Search Results (52)

Coffee berry disease (CBD), caused by Colletotrichum kahawae, significantly threatens global Coffee arabica production, leading to major yield losses. Traditional detection methods are often subjective and inefficient, particularly in resource-limited settings. While deep learning has advanced plant disease detection, most existing research targets leaf diseases, with limited focus on berry-specific infections like CBD. This study proposes a lightweight and accurate solution using a Compact Convolutional Transformer (CCT) for classifying healthy and CBD-affected coffee berries. The CCT model combines parallel convolutional branches for hierarchical feature extraction with a transformer encoder to capture long-range dependencies, enabling high performance on limited data. A dataset of 1737 coffee berry images was enhanced using bilateral filtering and color segmentation. The CCT model, integrated with a Multilayer Perceptron (MLP) classifier and optimized through early stopping and regularization, achieved a validation accuracy of 97.70% and a sensitivity of 100% for CBD detection. Additionally, CCT-extracted features performed well with traditional classifiers, including Support Vector Machine (SVM) (82.47% accuracy; AUC 0.91) and Decision Tree (82.76% accuracy; AUC 0.86). Compared to pretrained models, the proposed system delivered superior accuracy (97.5%) with only 0.408 million parameters and faster training (2.3 s/epoch), highlighting its potential for real-time, low-resource deployment in sustainable coffee production systems. Full article

Coffee cultivation is vital to the global economy, but faces significant challenges with diseases such as rust, miner, phoma, and cercospora, which impact production and sustainable crop management. In this scenario, deep learning techniques have shown promise for the early identification of these diseases, enabling more efficient monitoring. This paper proposes an approach for detecting diseases and pests on coffee leaves using an efficient single-shot object-detection algorithm. The experiments were conducted using the YOLOv8, YOLOv9, YOLOv10 and YOLOv11 versions, including their variations. The BRACOL dataset, annotated by an expert, was used in the experiments to guarantee the quality of the annotations and the reliability of the trained models. The evaluation of the models included quantitative and qualitative analyses, considering the mAP, F1-Score, and recall metrics. In the analyses, YOLOv8s stands out as the most effective, with a mAP of 54.5%, an inference time of 11.4 ms and the best qualitative predictions, making it ideal for real-time applications. Full article

The application of marker-assisted selection in coffee breeding programs accelerates the identification and concentration of target alleles, being essential for developing cultivars resistant to multiple diseases. In this study, a population was developed from artificial crossings between Timor Hybrid and Tupi Amarelo, with the aim of promoting the pyramiding of resistance genes to the main diseases and pests of Coffea arabica: coffee leaf rust (CLR), coffee berry disease (CBD), cercospora, and leaf miner. Resistance was confirmed by nine molecular markers at loci associated with CLR (genes SH3, CC-NBS-LRR, RLK, QTL-GL2, and GL5) and with CBD (gene Ck-1). The resistance to CLR, cercospora, and leaf miner was evaluated using phenotypic diagrammatic scales. Mixed models estimated population superiority in 16 morphoagronomic traits over four agricultural years. The introgression of resistance alleles to CLR and CBD was identified in 98.6% of the population, with 29% showing pyramiding of five resistance genes. These pyramiding genotypes showed 100% resistance to the leaf miner and 90% to cercospora. The traits were grouped into univariate, bivariate, and trivariate repeatability models, with 11 significant ones. These results are indicative of genetic variability to be explored in the development of cultivars with multiple resistances and high agronomic potential. Full article

Objective: Metabolic dysfunction-associated steatotic liver disease (MASLD) is a chronic condition affecting a broad population. This review aimed to identify and summarize the current evidence on bioactive-substance-based interventions for adults with MASLD, formerly known as nonalcoholic fatty liver disease (NAFLD), covering publications from 2000 to 2023. Methods: A search was conducted across six databases (MEDLINE, CINAHL, Cochrane CENTRAL, Cochrane Database of Systematic Reviews, Food Science Source, and SPORTDiscus) for randomized controlled trials and other study types (e.g., prospective cohort studies and systematic reviews), reflecting the scoping nature of this review. The search was limited to studies in adults (>18 years old), with an intervention of interest and at least one comparator group. Results: A total of 4572 articles were retrieved, with 201 full-text articles screened for eligibility. Of these, 131 primary studies and 49 systematic reviews were included in the scoping review. The most studied bioactive substances were Curcumin (Turmeric) (n = 25), Silymarin (Milk Thistle) (n = 17), Resveratrol (n = 10), Coffee (n = 7), Green Tea (n = 5), and Berberine (n = 5 each). Moreover, 46 studies reported on 36 other bioactive substances with 2 or fewer articles each. Among the included systematic reviews, 13 focused on Curcumin, 12 on Coffee or Tea, 10 on bioactive substance combinations, 6 on Resveratrol, and 2 each on Silymarin and Artichoke Leaf. The included studies showed substantial heterogeneity in reported outcomes, which primarily focused on hepatic health, body weight, adverse events, glycemic control, blood lipids, and body composition. Conclusions: This scoping review highlights a range of bioactive substances used in the treatment of MASLD. While evidence is abundant for bioactive substances like Curcumin and Silymarin, further research and synthesis of findings is necessary to establish the clinical efficacy of all bioactive substances. Full article

