The impact of plant and fruit diseases on agricultural economies is significant, resulting in the reduction of crop quality and yield. The development of precise and automated detection techniques to overcome this issue is crucial in order to minimize agricultural losses and foster economic growth. A deep learning approach named YOLO-AppleScab is introduced, Which integrates the Content-Aware ReAssembly of Feature ( ) architecture into YOLOv7 to enhance the detection of apple fruits with healthy and disease classification. Moreover, the model used the traditional bounding box (R-Bbox) for apple fruit localization. The performance metrics of the proposed model were noteworthy, with F1, recall, and precision rates of 89.75%, 85.20%, and 94.80%, respectively. Furthermore, the results demonstrate a mean average precision ( ) of 89.30% when evaluated at an intersection over a union (IoU) threshold of 0.5. Additionally, the model achieved a of 64% with an average duration of inference per image of 175.2 milliseconds. The integration of the YOLOv7 head was a crucial factor in attaining superior detection capabilities in comparison to contemporary techniques. The research highlights the importance of utilizing deep-learning methodologies for accurate and automated detection of apple scab disease, which has potential benefits for reducing agricultural damages and promoting economic development.

A study was conducted to evaluate farmers' production practices and the incidence and management of pests and diseases, extension services, and factors limiting cotton production and quality in South Africa. One hundred and forty farmers, mainly smallholder farmers, were interviewed during the 2017/18 growing season. Most farmers planted genetically modified cotton on less than 5 ha of cotton, with 96% planting under dryland. The majority of the farmers neither practised conservation agriculture (95%) nor conducted soil analyses (87%). A mean cottonseed yield of 700 kg ha-1 was reported on dryland cotton, and 5 000 kg ha-1 was obtained from irrigated cotton. Most of the farmers (99%) harvested their cotton by handpicking. Farmers' pest knowledge was higher than their knowledge of different diseases. Most of the participants were unaware of nematodes (88%), or disease-resistant cultivars (74%), while 91% were aware of insect-resistant cultivars. Most respondents were only mentored and supported by extension officers (82%). Most farmers (93%) relied on pesticides to control cotton pests, and the rest (7%) used biological control. Climatic conditions (98%), labour costs (88%), and insect infestations (42%) were identified as the main constraints in cotton production. Based on the outcomes, the survey revealed that there is a need to develop pests and diseases resistant cultivars as well as alternative control methods to reduce the use of agrochemicals. Furthermore, farmers' awareness of improved production practices and mentoring are required.

The purpose of this work is to present a three-species harvesting food web model that takes into account with the interactions of susceptible prey, infected prey, and predator species. Prey species are assumed to expand logistically in the absence of predator species. Crowley-Martin and Beddington-DeAngelis Functional Responses are used by predators to consume both susceptible and infected prey. Additionally, susceptible prey is consumed by infected prey in the formation of Holling type II response. Both prey populations are considered when prey harvesting is taken into account. Boundedness, positivity, and positive invariance are considered in this study. The investigation covers all equilibrium points that are biologically feasible. Local stability is evaluated by analyzing the distribution of eigen values, while global stability is evaluated using suitable Lyapunov functions. Moreover, Hopf bifurcation has analyzed at the harvesting rate H1. In the end, we evaluate numerical solutions based on our findings.

Artificial intelligence (AI) has the potential to revolutionize agricultural analysis and improve climate-smart farming practices. This paper explores the transformative role of AI in climate-smart agriculture, focusing on recent advances and future directions. Climate change poses significant challenges for agriculture, including weather variability, water scarcity, and the emergence of new pests and diseases. Leveraging AI technology, this research delves into how agricultural analysis can be revolutionized, leading to improved climate-smart farming practices. Recent advances in AI, such as machine learning and deep learning, have enabled the development of powerful predictive models that can be used to forecast climate events, optimize irrigation schedules, and detect early indicators of crop stress or disease outbreaks. This information can be used to proactively alter farming operations and resource allocation tactics, resulting in increased productivity and less environmental impact. AI-powered precision agriculture technology, such as autonomous drones and sensor networks, also enables real-time monitoring and data collection. This allows farmers to collect precise data on crop health, soil moisture levels, and fertilizer requirements. AI algorithms can then deliver practical crop management advice, such as optimal planting schedules, fertilizer application rates, and pest control techniques. The integration of AI in climate-smart farming also holds potential for long-term agricultural practices. Predictive analytics and AI-based supply chain optimization can improve post-harvest management, storage, and distribution processes, reducing food loss and increasing overall efficiency. The research emphasizes how AI can enable farmers to make data-driven decisions, optimize resource consumption, and enhance resilience in the face of climate challenges. By integrating AI into agriculture, this paper presents a pathway toward sustainable food production, environmental stewardship, and improved farmer livelihoods.

