Search Results (12)

Leaf diseases, such as Black Sigatoka and Cordana, represent a growing threat to banana crops in Ecuador. These diseases spread rapidly, impacting both leaf and fruit quality. Early detection is crucial for effective control measures. Recently, deep learning has proven to be a powerful tool in agriculture, enabling more accurate analysis and identification of crop diseases. This study applied the CRISP-DM methodology, consisting of six phases: business understanding, data understanding, data preparation, modeling, evaluation, and deployment. A dataset of 900 banana leaf images was collected—300 of Black Sigatoka, 300 of Cordana, and 300 of healthy leaves. Three pre-trained models (EfficientNetB0, ResNet50, and VGG19) were trained on this dataset. To improve performance, data augmentation techniques were applied using TensorFlow Keras’s ImageDataGenerator class, expanding the dataset to 9000 images. Due to the high computational demands of ResNet50 and VGG19, training was performed with EfficientNetB0. The models—EfficientNetB0, ResNet50, and VGG19—demonstrated the ability to identify leaf diseases in bananas, with accuracies of 88.33%, 88.90%, and 87.22%, respectively. The data augmentation increased the performance of EfficientNetB0 to 87.83%, but did not significantly improve its accuracy. These findings highlight the value of deep learning techniques for early disease detection in banana crops, enhancing diagnostic accuracy and efficiency. Full article

Studies were initiated to find new effective fungicides to use under field conditions to discover novel approaches for optimizing disease management in sugar beet crops. Cercospora leaf spot (CLS), a prevalent foliar disease in sugar beet crops worldwide, is caused by the fungal pathogen Cercospora beticola Sacc. This disease has become the most prevalent pathogen in sugar beet crops across nearly all European growing regions, including Hungary. The epidemic spread of this disease can cause up to 50% yield loss. The use of fungicides has been a cornerstone in managing CLS of sugar beet due to the limited efficacy of non-chemical alternatives. However, the emergence of fungicide-resistant strains of Cercospora beticola Sacc. in recent decades has compromised the effectiveness of certain fungicides, particularly those belonging to the QoI (FRAC Group 11) and DMI (FRAC Group 3) classes. Hungary is among the many countries where resistance to these fungicides has developed due to their frequent application. Picolinamides represent a novel class of fungal respiration inhibitors targeting Complex III within the Quinoine-Inside Inhibitor (QiI) group. Two innovative fungicides from this class, fenpicoxamid and florylpicoxamid (both classified under FRAC Group 21), were evaluated for their efficacy in managing CLS of sugar beet in Hungary during the 2020 and 2021 growing seasons. Both fungicides were applied as formulated products at various application rates and demonstrated superior efficacy in controlling CLS compared to untreated control plots and the reference fungicides difenoconazole and epoxiconazole. The results consistently demonstrated that all tested application rates of fenpicoxamid and florylpicoxamid effectively controlled CLS in sugar beet, exhibiting a clear dose–response relationship. Disease severity, as measured by the area under the disease progress curve (AUDPC), was significantly correlated with yield reduction but showed no significant association with root sugar content. Moreover, data from both study years indicated that picolinamide fungicides applied at a rate of 75 g ai/ha significantly outperformed difenoconazole (100 g ai/ha) in controlling the CLS of sugar beet. Additionally, higher application rates of picolinamides at 100–150 g ai/ha outperformed epoxiconazole at 125 g ai/ha in disease suppression. Fenpicoxamid is currently registered for use in cereals within Europe, and outside of Europe in Banana against Black Sigatoka (eff. Mycosphaerella fijiensis). Florylpicoxamid, while not yet registered in Europe, is undergoing approval processes in various countries worldwide for a range of crops and is continually being evaluated for potential market introduction. Additional details regarding the efficacy of florylpicoxamid against CLS in sugar beet were presented at ‘The 10th International Conference on Agricultural and Biological Sciences (ABS 2024, Győr-Hungary)’ in 2024. Full article

