[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-912":3,"related-912":68},{"id":4,"title":5,"url":6,"summary":7,"summary_zh":8,"content":9,"source_name":10,"source_url":8,"published_at":8,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":14,"score_detail":15,"sources":22,"tags":24,"primary_topic":29,"secondary_topics":35,"classification":36,"search_phrases":62,"slug":65,"view_count":19,"doi":66,"paper":8,"created_at":67},912,"量子机器学习与经典方法在作物\u002F杂草检测中的比较","https:\u002F\u002Fbeta.iopscience.iop.org\u002Farticle\u002F10.1088\u002F2631-8695\u002Fae98fa","比较CNN（经典基线）、量子支持向量分类器与变分量子分类器（VQC）在航拍田间作物-杂草区分任务中的表现。CNN测试峰值准确率约94%，QML为85%-89%；CNN推理速度约10ms\u002F图像，量子模型为数百毫秒；QML模型可训练参数仅数十到上百个，远低于CNN的百万级。结论：经典深度学习仍是当前最可靠方案，QML随硬件\u002F算法进步有望加速追赶。",null,"![Image 1: Revisit consent button](https:\u002F\u002Fcdn-cookieyes.com\u002Fassets\u002Fimages\u002Frevisit.svg)\n\nWe value your privacy\n\nWe and our 3 partners use cookies and other tracking technologies to improve your experience on our website. We may store and\u002For access information on a device and process personal data, such as your IP address and browsing data, for personalised advertising and content, advertising and content measurement, audience research and services development. Additionally, we may utilize precise geolocation data and identification through device scanning.\n\nPlease note that your choices apply across all our subdomains. Once you give consent, a floating button will appear at the bottom of your screen, allowing you to change or withdraw your consent at any time. We respect your choices and are committed to providing you with a transparent and secure browsing experience.[Privacy and Cookies policy](https:\u002F\u002Fioppublishing.org\u002Flegal\u002Fprivacy-cookies-policy\u002F)\n\nCustomize Accept All\n\nCustomize Consent Preferences![Image 2](https:\u002F\u002Fcdn-cookieyes.com\u002Fassets\u002Fimages\u002Fclose.svg)\n\nCustomise your consent preferences for Cookie Categories and advertising tracking preferences for Purposes & Features and Vendors below. You can give granular consent for each Third Party Vendor. Most vendors require explicit consent for personal data processing, while some rely on legitimate interest. However, you have the right to object to their use of legitimate interest. Additionally, please note that your preferences regarding purposes and vendors are saved in a cookie named 'euconsent' on your device and may be retained for up to 730 days to remember your choices.\n\n*   Cookie Categories\n*   Purposes & Features\n*   Vendors\n\nCookie Categories\n\nWe use cookies to help you navigate efficiently and perform certain functions. You will find detailed information about all cookies under each consent category below.\n\nThe cookies that are categorized as \"Necessary\" are stored on your browser as they are essential for enabling the basic functionalities of the site. ...Show more\n\nNecessary Always Active\n\nNecessary cookies are required to enable the basic features of this site, such as providing secure log-in or adjusting your consent preferences. These cookies do not store any personally identifiable data.\n\n*   Cookie __uzma \n*   Duration 6 months \n*   Description No description available. \n\n*   Cookie __uzmb \n*   Duration 6 months \n*   Description No description available. \n\n*   Cookie __uzme \n*   Duration 6 months \n*   Description No description available. \n\n*   Cookie IOP_session_live \n*   Duration session \n*   Description No description available. \n\n*   Cookie __ssds \n*   Duration 6 months \n*   Description No description available. \n\n*   Cookie __uzmd \n*   Duration 6 months \n*   Description This cookie is set by the provider ShieldSquare. This is a performance and monitoring cookie used for distinguishing bot and scraper traffic. \n\n*   Cookie AWSALBCORS \n*   Duration 7 days \n*   Description Amazon Web Services set this cookie for load balancing. \n\n*   Cookie JSESSIONID \n*   Duration session \n*   Description New Relic uses this cookie to store a session identifier so that New Relic can monitor session counts for an application. \n\n*   Cookie __uzmc \n*   Duration 6 months \n*   Description This cookie is set by the provider ShieldSquare. This is a performance and monitoring cookie used for distinguishing bot and scraper traffic. \n\n*   Cookie AWSALB \n*   Duration 7 days \n*   Description AWSALB is an application load balancer cookie set by Amazon Web Services to map the session to the target. \n\n*   Cookie __cf_bm \n*   Duration 1 hour \n*   Description This cookie, set by Cloudflare, is used to support Cloudflare Bot Management.  \n\n*   Cookie PHPSESSID \n*   Duration session \n*   Description This cookie is native to PHP applications. The cookie stores and identifies a user's unique session ID to manage user sessions on the website. The cookie is a session cookie and will be deleted when all the browser windows are closed. \n\n*   Cookie __uzmf \n*   Duration 6 months \n*   Description Description is currently not available. \n\n*   Cookie uzmx \n*   Duration 6 months \n*   Description Description is currently not available. \n\n*   Cookie TiPMix \n*   Duration 1 hour \n*   Description The TiPMix cookie is set by Azure to determine which web server the users must be directed to. \n\n*   Cookie x-ms-routing-name \n*   Duration 1 hour \n*   Description Azure sets this cookie for routing production traffic by specifying the production slot. \n\n*   Cookie euconsent \n*   Duration 1 year \n*   Description CookieYes sets this cookie to store data when IAB TCF is enabled. \n\n*   Cookie rc::h \n*   Duration Never Expires \n*   Description This cookie is set by the Google recaptcha service to identify bots to protect the website against malicious spam attacks. \n\n*   Cookie rc::e \n*   Duration session \n*   Description This cookie is set by the Google recaptcha service to identify bots to protect the website against malicious spam attacks. \n\n*   Cookie uzmxj \n*   Duration 6 months \n*   Description Description is currently not available. \n\n*   Cookie __ssuzjsr0 \n*   Duration 6 months \n*   Description Description is currently not available. \n\n*   Cookie __uzmaj0 \n*   Duration 6 months \n*   Description Description is currently not available. \n\n*   Cookie __uzmbj0 \n*   Duration 6 months \n*   Description Description is currently not available. \n\n*   Cookie __uzmcj0 \n*   Duration 6 months \n*   Description Description is currently not available. \n\n*   Cookie __uzmdj0 \n*   Duration 6 months \n*   Description Description is currently not available. \n\n*   Cookie __uzmlj0 \n*   Duration 6 months \n*   Description Description is currently not available. \n\n*   Cookie __uzmfj0 \n*   Duration 6 months \n*   Description Description is currently not available. \n\n*   Cookie cookieyes-* \n*   Duration 1 year \n*   Description CookieYes sets this cookie for consent solution management. \n\n*   Cookie landing_page \n*   Duration session \n*   Description The _landing_page cookie tracks the first page a user visits on a website, helping to analyze user behavior and optimize the site's performance. \n\nFunctional\n\n- [x] \n\nFunctional cookies help perform certain functionalities like sharing the content of the website on social media platforms, collecting feedback, and other third-party features.\n\n*   Cookie issuem_lp \n*   Duration 1 month \n*   Description No description available. \n\n*   Cookie ytidb::LAST_RESULT_ENTRY_KEY \n*   Duration Never Expires \n*   Description The cookie ytidb::LAST_RESULT_ENTRY_KEY is used by YouTube to store the last search result entry that was clicked by the user. This information is used to improve the user experience by providing more relevant search results in the future. \n\n*   Cookie __Secure-YEC \n*   Duration past \n*   Description Description is currently not available. \n\n*   Cookie __Secure-YNID \n*   Duration 6 months \n*   Description Google cookie used to protect user security and prevent fraud, especially during the login process. \n\nAnalytics\n\n- [x] \n\nAnalytical cookies are used to understand how visitors interact with the website. These cookies help provide information on metrics such as the number of visitors, bounce rate, traffic source, etc.\n\n*   Cookie _ga_* \n*   Duration 1 year 1 month 4 days \n*   Description Google Analytics sets this cookie to store and count page views. \n\n*   Cookie _ga \n*   Duration 1 year 1 month 4 days \n*   Description Google Analytics sets this cookie to calculate visitor, session and campaign data and track site usage for the site's analytics report. The cookie stores information anonymously and assigns a randomly generated number to recognise unique visitors. \n\n*   Cookie _hjSessionUser_* \n*   Duration 1 year \n*   Description Hotjar sets this cookie to ensure data from subsequent visits to the same site is attributed to the same user ID, which persists in the Hotjar User ID, which is unique to that site. \n\n*   Cookie _hjSession_* \n*   Duration 1 hour \n*   Description Hotjar sets this cookie to ensure data from subsequent visits to the same site is attributed to the same user ID, which persists in the Hotjar User ID, which is unique to that site. \n\n*   Cookie pardot \n*   Duration past \n*   Description The pardot cookie is set while the visitor is logged in as a Pardot user. The cookie indicates an active session and is not used for tracking. \n\n*   Cookie _hjTLDTest \n*   Duration session \n*   Description To determine the most generic cookie path that has to be used instead of the page hostname, Hotjar sets the _hjTLDTest cookie to store different URL substring alternatives until it fails. \n\n*   Cookie vuid \n*   Duration 1 year 1 month 4 days \n*   Description Vimeo installs this cookie to collect tracking information by setting a unique ID to embed videos on the website.  \n\n*   Cookie SM \n*   Duration session \n*   Description Microsoft Clarity cookie set this cookie for synchronizing the MUID across Microsoft domains. \n\n*   Cookie MR \n*   Duration 7 days \n*   Description This cookie, set by Bing, is used to collect user information for analytics purposes. \n\n*   Cookie _clck \n*   Duration 1 year \n*   Description Microsoft Clarity sets this cookie to retain the browser's Clarity User ID and settings exclusive to that website. This guarantees that actions taken during subsequent visits to the same website will be linked to the same user ID. \n\n*   Cookie _clsk \n*   Duration 1 day \n*   Description Microsoft Clarity sets this cookie to store and consolidate a user's pageviews into a single session recording. \n\nPerformance\n\nPerformance cookies are used to understand and analyze the key performance indexes of the website which helps in delivering a better user experience for the visitors.