Search Results (394)

Accurate and timely diagnosis of rice leaf diseases is crucial for smart agriculture leveraging vision sensors. However, existing lightweight convolutional neural networks (CNNs) often struggle in complex field environments, where small lesions, cluttered backgrounds, and varying illumination complicate recognition. This paper presents I-GhostNetV3, an incrementally improved GhostNetV3-based network for RGB rice leaf disease recognition. I-GhostNetV3 introduces two modular enhancements with controlled overhead: (1) Adaptive Parallel Attention (APA), which integrates edge-guided spatial and channel cues and is selectively inserted to enhance lesion-related representations (at the cost of additional computation), and (2) Fusion Coordinate-Channel Attention (FCCA), a near-neutral SE replacement that enables efficient spatial–channel feature fusion to suppress background interference. Experiments on the Rice Leaf Bacterial and Fungal Disease (RLBF) dataset show that I-GhostNetV3 achieves 90.02% Top-1 accuracy with 1.831 million parameters and 248.694 million FLOPs, outperforming MobileNetV2 and EfficientNet-B0 under our experimental setup while remaining compact relative to the original GhostNetV3. In addition, evaluation on PlantVillage-Corn serves as a supplementary transfer sanity check; further validation on independent real-field target domains and on-device profiling will be explored in future work. These results indicate that I-GhostNetV3 is a promising efficient backbone for future edge deployment in precision agriculture. Full article

This study documents the ethnomedicinal knowledge of Konak (Malatya, Eastern Anatolia, Türkiye), a region with rich plant diversity but no prior comprehensive research. The aim of the study is to systematically document and analyze the ethnomedicinal practices of Konak village, focusing on plant taxa (species, subspecies and varieties) used, preparation methods, and therapeutic applications. Data were collected through semi-structured interviews with 68 local informants. Quantitative analysis was performed using Informant Consensus Factor (F_IC) and Use Value (UV) indices. Plant specimens were collected, identified, and deposited in the herbarium. The study documented 86 plant taxa from 35 families used in 230 therapeutic applications. Lamiaceae, Asteraceae, and Rosaceae were the most represented families. High F_IC values were recorded for colds (F_IC = 0.95), stomach pain (F_IC = 0.92), and inflammation (F_IC = 0.90), indicating strong community consensus. The most frequently cited species were Origanum vulgare subsp. gracile, Mentha spp., and Rosa canina. There are novel or locally specific uses, with 13 taxa having no previously recorded ethnomedicinal applications in the reviewed literature. The findings reveal Konak as a significant repository of ethnomedicinal knowledge. High-F_IC taxa represent prime candidates for phytochemical and pharmacological research to validate traditional uses and support evidence-based phytotherapy. This study enriches regional ethnopharmacological data and highlights candidate taxa for pharmacological validation. Full article

Accurate segmentation of fruit tree leaf diseases is critical for yield protection and precision crop management, yet it is challenging due to complex field conditions, irregular leaf morphology, and diverse lesion patterns. To address these issues, Disease-Seg, a lightweight real-time segmentation framework, is proposed. It integrates CNN and Transformer with a parallel fusion architecture to capture local texture and global semantic context. The Extended Feature Module (EFM) enlarges the receptive field while retaining fine details. A Deep Multi-scale Attention mechanism (DM-Attention) allocates channel weights across scales to reduce redundancy, and a Feature-weighted Fusion Module (FWFM) optimizes integration of heterogeneous feature maps, enhancing multi-scale representation. Experiments show that Disease-Seg achieves 90.32% mIoU and 99.52% accuracy, outperforming representative CNN, Transformer, and hybrid-based methods. Compared with HRNetV2, it improves mIoU by 6.87% and FPS by 31, while using only 4.78 M parameters. It maintains 69 FPS on 512 × 512 crops and requires approximately 49 ms per image on edge devices, demonstrating strong deployment feasibility. On two grape leaf diseases from the PlantVillage dataset, it achieves 91.19% mIoU, confirming robust generalization. These results indicate that Disease-Seg provides an accurate, efficient, and practical solution for fruit leaf disease segmentation, enabling real-time monitoring and smart agriculture applications. Full article

