Plant Diseases Research Articles

Cultivable root endophytic fungi associated with Acrocomia aculeata and its antagonistic activity against phytopathogenic oomycetes.

Macaw palm (Acrocomia aculeata Jacq.) is a palm, native to Brazilian territory that stands out due to the amount of oil produced with applications in the biodiesel industry, cosmetics, and food. Its commercial exploitation in Brazil, including phytosanitary management is based on concepts and practices of regenerative agriculture, which has the responsibility of sustainable cultivation by avoiding, for example, the use of chemical pesticides. Recently, root and stem rot disease were reported in macaw palm seedlings caused by Phytophthora palmivora. Managing this plant pathogen is complex, and the chemical control of this soil-borne oomycete is not viable, in addition to the negative impact on the environment. Many microorganisms are studied and used as biological control agents (BCAs) against pathogens, among them the community of endophytic fungi associated with plants. This is a sustainable biotechnological alternative for plant disease control. The community of cultivable endophytic fungi associated with healthy roots of macaw palm was explored using the extinction cultivation technique and a screening was carried out to select potential antagonists against oomycetes through the dual culture test. Specific gene regions from the best isolates were amplified for identification. A total of 250 isolates were obtained, and 46 were selected for in vitro tests against representatives of phytopathogenic oomycetes. After tests against Phytophthora heterospora, Phytophthora palmivora, Pythium aphanidermatum, and Pythium deliense, two isolates were selected as potential antagonists. The phylogenetic analysis of selected isolates showed that they belong to two different species: Talaromyces sayulitensis COAD 3605 and Epicoccum italicum COAD 3608. The percentage of inhibition of phytopathogenic oomycetes testedwas until 82% in the antagonism tests conducted. From the 46 isolates selected, only 2 were selected which showed great antagonistic activity towards all oomycetes tested. These fungi will be used in upcoming studies that aim to determine the effectiveness of endophytes in controlling diseases caused by oomycetes in the field.

Soil health is associated with higher primary productivity across Europe.

Soil health is expected to be of key importance for plant growth and ecosystem functioning. However, whether soil health is linked to primary productivity across environmental gradients and land-use types remains poorly understood. To address this gap, we conducted a pan-European field study including 588 sites from 27 countries to investigate the link between soil health and primary productivity across three major land-use types: woodlands, grasslands and croplands. We found that mean soil health (a composite index based on soil properties, biodiversity and plant disease control) in woodlands was 31.4% higher than in grasslands and 76.1% higher than in croplands. Soil health was positively linked to cropland and grassland productivity at the continental scale, whereas climate best explained woodland productivity. Among microbial diversity indicators, we observed a positive association between the richness of Acidobacteria, Firmicutes and Proteobacteria and primary productivity. Among microbial functional groups, we found that primary productivity in croplands and grasslands was positively related to nitrogen-fixing bacteria and mycorrhizal fungi and negatively related to plant pathogens. Together, our results point to the importance of soil biodiversity and soil health for maintaining primary productivity across contrasting land-use types.

First report of Fusarium oxysporum f. sp. fragariae race 1 causing Fusarium wilt of strawberry (Fragaria × ananassa) in the Alentejo region of Portugal.

