Precision Agriculture Digital Technologies for Sustainable Fungal Disease Management of Ornamental Plants

Integration of Diffusion Transformer and Knowledge Graph for Efficient Cucumber Disease Detection in Agriculture

In this study, a deep learning method combining knowledge graph and diffusion Transformer has been proposed for cucumber disease detection. By incorporating the diffusion attention mechanism and diffusion loss function, the research aims to enhance the model's ability to recognize complex agricultural disease features and to address the issue of sample imbalance efficiently. Experimental results demonstrate that the proposed method outperforms existing deep learning models in cucumber disease detection tasks. Specifically, the method achieved a precision of 93%, a recall of 89%, an accuracy of 92%, and a mean average precision (mAP) of 91%, with a frame rate of 57 frames per second (FPS). Additionally, the study successfully implemented model lightweighting, enabling effective operation on mobile devices, which supports rapid on-site diagnosis of cucumber diseases. The research not only optimizes the performance of cucumber disease detection, but also opens new possibilities for the application of deep learning in the field of agricultural disease detection.

Integrated Management of Pathogens and Microbes in Cannabis sativa L. (Cannabis) under Greenhouse Conditions

The increased cultivation of high THC-containing Cannabis sativa L. (cannabis), particularly in greenhouses, has resulted in a greater incidence of diseases and molds that can negatively affect the growth and quality of the crop. Among them, the most important diseases are root rots (Fusarium and Pythium spp.), bud rot (Botrytis cinerea), powdery mildew (Golovinomyces ambrosiae), cannabis stunt disease (caused by hop latent viroid), and a range of microbes that reduce post-harvest quality. An integrated management approach to reduce the impact of these diseases/microbes requires combining different approaches that target the reproduction, spread, and survival of the associated pathogens, many of which can occur on the same plant simultaneously. These approaches will be discussed in the context of developing an integrated plan to manage the important pathogens of greenhouse-grown cannabis at different stages of plant development. These stages include the maintenance of stock plants, propagation through cuttings, vegetative growth of plants, and flowering. The cultivation of cannabis genotypes with tolerance or resistance to various pathogens is a very important approach, as well as the maintenance of pathogen-free stock plants. When combined with cultural approaches (sanitation, management of irrigation, and monitoring for diseases) and environmental approaches (greenhouse climate modification), a significant reduction in pathogen development and spread can be achieved. The use of preventive applications of microbial biological control agents and reduced-risk biorational products can also reduce disease development at all stages of production in jurisdictions where they are registered for use. The combined use of promising strategies for integrated disease management in cannabis plants during greenhouse production will be reviewed. Future areas for research are identified.

A Conceptual Model Relationship between Industry 4.0-Food-Agriculture Nexus and Agroecosystem: A Literature Review and Knowledge Gaps

With the expected colonization of human daily life by artificial intelligence, including in industry productivity, the deployment of Industry 4.0 (I4) in the food agriculture industry (FAI) is expected to revolutionize and galvanize food production to increase the efficiency of the industry's production and to match, in tandem, a country's gross domestic productivity. Based on a literature review, there have been almost no direct relationships between the I4-Food-Agriculture (I4FA) Nexus and the agroecosystem. This study aimed to evaluate the state-of-the-art relationships between the I4FA Nexus and the agroecosystem and to discuss the challenges in the sustainable FAI that can be assisted by the I4 technologies. This objective was fulfilled by (a) reviewing all the relevant publications and (b) drawing a conceptual relationship between the I4FA Nexus and the agroecosystem, in which the I4FA Nexus is categorized into socio-economic and environmental (SEE) perspectives. Four points are highlighted in the present review. First, I4 technology is projected to grow in the agricultural and food sectors today and in the future. Second, food agriculture output may benefit from I4 by considering the SEE benefits. Third, implementing I4 is a challenging journey for the sustainable FAI, especially for the small to medium enterprises (SMEs). Fourth, environmental, social, and governance (ESG) principles can help to manage I4's implementation in agriculture and food. The advantages of I4 deployment include (a) social benefits like increased occupational safety, workers' health, and food quality, security, and safety; (b) economic benefits, like using sensors to reduce agricultural food production costs, and the food supply chain; and (c) environmental benefits like reducing chemical leaching and fertilizer use. However, more studies are needed to address social adaptability, trust, privacy, and economic income uncertainty, especially in SMEs or in businesses or nations with lower resources; this will require time for adaptation to make the transition away from human ecology. For agriculture to be ESG-sustainable, the deployment of I4FA could be an answer with the support of an open-minded dialogue platform with ESG-minded leaders to complement sustainable agroecosystems on a global scale.