Knowledge related to the use of plants and mushrooms in the Baranja region of Croatia was documented through semi-structured interviews of 105 informants in 12 villages. We found 117 plant species and 7 mushrooms with medicinal uses. Rosaceae, Lamiaceae, and Asteraceae were the families with the most species, while Sambucus nigra, Chamomilla recutita, and Taraxacum officinale were the most frequently mentioned species. Leaves, fruits, and flowers were the most commonly used plant parts, predominantly prepared as infusions, syrups, and tinctures. Plants were mainly used to treat digestive and respiratory ailments, with the highest informant consensus recorded for ear, eye, and respiratory disorders. The results emphasize the persistence of rich ethnobotanical knowledge in the study area and highlight the importance of preserving this cultural and biological heritage for future generations. Full article

Local vegetables and spices are essential components of traditional food and health systems in northeastern Thailand, yet quantitative ethnobotanical evidence remains limited. This study documents the diversity, utilization, and cultural significance of vegetables and spices used in Sang Kho Sub-district, Phu Phan District, Sakon Nakhon Province. Ethnobotanical data were collected in 2025 through field surveys, voucher-based plant identification, semi-structured interviews, and participant observation involving 92 informants across 23 villages. Cultural significance and medicinal knowledge were evaluated using the Cultural Importance Index (CI), Informant Consensus Factor (FIC), and Fidelity Level (FL). A total of 113 taxa belonging to 94 genera and 49 plant families were recorded. Poaceae and Zingiberaceae were the most species-rich families. Native species slightly predominated (51.33%), and herbaceous taxa were most common. Leaves were the most frequently used plant part. Most taxa were used as vegetables (92 species), followed by traditional medicines (20 species), spices or seasonings (18 species), and food ingredients or culinary additives (18 species). The highest CI values were recorded for Allium ascalonicum L. (1.152), Capsicum annuum L. (1.098), and Coriandrum sativum L. (1.043). FIC values ranged from 0.60 to 1.00, with complete consensus for circulatory and neurological disorders. Cymbopogon citratus showed the highest FL (75%) for gastrointestinal uses. These findings demonstrate the close integration of food and medicine in local plant-use systems and provide baseline data for food system resilience and cultural knowledge conservation. Full article

Early and accurate date palm disease detection is the key to successful smart farming ecosystem sustainability. In this paper, we introduce DoST-DPD, a new Dual-Stream Transformer architecture for multimodal disease diagnosis utilizing RGB, thermal and NIR imaging. In contrast with standard deep learning approaches, our model receives ontology-based semantic supervision (via per-dataset OWL ontologies), enabling knowledge injection via SPARQL-driven reasoning during training. This structured knowledge layer not only improves multimodal feature correspondence but also restricts label consistency for improving generalization performance, particularly in early disease diagnosis. We tested our proposed method on a comprehensive set of five benchmarks (PlantVillage, PlantDoc, Figshare, Mendeley, and Kaggle Date Palm) together with domain-specific ontologies. An ablation study validates the effectiveness of incorporating ontology supervision, consistently improving the performance across Accuracy, Precision, Recall, F1-Score and AUC. We achieve state-of-the-art performance over five widely recognized baselines (PlantXViT, Multi-ViT, ERCP-Net, andResNet), with our model DoST-DPD achieving the highest Accuracy of 99.3% and AUC of 98.2% on the PlantVillage dataset. In addition, ontology-driven attention maps and semantic consistency contributed to high interpretability and robustness in multiple crop and imaging modalities. Results: This work presents a scalable roadmap for ontology-integrated AI systems in agriculture and illustrates how structured semantic reasoning can directly benefit multimodal plant disease detection systems. The proposed model demonstrates competitive performance across multiple datasets and highlights the unique advantage of integrating ontology-guided supervision in multimodal crop disease detection. Full article

