[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-2963":3,"related-2963":57},{"id":4,"title":5,"url":6,"summary":7,"summary_zh":8,"content":9,"source_name":10,"source_url":6,"published_at":11,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":15,"score_detail":16,"sources":24,"tags":26,"search_phrases":32,"slug":35,"view_count":36,"doi":37,"paper":38,"created_at":56},2963,"A comprehensive review of deep learning methods for weed classification in precision agriculture","https:\u002F\u002Fdoi.org\u002F10.1007\u002Fs44163-026-01916-7","Weeds today are among the factors contributing to low agricultural productivity. As the world’s population continues to grow, there is an urgent need to meet global food demand. Nigeria currently lacks sufficient crop production to feed its growing population, and weeds are among the core contributors to poor agricultural yield. This study conducts a comprehensive review of Deep Learning (DL) approaches to weed classification in precision agriculture, covering literature from 2018 to 2025, was carried out. We employed a mix of quantitative and qualitative methods in the course of this review paper. Our data source is centred on Scopus-indexed papers, published with Sensors, Electronics, and Agriculture in MDPI as well as IEEE, Thomson Reuters, and Springer. The study systematically reviewed and analysed machine learning (ML), DL, and instance segmentation techniques to identify the key technological and environmental barriers, such as data limitations, class imbalance, environmental variability, and model scalability issues that affect the effectiveness and efficiency of these models when deployed in real time. These findings show that while weed management models like the YOLO variants, ResNet, and Vision Transformers achieved high accuracy in training and testing, they are associated with several challenges in their real world-deployment, such as occlusion, small object detection, and environmental adaptability. Overall, this research provides recommended solutions to enhance model robustness, scalability, and efficiency. It further provides a summary of the current state and future directions for AI-driven weed management.","杂草是当前导致农业生产力低下的因素之一。随着世界人口持续增长，满足全球粮食需求已成为迫切任务。尼日利亚目前的作物产量不足以养活其不断增长的人口，而杂草是导致农业产量低下的核心因素之一。本研究对精准农业中基于深度学习（Deep Learning，DL）的杂草分类方法进行了全面综述，涵盖2018年至2025年的文献。在综述过程中，我们采用了定量与定性相结合的方法。数据来源集中于Scopus索引论文，这些论文发表于MDPI旗下的Sensors、Electronics和Agriculture，以及IEEE、Thomson Reuters和Springer。本研究系统综述并分析了机器学习（Machine Learning，ML）、深度学习及实例分割技术，以识别影响这些模型实时部署效果与效率的关键技术和环境障碍，如数据局限性、类别不平衡、环境变异性及模型可扩展性问题。研究结果表明，尽管YOLO系列、ResNet和视觉Transformer（Vision Transformer）等杂草管理模型在训练和测试中达到了较高精度，但在实际部署中仍面临诸多挑战，如遮挡、小目标检测和环境适应性等问题。总体而言，本研究提出了增强模型鲁棒性、可扩展性和效率的推荐解决方案，并进一步总结了人工智能驱动杂草管理的现状与未来方向。",null,"Discover Artificial Intelligence","2026-09-18T00:00:00Z","论文",10,false,67,{"impact":17,"substance":18,"depth":19,"authority":20,"freshness":21,"relevant":22,"comment":23},12,18,16,13,8,1,"系统综述2018—2025年深度学习杂草分类方法，指出遮挡、小目标与环境适应性等落地瓶颈，对农业AI研究有参考价值，但属综述类论文、非突破性成果。",[25],{"name":10,"url":6},[27,28,29,30,31],"智慧农业","农业人工智能","深度学习","杂草识别","精准农业",[33,34],"深度学习 杂草分类 精准农业","YOLO 杂草识别 模型部署","深度学习杂草分类精准农业-2963",0,"10.1007\u002Fs44163-026-01916-7",{"doi":37,"openalex_id":39,"authors":40,"venue":10,"cited_by_count":36,"oa_url":6,"card":49,"direction":53,"ingested_from":55},"W7213558223",[41,43,45,47],{"name":42,"orcid":9},"Njoku