Early and accurate detection of pigeon pea leaf diseases is essential for improving crop productivity and ensuring food security, particularly under real-field agricultural conditions. This paper introduces a shallow and computationally off-the-shelf deep learning system to detect the presence of pigeon pea leaf disease with great accuracy and in real-time on resource-limited cameras. DSLR and smartphone cameras were used to make up a custom high-resolution dataset under natural field conditions, including healthy leaves and major diseases, such as Fusarium wilt, leaf spot, and powdery mildew. All the images were downsampled to 224 × 224 pixels and processed with a Gaussian smoothing filter to remove noise and a Canny edge detector to improve structural features. Disease regions were accurately isolated using a Skill Optimization Algorithm (SOA)-driven segmentation strategy that dynamically optimized threshold levels, morphological kernel sizes, and lesion area constraints to handle background clutter and illumination variations. A pretrained EfficientNet-B0 model was used to extract deep semantic features, which consisted of compact 1280-dimensional feature vectors. A novel FMDDCN approach was used to classify these features through exploiting the sensitivity to subtle disease patterns by relying on differential feature modeling and multi-layer fusion of features. The model was fitted on stochastic gradient descent with a learning rate of 1 x 10-3 and a batch size of 32, and assessed on a 60/20/20 train validation test split with 5-fold cross-validation. The results of the experiment show consistent convergence with low overfitting. The proposed framework was found to produce a classification accuracy of 94.5%, precision of 91.0%, recall of 85.5% and Matthews Correlation Coefficient of 88.5% when it was used with four optimized features. In comparison, it is demonstrated that FMDDCN performs better than traditional machine learning and deep learning models, with its F1-score of 0.965 and the overall accuracy of 0.965. The suitability of the real-time edge deployment is verified, as confirmed by the use of computational analysis to reduce inference latency and memory consumption.

A critical challenge in agricultural automation is the precise detection of mango leaf diseases that compromise crop quality and yield. To address the limitation of existing heavy models in resource-constrained agricultural environments, this study proposes MangoLeafNet-XAI, a novel lightweight deep learning architecture. The model synergistically integrates Efficient Channel Attention (ECA) modules with a DenseNet-121 backbone to adaptively refine features and capture subtle pathological patterns with high precision. The proposed framework was rigorously evaluated using a 5-fold cross-validation and soft-voting ensemble strategy across three public datasets (MLDID, Mango Leaf Disease, and Harumanis). These datasets encompass diverse environmental conditions and distinct disease classes, including Anthracnose, Bacterial Canker, Die Back, Gall Midge, Powdery Mildew, Sooty Mould, and Cutting Weevil. MangoLeafNet-XAI achieved state-of-the-art accuracies of 98.83% on MLDID, 98.09% on the Mango Leaf Disease Dataset, and 98.76% on the Harumanis dataset. A primary contribution of this work is the optimal balance between performance and computational efficiency, utilizing only 6.9 million parameters, making it highly suitable for deployment on edge devices. Moreover, the interpretability of AI methods, such as Grad-CAM and LIME, that are used to explain the rationale behind predictions to offer pathological explanations, also validate the focus on clinically important aspects of the model. The results discuss the key limitations of existing methods, such as computational complexity, inability to interpret the findings, and dataset-dependent overfitting, and demonstrate a high level of resilience and generalizability on diverse datasets. MangoLeafNet-XAI will be a new benchmark of reliable, deployable, as well as accurate disease diagnosis systems, in smart agriculture.

This study was conducted in Champaign, Illinois to evaluate the efficacy of selected fungicides for managing powdery mildew of pumpkin, caused by the fungus Podosphaera xanthii. Seeds of jack-o-lantern pumpkin ‘Howden’ were sown on 30 May. A few small patches of powdery mildew were first observed on vines of unsprayed plants on 10 August. After four days, powdery mildew spots developed on lower surfaces of leaves, and then on both sides of leaves. By the end of the first week of September, almost of vines and more than 90% of leaves in unsprayed plots were covered with powdery mildew. Also, from 22 August to harvest, powdery mildew was observed on vines and leaves of plants in some sprayed plots. Severity of the disease was significantly (P = 0.05) higher in unsprayed plots compared to sprayed plots. There was no significant difference in powdery mildew severity among treatments.