The global population is expected to reach 9.7 billion by 2050, requiring a 50% increase in food production. Climate change presents new challenges for agriculture, including extreme weather, rising temperatures, and precipitation changes. Artificial intelligence (AI) can help address these challenges by improving efficiency and productivity through monitoring crops and livestock, optimizing irrigation, predicting pests and diseases, and developing resistant crop varieties. This paper reviews the applications and challenges of AI in precision agriculture. AI-based technologies, such as machine learning algorithms and predictive models, can improve climate-smart agriculture by analyzing large volumes of climate, soil, and crop-related data. These algorithms generate accurate predictions and recommendations for optimizing farming practices, including precision irrigation scheduling, nutrient management, pest and disease monitoring, and yield forecasting. AI also contributes to resource efficiency by optimizing input usage, minimizing waste, and reducing environmental impact. The paper highlights the potential of AI to drive efficiency and productivity in climate-smart agriculture, despite challenges such as data quality, availability, technical expertise, and cost implications. By leveraging AI's capabilities, agriculture can move towards sustainable and resilient practices, achieving food security, enhancing resource efficiency, and mitigating climate change impacts.

Legumes belong to nutritionally attractive crops, because of their high protein content and very well-balanced nutritional value. However, in addition to nutritionally valuable components, they contain a relatively high amount of anti-nutritional factors such as glycosides, lectins, inhibitors of digestive enzymes, and anti-nutritional proteins, what include allergens as well. Different genomic based analysis of allergen coding parts are relevant in the research of legume gene resources. Here, a total of twenty nine different soybean (Glycine max L.) varieties were analysed for their polymorphism based in the specific homologous sequences of genes for vicilin and profilin, products of both belong to allergenic molecules of this specie. A total of 16 different amplicons were obtained when profilin was used as marker and 17 different amplicons for vicilin.
Comparing both of used techniques, vicilin provided more polymorphic profiles, but in five out of the analysed verieties no amplicons were obtained. Profilin fingerprints provided higher degree of similarity coefficients among individual varieties of soybean. Both of used PCR based techniques were proved to be applicable for genomic based screening of allergen homologs in the genetic resources of Glycine max L.

Currently, a lot of attention is being paid to the evaluation and classification of horticulture crops, especially fruits. Maturity prediction is a major step in deciding the value of a coconut (Cocos nucifera), which is directly linked to the quality of the product. The sound-based deep learning method used to predict the maturity of a coconut can also be greatly beneficial to a number of tropical countries like the Philippines, Indonesia, and India who produce and export coconuts worldwide due to its high demand. A way to accurately determine the maturity level of a coconut is essential, as it affects the benefits that the fruit will provide.

This paper aims to develop an effective AI-driven method to predict the maturity level of a coconut using acoustic signals. The proposed sound-based autonomous approach exploits various deep learning models including customized CNN, pre-trained networks, i.e. the ResNet-50, VGG-16, VGG-19 and Inception V3 models for maturity level classification of the coconuts. The proposed study also demonstrates the usefulness of various deep learning models in inspecting coconuts and providing a promising accuracy level to automatically predict the maturity of coconuts into three classes, i.e. pre-mature, mature, and overripe coconuts, by using a small amount of input acoustic data. We have used an open access dataset that consists of a total of 381 raw acoustic signals, which is the result of knocking 127 coconut samples on its three ridges namely ``Ridge A’’, ``Ridge B’’, and ``Ridge C’’. Promising results are obtained by the proposed method of coconut maturity prediction, enabling producers to accurately determine the yield and quality of the product.

Quickly and accurately judging the quality grades of apples is the basis for choosing suitable harvesting date and setting a suitable storage strategy. At present, the research of multi-task classification algorithm models based on CNN is still in the exploration stage, and there are still some problems such as complex model structure, high computational complexity and long computing time.