This paper presents an evaluation of different convolutional neural network (CNN) architectures using false-colour images obtained by multispectral sensors on drones for the detection of Black Sigatoka in banana crops. The objective is to use drones to improve the accuracy and efficiency of Black Sigatoka detection to reduce its impact on banana production and improve the sustainable management of banana crops, one of the most produced, traded, and important fruits for food security consumed worldwide. This study aims to improve the precision and accuracy in analysing the images and detecting the presence of the disease using deep learning algorithms. Moreover, we are using drones, multispectral images, and different CNNs, supported by transfer learning, to enhance and scale up the current approach using RGB images obtained by conventional cameras and even smartphone cameras, available in open datasets. The innovation of this study, compared to existing technologies for disease detection in crops, lies in the advantages offered by using drones for image acquisition of crops, in this case, constructing and testing our own datasets, which allows us to save time and resources in the identification of crop diseases in a highly scalable manner. The CNNs used are a type of artificial neural network widely utilised for machine training; they contain several specialised layers interconnected with each other in which the initial layers can detect lines and curves, and gradually become specialised until reaching deeper layers that recognise complex shapes. We use multispectral sensors to create false-colour images around the red colour spectra to distinguish infected leaves. Relevant results of this study include the construction of a dataset with 505 original drone images. By subdividing and converting them into false-colour images using the UAV’s multispectral sensors, we obtained 2706 objects of diseased leaves, 3102 objects of healthy leaves, and an additional 1192 objects of non-leaves to train classification algorithms. Additionally, 3640 labels of Black Sigatoka were generated by phytopathology experts, ideal for training algorithms to detect this disease in banana crops. In classification, we achieved a performance of 86.5% using false-colour images with red, red edge, and near-infrared composition through MobileNetV2 for three classes (healthy leaves, diseased leaves, and non-leaf extras). We obtained better results in identifying Black Sigatoka disease in banana crops using the classification approach with MobileNetV2 as well as our own datasets. Full article

Black Leaf Streak Disease (BLSD), caused by the fungus Pseudocercospora fijiensis, is a recent pandemic and the most economically and environmentally important leaf disease of banana. To assist breeding of varieties with durable resistance to the rapidly evolving P. fijiensis, we used a diploid genitor ‘IDN 110’ with partial resistance to BLSD to search for QTLs. We assessed diploid progeny of 73 hybrids between ‘IDN 110’ and the diploid cultivar ‘Khai Nai On’, which is susceptible to BLSD. Hybrids were phenotyped with artificial inoculation under controlled conditions. This method allowed us to focus on resistance in the early stages of the interaction already identified as strongly influencing BLSD epidemiology. Progeny were genotyped by sequencing. As both parents are heterozygous for large reciprocal translocations, the distribution of recombination was assessed and revealed regions with low recombination rates. Fourteen non-overlapping QTLs of resistance to BLSD were identified of which four main QTLs from the ‘IDN110‘ parent, located on chromosomes 06, 07, 08, and 09, were shown to be of interest for marker-assisted selection. Genes that underline those four QTLs are discussed in the light of previous literature. Full article

Mixed production systems play a vital role in the economic sustainability and ecological balance of agroecosystems. Cocoa and plantain are key crops in Ecuador but face phytosanitary challenges, like witches’ broom and black sigatoka diseases, especially when cultivated under monocropping systems. Combining habitat manipulation with adaptive pathogen management (APM) strategies can mitigate these challenges, but their efficacy in mixed cropping systems remains unclear. This study investigates disease and pest incidence in mixed cocoa–plantain systems during the establishment phase, focusing on the impact of spatial arrangements. Mixed agroecosystems showed a lower witches’ broom incidence in cocoa than monocultures. Whereas, in plantain, there was a consistent black sigatoka incidence across spatial arrangements but a lower infection rate per leaf within mixed systems. We found varied nematode populations with monocultures hosting the highest root damage due to phytoparasitic nematodes. Weevil populations were also influenced by spatial arrangements with monocultures among the highest. Overall, mixed agroecosystems influence disease and pest incidence, potentially hindering pathogen spread. Plantain–cocoa associations reduce disease incidence in cocoa but may not affect the overall incidence of black sigatoka in plantain, at least during the establishment phase. Continued monitoring is crucial for understanding the long-term impacts and microclimatic effects on pest populations that could offer sustainable pest management strategies, reducing the reliance on chemical pesticides. Full article