The main diseases that affect coffee production worldwide are coffee leaf rust (CLR) and coffee berry disease (CBD), caused by fungi Hemileia vastatrix and Colletotrichum kahawae, respectively. The identification of cultivars with stacking resistance genes is of paramount importance for the control of these diseases. This work aimed to profile the phenotypic and genetic resistance of 160 genotypes belonging to 36 commercial coffee cultivars from five Central American countries regarding resistance to races II and XXXIII of H. vastatrix through phenotypic evaluation and evaluations associated with the genetic loci of resistance to CLR and CBD by molecular markers. Of the 160 genotypes from Central America evaluated, 26.25% presented genes stacked to the three loci of resistance to CLR and the locus of resistance to CBD, and resistance to races II and XXXIII when inoculated with urediniospores. In addition, 14 genotypes were identified with the presence of the S_H3 gene, whose resistance has not yet been broken. This work revealed errors in passport data or hybridizations in cultivars and even possible resistance breakdown in the Catimor genetic group. These results are essential to the search for strategies in coffee genetic breeding programs. Full article

Agriculture is vital for providing food and economic benefits, but crop diseases pose significant challenges, including coffee cultivation. Traditional methods for disease identification are labor-intensive and lack real-time capabilities. This study aims to address existing methods’ limitations and provide a more efficient, reliable, and cost-effective solution for coffee leaf disease identification. It presents a novel approach to the real-time identification of coffee leaf diseases using deep learning. We implemented several transfer learning (TL) models, including ResNet101, Xception, CoffNet, and VGG16, to evaluate the feasibility and reliability of our solution. The experiment results show that the proposed models achieved high accuracy rates of 97.30%, 97.60%, 97.88%, and 99.89%, respectively. CoffNet, our proposed model, showed a notable processing speed of 125.93 frames per second (fps), making it suitable for real-time applications. Using a diverse dataset of mixed images from multiple devices, our approach reduces the workload of farmers and simplifies the disease detection process. The findings lay the groundwork for the development of practical and efficient systems that can assist coffee growers in disease management, promoting sustainable farming practices, and food security. Full article

Agroforestry systems can influence the occurrence and abundance of pests and diseases because integrating crops with trees or other vegetation can create diverse microclimates that may either enhance or inhibit their development. This study analyzes the severity of coffee rust in two agroforestry systems in the provinces of Jaén and San Ignacio in the department of Cajamarca (Peru). This research used a quantitative descriptive approach, and 319 photographs were collected with a professional camera during field trips. The photographs were segmented, classified and analyzed using the deep learning MobileNet and VGG16 transfer learning models with two methods for measuring rust severity from SENASA Peru and SENASICA Mexico. The results reported that grade 1 is the most prevalent rust severity according to the SENASA methodology (1 to 5% of the leaf affected) and SENASICA Mexico (0 to 2% of the leaf affected). Moreover, the proposed MobileNet model presented the best classification accuracy rate of 94% over 50 epochs. This research demonstrates the capacity of machine learning algorithms in disease diagnosis, which could be an alternative to help experts quantify the severity of coffee rust in coffee trees and broadens the field of research for future low-cost computational tools for disease recognition and classification Full article