Lesion mimic mutants (LMMs) are ideal for dissecting plant immunity mechanisms. Here, we characterized lm10373, a stable LMM isolated from an EMS-induced library of wheat cultivar AK58. lm10373 developed light-dependent lesion spots on leaves from the late tillering stage, accompanied by programmed cell death (PCD) and reactive oxygen species (ROS) accumulation. Phenotypically, lm10373 showed reduced photosynthetic capacity and yield-related traits, but enhanced powdery mildew resistance at the heading stage. Genetic analysis revealed the lesion trait was controlled by a single semi-dominant nuclear gene, mapped to a 35 Mb interval on chromosome 3B via bulked segregant analysis coupled with exome capture sequencing (BSE-seq). Integrating exome sequencing and transcriptome data, we identified TaWSD1-3B (encoding an O-acyltransferase of the WSD1 family) as the causal gene. A G-to-A mutation (p.Ala79Thr) in its conserved acyltransferase domain introduced a new phosphorylation site, disrupting triacylglycerol biosynthesis. Two independent mutants (lm129, p.Arg207His; lm295, 3'UTR mutation) validated TaWSD1-3B function. Haplotype analysis of 183 wheat accessions identified three TaWSD1-3B haplotypes: Hap1 was associated with higher 1000-grain weight and lower leaf tip necrosis (LTN) severity, making it a favorable allele for breeding. This study characterized a wheat LMM mutant and candidate gene TaWSD1-3B, suggesting a lipid-ROS-PCD pathway regulating immunity, and provides valuable markers for stress-tolerant, high-yield wheat breeding.

Genes important for research and breeding plant varieties are crucial for the survival and development of human civilization. Seeds of cereal germplasm are maintained in gene banks (GBs) and grain viability of GB accessions must be regularly restored by seed multiplication. During related operations human errors may lead to contaminated or mislabeled accessions and resultant genotype non-authenticity. Such mistakes accumulate over time. In this report, 1412 lines derived from 289 accessions of 93 barley varieties, each obtained from several GBs, were analyzed. Five single seed progenies (SSPs) were usually harvested from an accession and their major genes conferring powdery mildew resistance were postulated. Twenty-two known resistance genes and 60 of their combinations were identified. Non-authentic genotypes contained different genes compared with genes present in other genotypes of the same variety. Based on these results we found at least 40 (13.8%) mislabeled and 102 (35.3%) heterogeneous accessions in which 276 lines (19.7%) carried non-authentic genotypes. Misrepresented varieties in GBs are a great problem for research projects, especially those focused on finding new (e.g., molecular) varietal characteristics, and in breeding programs as the required gene combination cannot be obtained.

The expansion and functional diversification of gene families are key drivers of phenotypic innovation in plants. The SABATH family of methyltransferases, involved in growth regulation and stress responses, provides an ideal system to study such evolutionary processes. In this study, we identified and functionally characterized a novel member of this family in cucumber, designated CsIAMT. Phylogenetic and synteny analyses confirmed that CsIAMT shares a common ancestry with conserved IAA methyltransferase (IAMT) orthologs across angiosperms. Evolutionary analysis revealed that CsIAMT has undergone strong purifying selection (dN/dS < 1), indicating high functional conservation despite deep evolutionary divergence. Functional validation in transgenic tobacco plants revealed a decrease in IAA content accompanied by a significant increase in MeIAA. Expression profiling under various stress conditions showed that CsIAMT is notably up-regulated under biotic stresses-such as powdery mildew and nematode infection-while exhibiting variable responses to abiotic treatments. These findings collectively establish CsIAMT as a conserved IAA methyltransferase in cucumber and suggest its potential role in integrating auxin metabolism with biotic stress responses, highlighting the evolutionary conservation of core enzymatic functions within the SABATH family amid lineage-specific regulatory diversification.

