[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-2046":3},{"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,"view_count":32,"doi":33,"paper":34,"created_at":49},2046,"AI-Powered Crop Protection: Transforming Pest Surveillance and Decision-Making Through Digital Agriculture","https:\u002F\u002Fdoi.org\u002F10.9734\u002Fjsrr\u002F2026\u002Fv32i94503","Crop protection is increasingly challenged by changing pest population dynamics, pesticide resistance and the need for more sustainable agricultural production. Artificial intelligence (AI) and digital agriculture offer complementary tools for improving pest surveillance, forecasting and decision-making through automated detection, continuous monitoring and more precise interventions. This review synthesises the applications of machine learning, deep learning, computer vision, Internet of Things-enabled sensing, smart traps, remote sensing, unmanned aerial vehicles, robotics, predictive analytics and intelligent decision support systems in pest management. These approaches support pest identification, population monitoring, outbreak prediction, risk assessment and site-specific management, thereby strengthening the information base required for integrated pest management. The review also examines emerging technologies, including generative AI, foundation models, digital twins, explainable AI, edge intelligence and autonomous agricultural platforms, in relation to future crop protection systems. Despite rapid technological progress, practical deployment remains constrained by limited high-quality datasets, variable field conditions, model generalisation, interoperability, digital infrastructure, cost and farmer adoption. Effective implementation therefore requires transparent, robust and scalable systems that are validated under diverse agricultural conditions and aligned with ecological pest management principles. Overall, integrating AI-enabled surveillance and decision support with integrated pest management can support more timely, adaptive and resource-efficient crop protection while reducing unnecessary interventions.","作物保护正日益受到害虫种群动态变化、农药抗性以及更可持续农业生产需求的挑战。人工智能（AI）与数字农业通过自动检测、持续监测和更精准的干预措施，为改善害虫监测、预测和决策提供了互补性工具。本文综述了机器学习、深度学习、计算机视觉、物联网传感、智能诱捕器、遥感、无人机、机器人技术、预测分析和智能决策支持系统在害虫管理中的应用。这些方法支持害虫识别、种群监测、暴发预测、风险评估和位点特异性管理，从而强化了有害生物综合治理所需的信息基础。本文还探讨了新兴技术，包括生成式人工智能、基础模型、数字孪生、可解释人工智能、边缘智能和自主农业平台，及其在未来作物保护系统中的前景。尽管技术进展迅速，实际部署仍受限于高质量数据集不足、田间条件多变、模型泛化能力、互操作性、数字基础设施、成本以及农民采纳程度等因素。因此，有效实施需要透明、稳健且可扩展的系统，这些系统应在多样化农业条件下得到验证，并与生态害虫管理原则相一致。总体而言，将人工智能驱动的监测与决策支持同有害生物综合治理相结合，可支持更及时、更具适应性和资源效率更高的作物保护，同时减少不必要的干预。",null,"Journal of Scientific Research and Reports","2026-09-09T00:00:00Z","论文",10,false,76,{"impact":17,"substance":18,"depth":19,"authority":20,"freshness":21,"relevant":22,"comment":23},18,20,17,13,8,1,"系统综述AI与数字农业在病虫害监测预警与决策支持中的应用与瓶颈，信息密度高、结论可靠，对智慧植保方向有参考价值，但属综述类论文而非突破性成果，适合进入精选。",[25],{"name":10,"url":6},[27,28,29,30,31],"数字农业","智慧农业","农业人工智能","病虫害监测","精准植保",0,"10.9734\u002Fjsrr\u002F2026\u002Fv32i94503",{"doi":33,"openalex_id":35,"authors":36,"venue":10,"cited_by_count":32,"oa_url":6,"card":41,"direction":47,"ingested_from":48},"W7212081296",[37,39],{"name":38,"orcid":9},"R. Saritha",{"name":40,"orcid":9},"M. Swathi",{"tldr":42,"method":43,"finding":44,"direction":45,"opportunity":46},"综述AI与数字农业在害虫监测、预测及决策支持中的应用与挑战。","综述机器学习、深度学习、计算机视觉、物联网、遥感、无人机与决策支持系统。","AI可提升害虫识别、暴发预测和精准管理，但受数据、泛化、成本与采纳制约。","农业人工智能与决策模型","可探索生成式AI、数字孪生与边缘智能在田间害虫管理中的可解释、可扩展落地验证。","智慧农业 \u002F 农业物联网","openalex","2026-09-10T23:30:09.692422Z"]