This paper presents a novel approach to agricultural disease diagnostics through the integration of Deep Learning (DL) techniques with Visual Question Answering (VQA) systems, specifically targeting the detection of wheat rust. Wheat rust is a pervasive and destructive disease that significantly impacts wheat production worldwide. Traditional diagnostic methods often require expert knowledge and time-consuming processes, making rapid and accurate detection challenging. We drafted a new, WheatRustDL2024 dataset (7998 images of healthy and infected leaves) specifically designed for VQA in the context of wheat rust detection and utilized it to retrieve the initial weights on the federated learning server. This dataset comprises high-resolution images of wheat plants, annotated with detailed questions and answers pertaining to the presence, type, and severity of rust infections. Our dataset also contains images collected from various sources and successfully highlights a wide range of conditions (different lighting, obstructions in the image, etc.) in which a wheat image may be taken, therefore making a generalized universally applicable model. The trained model was federated using Flower. Following extensive analysis, the chosen central model was ResNet. Our fine-tuned ResNet achieved an accuracy of 97.69% on the existing data. We also implemented the BLIP (Bootstrapping Language-Image Pre-training) methods that enable the model to understand complex visual and textual inputs, thereby improving the accuracy and relevance of the generated answers. The dual attention mechanism, combined with BLIP techniques, allows the model to simultaneously focus on relevant image regions and pertinent parts of the questions. We also created a custom dataset (WheatRustVQA) with our augmented dataset containing 1800 augmented images and their associated question-answer pairs. The model fetches an answer with an average BLEU score of 0.6235 on our testing partition of the dataset. This federated model is lightweight and can be seamlessly integrated into mobile phones, drones, etc. without any hardware requirement. Our results indicate that integrating deep learning with VQA for agricultural disease diagnostics not only accelerates the detection process but also reduces dependency on human experts, making it a valuable tool for farmers and agricultural professionals. This approach holds promise for broader applications in plant pathology and precision agriculture and can consequently address food security issues.

This study evaluates the biocontrol efficacy of three bacterial strains (Pseudomonas fluorescens DTPF-3, Bacillus amyloliquefaciens DTBA-11, and Bacillus subtilis DTBS-5) and two fungal strains (Trichoderma harzianum Pusa-5SD and Aspergillus niger An-27) antagonists, along with their combinations at varying doses (5.0, 7.5, and 10.0 g/kg of seeds), against wheat powdery mildew. The most effective dose (10 g/kg seeds) was further analyzed for its impact on induced resistance and plant growth promotion under greenhouse conditions. The study measured defense enzyme activities, biochemical changes, and post-infection plant growth metrics. All tested microbial antagonists at 10 g/kg significantly reduced PM severity, with B. subtilis strain DTBS-5 outperforming others in reducing PM severity and achieving the highest biocontrol efficacy. It was followed by B. amyloliquefaciens strain DTBA-11 and P. fluorescens strain DTPF-3, with the fungal antagonists showing no significant effect. Wheat crops treated with B. subtilis strain DTBS-5 exhibited substantial increases in defense-related enzyme activities and biochemicals, suggesting an induced resistance mechanism. The study found a 45% increase in peroxidase (POD) activity, a 50% increase in catalase (CAT) activity, a 30% increase in phenolic content, and a 25% increase in soluble protein content in the wheat plants treated with microbial antagonists. The study highlights the effectiveness of microbial antagonists, particularly B. subtilis strain DTBS-5, in managing wheat PM through biocontrol, induced resistance, and enhanced plant growth, offering a sustainable alternative to chemical treatments.

Wheat rust is a severe fungal disease that significantly impacts wheat crops, resulting in substantial losses in quality and quantity, often exceeding 50%. Timely and early accurate estimation of disease severity in fields is critical for effective disease management. Early identification of Rust at low severity levels can facilitate prompt implementation of control measures, potentially saving crops. This paper introduces an automated wheat rust severity stage estimation model utilizing the EfficientNet architecture and attention mechanism. The convolutional Block Attention Module was integrated into EfficientNet-B0 in place of the SE module to enhance feature extraction by simultaneously considering channel and spatial information. The proposed hybrid approach aims to identify rust disease severity accurately. The model is trained on an image dataset comprising three major rust types—stripe, stem, leaf, and healthy plants captured under real-life field conditions. Each disease is categorized into four severity stages: healthy, low, medium, and high. Experimental results demonstrate that the proposed model achieves impressive performance, with a training accuracy of 99.51% and a testing accuracy of 96.68%. Moreover, comparative analysis against state-of-the-art CNN models highlights the superior performance of our approach. An Android application was also designed and developed to facilitate real-time classification of plant disease severity. This system incorporates a severity model optimized for enhanced classification accuracy and rapid recognition, ensuring efficient performance.

The yellow rust caused by Puccinia striiformis f.sp. tritici is an important constraint to wheat production worldwide. Host resistance is the most economicalway to manage yellow rust. Race-specific resistance is short-lived and overcome by the evolution of new races of the pathogens. However, non-race-specific, or quantitative resistance, controlled by many genes and effective at the adult plant stage, is generally considered to be more durable and long-lasting. Such type of resistance should be of primary interest to wheat breeders around the world. With this background, old wheat genotypes/cultivars were evaluated against different pathotypes of Puccinia striiformis for resistance at both the seedling and adult plant stages. By applying the gene matching technique, three yellow rust resistance genes viz., Yr2, Yr9 and Yr18 were postulated. Adult plant resistancewas assessed through host response and epidemiological parameters i. e. final rust severity, relative area under rust progress curve, coefficient of infection and infection rate. Promising adult plant resistance was observed on the cultivars DBW 17, DBW 71, PDW 314, HS 507, VL 804, VL 829, VL 907, HPW 251, HPW 349, HD 2967, HD 2985, HD 3043, HD 3086, PBW 660, C 306, HI 1563, WH 1021, WH 1080 and Raj 4083 consistently during rabi seasons of 2013–15. All these promising yellow rust resistant cultivars at adult plant stage were susceptible at seedling stage to one or more pathotype(s) of yellow rust, which indicated the presence of adult plant resistance. At seedling stage, adult plant resistance gene Yr18 was characterized in eight cultivars, namely, HS 277, VL 804, VL 829, HD 2733, NI 5439, NIAW 34, PBW 175 and C 306 where, it occurred in combination with other genes in the seven cultivars. All these wheat cultivars exhibited effective adult plant resistance.