Search Results (36)

Banana is an important cash and food crop worldwide. Recent outbreaks of banana diseases are threatening the global banana industry and smallholder livelihoods. Remote sensing data offer the potential to detect the presence of disease, but formal analysis is needed to compare inferred disease data with observed disease data. In this study, we present a novel remote-sensing-based framework that combines Landsat-8 imagery with meteorology-informed phenological models and machine learning to identify anomalies in banana crop health. Unlike prior studies, our approach integrates domain-specific crop phenology to enhance the specificity of anomaly detection. We used a pixel-level random forest (RF) model to predict 11 key vegetation indices (VIs) as a function of historical meteorological conditions, specifically daytime and nighttime temperature from MODIS and precipitation from NASA GES DISC. By training on periods of healthy crop growth, the RF model establishes expected VI values under disease-free conditions. Disease presence is then detected by quantifying the deviations between observed VIs from Landsat-8 imagery and these predicted healthy VI values. The model demonstrated robust predictive reliability in accounting for seasonal variations, with forecasting errors for all VIs remaining within 10% when applied to a disease-free control plantation. Applied to two documented outbreak cases, the results show strong spatial alignment between flagged anomalies and historical reports of banana bunchy top disease (BBTD) and Fusarium wilt Tropical Race 4 (TR4). Specifically, for BBTD in Australia, a strong correlation of 0.73 was observed between infection counts and the discrepancy between predicted and observed NDVI values at the pixel with the highest number of infections. Notably, VI declines preceded reported infection rises by approximately two months. For TR4 in Mozambique, the approach successfully tracked disease progression, revealing clear spatial spread patterns and correlations as high as 0.98 between VI anomalies and disease cases in some pixels. These findings support the potential of our method as a scalable early warning system for banana disease detection. Full article

The sterol demethylation inhibitors (DMIs) are among the most widely used fungicides for controlling black Sigatoka (Mycosphaerella fijiensis) and yellow Sigatoka (Mycosphaerella musicola) in banana plantations in Brazil. Black Sigatoka is considered more important due to causing yield losses of up to 100% in commercial banana crops under predisposing conditions. In contrast, yellow Sigatoka is important due to its widespread occurrence in the country. This study aimed to determine the current sensitivity levels of Mf and Mm populations to DMI fungicides belonging to the chemical group of triazoles. Populations of both species were sampled from commercial banana plantations in Registro, Vale do Ribeira, São Paulo (SP), Ilha Solteira, Northwestern SP, and Janaúba, Northern Minas Gerais, and were further characterized phenotypically. Additionally, allelic variation in the CYP51 gene was analyzed in populations of these pathogens to identify and characterize major mutations and/or mechanisms potentially associated with resistance. Sensitivity to the triazoles propiconazole and tebuconazole was determined by calculating the 50% inhibitory concentration of mycelial growth (EC₅₀) based on dose–response curves ranging from 0 to 5 µg mL⁻¹. Variation in sensitivity to fungicides was evident with all nine Mf isolates showing moderate resistance levels to both propiconazole or tebuconazole, while 11 out of 42 Mm strains tested showed low to moderate levels of resistance to these triazoles. Mutations leading to CYP51 substitutions Y136F, Y461N/H, and Y463D in Mm and Y461D, G462D, and Y463D in Mf were associated with low or moderate levels of resistance to the triazoles. Interestingly, Y461H have not been reported before in Mm or Mf populations, and this alteration was found in combination with V106D and A446S. More complex CYP51 variants and CYP51 promoter inserts associated with upregulation of the target protein were not detected and can explain the absence of highly DMI-resistant strains in Brazil. Disease management programs that minimize reliance on fungicide sprays containing triazoles will be needed to slow down the further evolution and spread of novel CYP51 variants in Mf and Mm populations in Brazil. Full article

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

Fusarium wilt, caused by Fusarium oxysporum f. sp. cubense (Foc), is recognized as one of the most devastating diseases affecting banana cultivation worldwide. In India, Foc extensively affects Malbhog banana (AAB genomic group) production. In this study, we isolated 25 Foc isolates from wilt-affected Malbhog plantations inIndia. A pathogenicity test confirmed the identity of these isolates as Foc, the primary causative agent of wilt in bananas. The morpho-cultural characterization of Foc isolates showed large variations in colony morphological features, intensity, and pattern of pigmentation, chlamydospores, and conidial size. The molecular identification of these isolates using Race1- and Race4-specific primers established their identity as Race1 of Foc, with the absence of Tropical Race 4 of Foc. For a more comprehensive understanding of the genetic diversity of Foc isolates, we employed ISSR molecular typing, which revealed five major clusters. About 96% of the diversity within the Foc population indicated the presence of polymorphic loci in individuals of a given population evident from the results of Nei’s genetic diversity, Shannon’s information index, and the polymorphism information content values, apart from the analysis of molecular variance (AMOVA). The current findings provide significant insights toward the detection of Foc variants and, consequently, the deployment of effective management practices to keep the possible epidemic development of disease under control along the Malbhog banana growing belts of northeast India. Full article

