Search Results (1,036)

The activities of birds present increasing challenges in agriculture, aviation, and environmental conservation. This has led to economic losses, safety risks, and ecological imbalances. Attempts have been made to address the problem, with traditional deterrent methods proving to be labour-intensive, environmentally unfriendly, and ineffective over time. Advances in artificial intelligence (AI) and the Internet of Things (IoT) present opportunities for enabling automated real-time bird detection and repellence. This study reviews recent developments (2020–2025) in AI-driven bird detection and repellence systems, emphasising the integration of image, audio, and multi-sensor data in IoT and edge-based environments. The Preferred Reporting Items for Systematic Reviews and Meta-Analyses framework was used, with 267 studies initially identified and screened from key scientific databases. A total of 154 studies met the inclusion criteria and were analysed. The findings show the increasing use of convolutional neural networks (CNNs), YOLO variants, and MobileNet in visual detection, and the growing use of lightweight audio-based models such as BirdNET, MFCC-based CNNs, and TinyML frameworks for microcontroller deployment. Multi-sensor fusion is proposed to improve detection accuracy in diverse environments. Repellence strategies include sound-based deterrents, visual deterrents, predator-mimicking visuals, and adaptive AI-integrated systems. Deployment success depends on edge compatibility, power efficiency, and dataset quality. The limitations of current studies include species-specific detection challenges, data scarcity, environmental changes, and energy constraints. Future research should focus on tiny and lightweight AI models, standardised multi-modal datasets, and intelligent, behaviour-aware deterrence mechanisms suitable for precision agriculture and ecological monitoring. Full article

Water-related ecosystem services provide a broad range of benefits, including the mitigation of extreme hydrometeorological events, the provision of water for various uses, the support of tourism, and the provision of cultural services. This study assesses the perceptions and accessibility of these services among communities located near the Alafiarou and Okpara dams in Benin and the Bagré dam in Burkina Faso. The methodology involved designing and implementing a questionnaire in KoboCollect, with trained agents deployed to conduct data collection at each of the three sites. Data analysis indicates that respondents identified biodiversity conservation and the provision of drinking water as the most crucial ecosystem services. Over two-thirds of participants reported observing both positive and negative changes in the services provided by rivers and in socio-economic activities since the construction of the dams. While the majority noted improvements in agriculture, irrigation, water quality, fisheries, and flow rates, other changes included biodiversity loss, a decrease in vegetation cover (notably trees and shrubs), an increase in the population of mosquitoes and other insects, and a decline in fishery resources downstream. Despite these challenges, local communities were strongly willing to participate in initiatives aimed at protecting and restoring river ecosystems and their related services. Full article

In recent decades, the rapid expansion of the food processing industry has led to significant losses and waste, with the fruit and vegetable sector among the most affected. According to the Food and Agriculture Organization of the United Nations (FAO), losses in this category can reach up to 60%. Vegetable waste includes edible parts discarded during processing, packaging, distribution, and consumption, often comprising by-products rich in bioactive compounds such as polyphenols, carotenoids, dietary fibers, vitamins, and enzymes. The underutilization of these resources constitutes both an economic drawback and an environmental and ethical concern. Current recovery practices, including their use in animal feed or bioenergy production, contribute to a circular economy but are often limited by high operational costs. In this context, fermentation has emerged as a promising, sustainable approach for converting vegetable by-products into value-added food ingredients. This process improves digestibility, reduces undesirable compounds, and introduces probiotics beneficial to human health. The present review examines how fermentation can improve the nutritional, sensory, and functional properties of plant-based foods. By presenting several case studies, it illustrates how fermentation can effectively valorize vegetable processing by-products, supporting the development of novel, health-promoting food products with improved technological qualities. Full article

Bruising in ‘Korla’ pears represents a prevalent phenomenon that leads to progressive fruit decay and substantial economic losses. The detection of early-stage bruising proves challenging due to the absence of visible external characteristics, and existing deep learning models have limitations in weak feature extraction under complex optical interference. To address the postharvest latent damage detection challenges in ‘Korla’ pears, this study proposes a collaborative detection framework integrating structured-illumination reflectance imaging (SIRI) with multi-order gated attention mechanisms. Initially, an SIRI optical system was constructed, employing 150 cycles·m⁻¹ spatial frequency modulation and a three-phase demodulation algorithm to extract subtle interference signal variations, thereby generating RT (Relative Transmission) images with significantly enhanced contrast in subsurface damage regions. To improve the detection accuracy of latent damage areas, the MOGA-UNet model was developed with three key innovations: 1. Integrate the lightweight VGG16 encoder structure into the feature extraction network to improve computational efficiency while retaining details. 2. Add a multi-order gated aggregation module at the end of the encoder to realize the fusion of features at different scales through a special convolution method. 3. Embed the channel attention mechanism in the decoding stage to dynamically enhance the weight of feature channels related to damage. Experimental results demonstrate that the proposed model achieves 94.38% mean Intersection over Union (mIoU) and 97.02% Dice coefficient on RT images, outperforming the baseline UNet model by 2.80% with superior segmentation accuracy and boundary localization capabilities compared with mainstream models. This approach provides an efficient and reliable technical solution for intelligent postharvest agricultural product sorting. Full article

