No abstract

No abstract

Digitalization in agriculture requires critical research into applications of artificial intelligence to various specialization domains. This work aimed at investigating the application of image synthesis technology to the mitigation of the data volume constraint to digital plant disease phenotyping accuracy. We designed an experiment involving the use of a deep convolutional generative adversarial network (DC-GAN) to synthesize photorealistic data for healthy and bacterial spot disease-infected tomato leaves. The training dataset contained 1,272 instances per class. We further employed a 3-block visual geometry group (VGG) convolutional neural network (CNN) model with dropout regularization and 1 epoch to compare classification accuracies of the original dataset and various synthetic datasets. Our results showed that the third DC-GAN synthesized training dataset containing 3,816 synthetic examples of both healthy and bacterial spot infected tomato leaf classes outperformed the original training dataset containing 1,272 real examples of both tomato leaf classes (77.088% accuracy with the former dataset on a 3-block VGG CNN model with dropout regularization and 1 epoch, as compared to 76.447% accuracy with the latter dataset on the same classifier).

The oil palm (Elaeis guineensis Jacq.) is one of the major cultivated crops among the economically important palm species. It is cultivated mainly for its edible oil. For a perennial crop like oil palm, the use of Marker Assisted Selection (MAS) techniques helps to reduce the breeding cycle and improve the economic products. Genetic and physical maps are important for sequencing experiments since they show the exact positions of genes and other distinctive features in the chromosomal DNA. This review focuses on the role of genome mapping in oil palm breeding. It assesses the role of genome mapping in oil palm breeding and discusses the major factors affecting such mapping. Generating a high-density map governed by several factors, for instance, marker type, marker density, number of mapped population, and software used are the major issues treated. The general conclusion is that genome mapping is pivotal in the construction of a genetic linkage map. It helps to detect QTL and identify genes that control quantitative traits in oil palm. In perspective, the use of high-density molecular markers with a large number of markers, a large number mapping population, and up-to-date software is necessary for oil palm genome mapping.

Watermelon (Citrullus lanatus) is one of the most popular fruits in Cameroon and the world at large. However, the extreme sensitivity of watermelon to parasites and climatic vagaries makes its cultivation demanding of chemical inputs that can have negative impacts on human health and the environment. In Cameroon, there is a slow improvement of fruit yield in watermelon breeding due to the lack of natural heritable genetic variation, which is a prerequisite for genetic improvement of crops. Such variation can be created through either random or targeted processes on genotypes with appropriate doses of radiation. Genetic improvement by induced mutagenesis appears today alongside hybridization as an alternative method of creating new plant varieties. However, the success of this approach is determined by the application of an appropriate and ideal dose of mutagen. The objective of this study was to evaluate the radiosensitivity of the two most cultivated watermelon varieties in Cameroon to gamma radiation from 60 Co in order to determine an optimal dose or lethal dose 50 (LD50) for the induction of the genetic variability necessary for genetic improvement. Seeds of the Kaolack and Crimson sweet watermelon varieties were irradiated with five doses of gamma radiation (100, 200, 300, 400 and 600 Gy) in the laboratory of the International Atomic Energy Agency in Seibersdorf, Austria. These seeds were cultivated in a greenhouse following an utterly randomized device with three repetitions, and parameters such as the germination rate, the survival rate and the shoot length of plants were evaluated. High rates of 90% and 75% germination were obtained, respectively, for the control treatments of Kaolack and Crimson sweet, while the lowest rates were 35% at 600 Gy for Kaolack and 30% at 400 Gy for Crimson sweet. The highest survival rate of plants (96.66%) was obtained with the control seeds of the Kaolack. This variety had the lowest survival rate (45.6%) at 600 Gy dose. Statistical analysis of data obtained helped to estimate the ideal LD50 doses based on growth reduction of seedlings' heights after gamma-ray treatment. Using a linear regression model based on parameters like plant size, the LD50 doses for Kaolack and Crimson sweet were calculated at 225.40 Gy and 221.56 Gy, respectively, and predicted between 200 and 250 Gy. These results show that the two varieties evaluated were radiosensitive as clearly expressed in the parameters evaluated, where the values decreased with the increase in the irradiation dose. The LD50 doses from this study could be safely applied as reference doses for large-scale gamma irradiation of watermelon genotypes to create desirable agronomic traits in the mutation breeding efforts.