Metarhizium species can be mutualistic symbionts of plants. They are able to colonize roots, promote plant growth and provide protection against pests. We previously found Metarhizium robertsii and M. brunneum associated with coffee roots in a diversified coffee system. Here, we investigated whether these fungi, when inoculated in coffee seedlings, can associate with roots, improve seedling growth and indirectly protect against the coffee leaf miner (CLM) Leucoptera coffeella (Lepidoptera: Lyonetiidae). We performed a greenhouse experiment with coffee seedlings using suspensions of each Metarhizium species applied as soil drenches to potted seedlings. We also challenged these plants with CLM infestation (two adult couples per plant). We recovered Metarhizium spp. from most of the seedling roots 43 days after fungal inoculation. Plants inoculated with M. robertsii showed a 30% leaf area increase compared to the control. Both isolates promoted protection against CLM in coffee seedlings, reducing the percentual of leaf area mined and prolonging CLM development time by two days versus controls. Besides this protection provided by Metarhizium, M. robertsii also improves seedling growth. Therefore, these Metarhizium species could be considered for the development of inoculants for coffee seedlings.

Conservation biological control of pests may be achieved using a variety of integrated strategies based on crop diversification. We investigated whether the insertion of the intercropped plants species (IPS) Inga edulis, Senna macranthera, and Varronia curassavica modified the abundance of mites, their feeding behavior, and the dissimilarity of predator and herbivore mites over a gradient of distance from the IPS on coffee. To accomplish this, we recorded the mite species on coffee plants along transects of 16 m extending from the IPS, including on the IPS. A total of 8946 specimens were sampled. Tenuipalpidae was the most abundant family on coffee, followed by Tydeidae, while Eriophyidae was the most abundant on the IPS, followed by Phytoseiidae. The abundance and richness of mites differed between their feeding behavior and distance. The dissimilarity of predators and herbivores increased along a gradient of distance. Furthermore, the IPS harbored several mite species and the diversity of predator and herbivore mites among the IPS was different. The findings suggest that the intercropped plant species can attract and serve as a reservoir of predatory mites on coffee crops, which could improve the biocontrol of pest mites on coffee.

The sustainability of coffee production is a concern for producers around the world. To be sustainable, it is necessary to achieve satisfactory levels of coffee productivity and quality. Pests and diseases cause reduced productivity and can affect the quality of coffee beans. To ensure sustainability, producers need to monitor pests that can lead to substantial crop losses, such as the coffee leaf miner, Leucoptera coffeella (Lepidoptera: Lyonetiidae), which belongs to the Lepidoptera order and the Lyonetiidae family. This research aimed to use machine learning techniques and vegetation indices to remotely identify infestations of the coffee leaf miner in coffee-growing regions. Field assessments of coffee leaf miner infestation were conducted in September 2023. Aerial images were taken using remotely piloted aircraft to determine 13 vegetative indices with RGB (red, green, blue) images. The vegetation indices were calculated using ArcGis 10.8 software. A comprehensive database encompassing details of coffee leaf miner infestation, vegetation indices, and crop data. The dataset was divided into training and testing subsets. A set of four machine learning algorithms was utilized: Random Forest (RF), Logistic Regression (LR), Support Vector Machine (SVM), and Stochastic Gradient Descent (SGD). Following hyperparameter tuning, the test subset was employed for model validation. Remarkably, both the SVM and SGD models demonstrated superior performance in estimating coffee leaf miner infestations, with kappa indices of 0.6 and 0.67, respectively. The combined use of vegetation indices and crop data increased the accuracy of coffee leaf miner detection. The RF model performed poorly, while the SVM and SGD models performed better. This situation highlights the challenges of tracking coffee leaf miner infestations in fields with varying ages of coffee plants, different cultivars, and other environmental variables.