Camillus Ekene",{"name":44,"orcid":9},"Francis A. Okoye",{"name":46,"orcid":9},"Ebere Uzoka Chidi",{"name":48,"orcid":9},"OGBU MARY NNENNA",{"tldr":50,"method":51,"finding":52,"direction":53,"opportunity":54},"综述2018-2025年深度学习杂草分类方法，分析技术瓶颈并给出改进建议。","混合定量定性法，基于Scopus及MDPI、IEEE等文献，分析ML、DL与实例","YOLO、ResNet、ViT等精度高，但实际部署受遮挡、小目标与环境适应性限制。","农业人工智能与决策模型","可研究轻量化、跨域自适应模型，解决小目标与遮挡下的实时杂草识别难题。","openalex","2026-09-19T23:30:56.875661Z",{"total":58,"page":22,"page_size":58,"items":59},6,[60,97,130,164,204,255],{"id":61,"title":62,"url":63,"summary":64,"summary_zh":65,"content":9,"source_name":66,"source_url":63,"published_at":67,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":68,"score_detail":69,"sources":74,"tags":76,"search_phrases":77,"slug":80,"view_count":36,"doi":81,"paper":82,"created_at":96},2335,"Deep Learning-Based Weed Classification, Detection, and Segmentation in Precision Agriculture: a Bibliometric and Comprehensive Review","https:\u002F\u002Fdoi.org\u002F10.1007\u002Fs10343-026-01424-9","Deep Learning-Based Weed Classification, Detection, and Segmentation in Precision Agriculture: a Bibliometric and Comprehensive Review。Journal of Plant Diseases and Protection","基于深度学习的精准农业杂草分类、检测与分割：文献计量与综合综述。《植物病害与保护杂志》","Journal of Plant Diseases and Protection","2026-09-12T00:00:00Z",75,{"impact":70,"substance":71,"depth":18,"authority":72,"freshness":21,"relevant":22,"comment":73},15,20,14,"核心期刊发表的深度学习杂草识别综述，方法梳理与文献计量兼具，对精准农业植保智能化有参考价值，但属学术综述而非产业级突破。",[75],{"name":66,"url":63},[27,28,29,30,31],[78,79],"农业人工智能 智慧农业 杂草识别 深度学习","农业人工智能 智慧农业","农业人工智能智慧农业杂草识别深度学习-2335","10.1007\u002Fs10343-026-01424-9",{"doi":81,"openalex_id":83,"authors":84,"venue":66,"cited_by_count":36,"oa_url":9,"card":91,"direction":53,"ingested_from":55},"W7212352052",[85,88],{"name":86,"orcid":87},"Furkan Ulaş","https:\u002F\u002Forcid.org\u002F0009-0002-3052-4457",{"name":89,"orcid":90},"Muhammad Aasım","https:\u002F\u002Forcid.org\u002F0000-0002-8524-9029",{"tldr":92,"method":93,"finding":94,"direction":53,"opportunity":95},"对精准农业中深度学习杂草分类、检测与分割研究进行文献计量与综述分析。","文献计量分析与综合综述，基于相关文献数据库。","梳理了深度学习在杂草识别三大任务中的方法、趋势与挑战。","可针对田间复杂光照与多物种场景，探索轻量化实时分割模型与跨数据集泛化。","2026-09-13T23:30:38.907624Z",{"id":98,"title":99,"url":100,"summary":101,"summary_zh":102,"content":9,"source_name":103,"source_url":100,"published_at":104,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":105,"score_detail":106,"sources":109,"tags":111,"search_phrases":113,"slug":116,"view_count":36,"doi":117,"paper":118,"created_at":129},2940,"A Hybrid CNN–Transformer–LSTM Deep Learning Framework for Automated Cotton Disease Detection","https:\u002F\u002Fdoi.org\u002F10.53365\u002Fnrfhh.1816","Cotton production is frequently affected by leaf diseases that can reduce plant productivity, deteriorate crop quality, and cause considerable financial losses for farmers. Consequently, rapid and reliable disease identification is an important requirement for precision agriculture and effective crop protection. Conventional image-based approaches predominantly employ CNN architectures for visual classification; however, such methods may have limited capability in learning long-range spatial dependencies and modeling changes associated with disease development over time. To overcome these limitations, this research introduces an