A novel ground truth multispectral image dataset with weight, anthocyanins, and Brix index measures of grape berries tested for its utility in machine learning pipelines.

BACKGROUND: The combination of computer vision devices such as multispectral cameras coupled with artificial intelligence has provided a major leap forward in image-based analysis of biological processes. Supervised artificial intelligence algorithms require large ground truth image datasets for model training, which allows to validate or refute research hypotheses and to carry out comparisons between models. However, public datasets of images are scarce and ground truth images are surprisingly few considering the numbers required for training algorithms. RESULTS: We created a dataset of 1,283 multidimensional arrays, using berries from five different grape varieties. Each array has 37 images of wavelengths between 488.38 and 952.76 nm obtained from single berries. Coupled to each multispectral image, we added a dataset with measurements including, weight, anthocyanin content, and Brix index for each independent grape. Thus, the images have paired measures, creating a ground truth dataset. We tested the dataset with 2 neural network algorithms: multilayer perceptron (MLP) and 3-dimensional convolutional neural network (3D-CNN). A perfect (100% accuracy) classification model was fit with either the MLP or 3D-CNN algorithms. CONCLUSIONS: This is the first public dataset of grape ground truth multispectral images. Associated with each multispectral image, there are measures of the weight, anthocyanins, and Brix index. The dataset should be useful to develop deep learning algorithms for classification, dimensionality reduction, regression, and prediction analysis.

The Effect of Post-harvest Conditions in Narcissus sp. Cut Flowers Scent Profile.

Narcissus flowers are used as cut flowers and to obtain high quality essential oils for the perfume industry. As a winter crop in the Mediterranean area, it flowers at temperatures ranging between 10 and 15°C during the day and 3-10°C during the night. Here we tested the impact of different light and temperature conditions on scent quality during post-harvest. These two types of thermoperiod and photoperiod. We also used constant darkness and constant temperatures. We found that under conditions of 12:12 Light Dark and 15-5°C, Narcissus emitted monoterpenes and phenylpropanoids. Increasing the temperature to 20°-10°C in a 12:12 LD cycle caused the loss of cinnamyl acetate and emission of indole. Under constant dark, there was a loss of scent complexity. Constant temperatures of 20°C caused a decrease of scent complexity that was more dramatic at 5°C, when the total number of compounds emitted decreased from thirteen to six. Distance analysis confirmed that 20°C constant temperature causes the most divergent scent profile. We found a set of four volatiles, benzyl acetate, eucalyptol, linalool, and ocimene that display a robust production under differing environmental conditions, while others were consistently dependent on light or thermoperiod. Scent emission changed significantly during the day and between different light and temperature treatments. Under a light:dark cycle and 15-5°C the maximum was detected during the light phase but this peak shifted toward night under 20-10°C. Moreover, under constant darkness the peak occurred at midnight and under constant temperature, at the end of night. Using Machine Learning we found that indole was the volatile with a highest ranking of discrimination followed by D-limonene. Our results indicate that light and temperature regimes play a critical role in scent quality. The richest scent profile is obtained by keeping flowers at 15°-5°C thermoperiod and a 12:12 Light Dark photoperiod.