Weed infestation contributes significantly to global agricultural yield loss and increases the reliance on herbicides, raising both economic and environmental concerns. Effective weed detection in agriculture requires high accuracy and architectural efficiency. This is particularly important under challenging field conditions, including densely clustered targets, small weed instances, and low visual contrast between vegetation and soil. In this study, we propose GTDR-YOLOv12, an improved object detection framework based on YOLOv12, tailored for real-time weed identification in complex agricultural environments. The model is evaluated on the publicly available Weeds Detection dataset, which contains a wide range of weed species and challenging visual scenarios. To achieve better accuracy and efficiency, GTDR-YOLOv12 introduces several targeted structural enhancements. The backbone incorporates GDR-Conv, which integrates Ghost convolution and Dynamic ReLU (DyReLU) to improve early-stage feature representation while reducing redundancy. The GTDR-C3 module combines GDR-Conv with Task-Dependent Attention Mechanisms (TDAMs), allowing the network to adaptively refine spatial features critical for accurate weed identification and localization. In addition, the Lookahead optimizer is employed during training to improve convergence efficiency and reduce computational overhead, thereby contributing to the model’s lightweight design. GTDR-YOLOv12 outperforms several representative detectors, including YOLOv7, YOLOv9, YOLOv10, YOLOv11, YOLOv12, ATSS, RTMDet and Double-Head. Compared with YOLOv12, GTDR-YOLOv12 achieves notable improvements across multiple evaluation metrics. Precision increases from 85.0% to 88.0%, recall from 79.7% to 83.9%, and F1-score from 82.3% to 85.9%. In terms of detection accuracy, mAP:0.5 improves from 87.0% to 90.0%, while mAP:0.5:0.95 rises from 58.0% to 63.8%. Furthermore, the model reduces computational complexity. GFLOPs drop from 5.8 to 4.8, and the number of parameters is reduced from 2.51 M to 2.23 M. These reductions reflect a more efficient network design that not only lowers model complexity but also enhances detection performance. With a throughput of 58 FPS on the NVIDIA Jetson AGX Xavier, GTDR-YOLOv12 proves both resource-efficient and deployable for practical, real-time weeding tasks in agricultural settings. Full article

The detection of plant constituents is a crucial issue in precision agriculture, as monitoring these enables the automatic analysis of factors such as growth rate, health status, and crop yield. Tomatoes (Solanum sp.) are an economically and nutritionally important crop in Mexico and worldwide, which is why automatic monitoring of these plants is of great interest. Detecting leaves on images of outdoor tomato plants is challenging due to the significant variability in the visual appearance of leaves. Factors like overlapping leaves, variations in lighting, and environmental conditions further complicate the task of detection. This paper proposes modifications to the Yolov11n architecture to improve the detection of tomato leaves in images of complex outdoor environments by incorporating attention modules, transformers, and WIoUv3 loss for bounding box regression. The results show that our proposal led to a 26.75% decrease in the number of parameters and a 7.94% decrease in the number of FLOPs compared with the original version of Yolov11n. Our proposed model outperformed Yolov11n and Yolov12n architectures in recall, F1-measure, and mAP@50 metrics. Full article

Meloidogyne enterolobii, a highly virulent and broad-host-range plant-parasitic nematode, poses an increasing threat to global agricultural production. By inducing the formation of nutrient-rich giant cells in host roots and deploying a diverse array of effector proteins to modulate plant immune responses, this nematode achieves efficient colonization and invasion, resulting in impaired crop growth and significant economic losses. In recent years, global climate warming combined with the rapid development of protected agriculture has broken the traditional geographical limits of tropical and subtropical regions, thereby increasing the risk of M. enterolobii occurrence in temperate and high-latitude areas. Concurrently, conventional chemical control methods are increasingly limited by environmental pollution and the development of resistance, steering research toward green control strategies. This review systematically summarizes the latest research progress of M. enterolobii in terms of ecological diffusion trends, pathogenic mechanisms, and green control, and explored the feasibility of integrating multidisciplinary technologies to construct an efficient and precise control system. The ultimate aim is to provide theoretical support and technical supports for green and sustainable development of global agriculture. Full article