integrated hybrid deep learning framework that combines Convolutional Neural Networks (CNNs), Transformer-based self-attention, and Long Short-Term Memory (LSTM) networks for intelligent cotton leaf disease recognition. The proposed framework utilizes a pre-trained EfficientNet network to extract discriminative spatial characteristics from cotton leaf images. The extracted representations are subsequently processed through a multi-head self-attention Transformer module, which enables the network to identify relationships between distant and relevant regions of the leaf. An LSTM component is then incorporated to learn sequential dependencies and provide a foundation for analyzing disease evolution and progression. To improve model reliability and generalization, the network is trained using an appropriately organized cotton leaf image dataset together with image augmentation, transfer learning, and fine-tuning techniques. The experimental evaluation indicates that the proposed CNN–Transformer–LSTM architecture provides improved disease classification performance and more effective feature learning compared with conventional CNN-based models. Performance assessment using classification metrics, confusion matrices, and ROC curves demonstrates strong discrimination among the considered cotton disease categories. The combined learning of local visual characteristics, global contextual information, and sequential dependencies provides a comprehensive framework for automated cotton disease assessment. The proposed approach can serve as a scalable artificial intelligence solution for precision agriculture applications. Its architecture also provides opportunities for future integration with IoT-based crop monitoring systems, environmental data acquisition, and disease progression prediction, supporting early warning systems and intelligent crop health management in smart farming environments.","棉花生产常受叶片病害影响，这些病害会降低植株生产力、恶化作物品质，并给农民造成相当大的经济损失。因此，快速可靠的病害识别是精准农业和有效作物保护的重要需求。传统的基于图像的方法主要采用CNN架构进行视觉分类；然而，此类方法在学习长程空间依赖关系以及建模与病害随时间发展相关的变化方面能力有限。为克服这些局限，本研究提出了一种集成混合深度学习框架，将卷积神经网络（CNN）、基于Transformer的自注意力机制和长短期记忆（LSTM）网络相结合，用于智能棉花叶片病害识别。所提出的框架利用预训练的EfficientNet网络从棉花叶片图像中提取具有判别力的空间特征。提取到的表示随后通过多头自注意力Transformer模块进行处理，使网络能够识别叶片中相距较远且相关区域之间的关系。随后引入LSTM组件以学习序列依赖关系，并为分析病害演变和进展提供基础。为提高模型可靠性和泛化能力，网络使用组织良好的棉花叶片图像数据集进行训练，并结合图像增强、迁移学习和微调技术。实验评估表明，与传统的基于CNN的模型相比，所提出的CNN–Transformer–LSTM架构提供了更好的病害分类性能和更有效的特征学习。使用分类指标、混淆矩阵和ROC曲线进行的性能评估表明，该方法在所考虑的棉花病害类别之间具有较强的判别能力。局部视觉特征、全局上下文信息和序列依赖关系的联合学习为自动化棉花病害评估提供了一个全面的框架。所提出的方法可作为精准农业应用中可扩展的人工智能解决方案。其架构也为未来与基于物联网的作物监测系统、环境数据采集和病害进展预测的集成提供了机会，从而支持预警系统和智能","Natural Resources for Human Health","2026-09-16T00:00:00Z",69,{"impact":17,"substance":71,"depth":107,"authority":17,"freshness":21,"relevant":22,"comment":108},17,"提出CNN-Transformer-LSTM混合框架用于棉花叶病识别，方法有创新但属实验室验证阶段，产业影响有限。",[110],{"name":103,"url":100},[27,28,29,31,112],"棉花病害识别",[114,115],"棉花叶病 CNN Transformer LSTM","EfficientNet 棉花病害检测","棉花叶病CNNTransformerLSTM-2940","10.53365\u002Fnrfhh.1816",{"doi":117,"openalex_id":119,"authors":120,"venue":103,"cited_by_count":36,"oa_url":9,"card":123,"direction":128,"ingested_from":55},"W7213544712",[121],{"name":122,"orcid":9},"Prajakta Sunil Gupta",{"tldr":124,"method":125,"finding":126,"direction":53,"opportunity":127},"提出CNN-Transformer-LSTM混合框架，实现棉花叶片病害自动识别。","EfficientNet提取特征，Transformer自注意力与LSTM建模，","混合模型分类性能优于传统CNN，能同时学习局部特征、全局上下文和序列依赖。","可融合IoT环境数据与时间序列，开展病害进展预测和早期预警系统研究。","智慧农业 \u002F 农业物联网","2026-09-19T23:30:19.558449Z",{"id":131,"title":132,"url":133,"summary":134,"summary_zh":135,"content":9,"source_name":10,"source_url":133,"published_at":136,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":137,"score_detail":138,"sources":140,"tags":142,"search_phrases":144,"slug":146,"view_count":36,"doi":147,"paper":148,"created_at":163},2179,"Comparative evaluation of classical machine learning and deep learning models for early weed detection in precision agriculture","https:\u002F\u002Fdoi.org\u002F10.1007\u002Fs44163-026-02195-y","Unless treated and controlled early, weeds considerably impede the growth of crops as they compete over vital factors (resources) like nutrients, water, and light. To overcome this problem, an automated weed species early detection and classification system using machine learning-based image analysis is suggested. The framework integrates classical machine learning algorithms Support Vector Machines (SVM), Random Forests and k-Nearest Neighbors (k-NN), using handcrafted features like texture, shape, and color with deep learning models, Convolutional Neural Networks (CNNs) which automatically learn discriminative features in the data. The study comparatively evaluates classical ML and deep learning models. In order to test the experiments, a publicly available Sugar Beet dataset was used, as well as a custom maize seedling dataset. To enhance generalization and robustness, some preprocessing steps were performed, including normalization, background removal, and augmentation. Common metrics used to assess the performance of the models are F1-score and Intersection over Union (IoU). The experimental results show deep learning models outperforming the traditional machine learning methods, especially CNNs The CNN model also exhibited a classification accuracy of 98.7%. These results demonstrate the promise of deep learning to quickly, reliably, and in large scale detect weeds in the early stages of precision agriculture. This study highlights the feasibility of machine learning systems in proactive management of weed as well as in supporting healthy crop growth at the early stages of development.","除非在早期进行处理和控制，否则杂草会争夺养分、水分和光照等关键因素（资源），从而严重阻碍作物生长。为解决这一问题，提出了一种基于机器学习的图像分析自动化杂草物种早期检测与分类系统。该框架整合了经典机器学习算法——支持向量机（SVM）、随机森林和k近邻（k-NN），利用纹理、形状和颜色等手工特征，并结合深度学习模型——卷积神经网络（CNN），后者可自动学习数据中的判别性特征。本研究对经典机器学习和深度学习模型进行了对比评估。为验证实验，使用了公开的甜菜数据集以及自建的玉米幼苗数据集。为增强泛化性和鲁棒性，执行了一些预处理步骤，包括归一化、背景去除和数据增强。用于评估模型性能的常用指标为F1分数和交并比（IoU）。实验结果表明，深度学习模型优于传统机器学习方法，尤其是CNN。CNN模型的分类准确率达到了98.7%。这些结果证明了深度学习在精准农业中快速、可靠且大规模地早期检测杂草的潜力。本研究凸显了机器学习系统在杂草主动管理以及支持作物早期健康生长方面的可行性。","2026-09-10T00:00:00Z",72,{"impact":19,"substance":71,"depth":19,"authority":17,"freshness":21,"relevant":22,"comment":139},"对比经典机器学习与深度学习在作物早期杂草检测中的表现，CNN 分类准确率达 98.7%，方法扎实、结论明确，对精准农业智能除草有参考价值。",[141],{"name":10,"url":133},[27,28,143,30,31],"机器学习",[145,79],"农业人工智能 智慧农业 机器学习 杂草识别","农业人工智能智慧农业机器学习杂草识别-2179","10.1007\u002Fs44163-026-02195-y",{"doi":147,"openalex_id":149,"authors":150,"venue":10,"cited_by_count":36,"oa_url":133,"card":158,"direction":53,"ingested_from":55},"W7212111551",[151,154,156],{"name":152,"orcid":153},"Rajeev Kumar","https:\u002F\u002Forcid.org\u002F0000-0001-8414-3778",{"name":155,"orcid":9},"P. K. Singh",{"name":157,"orcid":9},"Rohit