In the summer of 2023, within the Alentejo region (Portugal), a new occurrence of a plant disease of strawberry (Fragaria × ananassa) cv. 'Monterey' was observed in a Spring commercial planting. Symptoms consisted of foliar wilting, drying of older leaves, deformed and highly chlorotic leaflets, crown discoloration, plant stunting, and in some cases death. Several outbreak foci, covering nearly half a hectare, were observed within the affected farm, with almost 80% of the plants showing symptoms. Four samples,of 6 plants, were collected from 4 locations within the field. Petiole sections (1 cm) were rinsed with 0.1% Tween 20, submersed in 70% EtOH for 20 s followed by 60 s in 1% NaOCL, and then placed on Komada's medium (Komada, 1975). After incubation at room temperature in the dark for a week, white-colored fluffy mycelia grew profusely from the petioles of all samples. Colony morphology and non-septate, ellipsoidal microconidia (5.7-12.4×2.5-4.3 μm) borne on monophialides, exhibited a resemblance to Fusarium oxysporum (Leslie and Summerell, 2006). Ten single strains were obtained from different plants by single hyphal tip isolation. For molecular confirmation, a portion of the translation elongation factor 1-alpha (EF1α) was amplified by PCR using EF1/EF2 primers (O'Donnell et al., 1998). Additionally, the RNA polymerase subunit RPB2 was amplified as two contiguous fragments via primers and protocols described by O'Donnell et al., 2021. Amplicons were sequenced (GenBank Accession Nos. PP426617 - 426626, PQ058494 - 058513). Using Fusarium-ID and Fusarioid-ID databases, EF1α and RPB2 sequences were found to be more than 99% identical to published F. oxysporum type isolates and Fusarium sp. isolates in the F. oxysporum species complex (Crous et al., 2021; Wang et al., 2022). A specific F. oxysporum f. sp. fragariae (Fof) qPCR assay (Burkhardt et al., 2019) was used to determine if these isolates could be Fof race 1. A Fof race 1 isolate (MAFF305558), negative controls, and water controls were included. All ten isolates and the Fof race 1 control were positive (Ct < 30), while other Fusarium spp. used as negative controls and the water controls did not amplify. Two isolates (F.200 and F.202) and MAFF305558 (positive control) were included in a pathogenicity test on two strawberry cultivars, 'Monterey' (susceptible to race 1) and 'Fronteras' (resistant to race 1) (Dilla-Ermita et al., 2023). Each isolate was included in two independent trials. In each trial, 5 plants per cultivar were inoculated by dipping roots for 10 min in 5 × 106 conidia/mL of 0.1% water agar (WA) or in sterile 0.1% WA for the negative control plants. Each plant was then planted in a pot filled with peat. Pots were placed randomly in random positions in a growth chamber at 28/20°C and 12h photoperiod. After 8 - 10 weeks, the control plants and 'Fronteras' plants remained healthy, while the inoculated plants cv. 'Monterey' were severely wilted and/or dead. Fusarium oxysporum was re-isolated from all symptomatic plants. Recovered isolates were confirmed to be the same as the inoculated ones using the Fof-qPCR, including the same controls as above. This is the first report of Fof race 1 in the Iberian Peninsula. Given that the land was not previously used for strawberry, it is highly probable that the pathogen was introduced with the planting material originated from a Spanish nursery. In conclusion, it is imperative to implement more severe control measures in nurseries to avoid the spread of this race.

Endophytes infection increased the disease resistance of host Achnatherum sibiricum and non-symbiotic neighbours to pathogenic fungi

Epichloë infection can affect the fungal disease resistance of host grasses. However, few studies have been reported on the effects of endophyte infection on non-symbiotic neighbours. We surveyed the plant diseases in natural grassland, and compared differences of total disease index between neighboring and non-neighboring plants of Achnatherum sibiricum. Then laboratory experiments were conducted to investigate the effects of endophyte on the growth of four pathogen species as well as the brown patch of the host and its neighboring plants. The results of plant disease investigation in natural grassland showed that the major epidemic diseases of grasses were spot blight, rust disease and powdery mildew in Hulunbuir natural grassland. Among common herbages, the total disease index of endophyte-infected A. sibiricum was the lowest. Compared with non-neighboring plants, the brown patch disease index of Leymus chinensis, Stipa baicalensis and Agropyron cristatum was significantly reduced when neighbouring with A. sibiricum. The laboratory experiments results showed that the culture filtration of both Epichloë gansuensis and Epichloë sibiricum significantly restrained the growth of Curvularia lunata, Bipolaris sorokiniana, Sclerotinia sclerotiorum and Sclerotinia trifoliorum. The two species of endophytes could reduce lesion area of detached host leaves. In vivo plant experiments, the endophyte reduced the disease resistance of both the host and its neighbor grasses L. chinensis to C. lunata and B. sorokiniana. This study first verified that the endophytes in A. sibiricum have a positive effect on disease resistance of neighbor grasses to brown patch. The study contributes to the understanding of endophyte-host interactions and suggests potential applications of endophytes in biological control strategies for grassland management.