\n\nNo cookies to display.\n\nAdvertisement\n\n- [x] \n\nAdvertisement cookies are used to provide visitors with customized advertisements based on the pages you visited previously and to analyze the effectiveness of the ad campaigns.\n\n*   Cookie __eoi \n*   Duration 6 months \n*   Description Description is currently not available. \n\n*   Cookie test_cookie \n*   Duration 15 minutes \n*   Description doubleclick.net sets this cookie to determine if the user's browser supports cookies. \n\n*   Cookie IDE \n*   Duration 1 year 24 days \n*   Description Google DoubleClick IDE cookies store information about how the user uses the website to present them with relevant ads according to the user profile. \n\n*   Cookie __gpi \n*   Duration 1 year 24 days \n*   Description Google Ads Service uses this cookie to collect information about from multiple websites for retargeting ads. \n\n*   Cookie __gads \n*   Duration 1 year 24 days \n*   Description Google sets this cookie under the DoubleClick domain, tracks the number of times users see an advert, measures the campaign's success, and calculates its revenue. This cookie can only be read from the domain they are currently on and will not track any data while they are browsing other sites. \n\n*   Cookie YSC \n*   Duration session \n*   Description Youtube sets this cookie to track the views of embedded videos on Youtube pages. \n\n*   Cookie VISITOR_INFO1_LIVE \n*   Duration 6 months \n*   Description YouTube sets this cookie to measure bandwidth, determining whether the user gets the new or old player interface. \n\n*   Cookie VISITOR_PRIVACY_METADATA \n*   Duration 6 months \n*   Description YouTube sets this cookie to store the user's cookie consent state for the current domain.  \n\n*   Cookie MUID \n*   Duration 1 year 24 days \n*   Description Bing sets this cookie to recognise unique web browsers visiting Microsoft sites. This cookie is used for advertising, site analytics, and other operations. \n\n*   Cookie ANONCHK \n*   Duration 10 minutes \n*   Description The ANONCHK cookie, set by Bing, is used to store a user's session ID and verify ads' clicks on the Bing search engine. The cookie helps in reporting and personalization as well. \n\n*   Cookie SRM_B \n*   Duration 1 year 24 days \n*   Description Used by Microsoft Advertising as a unique ID for visitors. \n\n*   Cookie __Secure-ROLLOUT_TOKEN \n*   Duration 6 months \n*   Description Registers a unique ID to keep statistics of what videos from YouTube the user has seen. \n\n*   Cookie last_visit_bc \n*   Duration 1 year \n*   Description BlueConic last visit cookie \n\n*   Cookie BCTempID \n*   Duration 10 minutes \n*   Description Temporary BlueConic ID \n\n*   Cookie BCSessionID \n*   Duration 1 year 1 month 4 days \n*   Description Blueconic sets this cookie as a unique identifier for the BlueConic profile. \n\n*   Cookie BCSessionID \n*   Duration 1 year 1 month 4 days \n*   Description Blueconic sets this cookie as a unique identifier for the BlueConic profile. \n\n*   Cookie BCTempID \n*   Duration 10 minutes \n*   Description Temporary BlueConic ID \n\n*   Cookie last_visit_bc \n*   Duration 1 year \n*   Description BlueConic last visit cookie \n\n*   Cookie _gcl_au \n*   Duration 3 months \n*   Description Google Tag Manager sets this cookie to experiment advertisement efficiency of websites using their services. \n\nPurposes & Features\n\n Purposes (11) \n\n- [x] \n\nStore and\u002For access information on a device\n\nConsent\n\n- [x] \n\nCookies, device or similar online identifiers (e.g. login-based identifiers, randomly assigned identifiers, network based identifiers) together with other information (e.g. browser type and information, language, screen size, supported technologies etc.) can be stored or read on your device to recognise it each time it connects to an app or to a website, for one or several of the purposes presented here.\n\nIllustrations\n\n*   Most purposes explained in this notice rely on the storage or accessing of information from your device when you use an app or visit a website. For example, a vendor or publisher might need to store a cookie on your device during your first visit on a website, to be able to recognise your device during your next visits (by accessing this cookie each time).\n\nNumber of Vendors seeking consent: 3\n\nUse limited data to select advertising\n\nLegitimate Interest\n\n- [x] \n\nConsent\n\n- [x] \n\nAdvertising presented to you on this service can be based on limited data, such as the website or app you are using, your non-precise location, your device type or which content you are (or have been) interacting with (for example, to limit the number of times an ad is presented to you).\n\nIllustrations\n\n*   A car manufacturer wants to promote its electric vehicles to environmentally conscious users living in the city after office hours. The advertising is presented on a page with related content (such as an article on climate change actions) after 6:30 p.m. to users whose non-precise location suggests that they are in an urban zone.