This paper presents a light-weight architecture based on multi-task convolutional neural networks for maturity (L-MTCNN) to eliminate immature and defective apples in the intelligent integration harvesting task. L-MTCNN architecture with diseases classification sub-network (D-Net) and maturity classification sub-network (M-Net), to realize multi-task discrimination of the apple appearance defect and maturity level. Under different light conditions, the image of fruit may have color damage, which makes it impossible to accurately judge the problem, an image preprocessing method based on brightness information was proposed to restore fruit appearance color under different illumination conditions in this paper. In addition, for the problems of inaccurate prediction results caused by tiny changes in apple appearance between different maturity levels, triplet loss is introduced as the loss function to improve the discriminating ability of maturity classification task. Based on the study and analysis of apple grade standards, three types of apples were taken as the research objects. By analyzing the changes in apple fruit appearance in each stage, the data set corresponding to the maturity level and fruit appearance was constructed. Experimental results show that D-Net and M-Net have significantly improved recall rate, precision rate and F1-Score in all classes compared with AlexNet, ResNet18, ResNet34 and VGG16.

The principal goal of sustainable agricultural development is to ensure food production to meet the needs of an ever-growing world population. However, agriculture faces multiple challenges, including climate change, energy supply, and the scarcity of arable land. These facts show the relevance of encouraging innovation in agriculture, especially that directly related to the development and selection of plant varieties expressing traits of interest. The protection of researchers' intellectual property by a plant variety certificate or patent is highly relevant in this context. The United States, followed by some other jurisdictions, has even introduced a plant patent, which, like patents, grants a 20-year monopoly of exploitation, especially to breeders who have invented or asexually discovered and reproduced a distinct and novel plant variety. In addition, the patent system incorporates several classifications specific to plant production, and since 2018, a particular classification has concerned new plants or processes to obtain and reproduce them by tissue culture techniques.

This study aims to analyze patents relating to new plant varieties of Lamiaceae, a plant family recognized for the interest of these genera in the medicinal and aromatic fields. The study also seeks to identify the genera and species most exploited in innovative applications. To identify the latest trends in this area, we systematically reviewed patents concentrating on new varieties of Lamiaceae. The relevant patents were identified in various specialized databases using the International Patent Classification.

The essential objective claimed by the patents studied is ornamental (71% of the documents); this is essentially the case of plant patents. The other granted patents claimed innovations in genetic engineering (13%) or plant breeding (6%) that seek a better yield of proteins or other compounds of interest. The rest of the patents claimed plants that are more tolerant of climate effects (5%), plants resistant to powdery mildew (3%), and suitable substrates for the cultivation of certain Lamiaceae species (1%).

The cabbage webworm, Hellula undalis (Fabricius) (Lepidoptera: Pyralidae), is a significant pest of brassicas and other cruciferous plants in warm regions worldwide. Transcriptome analysis is valuable for investigation of molecular mechanisms underlying the insect development and reproduction. De novo assembly is particularly useful for acquiring complete transcriptome information of insect species when there is no reference genome available. In case of Hellula undalis, only 17 nucleotide records are currently available throughout NCBI nucleotide database. Genes associated with metabolic processes, general development, reproduction, defense and functional genomics were not previously predicted in the Hellula undalis at the genomic level. To address this issue, we constructed Hellula undalis transcriptome using Illumina NovaSeq6000 technology. Approximately 48 million 125 bp paired-end reads were obtained from sequencing. A total of 30,451 contigs were generated by de novo assembly of sample and were compared with the sequences in the NCBI non-redundant protein database (Nr). In total, 71% of contigs were matched to known proteins in public databases including Nr, Gene Ontology (GO), and Cluster Orthologous Gene Database (COG), and then, contigs were mapped to 123 via functional annotation against the Kyoto Encyclopedia of Genes and Genomes pathway database (KEGG). In addition, we compared the ortholog gene family of the Hullula undalis, transcriptome to Spodoptera frugiperda, spodotera litura and spodoptera littoralis and found that 2,749 orthologous gene families are specific to Hullula undalis. This study is the first transcriptome data for Hullula undalis. Additionally, it serves as a valuable resource for identifying target genes and developing effective and environmentally friendly strategies for pest control.