Study of bacterium associated with Spinacia oleracea and nematode, Pseudomonas fragi using 16S rDNA from Limpopo Province, South Africa

Microorganisms known as Plant-associated Pseudomonas can thrive as parasites or saprophytes on plant surfaces and within plant tissues. They are crucial in enhancing plant growth by suppressing pathogenic microorganisms, synthesizing growth-stimulating plant hormones, and boosting plant disease resistance. At the University of Limpopo in South Africa, a molecular study was conducted in 2023 to identify a Pseudomonas bacterium in a spinach field associated with a free-living nematode, Acrobeles complexus, in Limpopo Province. The study utilized the Chelex method to extract DNA and the 16S rDNA marker to identify the bacterium as Pseudomonas fragi. Specific primers were then used to amplify 16S rDNA, which identified the bacterium, and Nblast analysis revealed a 96% similarity to a strain from India. Phylogenetic analysis placed this species with those identified as P. fragi in the same clade with highly supported (100) bootstrap values. This marker (16S rDNA) is recommended to use. But for a better understanding of P. fragi's phylogeny, the other DNA markers are recommended to identify this species.

Design, Synthesis, and Bioactivity Determination of Novel Malononitrile Derivatives Containing 1,2,3-Triazole.

Using antifungal agrochemicals as the most economical solution might reduce plant diseases caused by pathogenic fungi, which have a significant negative impact on the quality and yield of food worldwide. In this work, 33 compounds (G) containing 1,2,3-triazole and malononitrile structures were synthesized. When the compounds were tested in vitro against six fungal species, they exhibited significant fungicidal activity toward Botrytis cinerea and Rhizoctonia solani. Compounds G17 and G30 displayed promising in vivo efficacy, with an EC50 of 0.19 and 0.27 mg/L respectively against R. solani. Fungal ergosterol production was suppressed by compounds G17 and G30, according to a preliminary analysis of their mechanism of action on R. solani using transcriptomics and scanning electron microscopy. It has been shown through experimentation that compounds G17 and G30 prevent R. solani from synthesizing ergosterol. Ultimately, it was anticipated that compounds G17 and G30 would be discovered to be low-toxic.

Strategic biological control of difficult-to-control plant diseases and pests for sustainable agriculture

Strategic biological control of difficult-to-control plant diseases and pests for sustainable agriculture

Pathogen-driven Pseudomonas reshaped the phyllosphere microbiome in combination with Pseudostellaria heterophylla foliar disease resistance via the release of volatile organic compounds

BackgroundContinuous monocropping obstacles are common in plants, especially medicinal plants, resulting in disease outbreaks and productivity reductions. Foliar disease, mainly caused by Fusarium oxysporum, results in a severe decrease in the yield of Pseudostellaria heterophylla annually. Determining an effective biomethod to alleviate this disease is urgently needed to improve its productivity and quality.ResultsThis study screened thirty-two keystone bacterial genera induced by pathogens in P. heterophylla rhizosphere soil under continuous monocropping conditions. Pseudomonas, Chryseobacterium, and Flavobacterium, referred to as the beneficial microbiota, were significantly attracted by pathogen infection. The P. palleroniana strain B-BH16-1 can directly inhibit the growth and spore formation of seven primary pathogens of P. heterophylla foliar disease by disrupting fusaric acid production via the emission of volatile organic compounds (VOCs). In addition, strain B-BH16-1 enhances the disease resistance of P. heterophylla by obliterating the pathogen and assembling beneficial microbiota.ConclusionPathogen-induced Pseudomonas reshaped phyllosphere microbial communities via direct antagonism of pathogens and indirect disruption of the pathogen virulence factor biosynthesis to enhance disease suppression and improve yields. These results show that inhibiting pathogen virulence biosynthesis to reshape the plant microbial community using disease-induing probiotics will be an innovative strategy for managing plant disease, especially under continuous monoculture conditions.