Global warming and extreme climate conditions caused by unsuitable temperature and humidity lead to coffee leaf rust (Hemileia vastatrix) diseases in coffee plantations. Coffee leaf rust is a severe problem that reduces productivity. Currently, pesticide spraying is considered the most effective solution for mitigating coffee leaf rust. However, the application of pesticide spray is still not efficient for most farmers worldwide. In these cases, pruning the most infected leaves with leaf rust at coffee plantations is important to help pesticide spraying to be more efficient by creating a more targeted, accessible treatment. Therefore, detecting coffee leaf rust is important to support the decision on pruning infected leaves. The dataset was acquired from a coffee farm in Majalengka Regency, Indonesia. Only images with clearly visible spots of coffee leaf rust were selected. Data collection was performed via two devices, a digital mirrorless camera and a phone camera, to diversify the dataset and test it with different datasets. The dataset, comprising a total of 2024 images, was divided into three sets with a ratio of 70% for training (1417 images), 20% for validation (405 images), and 10% for testing (202 images). Images with leaves infected by coffee leaf rust were labeled via LabelImg^® with the label “CLR”. All labeled images were used to train the YOLOv5 and YOLOv8 algorithms through the convolutional neural network (CNN). The trained model was tested with a test dataset, a digital mirrorless camera image dataset (100 images), a phone camera dataset (100 images), and real-time detection with a coffee leaf rust image dataset. After the model was trained, coffee leaf rust was detected in each frame. The mean average precision (mAP) and recall for the trained YOLOv5 model were 69% and 63.4%, respectively. For YOLOv8, the mAP and recall were approximately 70.2% and 65.9%, respectively. To evaluate the performance of the two trained models in detecting coffee leaf rust on trees, 202 original images were used for testing with the best-trained weight from each model. Compared to YOLOv5, YOLOv8 demonstrated superior accuracy in detecting coffee leaf rust. With a mAP of 73.2%, YOLOv8 outperformed YOLOv5, which achieved a mAP of 70.5%. An edge device was utilized to deploy real-time detection of CLR with the best-trained model. The detection was successfully executed with high confidence in detecting CLR. The system was further integrated into pruning solutions for Arabica coffee farms. A pruning device was designed using Autodesk Fusion 360^® and fabricated for testing on a coffee plantation in Indonesia. Full article

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. Full article

Coffee leaf rust (CLR), a fungal disease caused by Hemileia vastatrix, represents Peru’s most significant threat to coffee production. The CLR epidemic (2012–2013) led Peru to implement an emergency plan under which coffee plantations underwent renewal using rust-resistant varieties derived from a Timor hybrid (HDT; Coffea arabica × canephora hybrid) like Catimors. Nevertheless, new pathogenic rust races capable of infecting these varieties have been recorded. Eighteen rust samples from coffee genotypes, such as Caturra, Typica, and Catimor, were collected in various Peruvian regions and sent to CIFC/ISA/UL (Centro de Investigação das Ferrugens do Cafeeiro/Instituto Superior de Agronomia/Universidade de Lisboa) in Portugal for race characterization. Assessing the virulence spectra of rust samples on a set of 27 coffee differentials resulted in the identification of 5 known and 2 new races. This study emphasizes the significance of conducting surveys on the diversity of H. vastatrix races in Peru for effective disease management. Moreover, Catimor lines, widely cultivated in coffee-growing countries, are susceptible to the 2 new races and to races XXXIV and XXXV identified in this study. Thus, coffee farmers need to know the resistance spectrum of new varieties before introducing them to CLR-affected regions. Full article

In Brazil, coffee leaf rust (CLR), caused by the fungus Hemileia vastatrix, was first detected in Coffea arabica in January of 1970 in southern Bahia. Now widespread across all cultivation areas, the disease poses a significant threat to coffee production, causing losses of 30–50%. In this context, the objective of this study was to identify and quantify the different classes of occurrence of CLR in areas apt and restricted to the cultivation of Arabica coffee in Brazil for a more informed decision regarding the cultivar to be implanted. The areas of climatic aptitude for Arabica coffee were defined, and then, the climatic favorability for the occurrence of CLR in these areas was evaluated based on climatic data from TerraClimate from 1992 to 2021. The apt areas, apt with some type of irrigation, restricted, and with some type of restriction for the cultivation of Arabica coffee add up to 16.34% of the Brazilian territory. Within this 16.34% of the area of the Brazilian territory, the class of climatic favorability for the occurrence of CLR with greater representation is the favorable one. Currently, the disease is controlled with the use of protective and systemic fungicides, including copper, triazoles, and strobilurins, which must be applied following decision rules that vary according to the risk scenario, and according to the use of resistant cultivars. This study provides a basis for choosing the most suitable cultivars for each region based on the degree of CLR resistance. Full article

