RESUMO
Counting nematodes is a labor-intensive and time-consuming task, yet it is a pivotal step in various quantitative nematological studies; preparation of initial population densities and final population densities in pot, micro-plot and field trials for different objectives related to management including sampling and location of nematode infestation foci. Nematologists have long battled with the complexities of nematode counting, leading to several research initiatives aimed at automating this process. However, these research endeavors have primarily focused on identifying single-class objects within individual images. To enhance the practicality of this technology, there's a pressing need for an algorithm that cannot only detect but also classify multiple classes of objects concurrently. This study endeavors to tackle this challenge by developing a user-friendly Graphical User Interface (GUI) that comprises multiple deep learning algorithms, allowing simultaneous recognition and categorization of nematode eggs and second stage juveniles of Meloidogyne spp. In total of 650 images for eggs and 1339 images for juveniles were generated using two distinct imaging systems, resulting in 8655 eggs and 4742 Meloidogyne juveniles annotated using bounding box and segmentation, respectively. The deep-learning models were developed by leveraging the Convolutional Neural Networks (CNNs) machine learning architecture known as YOLOv8x. Our results showed that the models correctly identified eggs as eggs and Meloidogyne juveniles as Meloidogyne juveniles in 94% and 93% of instances, respectively. The model demonstrated higher than 0.70 coefficient correlation between model predictions and observations on unseen images. Our study has showcased the potential utility of these models in practical applications for the future. The GUI is made freely available to the public through the author's GitHub repository (https://github.com/bresilla/nematode_counting). While this study currently focuses on one genus, there are plans to expand the GUI's capabilities to include other economically significant genera of plant parasitic nematodes. Achieving these objectives, including enhancing the models' accuracy on different imaging systems, may necessitate collaboration among multiple nematology teams and laboratories, rather than being the work of a single entity. With the increasing interest among nematologists in harnessing machine learning, the authors are confident in the potential development of a universal automated nematode counting system accessible to all. This paper aims to serve as a framework and catalyst for initiating global collaboration toward this important goal.
RESUMO
Coffee is an important commodity for Kenya, where production is steadily declining, despite a global rise in demand. Of the various constraints affecting production, plant-parasitic nematodes are a significant, but often overlooked, threat. As a perennial crop, treating plantations once infected with nematodes becomes difficult. The current study evaluated the drenching application of two biocontrol agents, Trichoderma asperellum and Purpureocillium lilacinum, for their nematode control efficacy, as well as their impact on the soil nematode community structure on mature, established coffee trees in Kenya. Seven Arabica coffee field trials were conducted over two years on trees of various ages. All the fields were heavily infested with Meloidogyne hapla, the first report of the species on coffee in Kenya. Both fungal biocontrol agents were detected endophytically infecting roots and recovered from soil but not until six months after initial applications. The population densities of M. hapla had significantly declined in roots of treated trees 12 months after the initial application, although soil nematode density data were similar across treatments. Based upon the maturity index and the Shannon index, treatment with T. asperellum led to improved soil health conditions and enrichment of diversity in the microbial community. Application of P. lilacinum, in particular, led to an increased abundance of fungivorous nematodes, especially Aphelenchus spp., for which P. lilacinum would appear to be a preferred food source. The soils in the trials were all stressed and denuded, however, which likely delayed the impact of such treatments or detection of any differences between treatments using indices, such as the functional metabolic footprint, over the period of study. A longer period of study would therefore likely provide a better indication of treatment benefits. The current study positively demonstrates, however, the potential for using biologically based options for the environmentally and climate-smart management of nematode threats in a sustainable manner on established, mature coffee plantations.