Kumar Tiwari",{"tldr":159,"method":160,"finding":161,"direction":53,"opportunity":162},"对比经典机器学习与深度学习模型在精准农业早期杂草检测中的性能。","用SVM、随机森林、k-NN及CNN，基于甜菜和玉米幼苗图像数据集。","CNN分类准确率达98.7%，显著优于传统机器学习方法。","可探索轻量化模型在田间边缘设备实时检测杂草的部署与跨物种泛化能力。","2026-09-11T23:30:52.642134Z",{"id":165,"title":166,"url":167,"summary":168,"summary_zh":169,"content":9,"source_name":170,"source_url":167,"published_at":171,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":172,"score_detail":173,"sources":176,"tags":178,"search_phrases":180,"slug":183,"view_count":36,"doi":184,"paper":185,"created_at":203},1627,"Autonomous Multi-Crop Weeding and Nutrient Management","https:\u002F\u002Fdoi.org\u002F10.55041\u002Fijcope.v2i9.016","Agriculture faces major challenges such as weed growth, labor shortages, excessive fertilizer usage, and lack of real-time monitoring. This paper proposes an Autonomous Multi-Crop Weeding and Nutrient Management Machine using Artificial Intelligence (AI), Internet of Things (IoT), and embedded systems. The system uses AI-based image processing for weed detection and activates a mechanical cutter to remove weeds automatically. Soil pH and NPK sensors monitor nutrient levels and enable precision nutrient spraying only when required. An ESP32 microcontroller controls navigation, sensor interfacing, motor operation, and IoT communication. GPS, ultrasonic, and IMU sensors enable autonomous navigation and obstacle detection. Real-time data is transmitted to farmers through Wi-Fi or Bluetooth. The proposed system reduces labor dependency, minimizes chemical usage, improves crop productivity, and supports sustainable precision agriculture. The proposed machine is designed to provide an integrated approach to precision agriculture by combining intelligent weed management, soil monitoring, nutrient management, and autonomous field operation in a single system. The camera-based detection mechanism continuously observes the crop area and identifies weeds, after which the mechanical weeding unit is activated for selective removal. Simultaneously, soil pH and NPK sensors provide continuous information about soil conditions, allowing the system to determine nutrient requirements and operate the spraying mechanism accordingly. The integration of GPS, ultrasonic, and IMU sensors supports autonomous movement, obstacle detection, and directional stability during field operations. The ESP32 coordinates the different subsystems and enables communication of important field and machine parameters through Wi-Fi or Bluetooth. This integrated operation reduces unnecessary human intervention and promotes efficient utilization of agricultural resources. By combining AI-based decision-making with embedded control, sensing, robotics, and IoT connectivity, the system provides a practical approach for reducing labor requirements, minimizing input wastage, improving crop management, and supporting sustainable and data-driven agricultural practices. Keywords— Autonomous agriculture, ESP32, AI in farming, IoT, weed detection, precision farming, nutrient monitoring.","农业面临着杂草生长、劳动力短缺、化肥过量使用以及缺乏实时监测等重大挑战。本文提出了一种基于人工智能（AI）、物联网（IoT）和嵌入式系统的自主多作物除草与养分管理机器。该系统利用基于AI的图像处理进行杂草检测，并自动激活机械切割器以清除杂草。土壤pH值和氮磷钾（NPK）传感器监测养分水平，并仅在需要时实现精准养分喷洒。ESP32微控制器控制导航、传感器接口、电机运行和物联网通信。GPS、超声波和惯性测量单元（IMU）传感器实现自主导航和障碍物检测。实时数据通过Wi-Fi或蓝牙传输给农民。