An Analysis of Plant Diseases Identification Based on Deep Learning Methods

Abstract

Plant disease is an important factor affecting crop yield. With various types and complex conditions, plant diseases cause serious economic losses, as well as modern agriculture constraints. Hence, rapid, accurate, and early identification of crop diseases is of great significance. Recent developments in deep learning, especially convolutional neural network (CNN), have shown impressive performance in plant disease classification. However, most of the existing datasets for plant disease classification are a single background environment rather than a real field environment. In addition, the classification can only obtain the category of a single disease and fail to obtain the location of multiple different diseases, which limits the practical application. Therefore, the object detection method based on CNN can overcome these shortcomings and has broad application prospects. In this study, an annotated apple leaf disease dataset in a real field environment was first constructed to compensate for the lack of existing datasets. Moreover, the Faster R-CNN and YOLOv3 architectures were trained to detect apple leaf diseases in our dataset. Finally, comparative experiments were conducted and a variety of evaluation indicators were analyzed. The experimental results demonstrate that deep learning algorithms represented by YOLOv3 and Faster R-CNN are feasible for plant disease detection and have their own strong points and weaknesses.

Influence of Temperature and Wetness on Taphrina deformans Ascospore and Blastospore Germination: Disease Forecasting and Validation

“…Different cultivars might respond differently to the same climate conditions, affecting the intensity of disease symptoms. In previous works, a modified version of the model developed by Giosue et al [10] was evaluated in the commercial peach orchards of Imathia, Northern Greece [9]. However, this model did not use data on the effect of environmental conditions on the germination of spores of native isolates of the fungus, resulting in a reduced accuracy of the model's indications compared to the models described in the present study.…”

“…Care was taken to ensure that the slides did not come into contact with the filter paper. The Petri dishes were sealed with parafilm and placed in chambers with controlled conditions for 12 h. Temperatures of −3, 0, 5,10,15,20,25,30,35 • C were tested to calculate the minimum, maximum, and optimal temperature for spore germination. The results were collected by recording the percentage of germination in 100 randomly selected ascospores and blastospores, respectively [6,7], using the formula described by Kardam et al [6].…”

“…The selection of an appropriate model depends on several factors, including the type of disease, the geographic region, the available data, and the desired level of accuracy [9]. Some of the commonly used modeling approaches for plant disease forecasting include statistical models, machine learning models, and simulation models [10][11][12]. Statistical models are a popular approach for plant disease forecasting because they can use historical data to identify patterns and relationships between environmental factors and disease incidence [13].…”