Bacterial diseases of bananas and enset have not received, until recently, an equal amount of attention compared to other major threats to banana production such as the fungal diseases black leaf streak (Mycosphaerella fijiensis) and Fusarium wilt (Fusarium oxysporum f. sp. cubense). However, bacteria cause significant impacts on bananas globally and management practices are not always well known or adopted by farmers. Bacterial diseases in bananas and enset can be divided into three groups: (1) Ralstonia-associated diseases (Moko/Bugtok disease caused by Ralstonia solanacearum and banana blood disease caused by R. syzygii subsp. celebesensis); (2) Xanthomonas wilt of banana and enset, caused by Xanthomonas campestris pv. musacearum and (3) Erwinia-associated diseases (bacterial head rot or tip-over disease Erwinia carotovora ssp. carotovora and E. chrysanthemi), bacterial rhizome and pseudostem wet rot (Dickeya paradisiaca formerly E. chrysanthemi pv. paradisiaca). Other bacterial diseases of less widespread importance include: bacterial wilt of abaca, Javanese vascular wilt and bacterial fingertip rot (probably caused by Ralstonia spp., unconfirmed). This review describes global distribution, symptoms, pathogenic diversity, epidemiology and the state of the art for sustainable disease management of the major bacterial wilts currently affecting banana and enset.

No abstract

Background: Banana (Musa spp.) is the most popular marketable fruit crop grown all over the world, and a dominant staple food in many developing countries. Worldwide, banana production is affected by numerous diseases and pests. Novel and rapid methods for the timely detection of pests and diseases will allow to surveil and develop control measures with greater efficiency. As deep convolutional neural networks (DCNN) and transfer learning has been successfully applied in various fields, it has freshly moved in the domain of just-in-time crop disease detection. The aim of this research is to develop an AI-based banana disease and pest detection system using a DCNN to support banana farmers. Results: Large datasets of expert pre-screened banana disease and pest symptom/damage images were collected from various hotspots in Africa and Southern India. To build a detection model, we retrained three different convolutional neural network (CNN) architectures using a transfer learning approach. A total of six different models were developed from 18 different classes (disease by plant parts) using images collected from different parts of the banana plant. Our studies revealed ResNet50 and InceptionV2 based models performed better compared to MobileNetV1. These architectures represent the state-of-the-art results of banana diseases and pest detection with an accuracy of more than 90% in most of the models tested. These experimental results were comparable with other state-of-the-art models found in the literature. With a future view to run these detection capabilities on a mobile device, we evaluated the performance of SSD (single shot detector) MobileNetV1. Performance and validation metrics were also computed to measure the accuracy of different models in automated disease detection methods. Conclusion: Our results showed that the DCNN was a robust and easily deployable strategy for digital banana disease and pest detection. Using a pre-trained disease recognition model, we were able to perform deep transfer learning (DTL) to produce a network that can make accurate predictions. This significant high success rate makes the model a useful early disease and pest detection tool, and this research could be further extended to develop a fully automated mobile app to help millions of banana farmers in developing countries.

Banana xanthomonas wilt (XW) caused by Xanthomonas campestris pv. musacearum (Xcm) attacks all banana cultivars. Xcm in inflorescence-infected Pisang Awak plants with wilting male bud bracts is restricted to the upper parts of the true stem; therefore, cutting these plants at the pseudostem base has been recommended to prevent further Xcm spread. In order to fine-tune existing control strategies, this study examined the movement of Xcm into plants and mats, in relation to disease incubation period. Mature Pisang Awak and East African highland (AAA-EA) plants were inoculated with Xcm through abscission wounds of female bracts, male bud bracts, male flowers, a combination of male bud bracts and flowers, and by cutting male buds with a contaminated machete. Thirty plants per genotype and treatment were monitored for 24 months for disease symptoms. An additional 68 AAA-EA and 33 Pisang Awak plants were sampled weekly to assess the rate of Xcm spread within the plants. All floral entry points resulted in disease, with the highest incidence in combined male bract and male flower abscission wound inoculations. The study confirmed the systemicity of Xcm, with the pathogen able to live within the mat for long periods (5-16 months) without causing disease. Reliance on disease symptom expression to manage XW is therefore not sufficient. The long incubation period in lateral shoots may explain the current resurgence of the disease in locations where the disease was thought to have been successfully eradicated.

No abstract