Yellow and black Sigatoka, caused by Mycosphaerella fijiensis and M. musicola, respectively, are the most important worldwide foliar diseases of bananas. Disease control is heavily dependent on intensive fungicide sprays, which increase selection pressure for fungicide resistance in pathogen populations. The primary objective of this study was to assess the level and spread of resistance to quinone-outside inhibitors (QoI—strobilurin) fungicides in populations of both pathogens sampled from banana fields under different fungicide spray regimes in Southeastern Brazil. Secondly, we aimed to investigate when QoI resistance was confirmed if this was associated with the target-site alteration G143A caused by a mutation in the mitochondrial encoded cytochrome b gene. QoI resistance was detected in fungicide treated banana fields, while no resistance was detected in the organic banana field. A total of 18.5% of the isolates sampled from the pathogens’ populations were resistant to QoI. The newly described M. thailandica was also found. It was the second most abundant Mycosphaerella species associated with Sigatoka-like leaf spot symptoms in the Ribeira Valley and the highest level of QoI resistance was found for this pathogen. The G143A cytochrome b alteration was associated with the resistance to the QoI fungicides azoxystrobin and trifloxystrobin in M. fijiensis, M. musicola and M. thailandica strains. In order to reduce resistance development and maintain the efficacy of QoI fungicides, anti-resistance management strategies based on integrated disease management practices should be implemented to control the Sigatoka disease complex. Full article

Accurate predictions of crop production are critical to developing effective strategies at the farm level. Knowing banana production is due to the need to maximize the investment–profit ratio, and the availability of this information in advance allows decisions to be made about the management of important diseases. The objective of this study was to predict the number of banana bunches from epidemiological parameters of Black Sigatoka (BS), using random forests (RF) for its ability to predict crop production responses to epidemiological variables. Weekly production data (number of banana bunches) and epidemiological parameters of BS from three adjacent banana sites in Panama during 2015–2018 were used. RF was found to be very capable of predicting the number of banana bunches, with variance explained as 70.0% and root mean square error (RMSE) of 1107.93 ± 22 of the mean banana bunches observed in the test case. The site, week, youngest leaf spotted and youngest leaf with symptoms in plants with 10 weeks of physiological age were found to be the best predictor group. Our results show that RF is an efficient and versatile machine learning method for banana production predictions based on epidemiological parameters of BS due to its high accuracy and precision, ease of use, and usefulness in data analysis. Full article

Bananas are the main fruits responsible for feeding more than 500 million people in tropical and subtropical countries. Black Sigatoka, caused by the fungus Pseudocercospora fijiensis, is one of the most destructive disease for the crop. This fungus is mainly controlled with the use of fungicides; however, in addition to being harmful to human health, they are associated with a high cost. The development of resistant cultivars through crosses of susceptible commercial cultivars is one of the main focuses of banana breeding programs worldwide. Thus, the objective of the present study was to investigate the interaction between Musa sp. and P. fijiensis through the relative expression of candidate genes involved in the defence response to black Sigatoka in four contrasting genotypes (resistant: Calcutta 4 and Krasan Saichon; susceptible: Grand Naine and Akondro Mainty) using quantitative real-time PCR (RT–qPCR) in addition to histological and histochemical analyses to verify the defence mechanisms activated during the interaction. Differentially expressed genes (DEGs) related to the jasmonic acid and ethylene signalling pathway, GDSL-like lipases and pathogenesis-related proteins (PR-4), were identified. The number and distance between stomata were directly related to the resistance/susceptibility of each genotype. Histochemical tests showed the production of phenolic compounds and callosis as defence mechanisms activated by the resistant genotypes during the interaction process. Scanning electron microscopy (SEM) showed pathogenic structures on the leaf surface in addition to calcium oxalate crystals. The resistant genotype Krasan Saichon stood out in the analyses and has potential for use in breeding programs for resistance to black Sigatoka in banana and plantains. Full article