Chestnut is an important economic plant for ecology and farmers in mountainous areas in China. We conducted surveys and experiments to assess the economic value of the pollination service provided by insect pollinators for chestnuts via the Toolkit for Ecosystem Service Site-based Assessment (TESSA) in Bapeng Village, Wangmo County, Guizhou Province of China. We applied three methods presented by TESSA, the desk-based method, the field survey method, and the exclusion experiment, for the assessment. The resulting pollination values for the three methods are (1) CNY 3712.5∙ha⁻¹∙yr⁻¹ in the assessment site and an average of CNY 1386∙ha⁻¹∙yr⁻¹ with buffer zones included for the desk-based method; (2) CNY 3712.5∙ha⁻¹∙yr⁻¹ in the assessment site and an average of CNY 1124∙ha⁻¹∙yr⁻¹ with buffer zones included for the field survey method; and (3) CNY 4158∙ha⁻¹∙yr⁻¹ in the assessment site and an average of CNY 1485∙ha⁻¹∙yr⁻¹ with buffer zones included for the exclusion experiment method. The total value of chestnut pollination of the Bapeng Village ranges from CNY 311,943 yr⁻¹ to CNY 404,663 yr⁻¹. The chestnut pollination of the village is substantially insufficient. This could be the result of the decrease in diversity and uneven distribution of insect pollinators which, per se, are caused by the lack of larval hosts for those pollinators. Full article

In recent years, many locales featuring therapeutic landscapes have seen a rise in health tourism. Existing scholarship tends to either concentrate on specific types of landscape or analyze human emotional experiences separately, often overlooking how therapeutic landscape experiences arise from interactions among human and non-human actors. This study focuses on the relationship between tourists and non-human actors (plants such as rice and lotus leaves, etc.) through immersive interaction. This research is built on critical plant theory and draws on a case study of Xixiang Rural Garden, Erlang Town, China, to examine the co-evolution of therapeutic landscape experience and health tourism and its inherent dynamism. Utilizing qualitative methods, data were collected between October 2024 and September 2025 through participatory observation, semi-structured interviews, and policy document analysis, involving diverse stakeholders, including local government officials, project designers, villagers, and tourists. From a micro-level empirical perspective, the study examines the co-evolution of therapeutic landscape experiences and health tourism and its underlying dynamics. The results show that visitors’ therapeutic experiences deepen through a cyclical process of “therapeutic spatial practices–relational negotiations–experiential transformation.” Key mechanisms driving this process include plant agency, cross-cultural dialogue, and multisensory engagement, which collectively facilitate the transition from initial sensory perceptions to deeper ecological awareness and multispecies relations. Based on micro-level empirical analysis, this study offers concrete policy insights for local governments seeking to promote the sustainable development of therapeutic tourism. In response to practical challenges, specific pathways are proposed: constructing plant-led symbiotic environments, establishing multisensory activity mechanisms, and adopting community-driven management models. These recommendations provide practical guidance for enhancing therapeutic landscape experiences and promoting the sustainable advancement of rural health tourism. Full article

The first comprehensive study about of amber from the Lower Cretaceous of the Lusitanian Basin, in the Estremadura region of western Portugal, is here reported. The amber was recovered as isolated clasts in the Portela da Vila outcrop section, near the small villages of Ramalhal and Ameal, from sedimentary deposits belonging to the Lugar d’Além Formation considered to be of Hauterivian age. The chemical composition of amber clasts was examined in order to infer their botanical source via biomarker analysis. GC–MS and GC×GC–TOFMS showed a strong predominance of abietane-type diterpenoids, including compounds such as amberene, ferruginol (phenolic abietane), kaurane and the derivative of clerodane. The dominance of abietane diterpenoids along with these specific biomarkers is consistent with resin exudation by Araucariaceae/Cheirolepidiaceae conifers, as supported by previous chemotaxonomic studies of Cretaceous amber. Palynological studies of the same sedimentary rock samples highlighted a pollen–spore assemblage characterized by low diversity and number of specimens, and dominated by conifer pollen assigned to the genera Classopollis, Araucariacites and coniferous bisaccate pollen, with relative occurrences of fern spores. The combined geochemical and palynological studies strongly support a source related to conifer plants for the amber here reported. Full article