Genome-wide association studies (GWASs) allow for inferences about the relationships between genomic variants and phenotypic traits in natural or breeding populations. However, few have used this methodology in Coffea arabica. We aimed to identify chromosomal regions with significant associations between SNP markers and agronomic traits in C. arabica. We used a coffee panel consisting of 195 plants derived from 13 families in F2 generations and backcrosses of crosses between leaf rust-susceptible and -resistant genotypes. The plants were phenotyped for 18 agronomic markers and genotyped for 21,211 SNP markers. A GWAS enabled the identification of 110 SNPs with significant associations (p < 0.05) for several agronomic traits in C. arabica: plant height, plagiotropic branch length, number of vegetative nodes, canopy diameter, fruit size, cercosporiosis incidence, and rust incidence. The effects of each SNP marker associated with the traits were analyzed, such that they can be used for molecular marker-assisted selection. For the first time, a GWAS was used for these important agronomic traits in C. arabica, enabling applications in accelerated coffee breeding through marker-assisted selection and ensuring greater efficiency and time reduction. Furthermore, our findings provide preliminary knowledge to further confirm the genomic loci and potential candidate genes contributing to various structural and disease-related traits of C. arabica. Full article

It all began with Arabica coffee seeds that crossed the Red Sea from Ethiopia to Yemen. It continued with seeds smuggled out of Yemen in various directions. Gesha, one of the cultivars producing the most expensive coffees in the world, went from Ethiopia to Tanzania, Kenya, Costa Rica and, finally, Panama, where it would become famous. Who would have thought that the main genetic solution to the devastating Coffee Leaf Rust disease would come from an unlikely natural cross between two species—Coffea canephora and Coffea arabica—introduced from Africa to the little-known Timor island in Southeast Asia? It is these numerous and uncontrolled movements of plant material that have shaped the genetic improvement of the Arabica coffee plant. It is highly likely that the present and future challenges facing the coffee sector will require new exchanges of plant material. We can already see that species that could be of interest in tackling climate change, for instance, C. racemosa, C. stenophylla, C. zanguebariae, are still in their natural African habitat. They will have to be studied and tested in different environments. A new wave of genetic material exchange will be needed from their natural habitat or domestication center to various coffee-producing countries from various Coffea species. This will first be so for agronomic research and then for actual production. However, in the 21st century, it is fortunately compulsory to perform this ethically and in compliance with international regulations. The coffee scientific community needs to be prepared and aligned. Full article

Coffee leaf diseases are a significant challenge for coffee cultivation. They can reduce yields, impact bean quality, and necessitate costly disease management efforts. Manual monitoring is labor-intensive and time-consuming. This research introduces a pioneering mobile application equipped with global positioning system (GPS)-enabled reporting capabilities for on-site coffee leaf disease detection. The application integrates advanced deep learning (DL) techniques to empower farmers and agronomists with a rapid and accurate tool for identifying and managing coffee plant health. Leveraging the ubiquity of mobile devices, the app enables users to capture high-resolution images of coffee leaves directly in the field. These images are then processed in real-time using a pre-trained DL model optimized for efficient disease classification. Five models, Xception, ResNet50, Inception-v3, VGG16, and DenseNet, were experimented with on the dataset. All models showed promising performance; however, DenseNet proved to have high scores on all four-leaf classes with a training accuracy of 99.57%. The inclusion of GPS functionality allows precise geotagging of each captured image, providing valuable location-specific information. Through extensive experimentation and validation, the app demonstrates impressive accuracy rates in disease classification. The results indicate the potential of this technology to revolutionize coffee farming practices, leading to improved crop yield and overall plant health. Full article

In this case study, the current situation faced by coffee growers attempting to control coffee leaf rust (Hemileia vastatrix) in Hawaii is reported. CLR is considered the most devastating disease affecting coffee crops worldwide and was detected in Hawaii in 2020. Three small coffee farms from the South Kona district of Hawaii Island were selected. The goals of this case study were to: (1) assist coffee growers in the early detection of CLR incidence, and consequently support farmers with recommendations for control, (2) record agronomic information and management practices, and (3) estimate the cost to control CLR during 2021 and 2022 seasons. Low CLR incidence (<4%) was initially observed at all farms (January–June 2021), but increased as the harvest began, ending the season (December 2021) at 77%, 21% and 6% incidence at farms 1, 2 and 3, respectively. At the end of 2022 season (December), CLR incidence reached 43%, 20% and 3% at farms 1, 2 and 3, respectively. The number of sprays per season (5–10), the type of fungicides applied (preventive, curative), the timing of sprays, the efficacy of applications and weather conditions all played a role in determining the infection rates at each farm. Effective control of CLR is possible in Hawaii if the sprays of fungicides are carried out with the right products, appropriate timing and good coverage. Full article