The strawberry (Fragaria × ananassa Duch.) is a high-value crop with an annual cultivated area of ~500 ha in Taiwan. Over 90% of strawberry cultivation is in Miaoli County. Unfortunately, various diseases significantly decrease strawberry production. The leaf and fruit disease became an epidemic in 1986. From 2010 to 2016, anthracnose crown rot caused the loss of 30–40% of seedlings and ~20% of plants after transplanting. The automation of agriculture and image recognition techniques are indispensable for detecting strawberry diseases. We developed an image recognition technique for the detection of strawberry diseases using a convolutional neural network (CNN) model. CNN is a powerful deep learning approach that has been used to enhance image recognition. In the proposed technique, two different datasets containing the original and feature images are used for detecting the following strawberry diseases—leaf blight, gray mold, and powdery mildew. Specifically, leaf blight may affect the crown, leaf, and fruit and show different symptoms. By using the ResNet50 model with a training period of 20 epochs for 1306 feature images, the proposed CNN model achieves a classification accuracy rate of 100% for leaf blight cases affecting the crown, leaf, and fruit; 98% for gray mold cases, and 98% for powdery mildew cases. In 20 epochs, the accuracy rate of 99.60% obtained from the feature image dataset was higher than that of 1.53% obtained from the original one. This proposed model provides a simple, reliable, and cost-effective technique for detecting strawberry diseases.

For the past 30 years, the most predominant strawberry cultivar in Taiwan has been 'Taoyuan No. 1', which produces fruit with rich flavor and aroma but is highly susceptible to anthracnose (Chung et al. 2019). Because epidemics of anthracnose became more destructive, farmers switched to an anthracnose-tolerant cultivar 'Xiang-Shui' (~50% and ~80% of the cultivation area in 2018 and 2019, respectively). Since 2018, severe leaf blight and crown rot symptoms have been observed all year in 'Xiang-Shui' in Miaoli, Nantou, Hsinchu, Taipei, Taoyuan, and Chiayi Counties. The disease became more prevalent and severe during 2019 to 2020 and caused up to 30% plant loss after transplanting. Symptoms appeared as brown necrotic lesions with black acervuli on leaves, slightly sunken dark-brown necrosis on stolons, and sunken reddish-brown necrosis on fruit. The diseased crown tissue showed marbled reddish-brown necrosis with a dark-brown margin, and plants with severe crown rot usually showed reddish-brown discoloration on leaves (the leaves initially turned reddish-brown between the veins and could become entirely scorched at later stages). To isolate the causal agent, small fragments of diseased leaves, crowns, stolons, and fruits were surface-disinfested with 0.5% sodium hypochlorite for 30 seconds, rinsed with sterile water then placed on 1.5% water agar. Single hyphal tips extended from tissues were transferred to potato dextrose agar and cultured for 7 days at 25°C under a 12-h/12-h photoperiod. Total 20 isolates were obtained from diseased leaves, crowns, stolons, and fruits. Colonies were white with cottony aerial mycelium, irregular margins, and black acervuli distributed in concentric rings. Conidia were fusiform to ellipsoid (five cells) with one basal appendage and three or four (usually three) apical appendages. From colony and conidial morphology, the causal agent was identified as Neopestalotiopsis sp. (Maharachchikumbura et al. 2014). The internal transcribed spacer (ITS) region, β-tubulin (TUB), and translation elongation factor 1-alpha (TEF-1α) of three isolates (ML1664 from diseased crown tissue collected in Hsinchu County; ML2147 and ML2411 from diseased leaves collected in Miaoli County) were sequenced (GenBank nos. MT469940 to MT469948). All three isolates clustered with the ex-type strain of Neopestalotiopsis rosae in the multilocus (ITS+TUB+TEF-1α) phylogenetic tree. To fulfill Koch's postulates, spore suspensions of ML1664 and ML2147 at 1×10⁶ conidia/mL were used to spray-inoculate 'Xiang-Shui' seedlings at the 3 to 4 leaf stage until run-off (two trials, five seedlings per trial). Inoculated plants were put in a plastic bag (> 90% RH) at 25°C under a 12-h/12-h photoperiod. After 10-14 days, 80% of inoculated plants showed leaf or crown symptoms similar to those in the field. Control plants sprayed with sterile water showed no symptoms (4-5 seedlings per trial). The fungi were re-isolated from necrotic lesions with 100% frequency (n ≥ 3 isolates per trial), and morphological characters and ITS sequences were identical to the original ones. This is the first report of N. rosae causing leaf blight and crown rot in strawberry in Taiwan. N. rosae and N. clavispora have been reported as new threats to strawberry in several other countries (Rebollar-Alviter 2020; Gilardi 2019). Clarification of the pathogen provides a basis for developing strategies to control the emerging disease. Further studies are needed to evaluate the resistance/susceptibility of major strawberry cultivars and the fungicide sensitivity of the pathogen.

Angular leaf spot of strawberry, considered an A2 quarantine pest by the European and Mediterranean Plant Protection Organization (EPPO 2019), is an important bacterial disease in many regions. Sin...