\n*   A large producer of watercolour paints wants to carry out an online advertising campaign for its latest watercolour range, diversifying its audience to reach as many amateur and professional artists as possible and avoiding showing the ad next to mismatched content (for instance, articles about how to paint your house). The number of times that the ad has been presented to you is detected and limited, to avoid presenting it too often.\n\nNumber of Vendors seeking consent or relying on legitimate interest: 3\n\nCreate profiles for personalised advertising\n\nConsent\n\n- [x] \n\nInformation about your activity on this service (such as forms you submit, content you look at) can be stored and combined with other information about you (for example, information from your previous activity on this service and other websites or apps) or similar users. This is then used to build or improve a profile about you (that might include possible interests and personal aspects). Your profile can be used (also later) to present advertising that appears more relevant based on your possible interests by this and other entities.\n\nIllustrations\n\n*   If you read several articles about the best bike accessories to buy, this information could be used to create a profile about your interest in bike accessories. Such a profile may be used or improved later on, on the same or a different website or app to present you with advertising for a particular bike accessory brand. If you also look at a configurator for a vehicle on a luxury car manufacturer website, this information could be combined with your interest in bikes to refine your profile and make an assumption that you are interested in luxury cycling gear.\n*   An apparel company wishes to promote its new line of high-end baby clothes. It gets in touch with an agency that has a network of clients with high income customers (such as high-end supermarkets) and asks the agency to create profiles of young parents or couples who can be assumed to be wealthy and to have a new child, so that these can later be used to present advertising within partner apps based on those profiles.\n\nNumber of Vendors seeking consent: 3\n\nUse profiles to select personalised advertising\n\nConsent\n\n- [x] \n\nAdvertising presented to you on this service can be based on your advertising profiles, which can reflect your activity on this service or other websites or apps (like the forms you submit, content you look at), possible interests and personal aspects.\n\nIllustrations\n\n*   An online retailer wants to advertise a limited sale on running shoes. It wants to target advertising to users who previously looked at running shoes on its mobile app. Tracking technologies might be used to recognise that you have previously used the mobile app to consult running shoes, in order to present you with the corresponding advertisement on the app.\n*   A profile created for personalised advertising in relation to a person having searched for bike accessories on a website can be used to present the relevant advertisement for bike accessories on a mobile app of another organisation.\n\nNumber of Vendors seeking consent: 3\n\nCreate profiles to personalise content\n\nConsent\n\n- [x] \n\nInformation about your activity on this service (for instance, forms you submit, non-advertising content you look at) can be stored and combined with other information about you (such as your previous activity on this service or other websites or apps) or similar users. This is then used to build or improve a profile about you (which might for example include possible interests and personal aspects). Your profile can be used (also later) to present content that appears more relevant based on your possible interests, such as by adapting the order in which content is shown to you, so that it is even easier for you to find content that matches your interests.\n\nIllustrations\n\n*   You read several articles on how to build a treehouse on a social media platform. This information might be added to a profile to mark your interest in content related to outdoors as well as do-it-yourself guides (with the objective of allowing the personalisation of content, so that for example you are presented with more blog posts and articles on treehouses and wood cabins in the future).\n*   You have viewed three videos on space exploration across different TV apps. An unrelated news platform with which you have had no contact builds a profile based on that viewing behaviour, marking space exploration as a topic of possible interest for other videos.\n\nNumber of Vendors seeking consent: 0\n\nUse profiles to select personalised content\n\nConsent\n\n- [x] \n\nContent presented to you on this service can be based on your content personalisation profiles, which can reflect your activity on this or other services (for instance, the forms you submit, content you look at), possible interests and personal aspects. This can for example be used to adapt the order in which content is shown to you, so that it is even easier for you to find (non-advertising) content that matches your interests.