Suspected Dickeya sp. strains were obtained from potato plants and tubers collected from commercial plots. The disease was observed on crops of various cultivars grown from seed tubers imported from the Netherlands during the spring seasons of 2004-2006, with disease incidence of 2-30% (10% in average). In addition to typical wilting symptoms on the foliage, in cases of severe infection, progeny tubers were rotten in the soil. Six strains were characterised by biochemical, serological and PCR-amplification. All tests verified the strains as Dickeya sp. The rep-PCR and the biochemical assays showed that the strains isolated from blackleg diseased plants in Israel were very similar, if not identical to strains isolated from Dutch seed potatoes, suggesting that the infection in Israel originated from the Dutch seed. The strains were distantly related to D. dianthicola strains, typically found in potatoes in Western Europe, and were similar to biovar 3 D. dadanti or D. zeae. This is the first time that the presence of biovar 3 strains in potato in the Netherlands is described. One of the strains was used for pathogenicity assays on potato cvs Nicola and Mondial. Symptoms appeared 2 to 3 days after stem inoculation, and 7 to 10 days after soil inoculation. The control plants treated with water, or plants inoculated with Pectobacterium carotovorum, did not develop any symptoms with either method of inoculation. The identity of Dickeya sp. and P. carotovorum re-isolated from inoculated plants was confirmed by PCR and ELISA.

Many plant diseases have distinct visual symptoms, which can be used to identify and classify them correctly. This article presents a potato disease classification algorithm that leverages these distinct appearances and advances in computer vision made possible by deep learning. The algorithm uses a deep convolutional neural network, training it to classify the tubers into five classes: namely, four disease classes and a healthy potato class. The database of images used in this study, containing potato tubers of different cultivars, sizes, and diseases, was acquired, classified, and labeled manually by experts. The models were trained over different train-test splits to better understand the amount of image data needed to apply deep learning for such classification tasks. The models were tested over a data set of images taken using standard low-cost RGB (red, green, and blue) sensors and were tagged by experts, demonstrating high classification accuracy. This is the first article to report the successful implementation of deep convolutional networks, popular in object identification, to the task of disease identification in potato tubers, showing the potential of deep learning techniques in agricultural tasks.

The response of five potato cultivars to Colletotrichum coccodes was tested in artificially inoculated fields for three consecutive spring and autumn seasons during 1994 to 1996. Significant yield reductions (22 to 30%) were observed in all tested cultivars. Results varied between years, but yield losses were more severe in autumn than in spring. Stem infections of plants were observed 90 days after planting on the surface of the stem and in vascular tissue. C. coccodes inoculation also resulted in reduction of the quality of daughter tubers. Cultivars Cara and Nicola were found to be less susceptible to tuber infection than Alpha, Desiree, and Agria. The incidence of diseased daughter tubers was higher when the soil was infested than when the foliage was inoculated. C. coccodes contamination of dry stems at harvest (in inoculated plots) was relatively high in all cultivars, with no difference between inoculation methods. Thus, C. coccodes infection not only affects potato yield and the quality of potatoes for seed and consumption, but also contaminates soil and serves as an important source of inoculum for future potato crops.

No abstract

Over a 5-year period (2006)(2007)(2008)(2009)(2010), 277 certified, visually healthy potato seed lots, imported from Europe to Israel for commercial use, were tested for Dickeya spp. latent infection by PCR analysis (277 seed lots) and ELISA (154 seed lots). Seeds from these lots were grown in commercial potato fields which were inspected twice a season by Plant Protection and Inspection Services (PPIS). Stem samples were tested for the presence of Dickeya spp. by PCR analysis. PCR and ELISA results from seed lot testing correlated with disease expression in 74 and 83AE8% of the cases, respectively. Positive laboratory results with no disease symptoms in the field ('+lab ⁄ )field' results) comprised 24AE7 and 9AE7% of the PCR and ELISA analyses, respectively, whereas negative laboratory results with disease symptoms in the field results (')lab ⁄ +field') were obtained in 1AE3 and 6AE5%, of cases respectively. Maximum disease incidence, as well as the number of cultivars expressing disease symptoms, increased over the years of this study, indicating an increase in the prevalence of the disease. Severe disease incidence was observed on cvs Dita, Rodeo, Desiree, Mondial, Tomensa and Jelly. Of the 55 imported seed lots from which disease was recorded in the field, 49 originated from the Netherlands, four from Germany and two from France. None originated from Scotland.