Dynamic analysis of the infection process of cucumber powdery mildew based on instance segmentation

Plant immunity is complex, and studies of leaf epidermal cells attacked by powdery mildew fungi have been instrumental in revealing how it relies on plant endomembrane trafficking. Immunity against these biotrophic fungi is manifested as cell wall deposits ('papillae') and the hypersensitive reaction (HR), both involving plant endomembrane traffic. Papillae contain extracellular vesicles (EVs), some of which depend on the 'endosomal sorting complexes required for transport' machinery, while others depend on mechanisms yet to be uncovered. Existence of two such EV pathways agrees with several old electron microscopy observations of papillae. Interestingly, resistance protein-activated HR has been shown to be a form of immunity also depending on membrane trafficking, namely the pathway to the vacuole.

Frequent rainfall during the ripening season in Shaanxi’s grape-growing regions increases the incidence of downy mildew and black rot. In recent years, rain-shelter cultivation has reduced the incidence of these diseases; however, it has been associated with frequent powdery mildew outbreaks that severely compromise fruit quality and yield. To mitigate powdery mildew under rain-shelter conditions, we characterized disease dynamics and evaluated “bio-based” or “microbial-derived” pesticide control strategies. A large number of studies have shown that rain shelter cultivation can significantly change the microclimate. This study found that changes in microclimate affect the incidence pattern of powdery mildew, and there are significant differences in the resistance of different grape varieties to powdery mildew. A prediction model based on microclimate showed that 15-day accumulated growing degree days (GDD15; base 10 °C) before disease onset were positively correlated with the disease index (r = 0.860), whereas relative humidity was negatively correlated (r = −0.637); a multiple regression including both variables explained 81.4% of the variance. In biopesticide screening, blasticidin S and polyoxin inhibited spore germination by &gt;95%. In-shelter efficacy varied among cultivars, and biopesticide effects on fruit quality were also cultivar dependent. For example, blasticidin S increased total phenol and anthocyanin contents in Cabernet Sauvignon but reduced phenolic accumulation in Chardonnay.

Powdery mildew is one of the most destructive diseases affecting greenhouse cucumber (Cucumis sativus L.) production in Mongolia, causing significant yield losses and increased management costs. The present study aimed to identify the causal agent of cucumber powdery mildew using morphological characteristics and molecular phylogenetic analysis. Cucumber leaf samples exhibiting typical powdery mildew symptoms were collected from greenhouse production systems in five climatically distinct regions of Mongolia. Morphological examination revealed abundant mycelia and conidiophores bearing chains of ovoid to ellipsoid–ovoid conidia. Fibrosin bodies were consistently observed within conidia from all samples, indicating characteristics typical of Podosphaera xanthii. Molecular identification was performed using PCR amplification of the internal transcribed spacer (ITS) region with universal and species-specific primers. PCR results confirmed the presence of powdery mildew fungi, and species-specific amplification identified P. xanthii as the predominant pathogen in three of the five sampled regions. Phylogenetic analysis based on ITS sequences, conducted using the Maximum Likelihood method, demonstrated that the Mongolian isolates clustered within the Podosphaera xanthii clade together with reference sequences retrieved from GenBank. DNA sequences of representative isolates were deposited in the NCBI GenBank database under accession numbers MW939431, MW939432, and MW939433. This study provides the first comprehensive morphological and molecular characterization of cucumber powdery mildew pathogens in Mongolia and confirms Podosphaera xanthii as the primary causal agent under greenhouse conditions. The findings contribute valuable baseline information for the development of effective disease management strategies and future epidemiological studies.