Non-chemical management of fungal diseases in berries: A review

Abstract Organically grown berries are highly valued for their significant economic and nutritional benefits, playing a crucial role in fostering sustainable agriculture. However, meeting the escalating demand for organic berries while sustaining profitable yields of top-quality produce remains challenging, primarily due to the obstacles presented by plant diseases and significant insect pests acting as vectors. Globally, significant losses in organic berry agriculture stem from pathogenic organisms such as bacteria, viruses, fungi, oomycetes, nematodes, and parasitic plants. Although chemical pesticides have historically served as effective control measures, their high costs and potential environmental and health risks necessitate exploring alternative approaches. Consequently, there have been groundbreaking advancements in biological methods for disease management, driven by an enhanced understanding of the intricate interactions between plant pathogens and the plant immune system. This comprehensive analysis elucidates the common pests and diseases affecting organic berry crops, with particular emphasis on fungal pathogens posing the greatest risk. The review documents efficient management strategies to mitigate the harm caused by fungal infections, focusing on biological control using antagonistic microorganisms. Thanks to years of intensive research, numerous commercially available products showcasing the effectiveness of biological control in combating pathogenic threats in organic berry crops have emerged. Furthermore, our review provides insights into recent advancements in the diagnosis and detection of plant diseases, encompassing both time-tested approaches from the previous generations and important methods currently in use. Ultimately, this review aims to help organic berry growers implement successful eco-friendly management strategies to safeguard their crops and boost yields by offering an overview of the latest developments in disease management.

Water Wheel Plant Dingo Optimizer enabled Deep Convolutional Neural Network for disease detection using hyperspectral leaf image

ProblemIn many countries, agriculture is themain sourceofpeople’s livelihoodandsatisfiestheir nutritional needs.Earlydetection ofplantdiseases throughagriculturalremote monitoringis important to prevent the disease’s spread. The traditional methods require sampling and can damage the plant, but hyperspectral imaging is non-destructive. AimThe major aim of this research is to devise a Water Wheel Plant Dingo Optimizer_Deep Convolutional Neural Network (WWPDO_Deep CNN) for disease detection using a hyperspectral leaf image. MethodsInitially, the input leaf image is given into the leaf segmentation phase, which is done using the proposed Water Wheel Plant Dingo Optimizer (WWPDO), which is the amalgamation of the Water Wheel Plant Algorithm (WWPA) and Dingo Optimizer (DOX). The selected bands’ outputs are subjected to leaf segmentation and which is carried out by employing Bayesian Fuzzy Clustering (BFC). Thereafter, leaf segmented outputs are fussed using the majority voting method. Fused output and individual leaf segmentation output are given into the feature extraction process to extract features, such as local binary patterns and Weber local descriptors. Finally, leaf disease detection is performed using a deep Convolutional Neural Network (Deep CNN) for normal and abnormal cases. The hyperparameters of the Deep CNN are fine-tuned based on the proposed WWPADO. ResultsThe proposed WWPDO_Deep CNN achieved an excellent performance with an accuracy of 91.35 %, a True Positive Rate (TPR) of 93.13 % and a True Negative Rate (TNR) of 90.76 %. ConclusionThe WWPDO_Deep CNN is applicable for early diagnosis under the new classification system and provides a new direction for early diagnosis based on hyperspectral images. Also, the devised model provides an accurate diagnosis of plant diseases. Early and accurate detection allows targeted treatment, reduces the need for widespread pesticide application and promotes more sustainable farming practices.

Nutrient requirements shape the preferential habitat of Allorhizobium vitis VAR03-1, a commensal bacterium, in the rhizosphere of Arabidopsis thaliana.