该系统减少了劳动力依赖，最小化化学品使用，提高作物生产力，并支持可持续的精准农业。所提出的机器旨在通过将智能杂草管理、土壤监测、养分管理和自主田间作业集成于单一系统中，提供精准农业的综合方法。基于摄像头的检测机制持续观察作物区域并识别杂草，随后激活机械除草单元进行选择性清除。同时，土壤pH值和NPK传感器提供关于土壤状况的连续信息，使系统能够确定养分需求并相应操作喷洒机制。GPS、超声波和IMU传感器的集成支持田间作业中的自主移动、障碍物检测和方向稳定性。ESP32协调各子系统，并通过Wi-Fi或蓝牙实现重要田间和机器参数的通信。这种集成操作减少了不必要的人为干预，促进了农业资源的高效利用。通过将基于AI的决策与嵌入式控制、传感、机器人技术和物联网连接相结合，该系统为减少劳动力需求、最小化投入浪费、改善作物管理以及支持可持续和数据驱动的农业实践提供了一种实用方法。\n\n关键词——自主农业，ESP32，农业中的AI，物联网，杂草检测，精准农业，养分监测。","International Journal of Creative and Open Research in Engineering and Management","2026-09-03T00:00:00Z",56,{"impact":17,"substance":70,"depth":72,"authority":21,"freshness":174,"relevant":22,"comment":175},7,"提出集成AI与IoT的自主除草与养分管理机器，系统设计较完整，但缺乏实验数据验证，影响有限。",[177],{"name":170,"url":167},[27,28,30,31,179],"养分管理",[181,182],"农业人工智能 养分管理 智慧农业 杂草识别","农业人工智能 养分管理","农业人工智能养分管理智慧农业杂草识别-1627","10.55041\u002Fijcope.v2i9.016",{"doi":184,"openalex_id":186,"authors":187,"venue":170,"cited_by_count":36,"oa_url":9,"card":198,"direction":128,"ingested_from":55},"W7207814982",[188,190,192,194,196],{"name":189,"orcid":9},"D.C Likitha",{"name":191,"orcid":9},"Ganavi N",{"name":193,"orcid":9},"Keerthana C",{"name":195,"orcid":9},"Manushree V",{"name":197,"orcid":9},"Yeshwini Yeshwini",{"tldr":199,"method":200,"finding":201,"direction":128,"opportunity":202},"提出一种集成AI、IoT和嵌入式系统的自主多作物除草与养分管理机器，实现精准农业。","AI图像处理识别杂草，机械切割；土壤pH和NPK传感器监测养分，精准喷洒；ESP","系统减少劳动力依赖、化学品使用，提高作物生产力，支持可持续精准农业。","可延伸研究多作物场景下杂草识别模型的泛化能力，以及基于边缘计算的实时决策优化。","2026-09-04T23:30:14.890290Z",{"id":205,"title":206,"url":207,"summary":208,"summary_zh":209,"content":9,"source_name":210,"source_url":207,"published_at":11,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":211,"score_detail":212,"sources":214,"tags":216,"search_phrases":219,"slug":222,"view_count":36,"doi":223,"paper":224,"created_at":254},2961,"Advances in Bioacoustics Sensing and Signal Processing Technologies","https:\u002F\u002Fdoi.org\u002F10.1088\u002F2631-7990\u002Faea9da","Abstract Driven by advances in flexible electronics, microfabrication, and artificial intelligence, bioacoustics is revolutionizing sensing and signal processing across health, ecology, and intelligent systems. This review systematically examines key progress in high-performance acoustic sensors (e.g., piezoelectric, triboelectric, MEMS) and acquisition schemes for multi-scale biological sounds, ranging from heart tones to plant stress emissions. Furthermore, we delve into advanced methodologies for acoustic signal preprocessing, feature extraction, and classification, with a particular emphasis on the powerful analytical capabilities of multimodal data fusion and deep learning algorithms in complex real-world scenarios. Crucially, although the sensing requirements and biological targets vary drastically across medical, ecological, and agricultural domains, this review establishes a unifying framework centered on the shared physical and algorithmic challenges of bioacoustic information flow. By juxtaposing these diverse fields, the potential strategies for the interdisciplinary integration of sensing methodologies are highlighted. We also critically assess the essential roles of acoustic physical modeling, standardized testing frameworks, and gold-standard databases in evaluating system performance. Finally, the review highlights cutting-edge applications of bioacoustics in human health monitoring, medical diagnostics, human-computer interaction, and precision agriculture. By synthesizing current technological convergences and outlining future trajectories, we provide a comprehensive perspective on the promising directions and pivotal challenges facing bioacoustics research.","摘要 在柔性电子、微加工和人工智能进步的推动下，生物声学正在革新健康、生态和智能系统中的传感与信号处理。