Dopamine is a neurotransmitter which is classified as a catecholamine. It is also one of the main metabolites produced by some tumor types (such as paragangliomas and neoblastomas). As such, determining and monitoring the level of dopamine is of the utmost importance, ideally using analytical techniques that are sensitive, simple, and low in cost. Due to this, we have developed a non-enzymatic dopamine sensor that is highly sensitive, selective, and rapidly detects the presence of dopamine in the body. A hybrid material fabricated with NiO and ZnO, based on date fruit extract, was synthesized by hydrothermal methods and using NiO as a precursor material. This paper discusses the role of date fruit extracts in improving NiO’s catalytic performance with reference to ZnO and the role that they play in this process. An X-ray powder diffraction study, a scanning electron microscope study, and a Fourier transform infrared spectroscopy study were performed in order to investigate the structure of the samples. It was found that, in the composite NiO/ZnO, NiO exhibited a cubic phase and ZnO exhibited a hexagonal phase, both of which exhibited well-oriented aggregated cluster shapes in the composite. A hybrid material containing NiO and ZnO has been found to be highly electro-catalytically active in the advanced oxidation of dopamine in a phosphate buffer solution at a pH of 7.3. It has been found that this can be accomplished without the use of enzymes, and the range of oxidation used here was between 0.01 mM and 4 mM. The detection limit of non-enzymatic sensors is estimated to be 0.036 μM. Several properties of the non-enzymatic sensor presented here have been demonstrated, including its repeatability, selectivity, and reproducibility. A test was conducted on Sample 2 for the detection of banana peel and wheat grass, and the results were highly encouraging and indicated that biomass waste may be useful for the manufacture of medicines to treat chronic diseases. It is thought that date fruit extracts would prove to be valuable resources for the development of next-generation electrode materials for use in clinical settings, for energy conversion, and for energy storage. Full article

This study characterized an endophytic fungus, DJE2023, isolated from healthy banana sucker of the cultivar (cv.) Dajiao. Its potential as a biocontrol agent against banana Fusarium wilt was assessed, aiming to provide a novel candidate strain for the biological control of the devastating disease. The fungus was isolated using standard plant tissue separation techniques and fungal culture methods, followed by identification through morphological comparisons, multi-gene phylogenetic analyses, and molecular detection targeting Fusarium oxysporum f. sp. cubense (Foc) race 1 and race 4. Furthermore, assessments of its characteristics and antagonistic effects were conducted through pathogenicity tests, biological trait investigations, and dual-culture experiments. The results confirmed isolate DJE2023 to be a member of the Fusarium oxysporum species complex but distinct from Foc race 1 or race 4, exhibiting no pathogenicity to banana plantlets of cv. Fenza No.1 or tomato seedlings cv. money maker. Only minute and brown necrotic spots were observed at the rhizomes of banana plantlets of ‘Dajiao’ and ‘Baxijiao’ upon inoculation, contrasting markedly with the extensive necrosis induced by Foc tropical race 4 strain XJZ2 at those of banana cv Baxijiao. Notably, co-inoculation with DJE2023 and XJZ2 revealed a significantly reduced disease severity compared to inoculation with XJZ2 alone. An in vitro plate confrontation assay showed no significant antagonistic effects against Foc, indicating a suppressive effect rather than direct antagonism of DJE2023. Research on the biological characteristics of DJE2023 indicated lactose as the optimal carbon source for its growth, while maltose favored sporulation. The optimal growth temperature for this strain is 28 °C, and its spores can germinate effectively within the range of 25–45 °C and pH 4–10, demonstrating a strong alkali tolerance. Collectively, our findings suggest that DJE2023 exhibits weak or non-pathogenic properties and lacks direct antagonism against Foc, yet imparts a degree of resistance against banana Fusarium wilt. The detailed information provides valuable insight into the potential role of DJE2023 in integrated banana disease control, presenting a promising candidate for biocontrol against banana Fusarium wilt. Full article