A diverse range of commensal bacteria inhabit the rhizosphere, influencing host plant growth and responses to biotic and abiotic stresses. While root-released nutrients can define soil microbial habitats, the bacterial factors involved in plant-microbe interactions are not well characterized. In this study, we investigated the colonization patterns of two plant disease biocontrol agents, Allorhizobium vitis VAR03-1 and Pseudomonas protegens Cab57, in the rhizosphere of Arabidopsis thaliana using Murashige and Skoog (MS) agar medium. VAR03-1 formed colonies even at a distance from the roots, preferentially in the upper part, while Cab57 colonized only the root surface. The addition of sucrose to the agar medium resulted in excessive proliferation of VAR03-1, similar to its pattern without sucrose, whereas Cab57 formed colonies only near the root surface. Overgrowth of both bacterial strains upon nutrient supplementation inhibited host growth, independent of plant immune responses. This inhibition was reduced in the VAR03-1 ΔrecA mutant, which exhibited increased biofilm formation, suggesting that some activities associated with the free-living lifestyle rather than the sessile lifestyle may be detrimental to host growth. VAR03-1 grew in liquid MS medium with sucrose alone, while Cab57 required both sucrose and organic acids. Supplementation of sugars and organic acids allowed both bacterial strains to grow near and away from Arabidopsis roots in MS agar. These results suggest that nutrient requirements for bacterial growth may determine their growth habitats in the rhizosphere, with nutrients released in root exudates potentially acting as a limiting factor in harnessing microbiota.

Advances in understanding plant-pathogen interactions: insights from tomato as a model system.

The impact of plant diseases coupled with climate change on agriculture worldwide cannot be overemphasized from negative effects on crop yield as well as economy to food insecurity. The model plants are essential for understanding the intricacies of plant-pathogen interactions. One of such plants is the tomato (Solanum lycopersicum L.). Researchers hope to increase tomato productivity and boost its resilience to pathogen attacks by utilizing OMICS and biotechnological methods. With an emphasis on tomato viral infections, this review summarizes significant discoveries and developments from earlier research. The analysis elucidates ongoing efforts to advance plant pathology by exploring the implications for sustainability and tomato production.

Characterization and Identification of Potential Lactic Acid Bacteria as Biological Control Agent against Ralstonia syzygii subsp. celebesensis of the Banana Blood Disease

Banana is one of the primary fruits cultivated in Malaysia and currently decimated by the emergence of a disease, known as banana blood disease (BBD) which caused by Ralstonia syzygii subsp. celebesensis (Rsc). The BBD has significantly affected the yield and profits of the worldwide banana industry. To date, various approaches including chemical and biological controls have been attempted to manage this disease but none of them succeed in controlling the disease. The uses of lactic acid bacteria (LAB) in managing plant diseases have been reported earlier but little information is available. Therefore, this project is designed to identify and investigate potential plant-associated LAB as biological control agent (BCA) against Rsc by using agar well diffusion method. The inhibition zones of each well were observed after 72h and the isolated LAB that showed inhibition zones were proceed for molecular characterization using PCR amplification followed by gel electrophoresis. The sequences were used for phylogenetic analysis. In addition, each of the potential LAB were used to identify their morphological characterizations and biochemical testing. Throughout the study, the highest inhibition zones of LAB from kimchi and fermented milk achieved a diameter of 21.30 mm and 28.70 mm, respectively. Kimchi isolates showed the highest similarity which is 97% as Lactiplantibacillus plantarum species. Among the fermented milk isolates, the highest similarity which is 98% identified as Lacticaseibacillus paracasei.

Multi-Class Classification and Transfer Learning for Rapid Disease Detection in Green Leafy Vegetables Using Convolutional Neural Networks

Plant diseases cause various pathogens, including bacteria, viruses, fungi, and protozoa. Plant diseases and pathogens have an impact on the entire crop and field area. Plant diseases can be identified by various techniques; however, traditional techniques are time-consuming and require more effort. Up-to-date machine learning based approaches are used to identify plant diseases based on the image data. This study investigated the application of convolutional neural network (CNN) models for the detection and classification of diseases affecting green leafy vegetables. Several state-of-the-art CNN architectures, including InceptionV3 and DenseNet121, were evaluated on an image dataset of diseased and healthy leaf samples. Preprocessing techniques such as scaling, cropping, grayscale conversion, and normalization were applied to enhance the input images. The CNN models demonstrated high diagnostic accuracy, with InceptionV3 and DenseNet121 exhibiting exceptional performance across multiple metrics like sensitivity, specificity, accuracy, recall, F-measure, and Matthews correlation coefficient (MCC).

