (UAV) derived VIs, and other ancillary variables including normalized difference vegetation index (NDVI_proximal) and soil electrical conductivity (ECa) measured by proximal sensors, elevation, slope, trunk circumference, and day of the year for each sampling date. When using 23 VIs and other ancillary variables as input variables, the results show that ensemble learning models (RFR, and XGBoost) outperform other regression models when predicting grape TSS, with the average of root mean square error (RMSE) of 1.19 and 1.2 °Brix, and coefficient of determination (R2) of 0.52 and 0.52, respectively, during the 20 times testing process. In addition, this study examines the prediction performance of using optimized soil adjusted vegetation index (OSAVI) or normalized green-blue difference index (NGBDI) as the main input for different machine learning models with other ancillary variables. When using OSAVI-based models, the best prediction model is RFR with an average R2 of 0.51 and RMSE of 1.19 °Brix, respectively. For NGBDI-based model, the RFR model showed the best average result of predicting TSS were a R2 of 0.54 and a RMSE of 1.16 °Brix, respectively. The approach proposed in this study provides an opportunity to grape growers to estimate the whole vineyard grape TSS in a non-destructive way.
  • Thumbnail Image
    Item
    Hyperspectral Imaging Spectroscopy for Non-Destructive Determination of Grape Berry Total Soluble Solids and Titratable Acidity
    (MDPI AG, 2024-05-07) Lyu H; Grafton M; Ramilan T; Irwin M; Sandoval E; Krasuki K; Weirzbicki D
  • Thumbnail Image
    Item
    Using Remote and Proximal Sensing Data and Vine Vigor Parameters for Non-Destructive and Rapid Prediction of Grape Quality
    (MDPI AG, 2023-11-19) Lyu H; Grafton M; Ramilan T; Irwin M; Wei H-E; Sandoval E; Zhang C; Liu D
    The traditional method for determining wine grape total soluble solid (TSS) is destructive laboratory analysis, which is time consuming and expensive. In this study, we explore the potential of using different predictor variables from various advanced techniques to predict the grape TSS in a non-destructive and rapid way. Calculating Pearson’s correlation coefficient between the vegetation indices (VIs) obtained from UAV multispectral imagery and grape TSS resulted in a strong correlation between OSAVI and grape TSS with a coefficient of 0.64. Additionally, seven machine learning models including ridge regression and lasso regression, k-Nearest neighbor (KNN), support vector regression (SVR), random forest regression (RFR), extreme gradient boosting (XGBoost), and artificial neural network (ANN) are used to build the prediction models. The predictor variables include the unmanned aerial vehicles (UAV) derived VIs, and other ancillary variables including normalized difference vegetation index (NDVI_proximal) and soil electrical conductivity (ECa) measured by proximal sensors, elevation, slope, trunk circumference, and day of the year for each sampling date. When using 23 VIs and other ancillary variables as input variables, the results show that ensemble learning models (RFR, and XGBoost) outperform other regression models when predicting grape TSS, with the average of root mean square error (RMSE) of 1.19 and 1.2 ◦Brix, and coefficient of determination (R2 ) of 0.52 and 0.52, respectively, during the 20 times testing process. In addition, this study examines the prediction performance of using optimized soil adjusted vegetation index (OSAVI) or normalized green-blue difference index (NGBDI) as the main input for different machine learning models with other ancillary variables. When using OSAVI-based models, the best prediction model is RFR with an average R2 of 0.51 and RMSE of 1.19 ◦Brix, respectively. For NGBDI-based model, the RFR model showed the best average result of predicting TSS were a R2 of 0.54 and a RMSE of 1.16 ◦Brix, respectively. The approach proposed in this study provides an opportunity to grape growers to estimate the whole vineyard grape TSS in a non-destructive way.
  • Thumbnail Image
    Item
    Evaluation of the use of two-stage calibrated PlanetScope images and environmental variables for the development of the grapevine water status prediction model
    (24/05/2023) Wei H-E; Grafton M; Bretherton M; Irwin M; Sandoval E
    Abstract Grapevine water status (GWS) assessment between flowering and veraison plays an important role in viticulture management in terms of producing high-quality grapes. Although satellites and uncrewed aerial vehicles (UAV) have successfully monitored GWS, these platforms are practically limited because data transfer is delayed due to post processing and UAV operation is weather dependent. This study focuses on addressing two issues: the unreliability of GWS estimation using satellite images with low-moderate spatial resolution and the inaccessibility of real-time satellite data. It aims to predict the temporal variation of GWS based on a prediction model using spectral information (calibrated PlanetScope (PS) images), soil/topography data (apparent electrical conductivity, elevation, slope), weather parameters (rainfall and potential evapotranspiration), cultivation practices (irrigation, fertigation, plucking, and trimming), and seasonality (day of the year) as predictors. Stem water potential (Ψstem) was used as a proxy for GWS. Two-stage calibration, including an initial calibration of UAV images with measured Ψstem and a subsequent calibration of satellite images with calibrated UAV data, was applied to calibrate the PS images. Three machine learning models (random forest regression, support vector regression, and multilayer perceptron) were used in the calibration and modeling process. The results showed that a two-stage calibration can generate reliable reference data, with a root mean square error of 113 kPa and 59 kPa on the test sets during the first and second calibration stage, respectively. The prediction model described the temporal variation of block Ψstem when compared with the measured Ψstem. In the similarity analysis, the Pearson correlation coefficient was 0.89 and 0.87 between predicted and reference Ψstem maps across four dates for the two study vineyards. This study supports the concept of developing an approach to predict grapevine Ψstem, which would enable growers to acquire Ψstem variation in advance during the growing season, leading to improved irrigation scheduling and optimal grape quality.
  • Thumbnail Image
    Item
  • Thumbnail Image
    Item
    Evaluation of Point Hyperspectral Reflectance and Multivariate Regression Models for Grapevine Water Status Estimation
    (MDPI AG, 12/08/2021) Wei H-E; Grafton M; Bretherton M; Irwin M; Sandoval E
    Monitoring and management of plant water status over the critical period between flower-ing and veraison, plays a significant role in producing grapes of premium quality. Hyperspectral spectroscopy has been widely studied in precision farming, including for the prediction of grapevine water status. However, these studies were presented based on various combinations of transformed spectral data, feature selection methods, and regression models. To evaluate the performance of different modeling pipelines for estimating grapevine water status, a study spanning the critical period was carried out in two commercial vineyards at Martinborough, New Zealand. The modeling used six hyperspectral data groups (raw reflectance, first derivative reflectance, second derivative reflectance, continuum removal variables, simple ratio indices, and vegetation indices), two variable selection methods (Spearman correlation and recursive feature elimination based on cross-validation), an ensemble of selected variables, and three regression models (partial least squares regression, random forest regression, and support vector regression). Stem water potential (used as a proxy for vine water status) was measured by a pressure bomb. Hyperspectral reflectance was undertaken by a handheld spectroradiometer. The results show that the best predictive performance was achieved by applying partial least squares regression to simple ratio indices (R2 = 0.85; RMSE = 110 kPa). Models trained with an ensemble of selected variables comprising multicombination of transformed data and variable selection approaches outperformed those fitted using single combinations. Although larger data sizes are needed for further testing, this study compares 38 modeling pipelines and presents the best combination of procedures for estimating vine water status. This may lead to the provision of rapid estimation of vine water status in a nondestructive manner and highlights the possibility of applying hyperspectral data to precision irrigation in vineyards.