\n\nIllustrations\n\n*   You read articles on vegetarian food on a social media platform and then use the cooking app of an unrelated com","Engineering Research Express Vol.8 No.16","论文",10,false,60,{"impact":16,"substance":17,"depth":18,"authority":16,"freshness":19,"relevant":20,"comment":21},12,18,16,2,1,"论文比较量子机器学习与经典方法在作物\u002F杂草检测中的应用，属于智慧农业前沿技术，但时效性差且正文被隐私声明占据，信息有限。",[23],{"name":10,"url":6},[25,26,27,28],"精准农业","杂草检测","量子机器学习","Engineering Research Express",{"code":30,"slug":31,"name":32,"path":33,"parent_code":34},"I2","agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai","I",[],{"status":37,"locked":13,"version":38,"method":39,"evidence":40},"classified","2026-10-22.2","rules",{"candidates":41,"agricultural_evidence":44},[42,50,57],{"code":30,"score":43,"supported":44,"title":45,"abstract":47,"tags":49},11,true,[46],"机器学习",[48],"深度学习",[],{"code":51,"score":52,"supported":44,"title":53,"abstract":54,"tags":56},"A7",3,[],[55],"间作",[],{"code":58,"score":20,"supported":13,"title":59,"abstract":60,"tags":61},"I1",[],[],[25],[63,64],"量子机器学习 杂草检测 精准农业 Engineering Research Express","量子机器学习 杂草检测","量子机器学习杂草检测精准农业EngineeringResearchExpress-912","10.1088\u002F2631-8695\u002Fae98fa","2026-08-24T00:06:13.355822Z",{"total":69,"page":20,"page_size":69,"items":70},6,[71,129,236,317,368,442],{"id":72,"title":73,"url":74,"summary":75,"summary_zh":76,"content":8,"source_name":77,"source_url":74,"published_at":78,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":79,"score_detail":80,"sources":85,"tags":87,"primary_topic":92,"secondary_topics":93,"classification":94,"search_phrases":108,"slug":111,"view_count":112,"doi":113,"paper":114,"created_at":128},5585,"Contrastive Self-Supervised Pretraining for Artificial Intelligence Agriculture Weed Detection Under Label Scarcity: A Computer Transfer-Robustness Evaluation","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23543814","Weed detection models for precision agriculture are typically trained on labelled field imagery that is expensive to obtain and geographically narrow, so that a model fitted in one region may fail silently when deployed in another. Contrastive self-supervised pretraining has been proposed as a remedy because it learns representations from unlabelled images, but the conditions under which the resulting representations transfer robustly across domains remain poorly characterised. We define a representation-level robustness functional that separates invariance to nuisance transformations from sensitivity to class-discriminative structure, and we derive a bound on target-domain error in terms of source-domain error, representation stability and a domain-divergence term. The bound implies that contrastive pretraining helps only when the augmentation distribution used during pretraining overlaps with the transformation set that distinguishes source from target domains; otherwise the learned invariances suppress exactly the features the downstream task requires. We operationalise the framework as a transfer-robustness evaluation protocol with three components: a label-budget sweep, a domain-shift ladder and a representation-stability diagnostic. The protocol is specified as a design template rather than executed on new field data, and we report the analytical operating characteristics of the evaluation under a declared variance structure. The main contribution is a precise statement of when contrastive pretraining is expected to improve weed-detection transfer and when it is expected to fail, together with an evaluation design that makes that expectation testable.","精准农业中的杂草检测模型通常基于标注田间影像训练，而这类影像获取成本高且地理覆盖范围狭窄，因此在一个地区拟合的模型部署到另一地区时可能悄然失效。对比自监督预训练被认为是一种补救方案，因为它能够从无标注图像中学习表征，但所得表征在何种条件下能够跨域稳健迁移，目前仍缺乏充分刻画。我们定义了一个表征层面的鲁棒性泛函，将对外扰变换的不变性与对类别判别结构的敏感性区分开来，并推导了目标域误差的上界，该上界由源域误差、表征稳定性和一个域散度项构成。该上界表明，对比预训练只有在预训练所用增强分布与区分源域和目标域的变换集合存在重叠时才有帮助；否则，所学到的不变性恰好会抑制下游任务所需的特征。我们将该框架具体化为一个迁移鲁棒性评估协议，包含三个组成部分：标签预算扫描、域偏移阶梯和表征稳定性诊断。该协议被规定为一种设计模板，而非在新的田间数据上执行，我们在声明的方差结构下报告了该评估的解析运行特性。主要贡献在于精确陈述了对比预训练何时有望改善杂草检测迁移、何时预期会失败，并给出了一种使该预期可检验的评估设计。","Zenodo (CERN European Organization for Nuclear Research)","2026-10-21T00:00:00Z",62,{"impact":81,"substance":17,"depth":82,"authority":83,"freshness":12,"relevant":20,"comment":84},8,17,9,"提出对比自监督预训练在标签稀缺下跨域迁移的可检验评估框架，方法学有新意，但仅为设计模板、未在真实田间数据上验证，属细分领域理论进展。",[86],{"name":77,"url":74},[88,89,90,26,91],"智慧农业","农业人工智能","自监督学习","迁移学习",{"code":30,"slug":31,"name":32,"path":33,"parent_code":34},[],{"status":37,"locked":13,"version":38,"method":39,"evidence":95},{"candidates":96,"agricultural_evidence":44},[97,102],{"code":30,"score":12,"supported":44,"title":98,"abstract":100,"tags":101},[99],"artificial intelligence",[],[89,91],{"code":58,"score":103,"supported":44,"title":104,"abstract":105,"tags":107},7,[],[25,106],"precision agriculture",[88],[109,110],"对比自监督 杂草检测","杂草检测 迁移鲁棒性","对比自监督杂草检测-5585",0,"10.5281\u002Fzenodo.23543814",{"doi":113,"openalex_id":115,"authors":116,"venue":77,"cited_by_count":112,"oa_url":74,"card":121,"direction":125,"ingested_from":127},"W7223090735",[117,119],{"name":118,"orcid":8},"Abebe Gebremedhin Desta",{"name":120,"orcid":8},"Kebede Mekonnen