Fusarium wilt of banana is a soil-borne vascular disease caused by Fusarium oxysporum f. sp. cubense. The rapid and accurate detection of this disease is of great significance to controlling its spread. The research objective was to explore rapid banana Fusarium wilt latency and onset detection methods and establish a disease severity grading model. Visible/near-infrared spectroscopy analysis combined with machine learning methods were used for the rapid in vivo detection of banana Fusarium wilt. A portable visible/near-infrared spectrum acquisition system was constructed to collect the spectra data of banana Fusarium wilt leaves representing five different disease grades, totaling 106 leaf samples which were randomly divided into a training set with 80 samples and a test set with 26 samples. Different data preprocessing methods were utilized, and Fisher discriminant analysis (FDA), an extreme learning machine (ELM), and a one-dimensional convolutional neural network (1D-CNN) were used to establish the classification models of the disease grades. The classification accuracies of the FDA, ELM, and 1D-CNN models reached 0.891, 0.989, and 0.904, respectively. The results showed that the proposed visible/near infrared spectroscopy detection method could realize the detection of the incubation period of banana Fusarium wilt and the classification of the disease severity and could be a favorable tool for the field diagnosis of banana Fusarium wilt. Full article

Fusarium wilt is a soil borne fungal disease that has devastated banana production in plantations around the world. Most Cavendish-type bananas are susceptible to strains of Fusarium oxysporum f. sp. cubense (Foc) belonging to the Subtropical Race 4 (STR4) and Tropical Race 4 (TR4). The wild banana diploid Musa acuminata ssp. malaccensis (AA, 2n = 22) carries resistance to Foc TR4. A previous study using segregating populations derived from M. acuminata ssp. malaccensis identified a quantitative trait locus (QTL) (12.9 cM) on the distal part of the long arm of chromosome 3, conferring resistance to both Foc TR4 and STR4. An SNP marker, based on the gene Macma4_03_g32560 of the reference genome ‘DH-Pahang’ v4, detected the segregation of resistance to Foc STR4 and TR4 at this locus. Using this marker, we assessed putative TR4 resistance sources in 123 accessions from the breeding program in Brazil, which houses one of the largest germplasm collections of Musa spp. in the world. The resistance marker allele was detected in a number of accessions, including improved diploids and commercial cultivars. Sequencing further confirmed the identity of the SNP at this locus. Results from the marker screening will assist in developing strategies for pre-breeding Foc TR4-resistant bananas. This study represents the first-ever report of marker-assisted screening in a comprehensive collection of banana accessions in South America. Accessions carrying the resistance marker allele will be validated in the field to confirm Foc TR4 resistance. Full article

The present work examines the relationship between aerial spraying and its health impacts on the population living in the banana production areas of Ecuador (the rural sectors of the cantons Milagro and Naranjito, Guayas Province). Objectives: the objectives of this study are to obtain information on sanitation, basic services, and environmental rationality and to interpret the low levels of cholinesterase and prevalent diseases among the population. Methods: the methodology involved a face-to-face questionnaire, the formal authorization of an informed consent document, and venipuncture for cholinesterase tests. The information was processed in the EPI–INFO system 7.2 (statistical software for professionals and researchers dedicated to public health), with the certification of protocols issued by the Bioethics Committee of the Kennedy Hospital Clinic of Ecuador. Results: the results showed that 89.5% of inhabitants do not have access to drinking water, 92.5% do not have a sewage disposal service, 97.50% experience aerial spraying at their homes or workplaces, and 57% have low cholinesterase levels. Additionally, several gastrointestinal, respiratory, neurological, dermatological, and reproductive disorders were detected among the inhabitants. Conclusions: we found that companies in the banana sector have not implemented corporate social responsibility measures. For example, no blood tests are conducted to monitor cholinesterase levels or to track hereditary disorders. Moreover, entities such as the Ministry of Public Health have not taken action to serve this at-risk population. Full article

This Special Issue contains a selection of papers dealing with Fusarium wilt of banana (FWB), with a special focus on the Fusarium strain Tropical Race 4 (TR4), and explores (1) options for effective integrated management strategies, (2) the detection and development of disease-resistant cultivars, and (3) the distribution and diversity of the pathogen [...] 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

