Search

Artificial intelligence techniques are now widely used in various agricultural applications, including the detection of devastating diseases such as late blight (Phytophthora infestans) and early blight (Alternaria solani) affecting potato (Solanum tuberorsum L.) crops. In this paper, we present a mobile application for detecting potato crop diseases based on deep neural networks. The images were taken from the PlantVillage dataset with a batch of 1000 images for each of the three identified classes (healthy, early blight-diseased, late blight-diseased). An exploratory analysis of the architectures used for early and late blight diagnosis in potatoes was performed, achieving an accuracy of 98.7%, with MobileNetv2. Based on the results obtained, an offline mobile application was developed, supported on devices with Android 4.1 or later, also featuring an information section on the 27 diseases affecting potato crops and a gallery of symptoms. For future work, segmentation techniques will be used to highlight the damaged region in the potato leaf by evaluating its extent and possibly identifying different types of diseases affecting the same plant. [ABSTRACT FROM AUTHOR]

Highly pathogenic avian influenza (HPAI) is a major global animal health problem with public health implications. The aim of this study was to estimate the magnitude of the consequences of HPAI virus incursion in Cuba and the effectiveness of the main control measures. A spatial stochastic model was used to represent biological, environmental and human interaction processes involved in transmission. NAADSM (v.3.3.2) tool was used for parameterization and simulation of the outbreak, and R (v. 3.5) tool for statistical analysis of outbreaks. Four hundred sixty-seven poultry farms in 216 scenarios were processed by evaluating 20 parameters associated with probability functions or linear models to represent the epidemic process of Susceptible-Infectious-Removed (SIR) model in the population studied. Simulation showed depopulation was able to stop the outbreak in all scenarios; however, the greatest animal losses were evident in scenarios with poor biosecurity, slow detection speed and reduced movement restriction. Adjacent farms within a 5 km radius had a significantly higher risk of spreading the virus to a greater extent. The model suggests that it is possible to contain the spread of HPAI virus if detection is reached within three days post-infection, and depopulation is completed within six days. [ABSTRACT FROM AUTHOR]

The objective of this work was to determine the probable occurrence of the mixed infection phytoplasma - BGYMV in Phaselous vulgaris L. and the symptoms associated. This probability was calculated using classical probability and a smoothed adjustment of the series of not centered moving median was used to estimate the presence of a mixed infection in two close points. The conditional probabilities of a mixed infection knowing the a priori probabilities of phytoplasma and begomovirus were calculated using the classical formula of probability. The influence of present symptoms in the agricultural ecosystem on the probability of this mixed infection to increase and its association with the vector presence were evaluated using principal component analysis and canonical discriminate test. The occurence of a mixed infection was more probable when it was known a priori that the phytoplasma was present than when it was the begomovirus. Symptoms in the bean crop associated with the mixed infection were wrinkled leaves, mosaic, and reduced size of the leaves. Even in the presence of the vector, leaf chlorosis and deformation were associated with a low probability of mixed infection, which suggested the presence of a unique virus or another disease. We suggest that this association can be used in the prediction of mixed diseases as an initial prognosis leading to a rapid diagnosis with reduced costs due to a better selection of samples. [ABSTRACT FROM AUTHOR]

Phytoplasmas are associated with two papaya diseases in Cuba, Papaya Bunchy Top (PBT) and Bunchy Top Symptoms (BTS), which decrease fruit production. Assessment of the 16S ribosomal DNA by nested PCR, conventional RFLP, sequencing and in silico RFLP analyses allowed the identification of a new phytoplasma subgroup designated BTSp-16SrI-Z associated with BTS disease in the eastern region of the country. BTSp-16SrI-Z subgroup was detected in 60.42 % of the surveyed plants with crown leaf chlorosis and necrosis of the young leaves. Results confirmed that this phytoplasma strain was consistently associated with the observed BTS symptoms, implying new epidemiological constraints for the disease management. [ABSTRACT FROM AUTHOR]