Characterization and control of Rhizoctonia solani affecting lucky bamboo (Dracaena sanderiana hort. ex. Mast.) using some bioagents

In a survey conducted during the period of March-May 2019 in nurseries, warehouses, and shops at three governorates (Alexandria, El-Behera, and Giza governorates, Egypt), symptoms of root rot, basal stem rot, and wilt disease complex were observed in the lucky bamboo (Dracaena sanderiana hort. ex. Mast.). The highest disease infection percentage was found in lucky bamboo collected from Alexandria City (47.67%), while the highest disease severity was in lucky bamboo collected from El-Behera Governorate (35.19%). Rhizoctonia solani, Fusarium oxysporum, F. solani, Aspergillus niger, and Alternaria alternate were isolated and identified in the infected lucky bamboo samples. R. solani isolates were the most dominant among the recovered fungal species with a percentage of 80.89% of the total isolates (246). Pathogenicity tests showed that R. solani was the most pathogen with 100% disease infection and 76.67% disease severity. Molecular identification characterized R. solani isolate as R. solani AUMC 15120, MZ723906. Meanwhile, four biological control agents (bioagents) were isolated from the healthy lucky bamboo samples and identified based on cultural, morphological, microscopic characteristics, and the molecular phylogenetic analysis as Clonostachys rosea AUMC 15121, OL461708; Bacillus circulans TAG1, MW441316; B. siamensis TAP1, MW441318 and Ochrobactrum anthropi TAM1, MW441317. The four bioagents showed potential inhibition of R. solani in vitro as well as in vivo on lucky bamboo plants in vase treatments compared to the untreated inoculated control as well as certain fungicides and biocides used (Moncut, Rizolex-T, Topsin-M, Bio-Zeid, and Bio-Arc). The bioagent O. anthropi showed the highest inhibition growth (85.11%) of the in vitro R. solani colony, which was not significantly different from the biocide Bio-Arc (83.78%). However, C. rosea, B. siamensis and B. circulans showed inhibition values of 65.33, 64.44, and 60.44%, respectively. On the other hand, the biocide Bio-Zeid showed less inhibitory effect (43.11%), while the lowest growth inhibition was recorded by Rizolex-T (34.22%) and Topsin-M (28.67%). Furthermore, the in vivo experiment supported the in vitro results for the most effective treatments, where all the treatments significantly decreased the percentage of infection and disease severity compared to the inoculated untreated control. Additionally, the bioagent O. anthropi showed the highest effect, i.e., the lowest disease incidence and disease severity being 13.33% and 10%, compared to 100% and 75%, respectively, in the untreated inoculated control. This was not significantly different from the fungicide Moncut (13.33% and 21%) and from the bioagent C. rosea (20% and 15%) treatments for both parameters, respectively. In conclusion, the bioagents O. anthropi MW441317 at 1 × 10⁸ CFU/ml as well as C. rosea AUMC15121 at 1 × 10⁷/ml proved to be efficient to control R. solani causing root rot, and basal stem rot on lucky bamboo, compared to fungicide Moncut and can be used for disease management without the negative impact of the chemical control. Furthermore, this is the first report of the isolation and identification of Rhizoctonia solani, a pathogenic fungus, and four biocontrol agents (Bacillus circulans, B. siamensis, Ochrobactrum anthropi and Clonostachys rosea) associated with the healthy lucky bamboo plants.

Proximal hyperspectral sensing of abiotic stresses in plants

Recent attempts, advances and challenges, as well as future perspectives regarding the application of proximal hyperspectral sensing (where sensors are placed within 10 m above plants, either on land-based platforms or in controlled environments) to assess plant abiotic stresses have been critically reviewed. Abiotic stresses, caused by either physical or chemical reasons such as nutrient deficiency, drought, salinity, heavy metals, herbicides, extreme temperatures, and so on, may be more damaging than biotic stresses (affected by infectious agents such as bacteria, fungi, insects, etc.) on crop yields. The proximal hyperspectral sensing provides images at a sub-millimeter spatial resolution for doing an in-depth study of plant physiology and thus offers a global view of the plant's status and allows for monitoring spatio-temporal variations from large geographical areas reliably and economically. The literature update has been based on 362 research papers in this field, published from 2010, most of which are from four years ago and, in our knowledge, it is the first paper that provides a comprehensive review of the applications of the technique for the detection of various types of abiotic stresses in plants.

Phytotoxic Metabolites Produced by Fungi Involved in Grapevine Trunk Diseases: Progress, Challenges, and Opportunities

Grapevine trunk diseases (GTDs), caused by fungal pathogens, are a serious threat to vineyards worldwide, causing significant yield and economic loss. To date, curative methods are not available for GTDs, and the relationship between the pathogen and symptom expression is poorly understood. Several plant pathologists, molecular biologists, and chemists have been investigating different aspects of the pathogenicity, biochemistry, and chemical ecology of the fungal species involved in GTDs. Many studies have been conducted to investigate virulence factors, including the chemical characterization of phytotoxic metabolites (PMs) that assist fungi in invading and colonizing crops such as grapevines. Moreover, multidisciplinary studies on their role in pathogenicity, symptom development, and plant-pathogen interactions have also been carried out. The aim of the present review is to provide an illustrative overview of the biological and chemical characterization of PMs produced by fungi involved in Eutypa dieback, Esca complex, and Botryosphaeria dieback. Moreover, multidisciplinary investigations on host-pathogen interactions, including those using cutting-edge Omics techniques, will also be reviewed and discussed. Finally, challenges and opportunities in the role of PMs for reliable field diagnosis and control of GTDs in vineyards will also be explored.