Genetically divergent 'Candidatus Phytoplasma solani' isolates in Croatian vineyard pathosystems suggest complex epidemiological networks

'Candidatus Phytoplasma solani’ (CPs), a phytoplasma endemic to the Euro-Mediterranean basin is a causative agent of several plant diseases, including the grapevine yellows disease “bois noir” (BN). As different CPs strains have been shown to have different ecological reservoirs and pathways for spread, the genetic characterization of CPs strains is a prerequisite, and better control of BN relies on the identification of reservoir plants. The variability of the phytoplasma genotypes involved in the BN pathosystem in Croatian vineyards was assessed by a multilocus sequence typing (MLST) approach. The genotyping was performed on selected grapevine, wild plants, and insects collected within the eleven years of national survey conducted in all Croatian viticultural regions. The extensive tuf, secY, stamp, and vmp1 genes-based MLST analyses revealed two new genotypes for stamp and vmp1 genes, designated as ST59 and V28, respectively, and overall identified 28 different CPs MLST genotypes. The prevalent MLST genotype in grapevine CPsSqt21 (S6/ST6/V18/tuf-b2) was widespread in nine counties across Uplands, Slavonia, and Danube wine regions and was affiliated to the known vector Hyalesthes obsoletus and to Urtica dioica. The other two most frequent genotypes were the U. dioica-associated CPsSqt28 (S39/ST46/V3/tuf-a) and the C. arvensis-associated CPsSqt2 (S1/ST9/V4/tuf-b1). CPs of different vmp1 genotypes was also detected in Cixius wagneri specimens originating from different parts of Croatia. In addition, CPs was detected in several Dichtyophara europaea insects and in two new potential plant reservoirs Ailanthus altissima and Robinia pseudoacacia. The substantial number of found MLST genotypes indicates the presence of several independent epidemiological cycles and is certainly a consequence of a unique geographical position of Croatia, bridging the different eco-climatic areas of central and south-eastern Europe.

Prune-FSL: Pruning-Based Lightweight Few-Shot Learning for Plant Disease Identification

Prune-FSL: Pruning-Based Lightweight Few-Shot Learning for Plant Disease Identification

Anti-Aflatoxigenic Burkholderia contaminans BC11-1 Exhibits Mycotoxin Detoxification, Phosphate Solubilization, and Cytokinin Production.

The productivity and quality of agricultural crops worldwide are adversely affected by disease outbreaks and inadequate nutrient availability. Of particular concern is the potential increase in mycotoxin prevalence due to crop diseases, which poses a threat to food security. Microorganisms with multiple functions have been favored in sustainable agriculture to address such challenges. Aspergillus flavus is a prevalent aflatoxin B1 (AFB1)-producing fungus in China. Therefore, we wanted to obtain an anti-aflatoxigenic bacterium with potent mycotoxin detoxification ability and other beneficial properties. In the present study, we have isolated an anti-aflatoxigenic strain, BC11-1, of Burkholderia contaminans, from a forest rhizosphere soil sample obtained in Luzhou, Sichuan Province, China. We found that it possesses several beneficial properties, as follows: (1) a broad spectrum of antifungal activity but compatibility with Trichoderma species, which are themselves used as biocontrol agents, making it possible to use in a biocontrol mixture or individually with other biocontrol agents in an integrated management approach; (2) an exhibited mycotoxin detoxification capacity with a degradation ratio of 90% for aflatoxin B1 and 78% for zearalenone, suggesting its potential for remedial application; and (3) a high ability to solubilize phosphorus and produce cytokinin production, highlighting its potential as a biofertilizer. Overall, the diverse properties of BC11-1 render it a beneficial bacterium with excellent potential for use in plant disease protection and mycotoxin prevention and as a biofertilizer. Lastly, a pan-genomic analysis suggests that BC11-1 may possess other undiscovered biological properties, prompting further exploration of the properties of this unique strain of B. contaminans. These findings highlight the potential of using the anti-aflatoxigenic strain BC11-1 to enhance disease protection and improve soil fertility, thus contributing to food security. Given its multiple beneficial properties, BC11-1 represents a valuable microbial resource as a biocontrol agent and biofertilizer.