本文系统梳理了高性能声学传感器（如压电、摩擦电、MEMS）以及从心音到植物胁迫发射等多尺度生物声音采集方案的关键进展。此外，我们深入探讨了声学信号预处理、特征提取和分类的先进方法，特别强调了多模态数据融合和深度学习算法在复杂现实场景中的强大分析能力。至关重要的是，尽管医学、生态和农业领域在传感需求和生物目标上差异巨大，本文建立了一个以生物声学信息流中共同的物理和算法挑战为中心的统一框架。通过将这些不同领域并置比较，凸显了传感方法学跨学科整合的潜在策略。我们还批判性地评估了声学物理建模、标准化测试框架和金标准数据库在评估系统性能中的重要作用。最后，本文重点介绍了生物声学在人体健康监测、医学诊断、人机交互和精准农业中的前沿应用。通过综合当前技术汇聚趋势并勾勒未来轨迹，我们为生物声学研究面临的有前景方向和关键挑战提供了全面视角。","International Journal of Extreme Manufacturing",78,{"impact":18,"substance":71,"depth":18,"authority":72,"freshness":21,"relevant":22,"comment":213},"该综述系统梳理生物声学传感与信号处理技术，并明确指向精准农业与植物胁迫声发射监测，对农业信息化具有跨领域参考价值，但属综述类论文，非产业级突破。",[215],{"name":210,"url":207},[27,28,31,217,218],"多模态融合","生物声学传感",[220,221],"生物声学 传感器 信号处理","植物胁迫 声发射 监测","生物声学传感器信号处理-2961","10.1088\u002F2631-7990\u002Faea9da",{"doi":223,"openalex_id":225,"authors":226,"venue":210,"cited_by_count":36,"oa_url":207,"card":249,"direction":53,"ingested_from":55},"W7213590695",[227,230,233,235,238,241,243,246],{"name":228,"orcid":229},"Chengyu Li","https:\u002F\u002Forcid.org\u002F0000-0002-2128-3420",{"name":231,"orcid":232},"Wenbo Li","https:\u002F\u002Forcid.org\u002F0000-0003-3599-3324",{"name":234,"orcid":9},"Jingyang Wu",{"name":236,"orcid":237},"Shuo Wang","https:\u002F\u002Forcid.org\u002F0000-0002-5411-7269",{"name":239,"orcid":240},"Han Liao","https:\u002F\u002Forcid.org\u002F0009-0001-6256-7438",{"name":242,"orcid":9},"xiang Yu",{"name":244,"orcid":245},"Cheng Li","https:\u002F\u002Forcid.org\u002F0000-0003-3424-2414",{"name":247,"orcid":248},"Xiaoming Tao","https:\u002F\u002Forcid.org\u002F0000-0002-2406-0695",{"tldr":250,"method":251,"finding":252,"direction":128,"opportunity":253},"综述生物声学传感与信号处理进展，涵盖医疗、生态与农业应用。","综述压电\u002F摩擦电\u002FMEMS声传感器、深度学习与多模态融合方法。","建立跨领域统一框架，强调物理建模、标准测试与数据库的关键作用。","植物胁迫声发射的标准化采集与深度学习分类，可填补农业声学监测空白。","2026-09-19T23:30:51.998646Z",{"id":256,"title":257,"url":258,"summary":259,"summary_zh":260,"content":9,"source_name":261,"source_url":258,"published_at":11,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":15,"score_detail":262,"sources":264,"tags":266,"search_phrases":269,"slug":272,"view_count":36,"doi":273,"paper":274,"created_at":306},2947,"AI-enabled UAV-based Soil Organic Carbon Mapping in Arid Environments: A Pilot Study Protocol","https:\u002F\u002Fdoi.org\u002F10.2174\u002F0118743315495282260915110324","Introduction Soil organic carbon (SOC) is an important indicator of soil health, agricultural productivity, and carbon sequestration potential. However, accurate and scalable SOC mapping in arid environments is constrained by high spatial heterogeneity and the limitations of conventional soil sampling. This study aims to develop a standardized UAV-enabled framework for high-resolution SOC mapping in arid agricultural environments. Methods A pilot-study protocol integrating UAV-based hyperspectral remote sensing with artificial intelligence and machine learning was developed. The workflow encompasses study-site selection, ground-reference sampling, UAV hyperspectral data