While Black Sigatoka Leaf Disease (Mycosphaerella fijiensis) has arguably been the most important pathogen affecting the banana industry over the past 50 years, there are no quantitative estimates of what risk factors determine its spread across the globe, nor how its spread has affected banana producing countries. This study empirically models the disease spread across and its impact within countries using historical spread timelines, biophysical models, local climate data, and country level agricultural data. To model the global spread a empirical hazard model is employed. The results show that the most important factor affecting first time infection of a country is the extent of their agricultural imports, having increased first time disease incidence by 69% points. In contrast, long distance dispersal due to climatic factors only raised this probability by 0.8% points. The impact of disease diffusion within countries once they are infected is modelled using a panel regression estimator. Findings indicate that under the right climate conditions the impact of Black Sigatoka Leaf Disease can be substantial, currently resulting in an average 3% reduction in global annual production, i.e., a loss of yearly revenue of about USD 1.6 billion. Full article

Timorex Gold based on the essential tea tree oil (TTO) derived from the Australian tea tree oil (Melaleuca alternifolia) plant has demonstrated high efficacy and a strong curative activity against black Sigatoka in banana and controlled it in stages 1, 2, 3, and 4 of disease development. Transmission electron microscope (TEM) examination of infected leaf sections treated with Timorex Gold revealed disruption of the fungal cell membrane and destruction of the fungal cell wall in disease development stages 4 and 5. Mineral oil and the fungicide difenoconazole, when applied alone, had no curative effect and did not disrupt the fungal cell wall or membrane, similar to the untreated control tissue. A single spray of Timorex Gold effectively controlled and suppressed powdery mildew in cucumber by causing the disappearance of 99% of established colonies recorded 1 or 2 days after the application and was effective for up to 8 days after application. Scanning electron microscope (SEM) examination of infected and Timorex Gold-treated leaves indicated strong shrinkage and disruption of fungal hyphae and conidial cells. The curative and suppressive modes of action of the Timorex Gold may explain its success in controlling both diseases. Full article

Black Sigatoka is the main constraint to banana production worldwide, and epidemic outbreaks are continuously causing huge losses. Successful management of diseases requires a profound knowledge of the epidemiological factors that influence disease dynamics. Information regarding alternative hosts of Pseudocercospora fijiensis, the causal agent, is still very scarce. To date, only Heliconia psittacorum has been reported as an alternative plant host, and we hypothesized that other plants can house P. fijiensis. In the present report, ten plant species with suspicious leaf spots were collected inside and around commercial banana crops in Mexico. Diagnostic PCR gave positive amplification for six of these plant species, and DNA sequencing confirmed the presence of the pathogen in four. This is the first report of the presence of P. fijiensis in unrelated plants and it represents a breakthrough in the current knowledge of black Sigatoka. This finding is very important given the polycyclic nature of this disease whose successful management requires the control of initial inoculum to minimize epidemic outbreaks. The results presented herein can be used to introduce innovations in integrated black Sigatoka management programs to reduce initial inoculum, and help the international initiative to reduce the use of fungicides in banana production. Full article

Black Sigatoka is a disease that occurs in banana plantations worldwide. This disease is caused by the hemibiotrophic fungus Pseudocercospora fijiensis, whose infection results in a significant reduction in both product quality and yield. Therefore, detection and identification in the early stages of this pathogen in plants could help minimize losses, as well as prevent the spread of the disease to neighboring cultures. To achieve this, a highly sensitive SPR immunosensor was developed to detect P. fijiensis in real samples of leaf extracts in early stages of the disease. A polyclonal antibody (anti-HF1), produced against HF1 (cell wall protein of P. fijiensis) was covalently immobilized on a gold-coated chip via a mixed self-assembled monolayer (SAM) of alkanethiols using the EDC/NHS method. The analytical parameters of the biosensor were established, obtaining a limit of detection of 11.7 µg mL⁻¹, a sensitivity of 0.0021 units of reflectance per ng mL⁻¹ and a linear response range for the antigen from 39.1 to 122 µg mL⁻¹. No matrix effects were observed during the measurements of real leaf banana extracts by the immunosensor. To the best of our knowledge, this is the first research into the development of an SPR biosensor for the detection of P. fijiensis, which demonstrates its potential as an alternative analytical tool for in-field monitoring of black Sigatoka disease. Full article