Small-scale farms produce more than one-third of the world’s food supply, making them a crucial contributor to global food security. In this study, an artificial intelligence of things (AIoT) framework is introduced for smart small-scale farm management. For plant disease detection, the lightweight MobileViT model, which integrates vision transformer and convolutional modules, was utilized to efficiently capture both global and local image features. Data augmentation and transfer learning were employed to enhance the model’s overall performance. MobileViT resulted in a test accuracy of 99.5%, with per-class precision, recall, and f1-score ranging between 0.92 and 1.00 considering the benchmark Plant Village dataset (14 species–38 classes). MobileViT was shown to outperform several standard deep convolutional networks, including MobileNet, ResNet and Inception, by 2–12%. Additionally, an LLM-powered interactive chatbot was integrated to provide farmers with instant plant care suggestions. For plant environment management, the powerful, cost-effective ESP32 microcontroller was utilized as the core processing unit responsible for collecting sensor data (e.g., soil moisture), controlling actuators (e.g., water pump for irrigation), and maintaining connectivity with Google Firebase Cloud. Finally, a mobile application was developed to integrate the AI and IoT system capabilities, hence providing users with a reliable platform for smart plant disease detection and environment management. Each system component was each tested individually, before being incorporated into the mobile application and tested in real-world scenarios. The presented AIoT-based solution has the potential to enhance crop productivity within small-scale farms while promoting sustainable farming practices and efficient resource management. Full article

The Congo Basin peatlands, the world’s largest tropical peatland complex, are critical for global carbon storage yet remain poorly understood from a human dimension’s perspective. This study explores the perceptions, lifestyles, and knowledge systems of Indigenous Peoples and local communities around Lake Tumba, Democratic Republic of Congo, to identify practices supporting peatland conservation. Using a mixed-methods approach—household surveys (n = 320), focus groups, and statistical analyses including chi-square tests and Multiple Correspondence Analysis (MCA)—the study reveals a predominantly Indigenous agrarian society with limited formal education and strong reliance on peatlands for food (93.7%), construction materials (79.0%), and medicines (75.9%). While regulating services such as carbon storage were seldom recognized, traditional ecological knowledge was evident in sacred species protection, ritual plant and animal uses, and intergenerational knowledge transfer, mainly father-to-son. However, 95.3% of respondents cited religion as the main barrier to this transmission. MCA confirmed that livelihoods, village status, and ritual practices form an integrated socio-cultural system aligned with conservation. These findings stress the role of endogenous governance in sustaining peatland-compatible lifestyles. Conservation efforts should move beyond carbon-centered or top-down approaches to reinforce land tenure, traditional governance, and knowledge transmission, thereby protecting both peatlands and the cultural identities sustaining them. Full article

Although Convolutional Neural Networks (CNNs) have delivered state-of-the-art accuracy in plant disease classification, their deployment is still hindered by data scarcity, computational cost, and architectural heterogeneity. Transfer learning from large-scale pre-trained datasets alleviates these issues, yet generic feature extraction suffers from domain shift, while indiscriminate fine-tuning risks over-fitting and elevated training budgets. To address the identified limitations, PlantClassiNet is implemented as a unified framework. This framework facilitates systematic comparative analysis of six CNN architectures, AlexNet, ResNet50, InceptionV3, MobileNetV3Small, DenseNet121 and EfficientNetB0, across three publicly available datasets: PlantVillage, PlantLeaves and Eggplant. Two alternative fine-tuning approaches are proposed: Adaptive Fine-tuning (AdapFitu), which adaptively determines the depth of unfrozen layers, learning rates, and reinitializes selected layers, and a fixed-parameter baseline, which trains only the newly added classifier while keeping the convolutional backbone frozen and unfreezes a fixed number of network layers for retraining. Extensive experiments demonstrate that large models AlexNet, ResNet50, and Inceptionv3 achieve test accuracy exceeding 98.74% on the sizable PlantVillage dataset, whereas lightweight counterparts MobileNetV3Small, DenseNet121, and EfficientNetB0 achieve high accuracy of 99.79% ± 0.21% on the smaller Eggplant collection after fine-tuning. Full article

