Accurate classification of fresh and charred grape seeds to the varietal level, using machine learning based classification method

Image-based classification of wheat spikes by glume pubescence using convolutional neural networks

Introduction

Pubescence is an important phenotypic trait observed in both vegetative and generative plant organs. Pubescent plants demonstrate increased resistance to various environmental stresses such as drought, low temperatures, and pests. It serves as a significant morphological marker and aids in selecting stress-resistant cultivars, particularly in wheat. In wheat, pubescence is visible on leaves, leaf sheath, glumes and nodes. Regarding glumes, the presence of pubescence plays a pivotal role in its classification. It supplements other spike characteristics, aiding in distinguishing between different varieties within the wheat species. The determination of pubescence typically involves visual analysis by an expert. However, methods without the use of binocular loupe tend to be subjective, while employing additional equipment is labor-intensive. This paper proposes an integrated approach to determine glume pubescence presence in spike images captured under laboratory conditions using a digital camera and convolutional neural networks.

Methods

Initially, image segmentation is conducted to extract the contour of the spike body, followed by cropping of the spike images to an equal size. These images are then classified based on glume pubescence (pubescent/glabrous) using various convolutional neural network architectures (Resnet-18, EfficientNet-B0, and EfficientNet-B1). The networks were trained and tested on a dataset comprising 9,719 spike images.

Results

For segmentation, the U-Net model with EfficientNet-B1 encoder was chosen, achieving the segmentation accuracy IoU = 0.947 for the spike body and 0.777 for awns. The classification model for glume pubescence with the highest performance utilized the EfficientNet-B1 architecture. On the test sample, the model exhibited prediction accuracy parameters of F1 = 0.85 and AUC = 0.96, while on the holdout sample it showed F1 = 0.84 and AUC = 0.89. Additionally, the study investigated the relationship between image scale, artificial distortions, and model prediction performance, revealing that higher magnification and smaller distortions yielded a more accurate prediction of glume pubescence.

Disentangling the origins of viticulture in the western Mediterranean

We present direct evidence of early grape domestication in southern Italy via a multidisciplinary study of pip assemblage from one site, shedding new light on the spread of viticulture in the western Mediterranean during the Bronze Age. This consist of 55 waterlogged pips from Grotta di Pertosa, a Middle Bronze Age settlement in the south of the Italian peninsula. Direct radiocarbon dating of pips was carried out, confirming the chronological consistency of the samples with their archaeological contexts (ca. 1450-1200 BCE). The extraordinary state of conservation of the sample allowed to perform geometric morphometric (GMM) and paleogenetic analyses (aDNA) at the same time. The combination of the two methods has irrefutably shown the presence of domestic grapevines, together with wild ones, in Southern Italy during the Middle/Late Bronze Age. The results converge towards an oriental origin of the domestic grapes, most likely arriving from the Aegean area through the Mycenaeans. A parent/offspring kinship was also recognised between a domestic/wild hybrid individual and a domestic clonal group. This data point out a little known aspect of the diffusion of the first viticulture in Italy, and therefore in the western Mediterranean, which involved the hybridization between imported domestic varieties with, likely local, wild vines.

A Review of Ampelometry: Morphometric Characterization of the Grape (Vitis spp.) Leaf

Grape (Vitis spp.) is one of the most important horticultural crops, cultivated worldwide on more than 7.3 million hectares for various purposes such as winemaking, fresh fruit consumption, rootstock, and ornamental plants. Based on the inter- and intraspecific morphological variability, several descriptor lists, manuals and ampelographic studies are available for identification. Among the organs, leaves have the most traits, while the young shoot, bunch and berry are also important in the characterization of the genotypes. Vitis species and cultivars are described by leaf morphological characterization developed in many ways for the identification of genotypes, to clarify synonymies and distinct clones or evaluate the diversity of wild Vitis taxa. Morphometric-also known as ampelometric-evaluation has an extensive background in the literature. However, for some reasons, only a part of the literature is cited, despite its significant scientific value. In this paper, we summarize the efforts of metric characterization of the grapevine leaf with the introduction of the scientific objectives and reviewing the studies showing the innovations in phenotyping during the past 120 years.

Morphological Traits Evaluated with Random Forest Method Explains Natural Classification of Grapevine (Vitis vinifera L.) Cultivars

There are hundreds of morphologic and morphometric traits available to classify and identify grapevine (Vitis vinifera L.) genotypes, while statistical evaluation of those has certain limitations, especially when we have no information about the traits that are discriminative to a certain sample set. High numbers of investigated characters could cause redundancy, while reducing those numbers may result in data loss. Grapevine is one of the most important horticultural crops, with many cultivars in production. The characterization of the genotypes is of undeniably high importance. In this study, we analyzed a dataset of scientific and historical importance with 125 morphological traits of 97 grapevine cultivars described by Németh in 1966. However, the traits are not independent in a set of a large number of categorical traits with too few cultivars. Therefore, the number of traits was first reduced using a simple and effective algorithm to eliminate traits with redundant information content using the asymmetric measure of association Goodman and Kruskal's λ. We reduced the number of traits from 125 to 59 without any information loss. For the classification, we applied a random forest (RF) method. In this way, 93% of the cultivars were correctly classified using only four traits of the data set. To our knowledge, only a few studies applied a trait elimination algorithm similar to ours in ampelography that can be used for other biological data sets of similar structure. The classification results give a morphological explanation to several cultivars from the Carpathian Basin, a territory where all three Vitis vinifera L. geographical groups, occidentalis, orientalis and pontica, are represented. We found that the information-loss-avoiding data reduction method we applied in our study solved the redundancy-caused interdependencies and provided a suitable dataset for classifying grapevine genotypes. For example, this method may successfully be applied in digital image analysis-based traditional morphometric investigations in ampelography.

Morphotype broadening of the grapevine (Vitis vinifera L.) from Oxus civilization 4000 BP, Central Asia

The region of Transoxiana underwent an early agricultural-demographic transition leading to the earliest proto-urban centers in Central Asia. The agronomic details of this cultural shift are still poorly studied, especially regarding the role that long-generation perennials, such as grapes, played in the cultivation system. In this paper, we present directly dated remains of grape pips from the early urban centers of Sapalli and Djarkutan, in south Uzbekistan. We also present linear morphometric data, which illustrate a considerable range of variation under cultivation that we divide into four distinct morphotypes according to pip shape. While some of the pips in these two assemblages morphologically fall within the range of wild forms, others more closely resemble modern domesticated populations. Most of the specimens measure along a gradient between the two poles, showing a mixed combination of domesticated and wild features. We also point out that the seeds recovered from the Djarkutan temple were, on average, larger and contained more affinity towards domesticated forms than those from domestic contexts. The potential preference of morphotypes seems to suggest that there were recognized different varieties that local cultivators might aware and possibly propagating asexually.