Tadesse",{"tldr":122,"method":123,"finding":124,"direction":125,"opportunity":126},"提出对比自监督预训练在杂草检测跨域迁移中何时有效的理论框架与评估协议。","定义表示级鲁棒性泛函，推导目标域误差上界，设计含标签预算扫描与域偏移阶梯的评估协","仅当预训练增强分布与源-目标域差异变换集重叠时，对比预训练才有助于迁移，否则会抑制任务所需特征。","农业人工智能与决策模型","可将该理论框架落地为真实田间多区域杂草检测实验，验证增强分布重叠假设并量化迁移失败边界。","openalex","2026-10-22T11:21:00.352502Z",{"id":130,"title":131,"url":132,"summary":133,"summary_zh":134,"content":8,"source_name":135,"source_url":132,"published_at":78,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":136,"score_detail":137,"sources":141,"tags":143,"primary_topic":146,"secondary_topics":147,"classification":159,"search_phrases":211,"slug":214,"view_count":112,"doi":215,"paper":216,"created_at":235},5553,"Artificial Intelligence–Driven Precision Agriculture Systems: Engineering Frameworks for Climate-Resilient Food Production","https:\u002F\u002Fdoi.org\u002F10.53982\u002Fajerd.2026.01.14-j","Climate change, soil issues, water scarcity, and the increasing need for food worldwide mean we need smart farming systems that can manage resources flexibly. Old farming methods used the same inputs and simple rules for decisions. AI can help us manage resources better by adapting and optimizing them as we deal with complex environmental factors. This paper looks closely at AI-powered precision agriculture systems designed to make food production more resilient to changing weather. The authors reviewed research from 2021 to 2026 in agricultural engineering, computer engineering, and environmental systems. The authors examined how machine learning, deep learning, reinforcement learning, computer vision, robotics, and IoT sensors are used for predicting crop yields, spotting diseases, improving irrigation, managing nutrients, and automating field tasks. Our analysis shows that hybrid deep learning models (CNN-LSTM) are better than single models for predicting crop yields over space and time. Reinforcement learning algorithms are also better at adjusting irrigation cycles when weather is unpredictable. Using edge computing for system design reduces delays and improves real-time decision-making compared to traditional cloud-based systems. However, there are still big challenges with understanding how AI models work, having enough diverse data, ensuring cybersecurity, setting common standards, and making these systems affordable, especially in developing countries. To tackle these problems, we suggest a framework that combines AI analysis, distributed sensor networks, adaptive controls, and climate risk assessments. The authors provided critical insights into essential research gaps and outline a technological roadmap towards achieving sustainable, resilient and intelligent agricultural systems.","气候变化、土壤问题、水资源短缺以及全球日益增长的粮食需求，意味着我们需要能够灵活管理资源的智能农业系统。传统农业方法对相同的投入采用固定模式，并依赖简单规则进行决策。人工智能可以帮助我们更好地管理资源，通过适应和优化资源利用来应对复杂的环境因素。本文深入探讨了人工智能驱动的精准农业系统，旨在使粮食生产对不断变化的天气更具韧性。作者综述了2021年至2026年间农业工程、计算机工程和环境系统领域的研究。作者考察了机器学习、深度学习、强化学习、计算机视觉、机器人技术及物联网传感器如何被用于作物产量预测、病害识别、灌溉优化、养分管理和田间作业自动化。我们的分析表明，混合深度学习模型（CNN-LSTM）在时空作物产量预测方面优于单一模型。在天气不可预测的情况下，强化学习算法在调整灌溉周期方面也表现更优。与传统基于云的系统相比，采用边缘计算进行系统设计可降低延迟并改善实时决策能力。然而，在理解人工智能模型的工作原理、获取足够多样化的数据、确保网络安全、制定通用标准以及使这些系统具备可负担性方面，仍存在重大挑战，尤其是在发展中国家。为应对这些问题，我们提出了一个融合人工智能分析、分布式传感器网络、自适应控制和气候风险评估的框架。作者对关键研究空白提供了重要见解，并勾勒了实现可持续、韧性和智能农业系统的技术路线图。","ABUAD Journal of Engineering Research and Development (AJERD)",80,{"impact":17,"substance":138,"depth":17,"authority":139,"freshness":83,"relevant":20,"comment":140},22,13,"系统综述AI驱动精准农业的工程框架与技术路线，方法梳理扎实、结论有参考价值，但属综述类论文，产业落地影响有限。",[142],{"name":135,"url":132},[88,89,144,25,145],"物联网","气候韧性",{"code":30,"slug":31,"name":32,"path":33,"parent_code":34},[148,153],{"code":149,"slug":150,"name":151,"path":152,"parent_code":34},"I5","agricultural-iot","物联网传感与边缘计算","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-iot",{"code":154,"slug":155,"name":156,"path":157,"parent_code":158},"H3","irrigation","水资源与灌溉","\u002Ftopic\u002Fenvironment\u002Firrigation","H",{"status":37,"locked":13,"version":38,"method":39,"evidence":160},{"candidates":161,"agricultural_evidence":44},[162,170,174,181,187,194,201,205],{"code":30,"score":17,"supported":44,"title":163,"abstract":164,"tags":169},[99],[48,46,165,166,167,168],"计算机视觉","machine learning","deep learning","computer vision",[89],{"code":58,"score":18,"supported":44,"title":171,"abstract":172,"tags":173},[106],[25,106],[88,25],{"code":149,"score":12,"supported":44,"title":175,"abstract":176,"tags":180},[],[144,177,178,179],"边缘计算","IoT","edge computing",[144],{"code":154,"score":83,"supported":44,"title":182,"abstract":183,"tags":186},[],[184,185,155],"灌溉","水资源",[],{"code":188,"score":103,"supported":44,"title":189,"abstract":190,"tags":193},"H7",[],[191,192],"气候变化","climate change",[145],{"code":195,"score":69,"supported":44,"title":196,"abstract":197,"tags":200},"H2",[],[198,199],"土壤","soil",[],{"code":51,"score":52,"supported":44,"title":202,"abstract":203,"tags":204},[],[55],[],{"code":206,"score":52,"supported":44,"title":207,"abstract":208,"tags":210},"F3",[],[209],"养分管理",[],[212,213],"AI 精准农业 气候韧性","CNN-LSTM 作物产量预测","AI精准农业气候韧性-5553","10.53982\u002Fajerd.2026.01.14-j",{"doi":215,"openalex_id":217,"authors":218,"venue":135,"cited_by_count":112,"oa_url":132,"card":229,"direction":234,"ingested_from":127},"W7223121456",[219,222,224,226],{"name":220,"orcid":221},"Olumayowa J. Iyanda","https:\u002F\u002Forcid.org\u002F0000-0002-5340-9884",{"name":223,"orcid":8},"Oluwadare OYEBODE",{"name":225,"orcid":8},"Iretiayo Adelaiye",{"name":227,"orcid":228},"Ayomide Afolabi","https:\u002F\u002Forcid.org\u002F0000-0002-5171-886X",{"tldr":230,"method":231,"finding":232,"direction":125,"opportunity":233},"综述2021-2026年AI驱动精准农业系统，提出气候韧性粮食生产工程框架。","综述机器学习、深度学习、强化学习、计算机视觉、机器人与物联网在精准农业中的应用。","CNN-LSTM混合模型和强化学习在产量预测与灌溉调度上优于单一方法，边缘计算提升实时性。","可研究边缘计算与强化学习结合的轻量级灌溉决策系统，并探索发展中国家低成本部署与标准化路径。","智慧农业 \u002F 农业物联网","2026-10-22T11:20:18.151376Z",{"id":237,"title":238,"url":239,"summary":240,"summary_zh":241,"content":8,"source_name":242,"source_url":239,"published_at":243,"category":11,"cover_url":8,"hotness":12,"is_selected":44,"score":244,"score_detail":245,"sources":251,"tags":253,"primary_topic":256,"secondary_topics":257,"classification":258,"search_phrases":285,"slug":288,"view_count":275,"doi":289,"paper":290,"created_at":316},5382,"Modeling the global potential of smart farming innovations","https:\u002F\u002Fdoi.org\u002F10.1073\u002Fpnas.2530081123","Smart farming innovations can improve agricultural productivity, resilience, and environmental sustainability, yet their real-world impact hinges on their diffusion dynamics, which in turn depend on their economic viability. We present here a global assessment of the profitability of smart farming innovation across croplands at a spatial resolution of ~5 km from the farmers’ and the societal perspectives. We cover application mapping for precision agriculture, automated application of inputs, autonomous weeding machines, GPS steering assistance systems, and autonomous irrigation systems. For this, we compiled a globally comprehensive dataset of smart farming innovation adoption locations (N = 4,422) based on a combination of a survey (N = 2,677) and a meta-analysis (N = 1,745) and combined them with remotely sensed and statistical data to train an ensemble of five geospatial machine learning models (generalized linear models, random forests, support vector machines, maximum entropy, and boosted regression trees), which show the global distribution of the different innovations’ profitability and its overlap with major environmental issues the innovations can help to mitigate. Simulations of future socioeconomic pathways combined with assumptions about future agri-environmental policies reveal that, especially in middle-income countries, the potential of smart farming will grow over time.","智慧农业创新能够提升农业生产力、韧性和环境可持续性，然而其现实影响取决于扩散动态，而扩散动态又取决于其经济可行性。本文从农民和社会两个视角，以约5公里的空间分辨率对全球农田范围内智慧农业创新的盈利能力进行了评估。研究涵盖精准农业的应用测绘、投入品的自动化施用、自主除草机械、GPS转向辅助系统以及自主灌溉系统。为此，我们基于一项调查（N = 2,677）和一项元分析（N = 1,745）相结合，编制了全球范围内较为全面的智慧农业创新采用地点数据集（N = 4,422），并将其与遥感和统计数据相结合，用于训练由五种地理空间机器学习模型（广义线性模型、随机森林、支持向量机、最大熵和提升回归树）组成的集成模型，这些模型揭示了不同创新盈利能力的全球分布及其与这些创新有助于缓解的主要环境问题的重叠情况。对未来社会经济路径的模拟结合对未来农业环境政策的假设表明，智慧农业的潜力将随时间推移而增长，尤其是在中等收入国家。","Proceedings of the National Academy of Sciences","2026-10-19T00:00:00Z",93,{"impact":246,"substance":247,"depth":248,"authority":249,"freshness":83,"relevant":20,"comment":250},26,24,19,15,"PNAS 全球尺度智慧农业盈利性评估，数据规模与方法新颖，结论对智慧农业推广具政策参考价值，值得进入每日精选。",[252],{"name":242,"url":239},[88,89,25,254,255],"遥感","全球评估",{"code":30,"slug":31,"name":32,"path":33,"parent_code":34},[],{"status":37,"locked":13,"version":38,"method":39,"evidence":259},{"candidates":260,"agricultural_evidence":44},[261,265,269,273,279],{"code":58,"score":43,"supported":44,"title":262,"abstract":263,"tags":264},[],[88,25,106],[88,25],{"code":30,"score":103,"supported":44,"title":266,"abstract":267,"tags":268},[],[46,166],[89],{"code":154,"score":69,"supported":44,"title":270,"abstract":271,"tags":272},[],[184,155],[],{"code":274,"score":275,"supported":44,"title":276,"abstract":277,"tags":278},"I3",4,[],[254],[254],{"code":280,"score":52,"supported":44,"title":281,"abstract":282,"tags":284},"F4",[],[283],"除草",[],[286,287],"农业人工智能 全球评估 智慧农业 精准农业","农业人工智能 全球评估","农业人工智能全球评估智慧农业精准农业-5382","10.1073\u002Fpnas.2530081123",{"doi":289,"openalex_id":291,"authors":292,"venue":242,"cited_by_count":112,"oa_url":239,"card":311,"direction":234,"ingested_from":127},"W7222974188",[293,296,299,302,305,308],{"name":294,"orcid":295},"Shahrear Roman","https:\u002F\u002Forcid.org\u002F0009-0006-5659-4292",{"name":297,"orcid":298},"Hadi Hadi","https:\u002F\u002Forcid.org\u002F0000-0002-2410-9751",{"name":300,"orcid":301},"Wyclife Agumba Oluoch","https:\u002F\u002Forcid.org\u002F0000-0003-0803-9279",{"name":303,"orcid":304},"David Zilberman","https:\u002F\u002Forcid.org\u002F0000-0001-5743-5134",{"name":306,"orcid":307},"Robert Finger","https:\u002F\u002Forcid.org\u002F0000-0002-0634-5742",{"name":309,"orcid":310},"David Wuepper","https:\u002F\u002Forcid.org\u002F0000-0002-1344-6023",{"tldr":312,"method":313,"finding":314,"direction":234,"opportunity":315},"全球5公里尺度评估五类智慧农业创新在农田的盈利性与扩散潜力。","整合4422个采用点调查与元分析数据，用五种地理空间机器学习集成建模。","智慧农业盈利性空间差异显著，中等收入国家未来潜力将随社会经济路径增长。","可结合区域政策与农户异质性，细化盈利性预测并评估环境协同效益。","2026-10-20T23:30:08.754594Z",{"id":318,"title":319,"url":320,"summary":321,"summary_zh":8,"content":8,"source_name":322,"source_url":320,"published_at":323,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":324,"score_detail":325,"sources":328,"tags":330,"primary_topic":332,"secondary_topics":333,"classification":334,"search_phrases":346,"slug":349,"view_count":112,"doi":350,"paper":351,"created_at":367},5307,"Enhancing seeding efficiency using a computer vision system to monitor furrow quality in real-time","https:\u002F\u002Fdoi.org\u002F10.1007\u002Fs11119-026-10461-3","Enhancing seeding efficiency using a computer vision system to monitor furrow quality in real-time。