Morphological Responses of Viola Accessions to Nutrient Solution Application and Electrical Conductivity

Growing of ornamental flowering plants represents an important sector of horticulture. Viola × wittrockiana (garden pansy) is used in garden beds and borders due to their colorful blooming, which occurs in early spring and late autumn. Nowadays, breeders focus on applying different nutrient solutions to improve the quality, flowering, and ornamental properties of plants, yet electrical conductivity (EC) level is an important fact to know. It is known that higher EC levels can inhibit plants’ growth. In the present study, pansy seedlings were subjected to different EC nutrient solutions 1 (control), 2, 3.5, 5, and 6.5 mS cm⁻¹ EC to assess the positive or negative effects regarding the plant’s growth and development. The results indicated that an appropriate EC level of nutrient solution can have a positive effect on growth parameters, as well as on the flowering of plants. According to the hierarchical clustering, the used EC nutrient solutions significantly influenced the growth, number of shoots and leaves and the inflorescences number. From the present study results, it can be concluded that even though all EC levels increased growth parameters compared with control, the greatest results were obtained in plants under the effect of the 5 mS cm⁻¹ of EC.

YOLO-JD: A Deep Learning Network for Jute Diseases and Pests Detection from Images

Recently, disease prevention in jute plants has become an urgent topic as a result of the growing demand for finer quality fiber. This research presents a deep learning network called YOLO-JD for detecting jute diseases from images. In the main architecture of YOLO-JD, we integrated three new modules such as Sand Clock Feature Extraction Module (SCFEM), Deep Sand Clock Feature Extraction Module (DSCFEM), and Spatial Pyramid Pooling Module (SPPM) to extract image features effectively. We also built a new large-scale image dataset for jute diseases and pests with ten classes. Compared with other state-of-the-art experiments, YOLO-JD has achieved the best detection accuracy, with an average mAP of 96.63%.

Surveying soil-borne disease development on wild rocket salad crop by proximal sensing based on high-resolution hyperspectral features

Wild rocket (Diplotaxis tenuifolia, Brassicaceae) is a baby-leaf vegetable crop of high economic interest, used in ready-to-eat minimally processed salads, with an appreciated taste and nutraceutical features. Disease management is key to achieving the sustainability of the entire production chain in intensive systems, where synthetic fungicides are limited or not permitted. In this context, soil-borne pathologies, much feared by growers, are becoming a real emergency. Digital screening of green beds can be implemented in order to optimize the use of sustainable means. The current study used a high-resolution hyperspectral array (spectroscopy at 350-2500 nm) to attempt to follow the progression of symptoms of Rhizoctonia, Sclerotinia, and Sclerotium disease across four different severity levels. A Random Forest machine learning model reduced dimensions of the training big dataset allowing to compute de novo vegetation indices specifically informative about canopy decay caused by all basal pathogenic attacks. Their transferability was also tested on the canopy dataset, which was useful for assessing the health status of wild rocket plants. Indeed, the progression of symptoms associated with soil-borne pathogens is closely related to the reduction of leaf absorbance of the canopy in certain ranges of visible and shortwave infrared spectral regions sensitive to reduction of chlorophyll and other pigments as well as to modifications of water content and turgor.

Cadmium Uptake and Growth Responses of Seven Urban Flowering Plants: Hyperaccumulator or Bioindicator?

The application of flowering plants is the basis of urban forest construction. A newly-found flowering hyperaccumulator is crucial for remediating urban contaminated soil sustainably by cadmium (Cd). This study evaluated growth responses, Cd uptake and bioaccumulation characteristics of seven urban flowering plants. Based on growth responses of these plants, Calendula officinalis L. showed high tolerance to at least 100 mg kg−1 Cd, in terms of significant increase in biomass and with no obvious changes in height. After 60 d exposure to 100 mg kg−1 Cd, the accumulated Cd in shoots of the plant reached 279.51 ± 13.67 μg g−1 DW, which is above the critical value defined for a hyperaccumulator (100 μg g−1 DW for Cd). Meanwhile, the plant could accumulate Cd to as much as 926.68 ± 29.11 μg g−1 DW in root and 1206.19 ± 23.06 μg g−1 DW in plant, and had higher Cd uptake and bioaccumulation values. According to these traits, it is shown that Calendula officinalis L. can become a potential Cd-hyperaccumulator for phytoremediation. By contrast, Dianthus caryophyllus L. is very sensitive to Cd stress in terms of significantly decreased biomass, height and Cd uptake, indicating the plant is considered as a Cd-bioindicator.