Fusarium oxysporum f. sp. cubense (Foc) is the causal pathogen of Fusarium wilt of banana. To understand infection of banana roots by Foc race 4, we developed a green fluorescent protein (GFP)-tagged transformant and studied pathogenesis using fluorescence microscopy and confocal laser scanning microscopy. The transformation was efficient, and GFP expression was stable for at least six subcultures with fluorescence clearly visible in both hyphae and spores. The transformed Foc isolate also retained its pathogenicity and growth pattern, which was similar to that of the wild type. The study showed that: (i) Foc race 4 was capable of invading the epidermal cells of banana roots directly; (ii) potential invasion sites include epidermal cells of root caps and elongation zone, and natural wounds in the lateral root base; (iii) in banana roots, fungal hyphae were able to penetrate cell walls directly to grow inside and outside cells; and (iv) fungal spores were produced in the root system and rhizome. To better understand the interaction between Foc race 4 and bananas, nine banana cultivars were inoculated with the GFP-transformed pathogen. Root exudates from these cultivars were collected and their effect on conidia of the GFP-tagged Foc race 4 was determined. Our results showed that roots of the Foc race 4-susceptible banana plants were well colonized with the pathogen, but not those of the Foc race 4-resistant cultivars. Root exudates from highly resistant cultivars inhibited the germination and growth of the Fusarium wilt pathogen; those of moderately resistant cultivars reduced spore germination and hyphal growth, whereas the susceptible cultivars did not affect fungal germination and growth. The results of this work demonstrated that GFP-tagged Foc race 4 isolates are an effective tool to study plant-fungus interactions that could potentially be used for evaluating resistance in banana to Foc race 4 by means of root colonization studies. Banana root exudates could potentially also be used to identify cultivars in the Chinese Banana Germplasm Collection with resistance to the Fusarium wilt pathogen.

No abstract

No abstract

It is widely accepted that conventional boost algorithms are of low efficiency and accuracy in dealing with big data collected from wind turbine operations. To address this issue, this paper is devoted to the application of an adaptive LightGBM method for wind turbine fault detections. To this end, the realization of feature selection for fault detection is firstly achieved by utilizing the maximum information coefficient to analyze the correlation among features in supervisory control and data acquisition (SCADA) of wind turbines. After that, a performance evaluation criterion is proposed for the improved LightGBM model to support fault detections. In this scheme, by embedding the confusion matrix as a performance indicator, an improved LightGBM fault detection approach is then developed. Based on the adaptive LightGBM fault detection model, a fault detection strategy for wind turbine gearboxes is investigated. To demonstrate the applications of the proposed algorithms and methods, a case study with a three-year SCADA dataset obtained from a wind farm sited in Southern China is conducted. Results indicate that the proposed approaches established a fault detection framework of wind turbine systems with either lower false alarm rate or lower missing detection rate.