Development of integrated factor modeling: Inhibiting Ganoderma lignocellulosic enzymes while promoting Trichoderma sporulation for enhanced plant disease control

Ganoderma, a fungal pathogen, is the causal agent for basal stem rot disease in oil palms, which has led to significant losses in palm oil production. The fungal production of lignocellulosic enzymes is crucial for successful infection, hence the disease severity could be significantly reduced by inhibiting these enzymes. The current study investigated the impact of integrated factors on inhibiting these enzymes and promoting Trichoderma virens spore production using response surface methodology. The identified optimal conditions of temperature (27.5–36.5 °C), boron (0.07–0.30 mg/mL), potassium (3.5 mg/mL), and mancozeb (1.0 mg/mL) can lead to the production of ≥5.0✕105 spores/mL of T. virens, while minimizing the laccase, cellulase, and xylanase activities to ≤0.08, 0.0, and 0.0 U/mL, respectively. The model's prediction accuracy was 81.25 %. In a greenhouse application, soil temperature was increased to 43.7 °C by solarization before applying the optimal concentration of boron, potassium, mancozeb, and T. virens. The results demonstrated the inhibition of lignocellulosic enzymes in G. boninense, as indicated by 69.0 % and 68.7 % lignocellulose contents in Trichoderma-treated and Ganoderma + Trichoderma-treated oil palm roots, respectively, which were higher than that in Ganoderma-treated roots (58.1 %). This highlights the practical relevance of our findings. Therefore, these results will help the oil palm growers to develop disease management strategies to control basal stem rot.

Tomato Leaf Disease Classification by Combining EfficientNetv2 and a Swin Transformer

Recently, convolutional neural networks (CNNs) and self-attention mechanisms have been widely applied in plant disease identification tasks, yielding significant successes. Currently, the majority of research models for tomato leaf disease recognition rely solely on traditional convolutional models or Transformer architectures and fail to capture both local and global features simultaneously. This limitation may result in biases in the model’s focus, consequently impacting the accuracy of disease recognition. Consequently, models capable of extracting local features while attending to global information have emerged as a novel research direction. To address these challenges, we propose an Eff-Swin model that integrates the enhanced features of the EfficientNetV2 and Swin Transformer networks, aiming to harness the local feature extraction capability of CNNs and the global modeling ability of Transformers. Comparative experiments demonstrate that the enhanced model has achieved a further increase in training accuracy, reaching an accuracy rate of 99.70% on the tomato leaf disease dataset, which is 0.49~3.68% higher than that of individual network models and 0.8~1.15% higher than that of existing state-of-the-art combined approaches. The results show that integrating attention mechanisms into convolutional models can significantly enhance the accuracy of tomato leaf disease recognition while also offering the great potential of the Eff-Swin backbone with self-attention in plant disease identification.

Deep learning for mango leaf disease identification: A vision transformer perspective

Over the last decade, the use of machine learning in smart agriculture has surged in popularity. Deep learning, particularly Convolutional Neural Networks (CNNs), has been useful in identifying diseases in plants at an early stage. Recently, Vision Transformers (ViTs) have proven to be effective in image classification tasks. These architectures often outperform most state-of-the-art CNN models. However, the adoption of vision transformers in agriculture is still in its infancy. In this paper, we evaluated the performance of vision transformers in identification of mango leaf diseases and compare them with popular CNNs. We proposed an optimized model based on a pretrained Data-efficient Image Transformer (DeiT) architecture that achieves 99.75% accuracy, better than many popular CNNs including SqueezeNet, ShuffleNet, EfficientNet, DenseNet121, and MobileNet. We also demonstrated that vision transformers can have a shorter training time than CNNs, as they require fewer epochs to achieve optimal results. We also proposed a mobile app that uses the model as a backend to identify mango leaf diseases in real-time.