Leaf and spike diseases can significantly reduce wheat yield and grain quality. To mitigate these impacts, an integrated disease management approach can be adopted, incorporating measures such as the use of resistant cultivars, fungicides and nitrogen fertilization. This study aimed to evaluate the impact of these practices on chlorophyll a fluorescence, yield components, and the technological quality of wheat grains. The area under the disease progress curve (AUDPC) was correlated with the maximum efficiency of photosystem II (PSII) photochemistry (Fv/Fm), as measured at the dough development stage (ZGS80) under field conditions, which also affected quality parameters. Additionally, an increase in AUDPC values reduced the thousand kernel weight (TKW) and test weight (TW). Conversely, AUDPC values for tan spot, powdery mildew and leaf rust were positively related to ash content (affecting flour color), protein content (PC) and grain falling number. Both the recommended nitrogen rate (130 kg ha-1) and the high rate (200 kg ha-1) increased grain protein content (PC) and gluten index (GI), while maintaining dough stability and water absorption. Fungicide application increased flour lightness and yellowness. Overall, integrated disease management combining moderately resistant cultivars, fungicide applications and nitrogen fertilization reduced AUDPC values, increased Fv/Fm (indicating optimal physiological performance) and ensured yield components and maintenance of wheat technological quality.

Tree peony (Paeonia × suffruticosa ) is a widely distributed perennial ornamental plant in China. In recent years, powdery mildew on tree peony has been consistently prevalent from late summer to autumn in the campus of Hebei Agricultural University in Baoding, China. Initially, infected leaves developed white circular mildew. As the disease progressed, the entire leaf surface and stems were covered with effuse or irregular white powder (mycelium). Subsequently, small black particles (chasmothecia) were observed in September. Conidiophores were erect and conidia were single and ellipsoid to ovoid, 25.77 to 51.40×13.36 to 22.94 μm (n=50). Chasmothecia were globose and brown, around 72.01 to 185.27 μm in diameter (n=50) and contained 3-7 asci. Appendages were mycelioid, with their length ranging from 61.14 to 163.11 μm (n=100), which was about 0.85 to 2.27 times the diameter of chasmothecia. Asci were ellipsoid to ovoid, and contained 2-5 ascospores; ascospores were ellipsoid to oblong-ellipsoid, 10.57 to 18.54 × 6.76 to 11.78 μm (n=100). Based on morphological characteristics, the fungus (designated EM) was identified as Erysiphe paeoniae (La et al. 2016). For molecular confirmation, partial sequences of the internal transcribed spacer (ITS) (White et al. 1990) and the RNA polymerase Ⅱ second largest subunit (RPB2) (Bradshaw et al. 2022) of this isolate were amplified by PCR. BLASTn analysis revealed that the obtained ITS and RPB2 sequences (accession numbers: PV628181.1 and PV654332.1) shared 99.84% and 99.57% identity with those of E. paeoniae (MT309702.1 and OR045233.1) in the NCBI database. Pathogenicity was tested by gently pressing diseased leaves onto 10 healthy leaves, and non-inoculated leaves as controls, in the field at Hebei Agricultural University. After 12 days, all inoculated leaves showed symptoms with powdery mildew colonies and the PCR amplicon sequence using primers ITS1/ITS4 was identical, fulfilling Koch’s postulates. The pathogens of powdery mildew on tree peony that have been reported include E. polygoni in Yunnan Province (MHYAU 03095), E. paeoniae-suffruticosae in Gansu, Shaanxi, and Jilin Provinces (Zhang et al. 2025), and E. paeoniae in Qingdao, Shandong Province, China (Qiao et al. 2016). To our knowledge, this is the first report of powdery mildew caused by E. paeoniae on tree peony in Baoding, Hebei Province. This finding helps clarify the genetic characteristics and distribution of the pathogen in China, and lays the groundwork for the forecasting and management of this disease.