Unobserved fruit crop illnesses are a major threat to agricultural productivity worldwide and frequently cause farmers to suffer large financial losses. Manual field inspection-based disease detection techniques are time-consuming, unreliable, and unsuitable for extensive monitoring. Deep learning approaches, in particular convolutional neural networks, have shown promise for automated plant disease identification, although they still face significant obstacles. These include poor generalization across complicated visual backdrops, limited resilience to different illness sizes, and high processing needs that make deployment on resource-constrained edge devices difficult. We suggest a Hybrid Multi-Scale Neural Network (HMCT-AF with GSAF) architecture for precise and effective fruit crop disease identification in order to overcome these drawbacks. In order to extract long-range dependencies, HMCT-AF with GSAF combines a Vision Transformer-based structural branch with multi-scale convolutional branches to capture both high-level contextual patterns and fine-grained local information. These disparate features are adaptively combined using a novel HMCT-AF with a GSAF module, which enhances model interpretability and classification performance. We conduct evaluations on both PlantVillage (controlled environment) and CLD (real-world in-field conditions), observing consistent performance gains that indicate strong resilience to natural lighting variations and background complexity. With an accuracy of up to 93.79%, HMCT-AF with GSAF outperforms vanilla Transformer models, EfficientNet, and traditional CNNs. These findings demonstrate how well the model captures scale-variant disease symptoms and how it may be used in real-time agricultural applications using hardware that is compatible with the edge. According to our research, HMCT-AF with GSAF presents a viable basis for intelligent, scalable plant disease monitoring systems in contemporary precision farming. Full article

Technology-driven agriculture, or precision agriculture (PA), is indispensable in the contemporary world due to its advantages and the availability of technological innovations. Particularly, early disease detection in agricultural crops helps the farming community ensure crop health, reduce expenditure, and increase crop yield. Governments have mainly used current systems for agricultural statistics and strategic decision-making, but there is still a critical need for farmers to have access to cost-effective, user-friendly solutions that can be used by them regardless of their educational level. In this study, we used four apple leaf diseases (leaf spot, mosaic, rust and brown spot) from the PlantVillage dataset to develop an Automated Agricultural Crop Disease Identification System (AACDIS), a deep learning framework for identifying and categorizing crop diseases. This framework makes use of deep convolutional neural networks (CNNs) and includes three CNN models created specifically for this application. AACDIS achieves significant performance improvements by combining cascade inception and drawing inspiration from the well-known AlexNet design, making it a potent tool for managing agricultural diseases. AACDIS also has Region of Interest (ROI) awareness, a crucial component that improves the efficiency and precision of illness identification. This feature guarantees that the system can quickly and accurately identify illness-related areas inside images, enabling faster and more accurate disease diagnosis. Experimental findings show a test accuracy of 99.491%, which is better than many state-of-the-art deep learning models. This empirical study reveals the potential benefits of the proposed system for early identification of diseases. This research triggers further investigation to realize full-fledged precision agriculture and smart agriculture. Full article

The rapid growth of artificial intelligence (AI) has enabled efficient crop disease detection even in data-scarce agricultural settings. This study proposes AgriFewNet, a few-shot learning framework designed to improve classification accuracy using RGB imagery captured from publicly available datasets. The objective is to enable fast model adaptation to new disease classes using minimal labeled samples while maintaining high reliability in real-world conditions. AgriFewNet employs a hierarchical attention-enhanced ResNet-18 backbone incorporating dual spatial and channel attention to extract discriminative RGB features. A Model-Agnostic Meta-Learning (MAML) approach facilitates quick generalization to previously unexplored illness categories, while a prototype-based classifier guarantees compact representation learning. Using only RGB images, experiments on the PlantVillage and New PlantVillage datasets produced accuracies of 87.3% (1-shot), 94.8% (5-shot), and 97.1% (10-shot), surpassing leading few-shot baselines by as much as 7.9%. The findings show that AgriFewNet offers a resource-efficient and scalable method for intelligent crop monitoring, enhancing food security and precision agriculture. Full article