acquisition, radiometric and geometric preprocessing, spectral feature extraction and selection, machine-learning model development, validation, uncertainty assessment, and performance evaluation using R 2 , RMSE, and MAE. The protocol also incorporates assessment of environmental confounders, including soil moisture, surface roughness, and crop residues. Results The resulting framework provides a systematic and reproducible workflow for UAV-based SOC estimation, integrating field observations, hyperspectral features, predictive modelling, and uncertainty assessment. It establishes defined procedures for evaluating model robustness and transferability across varying field conditions. Discussion The framework addresses an important methodological gap in UAV-enabled SOC mapping by integrating remote sensing and AI within a standardized pilot-study design. Its emphasis on environmental confounders and uncertainty assessment can improve the reliability and comparability of SOC mapping studies. However, field validation across diverse arid environments remains necessary. Conclusion The proposed protocol provides a practical foundation for reproducible SOC mapping and subsequent field validation, supporting precision agriculture, sustainable soil management, and carbon monitoring, reporting, and verification (MRV) in arid regions.","引言 土壤有机碳（SOC）是衡量土壤健康、农业生产力及碳固存潜力的重要指标。然而，干旱环境中高空间异质性和传统土壤采样的局限性制约了准确且可扩展的SOC制图。本研究旨在开发一个标准化的无人机（UAV）框架，用于干旱农业环境中的高分辨率SOC制图。方法 开发了一套整合无人机高光谱遥感与人工智能及机器学习的试点研究方案。该工作流程涵盖研究地点选择、地面参考采样、无人机高光谱数据采集、辐射与几何预处理、光谱特征提取与选择、机器学习模型开发、验证、不确定性评估，以及使用R²、RMSE和MAE进行的性能评价。该方案还包括对环境混杂因素的评估，包括土壤水分、地表粗糙度和作物残茬。结果 所构建的框架为基于无人机的SOC估算提供了系统且可重复的工作流程，整合了野外观测、高光谱特征、预测建模和不确定性评估。它建立了明确的程序，用于评估模型在不同田间条件下的稳健性和可迁移性。讨论 该框架通过将遥感与人工智能整合于标准化的试点研究设计中，填补了无人机SOC制图领域的重要方法学空白。其对环境混杂因素和不确定性评估的重视，可提高SOC制图研究的可靠性和可比性。然而，仍需在不同干旱环境中进行田间验证。结论 所提出的方案为可重复的SOC制图及后续田间验证提供了实用基础，支持干旱地区的精准农业、可持续土壤管理以及碳监测、报告与核查（MRV）。","The Open Agriculture Journal",{"impact":17,"substance":18,"depth":19,"authority":20,"freshness":21,"relevant":22,"comment":263},"提出无人机高光谱结合AI的干旱区土壤有机碳制图标准化方案，方法框架清晰但尚属试点协议、缺乏实地验证，具备一定参考价值。",[265],{"name":261,"url":258},[27,28,31,267,268],"遥感","土壤碳汇",[270,271],"无人机 土壤有机碳 制图","AI 高光谱 干旱农业","无人机土壤有机碳制图-2947","10.2174\u002F0118743315495282260915110324",{"doi":273,"openalex_id":275,"authors":276,"venue":261,"cited_by_count":36,"oa_url":258,"card":300,"direction":304,"ingested_from":55},"W7213561504",[277,280,283,286,289,292,294,296,298],{"name":278,"orcid":279},"Moath Awawdeh","https:\u002F\u002Forcid.org\u002F0000-0003-1404-6782",{"name":281,"orcid":282},"Irfan Ahmed","https:\u002F\u002Forcid.org\u002F0000-0002-2172-4177",{"name":284,"orcid":285},"Anees Bashir","https:\u002F\u002Forcid.org\u002F0000-0002-4668-6592",{"name":287,"orcid":288},"Tarig Faisal","https:\u002F\u002Forcid.org\u002F0000-0001-6451-7576",{"name":290,"orcid":291},"Nicky Rahmana Putra","https:\u002F\u002Forcid.org\u002F0000-0003-4886-496X",{"name":293,"orcid":9},"Almaha Jamal",{"name":295,"orcid":9},"Afra Rashed",{"name":297,"orcid":9},"Hamda Yousif",{"name":299,"orcid":9},"Sarah Sadeq",{"tldr":301,"method":302,"finding":303,"direction":304,"opportunity":305},"提出一套无人机高光谱结合AI的干旱区土壤有机碳制图标准化试点方案。","无人机高光谱遥感、地面采样、光谱特征选择与机器学习建模，用R²、RMSE、MAE","构建了可复现的SOC估算流程，并纳入环境混杂因素与不确定性评估。","农业遥感与作物表型","可在多干旱区开展跨区域验证，探索模型迁移性与不确定性量化方法。","2026-09-19T23:30:33.273156Z"]