Parasitism is a harmful relationship between microorganisms and their host. Biotrophic fungi, such as powdery mildew and rusts, are obligate parasites that extract nutrients from living plant cells using specialized structures like haustoria and appressoria. These pathogens weaken plant defenses by inhibiting enzyme secretion, making them particularly dangerous. Blumeria graminis, causing powdery mildew, affects all cereals and forms a white coating. Pucciniales, or rusts, represent the largest group of biotrophs, with complex life cycles involving up to five spore stages, complicating their identification. Resistance to chemical pesticides and environmental concerns have driven interest in alternative, safer, plant protection solutions. One promising group is coumarin and its derivatives, known for antifungal properties and biodegradability. Our study aimed to test the effectiveness of selected coumarin compounds in inhibiting the growth of powdery mildew and rust under laboratory conditions. These findings may support the development of modern, eco-friendly fungicides. Our studies have shown that the tested coumarin derivatives were characterized by varying effectiveness in inhibiting the growth of biotrophic pathogenic fungi. Histological studies showed that two compounds led to a reduction in the number of pathogen structures, suggesting their potential effectiveness in inhibiting the spread of infection.

Rubia alata, belonging to the genus Rubia, has been widely used as a folk medicine in China (Zhao et al. 2014). In March 2023, typical powdery mildew symptoms were observed on R. alata on Longwen hill, Guizhou Normal University, China. The incidence was ~25% among 60 R. alata plants assessed. Infected leaves presented chlorotic to necrotic phenotypes, with occasional anthocyanin accumulation. Mycelia most commonly occurred on the adaxial surfaces of infected leaves. Hyphae were hyaline and 4–7 μm wide. Hyphal appressoria were slightly lobed and produced singly or in opposite pairs (Fig. S1). Conidiophores were erect, straight to somewhat flexuous, and 60–200 µm long (n = 30). Foot cells were subcylindrical, followed by 2–4 cells. Conidia formed 2–5 in a chain and were ellipsoid to ovoid in shape with dimensions of 22–46 × 11.5–18 µm (n = 50). No fibrosin bodies were observed. Based on these morphological characteristics, the powdery mildew fungus was identified as Golovinomyces tabaci (Qiu et al. 2020). To identify the species, the ITS and LSU regions were amplified with the PM10/PM28R primer pair (Bradshaw and Tobin 2020); the CAM, GAPDH, GS, RPB2, IGS, and TUB regions were amplified using the PMCAM1/PMCAM4R, PMGAPDH1/PMGAPDH3R, GSPM2/GSPM3R, PMRpb2_4/PMRpb2_6R, IGS-12a/NS1R, and BTF5b/BTR7a primer pairs, respectively (Carbone and Kohn 1999; Ellingham et al. 2019; Bradshaw et al. 2022a). The obtained 1311-bp ITS-LSU sequence (GenBank accession no. PV368321), 284-bp CAM sequence (PV384439), 319-bp GAPDH sequence (PV384435), 468-bp GS sequence (PV384436), 758-bp RPB2 sequence (PV384437), 384-bp IGS sequence (PV391934) and 777-bp TUB sequence (PV384438) were deposited in GenBank. Based on the concatenated GAPDH+IGS+ITS+LSU sequences of the Golovinomyces taxa (Bradshaw et al. 2022b), phylogenetic tree was constructed and the isolate GZRA-1 was grouped in the same clade as G. tabaci (Fig. S2). To perform pathogenicity test, leaves of three healthy potted R. alata plants were inoculated by gently pressing with diseased leaves and were incubated in a greenhouse at 25 ± 2°C with 80% relative humidity. Non-inoculated plants served as controls. After 14 days, similar powdery mildew symptoms were observed on inoculated plants, whereas control plants showed no powdery mildew symptoms. Fungal samples from inoculated R. alata plants were morphologically identical to that on originally diseased plants, and ITS-LSU sequences of reisolated fungus shared 100% identity with PV368321. In addition, another powdery mildew isolate (GZRA-2) from naturally diseased R. alata plant was identified. The results revealed that GZRA-2 exhibited comparable morphological and molecular characteristics to GZRA-1. Based on these consistent traits, the powdery mildew fungus infecting R. alata plants was determined to be G. tabaci. Although G. tabaci has been reported to infect R. cordifolia in China (Qiu et al. 2020), this is the first report of powdery mildew caused by G. tabaci on R. alata. This work expands the known host range of G. tabaci on the genus Rubia and also highlights the importance of monitoring and managing this powdery mildew disease.