With the acceleration of global urbanization, cropland loss and fragmentation due to construction land expansion have become critical threats to food security and ecological sustainability, particularly in rapidly developing coastal regions. Understanding urban–rural differences in these processes is essential as divergent governance policies, socioeconomic pressures, and land use transition pathways may lead to uneven impacts on agricultural systems. However, past comparisons of urban–rural differences regarding this issue have been insufficient. Therefore, this study takes Jiangsu Province, China, as an example. Based on 30 m-resolution land use data, Geographic Information System (GIS) spatial analysis, and landscape pattern indices, it delves into the urban–rural differences in cropland loss and fragmentation caused by construction land expansion from 1990 to 2020. The results show that cropland in urban and rural areas decreased by 44.14% and 5.97%, respectively, while the area of construction land increased by 2.61 times and 90.14%, respectively. 94.36% of the newly added construction land originated from cropland, with the conversion of rural cropland to construction land being particularly prominent in northern Jiangsu, while the conversion of urban cropland to construction land is more pronounced in southern Jiangsu. The expansion of construction land has led to the continuous fragmentation of cropland, which is more severe in urban areas than in rural areas, while construction land is becoming increasingly agglomerated. There are significant differences in the degree of land use change between urban and rural areas, necessitating the formulation of differentiated land management policies to balance economic development with agricultural sustainability. Full article

Spodoptera frugiperda is a major agricultural pest worldwide, causing significant economic loss to maize crops. Its control largely depends on synthetic pesticides, which contribute to resistance development, harm non-target organisms, and lead to environmental degradation. Essential oils and their main components offer a more sustainable and ecologically sound alternative for the management of S. frugiperda. This study evaluated the effects of selected essential oils and their bioactive compounds on the survival and behavior of S. frugiperda using toxicity and preference assays. Peppermint essential oil and its major constituent, pulegone, significantly reduced the survival of S. frugiperda, with effects similar to those caused by synthetic insecticides. Eucalyptus essential oil and its main compound, 1,8-cineole, also influenced the behavior of S. frugiperda, suggesting potential for use in repellents. These findings highlight the use of essential oils and their main constituents/active constituents as bioinsecticides and their integration into environmentally friendly pest management strategies. Full article

Cropland is a critical resource for safeguarding food security. Ensuring both the quantity and quality of cropland is essential for achieving zero hunger and promoting sustainable agriculture. However, whether urbanization-induced cropland loss poses a substantial threat to regional food security remains a key concern. This study examines the central region of the Yangtze River Delta (YRD) in China, integrating CLCD (China Land Cover Dataset) land use/cover data (2001–2023), MOD17A2H net primary productivity (NPP) data, and statistical records to evaluate the impacts of urban expansion on grain yield. The analysis focuses on three components: (1) grain yield loss due to cropland conversion, (2) compensatory yield from newly added cropland under the requisition–compensation policy, (3) yield increases from stable cropland driven by agricultural enhancement strategies. Using Sen’s slope analysis, the Mann–Kendall trend test, and hot/coldspot analysis, we revealed that urban expansion converted approximately 14,598 km² of cropland, leading to a grain production loss of around 3.49 million tons, primarily in the economically developed cities of Yancheng, Nantong, Suzhou, and Shanghai. Meanwhile, 8278 km² of new cropland was added through land reclamation, contributing only 1.43 million tons of grain—offsetting just 41% of the loss. In contrast, stable cropland (102,188 km²) contributed an increase of approximately 9.84 million tons, largely attributed to policy-driven productivity gains in areas such as Chuzhou, Hefei, and Ma’anshan. These findings suggest that while compensatory cropland alone is insufficient to mitigate the food security risks from urbanization, the combined strategy of “Safeguarding Grain in the Land and in Technology” can more than compensate for production losses. This study underscores the importance of optimizing land use policy, strengthening technological interventions, and promoting high-efficiency land management. It provides both theoretical insight and policy guidance for balancing urban development with regional food security and sustainable land use governance. Full article

Flow regulation and water quality maintenance are considered ecosystem services, as they provide environmental benefits with a measurable economic value to society. Distributed or semi-distributed hydrological models can help identify where land use decisions yield the greatest economic and environmental returns related to water resources. For these reasons, this study integrated simulations performed with the SWAT (Soil and Water Assessment Tool) model under varying land use conditions, aiming to balance potential benefits with the loss of ecosystem services. Among the tested parameters, those associated with surface runoff showed the highest sensitivity in simulating streamflow for the Jundiaí River Basin. Based on the statistical indicators R², Nash–Sutcliffe efficiency (NS), and Percent Bias (PBIAS), the SWAT model demonstrated a reliable performance in replicating observed streamflows on a monthly scale, even with limited spatially distributed input data. Scenario 2, which involved converting 15% of pasture/agricultural land into forest, yielded the most favorable hydrological outcomes by increasing soil water infiltration and aquifer recharge while reducing surface runoff and sediment yield. These findings highlight the value of reforestation and land use planning as effective strategies for improving watershed hydrological performance and ensuring long-term water sustainability. Full article

