Sclerotinia stem rot, caused by Sclerotinia sclerotiorum, is a destructive soil-borne disease leading to huge yield loss.  We previously reported that Klebsiella variicola FH-1 could degrade atrazine herbicides, and the vegetative growth of atrazine-sensitive crops (i.e., soybean) was significantly increased in the FH-1-treated soil.  Interestingly, we found that FH-1 could promote soybean growth and induce resistance to S. sclerotiorum.  In our study, strain FH-1 could grow in a nitrogen-free environment, dissolve inorganic phosphorus and potassium, and produce indoleacetic acid and a siderophore.  The results of pot experiments showed that K. variicola FH-1 promoted soybean plant development, substantially improving plant height, fresh weight, and root length, and induced resistance against S. sclerotiorum infection in soybean leaves.  The area under the disease progression curve (AUDPC) for treatment with strain FH-1 was significantly lower than the control and was reduced by up to 42.2% within 48 h (P<0.001).  Moreover, strain FH-1 rcovered the activities of catalase, superoxide dismutase, peroxidase, phenylalanine ammonia lyase, and polyphenol oxidase, which are involved in plant protection, and reduced malondialdehyde accumulation in the leaves.  The mechanism of induction of resistance appeared to be primarily resulted from the enhancement of transcript levels of PR10, PR12, AOS, CHS, and PDF1.2 genes.  The colonization of FH-1 on soybean root, determined using CLSM and SEM, revealed that FH-1 colonized soybean root surfaces, root hairs, and exodermis to form biofilms.  In summary, K. variicola FH-1 exhibited the biological control potential by inducing resistance in soybean against S. sclerotiorum infection, providing new suggestions for green prevention and control.

Maize (Zea mays L.), also known as corn, is the third most cultivated crop in the world.  Northern corn leaf blight (NCLB) is a globally devastating maize foliar disease caused by Setosphaeria turcica (Luttrell) Leonard and Suggs.  Early intelligent diagnosis and warning is an effective and economical strategy to control this disease.  Today, deep learning is beginning to play an essential role in agriculture.  Notably, deep convolutional neural networks (DCNN) are amongst the most successful machine learning techniques in plant disease detection and diagnosis.  Our study aims to identify NCLB in the maize-producing area in Jilin Province based on several DCNN models.  We established a database of 985 leaf images of healthy and infected maize and applied data augmentation techniques including image segmentation, image resizing, image cropping, and image transformation, to expand to 30 655 images.  Several proven convolutional neural networks, such as AlexNet, GoogleNet, VGG16, and VGG19, were then used to identify diseases.  Based on the best performance of the DCNN pre-trained model GoogleNet, some of the recent loss functions developed for deep facial recognition tasks such as ArcFace, CosFace, and A-Softmax were applied to detect NCLB.  We found that a pre-trained GoogleNet architecture with the Softmax loss function can achieve an excellent accuracy of 99.94% on NCLB diagnosis.  The analysis was implemented in Python with two deep learning frameworks, Pytorch and Keras.  The techniques, training, validation, and test results are presented in this paper.  Overall, our study explores intelligent identification technology for NCLB and effectively diagnoses NCLB from images of maize.