To implement a successful strawberry (Fragaria × ananassa) farming, fungal diseases must be detected in a timely manner so that informed crop protection decisions can be made. While field scouting is an option, it is manual and labor intensive. Scouting is also inaccurate and reduces efficiency due to micro-climatic lighting and field clutter, among other factors. StrawberryDualNet is a framework that supports Integrated Pest Management and automates symptom surveillance. We present dual-path CNN–Transformer fusion design that integrates two branches: a dynamic multi-scale convolution and a lightweight transformer. The former is able to capture fine-grained morphological lesion textures, while the latter captures overall contextual patterns. The two representations are fused through a learnable gating mechanism to decrease visual uncertainty amongst differing symptoms. We used a stratified five-fold cross-validation to evaluate the framework among five economically significant pathogens. Our approach significantly outperformed other automated scouting baselines, achieving 95.1% accuracy and 95.3% precision, respectively, and it is successful for Anthracnose, Gray Mold, Powdery Mildew, Rhizopus Rot, and Black Spot. The model is also scaled down compared to others (0.04 M parameters; 0.72 MB, 13–20× smaller than MobileNetV2/ShuffleNetV2) and is thus able to be deployed on devices that are lacking computational resources. For edge feasibility, we assessed reduced-precision inference; 16-bit floating point quantization preserved baseline performance at 83 FPS, whereas 8-bit integer quantization caused notable accuracy degradation. Overall, the proposed local–global fusion design provides an accurate, interpretable, and scalable tool for real-time disease phenotyping in precision horticulture.

Wheat powdery mildew, caused by Blumeria graminis f. sp. tritici (Bgt), is one of the most significant diseases affecting production in wheat-growing regions of China. Fluxapyroxad and mefentrifluconazole exhibit broad-spectrum activity against a wide range of plant pathogens, including Bgt. This study presents a comprehensive investigation of the efficacy of fluxapyroxad and mefentrifluconazole in controlling wheat powdery mildew in three Chinese provinces. Sensitivity baselines for Bgt isolates against fluxapyroxad (0.9111 μg/ml) and mefentrifluconazole (1.3224 μg/ml) were established. Bgt isolates collected from 2022 to 2024 demonstrated sensitivity or low resistance to fluxapyroxad and sensitivity, low resistance, or moderate resistance to mefentrifluconazole. The results revealed positive cross-resistance between mefentrifluconazole and tebuconazole but not between fluxapyroxad or mefentrifluconazole and other fungicides. For fluxapyroxad, three site mutations were identified within the SDHD subunit, but they did not result in amino acid changes. For mefentrifluconazole, overexpression of QCYP51A and QCYP51B genes was identified as a significant factor contributing to low-level resistance in Bgt. Both fluxapyroxad and mefentrifluconazole, individually and in combination, exhibited high control efficacy (>89%) against wheat powdery mildew. This research provides valuable insights into the current status of Bgt resistance to these fungicides and offers guidance for their judicious application in the field.