Volatile organic compounds (VOCs), as a biological element released from plants, have been correlated with disease status. Although analysis of VOCs using GC-MS is a routine procedure, it has limitations, including being time-consuming, laboratory-based, and requiring specialist training. Electronic nose devices (E-nose) provide a portable and rapid alternative. This is the first pilot study exploring three types of commercially available E-nose to assess how accurately they could detect mango twig tip dieback and Panama disease in bananas. The devices were initially trained and validated on known volatiles, then pure cultures of Pantoea sp., Staphylococcus sp., and Fusarium odoratissimum, and finally, on infected and healthy mango leaves and field-collected, infected banana pseudo-stems. The experiments were repeated three times with six replicates for each host-pathogen pair. The variation between healthy and infected host materials was evaluated using inbuilt data analysis methods, mainly by principal component analysis (PCA) and cross-validation. GC-MS analysis was conducted contemporaneously and identified an 80% similarity between healthy and infected plant material. The portable C 320 was 100% successful in discriminating known volatiles but had a low capability in differentiating healthy and infected plant substrates. The advanced devices (PEN 3/MSEM 160) successfully detected healthy and diseased samples with a high variance. The results suggest that E-noses are more sensitive and accurate in detecting changes of VOCs between healthy and infected plants compared to headspace GC-MS. The study was conducted in controlled laboratory conditions, as E-noses are highly sensitive to surrounding volatiles. Full article

The Sigatoka disease complex (SDC), caused by Mycosphaerella fijiensis (Mf) and M. musicola (Mm), comprises the most destructive fungal leaf streak and spot diseases of commercial banana crops worldwide. In Brazil, the site-specific succinate dehydrogenase inhibitor (SDHI) fungicides labeled for SDC management since 2014 present a high risk for the emergence of resistance if deployed intensively and solo. Our study determined the levels of sensitivity to boscalid and fluxapyroxad in four populations of the SDC pathogens sampled in 2020 from three distinct geographical regions under contrasting fungicide programs. Resistance, defined as EC₅₀ values exceeding 20 µg mL⁻¹, was prevalent at 59.7% for fluxapyroxad and 94.0% for boscalid. Only 1.5% of isolates exhibited sensitivity to both fungicides. We also assessed the changes in the corresponding fungicide target protein-encoding genes (SdhB, C, and D). None of the target site alterations detected were associated with reduced sensitivity. A second SdhC paralog was also analyzed, but target alterations were not found. However, MDR (multidrug resistance) was detected in a selection of isolates. Further monitoring for Sdh target mutations will be important, but an important role for other resistance mechanisms such as the presence of additional Sdh paralogs and MDR cannot be ruled out. These results highlight the importance of implementing sound anti-resistance management strategies when SDHI fungicides are deployed for the management of SDC. Full article

Banana bunchy top disease (BBTD) is an invasive viral disease spreading in Africa. It is transmitted by banana aphids and infected planting material, causing production losses. Clean seeds and timely eradication of diseased plants are effective tools in BBTD management. These depend on timely disease detection. We assessed the relationship between symptom expression and infectivity of the virus in four cultivars of banana. Plantlets from four cultivars, ‘FHIA 25’; ‘Aloga’; ‘Ebenga’ and ‘Sotoumon’, were exposed to viruliferous aphids and monitored for symptom expression. They were also tested as sources for virus transmission fortnightly by allowing non-viruliferous aphids acquisition access prior to transfer to healthy test plants. The time required to show symptoms and the symptom expression were compared, and infection tested by PCR. Disease expression varied from four weeks in ‘FHIA 25’ to fifteen in ‘Sotoumon’. Only the symptomatic leaves tested positive and could act as infection sources. Overall, ‘FHIA 25’ was the most susceptible cultivar, while ‘Sotoumon’ was the least susceptible and most rapidly expressive of BBTD, yet there was no difference in the leaf emergence rate between the cultivars. These results present important aspects of BBTD control and the safety of planting materials that should be tested in the field. Full article

Recently, Panama wilt disease that attacks banana leaves has caused enormous economic losses to farmers. Early detection of this disease and necessary preventive measures can avoid economic damage. This paper proposes an improved method to predict Panama wilt disease based on symptoms using an agro deep learning algorithm. The proposed deep learning model for detecting Panama wilts disease is essential because it can help accurately identify infected plants in a timely manner. It can be instrumental in large-scale agricultural operations where Panama wilts disease could spread quickly and cause significant crop loss. Additionally, deep learning models can be used to monitor the effectiveness of treatments and help farmers make informed decisions about how to manage the disease best. This method is designed to predict the severity of the disease and its consequences based on the arrangement of color and shape changes in banana leaves. The present proposed method is compared with its previous methods, and it achieved 91.56% accuracy, 91.61% precision, 88.56% recall and 81.56% F1-score. Full article