Plant diseases can cause a significant decrease in tea crop production. Early disease detection can help to minimize the loss. For tea plants, experts can identify the diseases by visual inspection on the leaves. However, providing experts to deal with disease identification may be very costly. The machine learning technology can be implemented to provide automatic plant disease detection. Currently, deep learning is state-of-the-art for object identification in computer vision. In this study, the researchers propose the Convolutional Neural Network (CNN) for tea disease detections. The researchers focus on the implementation of concatenated CNN, namely GoogleNet, Xception, and Inception-ResNet-v2, for this task. About 4727 images of tea leaves are collected, comprising of three types of diseases that commonly occur in Indonesia and a healthy class. The experimental results confirm the effectiveness of concatenated CNN for tea disease detections. The accuracy of 89.64% is achieved.

<p><em>Tea (</em>Camellia sinensis<em> (L.) O. Kuntze) is a cross-pollinated plant that has self-incompatible character. Assembly of superior clones through artificial pollination requires information of genetic relationships between accessions as a reference for parental lines selection. The study was aimed to determine the genetic diversity and relationships of 49 tea clones based on leaf morphology and yield components. The research was conducted at Pasir Sarongge experimental garden, Cianjur, West Java, from April to November 2015. The observed morphological characters were leaf length and width, leaf area, leaf angle, number of vein leaf, and internode between first and second leaves. Meanwhile, yield components were pecco number, pecco weight (p+3), banji bud number, banji bud weigth (b+1), and yield. The data were then used for descriptive analysis and grouping using UPGMA method based on dissimilarity matrix by XL-STAT software version 2009. The research showed that 49 clones observed here have variability on yield, leaf area, number of banji bud, and pecco number with coefficient of diversity 27.77%–51.83%. On the other hand, result of cluster analysis divided tea clones into four groups. The first group consisted of 34 clones with morphological characteristics similar to sinensis type (narrow leaves and low productivity). Group II comprised 12 clones with morphological characteristics (wide leaf) and productivity (high) similar to assamica type. Group III and IV, each contained one clone, and have similarity to assamica. The most far genetic relationships was found between group I and II (55.59%), while the closest one observed between group III and IV (5.76%).</em></p>

The objectives of this study were to compare nonparametric stability measures, and to identify promising high yield and stability of chili pepper (Capsicum annuum L.) genotypes in eight environments. In every environment, a Randomized Complete Block Design was used with three replications. The method of Nassar and Huehn, Kang, Fox, and Thennarasu was used to analyze the stability and high yield. Spearman's correlation and Principal Component analysis distinguishes the methods based on two different concepts of stability: the static (biological) and dynamic (agronomic) concepts. The top method was found to be the dynamic stability. Meanwhile, the methods of Si 1 , Si 2 , Si 3 , Si 6 , Npi 1 , NPi 2 , NPi 3 and NPi 4 were found to be the static stability. Based on the ranking frequency stability of the nonparametric method, the genotypes with the highest frequency of static stability ranking were genotypes IPB002003, IPB002046, IPB009019 and Tit Super, whereas IPB009002 and Tombak were categorized as those of dynamic stability. Genotype IPB120005 and IPB019015 were less adaptable in the multiple environments tested. It shows that the genotypes were specific in certain environments. IPB120005 had high yield and specific location in Boyolali in dry season and IPB019015 genotype was specific in Bogor in wet season.

Tea clone of Gambung series is a superior variety of tea that has high productivity and quality. Smallholder farmers usually plant these clones in the same areas. However, each clone has different productivity or quality, so it is difficult to predict the production quality in the same area. To uniform the variety of clones in an area, smallholder farmers still need experts to identify each plant because one and other clones share the same visual characteristics. We propose a tea clone identification system using deep CNN with skip connection methods, i.e., residual connections and densely connections, to tackle this problem. Our study shows that the proposed method is affected by the hyperparameter setting and the combining feature maps method. For the combining method, the concatenation method on a densely connected network shows better performance than the summation method on a residual connected network.

Natural disasters, climate change[54] and plant diseases[51] are among many factors that threaten the food security. Plant diseases in particular, may cause great loss not only for farmers, but also for global economy. For instance, The International Potato Center (CIP) reports that around 15 % loss of potatoes production[24] is due to late blight diseases only. Globally, plant diseases cause more than 20 % crop loss annually[49]. The