Grapevine powdery mildew, caused by the fungal pathogen Erysiphe necator, severely impacts plant growth and berry quality. However, the grapevine receptors and molecular mechanisms underlying grapevine resistance to E. necator remain poorly understood. In this study, we identify a G-type Lectin receptor-like kinase (LecRK), VqLecRKV.4, identified from the wild Chinese grapevine Vitis quinquangularis, whose expression is significantly upregulated in response to E. necator infection. Overexpression of VqLecRKV.4 in the susceptible cultivar V. vinifera 'Thompson Seedless' confers enhanced resistance against the pathogen, as evidenced by significantly reduced fungal colonisation and sporulation. Through TurboID-mediated proximity labelling, we demonstrate that VqLecRKV.4 interacts with VqCu/ZnSOD1. Further analysis reveals that VqLecRKV.4 promotes ROS accumulation and cell death by upregulating VqCu/ZnSOD1 expression, thereby inhibiting E. necator colonisation. A critical challenge in plant immunity is balancing immune responses to avoid overactivation. Here, we discover that VqBAK1 interacts with VqLecRKV.4 and attenuates its overreaction. Collectively, our findings reveal that the VqLecRKV.4-VqBAK1 module fine-tunes grapevine resistance to powdery mildew by maintaining ROS homeostasis, providing novel insights into the molecular mechanisms of grapevine immunity and its regulation to prevent detrimental overreaction.

Powdery mildew is one of the most common and important fungal diseases and may cause huge economic losses to crop yields worldwide. During survey of powdery mildews in 2011 and 2013, six samples of Ageratum conyzoides were collected from different regions in Indonesia, i.e. Bali, South Sumatera and West Java provinces. Anamorphic features revealed that the fungus belongs to the genus Podosphaera. Two sets of sequences of both ITS rRNA and 28S regions were obtained from the six samples. Phylogenetic analyses, including maximum parsimony (MP) and maximum likelihood (ML) were executed using MEGA7. The strength of internal branches of the resulting trees were tested with bootstrap analysis. Tree scores, including tree length, CI, RI and RC were also calculated. The phylogenetic analysis confirmed that the fungus belongs to the genus Podosphaera, forming a clade with the sequences from Podosphaera xanthii. This is the first report of powdery mildews on Ageratum conyzoides from Indonesia.

The cotton industry is a significant agricultural sector that has a profound impact on the nation's economy. To gauge a nation's economic performance, it is crucial to examine both the quality and quantity of its agricultural production. Early diagnosis of leaf diseases may lead to higher revenues in manufacturing. Various image-processing techniques have been developed throughout the years to identify illnesses that damage leaves. Advancements in technology are accelerating the process, although it is still in its initial phases. The agriculture business has a major challenge in dealing with the rise of leaf diseases. Many diseases, such as powdery mildew, army worm, bacterial blight, target spot, and aphids, may affect cotton plants. Extensive observations may be time-consum-ing, expensive, and sometimes inaccurate for the producers involved. We suggest utilizing machine learning techniques like Support Vector Machine (SVM), K-Nearest Neighbors (KNN), Random Forest (RF), Logistic Regression, and Convolutional Neural Network (CNN) to automatically detect diseases on cotton leaves. This method is designed for the agricultural sector to distinguish between healthy and sick leaves. The study found that CNN performs best in image classification as it has the greatest accuracy percentage of 99.1%.

Wheat relatives harbour abundant variations that can be used for genetic improvement against diseases through complex domestication processes. Here, we report the isolation of the powdery mildew resistance gene Pm37 in common wheat through a strategy integrating map-based cloning, PacBio SMRT long-read genome sequencing, mutagenesis, barley stripe mosaic virus-induced gene silencing and stable transformation. Pm37 encodes a coiled-coil nucleotide-binding site leucine-rich repeat (CC-NBS-LRR) receptor. The cell death-inducing activity of PM37 in Nicotiana benthamiana is mainly mediated by its CC domain. De novo genome sequencing and haplotype analysis reveal that Pm37 may be derived from Triticum monococcum, and transferred into common wheat through T. timopheevii. Interestingly, Pm37 is a susceptible allele of the stem rust resistance locus Sr22, and also confers moderate resistance to leaf rust. Our findings identify a gene characterized by allelic variation-driven functional divergence in response to different wheat diseases.