Insect pests inflict significant agricultural and economic losses on crops globally. Chemical control refers to the use of agrochemicals, such as insecticides, herbicides, and fungicides, to manage pests and diseases. Chemical control is still the prioritized method, as insecticides are highly effective and toxic to insect pests. However, it reduces the quality of the environment, threatens human health, and causes serious 3R (reduce, reuse, and recycle) problems. Current advances in the mining of functional symbiotic bacteria resources provide the potential to assuage the use of insecticides while maintaining an acceptably low level of crop damage. Recent research on insect–microbe symbiosis has uncovered a mechanism labeled “detoxifying symbiosis”, where symbiotic microorganisms increase host insect resistance through the metabolism of toxins. In addition, the physiological compensation effect caused by insect resistance affects the ability of the host to regulate the community composition of symbiotic bacteria. This paper reviews the relationship between symbiotic bacteria, insects, and insecticide resistance, focusing on the effects of insecticide resistance on the composition of symbiotic bacteria and the role of symbiotic bacteria in the formation of resistance. The functional symbiotic bacteria resources and their mechanisms of action need to be further explored in the future so as to provide theoretical support for the development of pest control strategies based on microbial regulation. Full article

Plant-parasitic nematodes represent a significant threat to agriculture, causing substantial economic losses worldwide. Among the biological alternatives for their control, the genus Trichoderma has emerged as a promising solution for suppressing various nematode species. This article reviews key studies on the interaction between Trichoderma spp. and plant-parasitic nematodes, highlighting the most studied species such as Trichoderma harzianum, Trichoderma longibrachiatum, Trichoderma virens, and Trichoderma viride, mainly against the genera Meloidogyne, Pratylenchus, Globodera, and Heterodera. Trichoderma spp. act through mechanisms such as mycoparasitism, antibiosis, competition for space in the rhizosphere, production of lytic enzymes, and modulation of plant defense responses. They also produce metabolites that affect nematode mobility, reproduction, and survival, such as gliotoxin, viridin and cyclosporine A. In addition, they secrete enzymes such as chitinases, proteases, lipases, and glucanases, which degrade the cuticle of nematodes and their eggs. Furthermore, Trichoderma spp. induce systemic resistance in plants through modulation of phytohormones such as jasmonic acid, ethylene, salicylic acid and auxins. The use of Trichoderma in integrated nematode management enables its application in combination with crop rotation, organic amendments, plant extracts, and resistant varieties, thereby reducing the reliance on synthetic nematicides and promoting more sustainable and climate-resilient agriculture. Full article

Grain drying technology is a core process for ensuring food quality, extending storage life, and improving processing adaptability. With the continuous growth of global food demand and the increasing requirements for food quality and energy efficiency, traditional drying technologies face multiple challenges. This paper reviews six major grain drying technologies, comprising hot air drying, microwave drying, infrared drying, freeze drying, vacuum drying, and solar drying. It provides an in-depth discussion of the working principles, advantages, and limitations of each technology, and analyzes their performance in practical applications. In response to challenges such as high energy consumption, uneven drying, and quality loss during the drying process, the paper also explores the research progress of several hybrid drying systems, such as microwave–hot air drying combined systems and solar–infrared drying systems. Although these emerging technologies show significant potential in improving drying efficiency, energy saving, and maintaining food quality, their high costs, scalability, and process stability still limit large-scale applications. Therefore, future research should focus on reducing energy consumption, improving drying precision, and optimizing drying system integration, particularly by introducing intelligent control systems. This would maximize the preservation of food quality while improving the system’s economic efficiency and sustainability, promoting innovation in food production and processing technologies, and further advancing global food security and sustainable agricultural development. Full article

Plant parasitic nematodes cause huge economic losses to agriculture and forestry every year, and chemical insecticides destroy the ecological environment. Researching the mechanism by which small-molecule signaling substances regulate nematode behavior and development is important for developing environmentally friendly biological control agents. Nematode pheromones are essential chemicals signaling intraspecies and interspecies communication, regulating development, reproduction, and social behavior. Their structural diversity enables ecological adaptation and cross-kingdom interactions, influencing fungal predation and plant immunity. This review focuses on the classification, function, and regulatory mechanisms of nematode pheromones, interspecific signal transmission, and biosynthesis pathways. We pay special attention to their potential as environmentally friendly biological control agents as well as the challenges currently encountered in their application. Full article