Precision Agriculture","Precision Agriculture","2026-10-18T00:00:00Z",74,{"impact":18,"substance":17,"depth":82,"authority":326,"freshness":83,"relevant":20,"comment":327},14,"该论文提出用计算机视觉实时监测播种沟质量，属于智慧农业细分技术进展，方法有创新但影响限于行业层面，值得进入每日精选。",[329],{"name":322,"url":320},[88,165,25,331],"播种质量",{"code":30,"slug":31,"name":32,"path":33,"parent_code":34},[],{"status":37,"locked":13,"version":38,"method":39,"evidence":335},{"candidates":336,"agricultural_evidence":44},[337,341],{"code":30,"score":16,"supported":44,"title":338,"abstract":339,"tags":340},[168],[168],[165],{"code":58,"score":342,"supported":44,"title":343,"abstract":344,"tags":345},5,[],[106],[88,25],[347,348],"实时监测 播种 沟形质量","计算机视觉 播种质量 智慧农业 精准农业","实时监测播种沟形质量-5307","10.1007\u002Fs11119-026-10461-3",{"doi":350,"openalex_id":352,"authors":353,"venue":322,"cited_by_count":112,"oa_url":8,"card":8,"direction":8,"ingested_from":127},"W7222892423",[354,356,358,361,364],{"name":355,"orcid":8},"Sidharth Rai",{"name":357,"orcid":8},"Riley Sleichter",{"name":359,"orcid":360},"Aryan Singh Dalal","https:\u002F\u002Forcid.org\u002F0000-0003-0720-7306",{"name":362,"orcid":363},"Rahul Harsha Cheppally","https:\u002F\u002Forcid.org\u002F0009-0001-3897-6725",{"name":365,"orcid":366},"Ajay Sharda","https:\u002F\u002Forcid.org\u002F0000-0001-5161-4123","2026-10-19T23:30:02.435881Z",{"id":369,"title":370,"url":371,"summary":372,"summary_zh":373,"content":8,"source_name":322,"source_url":371,"published_at":323,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":374,"score_detail":375,"sources":378,"tags":380,"primary_topic":382,"secondary_topics":383,"classification":384,"search_phrases":399,"slug":402,"view_count":112,"doi":403,"paper":404,"created_at":441},5306,"A growing challenge: stakeholder perceptions of AI and ML applications in U.S. agriculture","https:\u002F\u002Fdoi.org\u002F10.1007\u002Fs11119-026-10459-x","Abstract Context The global population is expected to exceed ten billion by 2050 and food demand is projected to increase by up to 100% in the same timeframe. Agricultural management must adapt to meet the increasing global demands. Artificial intelligence (AI) and machine learning (ML) technologies can help the agricultural community respond to these needs. Aims An online survey and follow-up interviews were conducted to examine patterns of use, perceptions, and barriers among early adopting stakeholders regarding AI and ML. Methods The online survey with agricultural stakeholders (n=129) included questions regarding the participants’ views on incorporating AI and ML techniques into farming practices and individual follow-up interviews with agricultural stakeholders (n=10) were conducted to better understand their concerns toward technology use and adoption of AI-enabled tools and technologies. Key results Using a mixed-methods approach, four challenges to establishing AI-\u002FML-enabled technology in agriculture were identified. Namely, challenges related to (1) systems of systems (SoS), (2) sub-seasonal to seasonal weather (S2S) forecasts, (3) precision soil management, and (4) policy and economics. Each challenge was discussed in the context of recent literature. Conclusion Concerns were voiced clustered around four broad research themes. This brief communication brings the perspective of agricultural stakeholders to the discussion of the potential of AI\u002FML-enabled technology and the direction of their development in the agricultural sector. Implications Data collected in 2021, establish an important baseline for the early phase of AI\u002FML use in U.S. agriculture, enabling comparison of future perceptions and developments in the sector. Impact This brief communication describes a survey and follow-up interviews conducted with agricultural stakeholders on factors influencing their willingness and reluctance to incorporate AI and ML techniques into farming practices. The findings, summarized and discussed as four key challenges for AI and ML in the agricultural sector, have the potential to streamline research activities.","摘要\n\n背景 预计到2050年全球人口将超过100亿，同期粮食需求预计将增加多达100%。农业管理必须作出调整以满足不断增长的全球需求。人工智能（AI）和机器学习（ML）技术可帮助农业界应对这些需求。\n\n目的 通过开展在线调查和后续访谈，考察早期采用相关技术的利益相关者在AI和ML方面的使用模式、认知及障碍。\n\n方法 针对农业利益相关者（n=129）的在线调查包含有关参与者对将AI和ML技术纳入农业实践看法的问题，并对农业利益相关者（n=10）进行个体后续访谈，以更好地了解他们对技术使用及采用AI赋能工具和技术的顾虑。\n\n主要结果 采用混合方法，识别出在农业中建立AI\u002FML赋能技术面临的四项挑战，即与以下方面相关的挑战：（1）系统之系统（SoS），（2）次季节至季节天气（S2S）预报，（3）精准土壤管理，以及（4）政策与经济。每项挑战均结合近期文献进行了讨论。\n\n结论 所表达的顾虑集中于四个广泛的研究主题。本简报将农业利益相关者的视角引入关于AI\u002FML赋能技术潜力及其在农业部门发展方向讨论中。\n\n意义 2021年收集的数据为美国农业中AI\u002FML应用的早期阶段建立了重要基线，有助于比较该部门未来的认知和发展。\n\n影响 本简报描述了针对农业利益相关者开展的一项调查和后续访谈，内容涉及影响其愿意和不愿将AI和ML技术纳入农业实践的因素。研究结果总结并讨论为农业部门AI和ML的四项关键挑战，有望优化研究活动。",77,{"impact":17,"substance":376,"depth":82,"authority":326,"freshness":81,"relevant":20,"comment":377},20,"基于129份问卷与10次访谈的混合方法研究，系统梳理美国农业AI\u002FML应用的四大挑战，为早期采用者认知提供基线数据，对智慧农业研究有参考价值。",[379],{"name":322,"url":371},[88,89,46,25,381],"农户认知",{"code":30,"slug":31,"name":32,"path":33,"parent_code":34},[],{"status":37,"locked":13,"version":38,"method":39,"evidence":385},{"candidates":386,"agricultural_evidence":44},[387,391,395],{"code":30,"score":43,"supported":44,"title":388,"abstract":389,"tags":390},[],[46,166,99],[89,46],{"code":195,"score":69,"supported":44,"title":392,"abstract":393,"tags":394},[],[198,199],[],{"code":58,"score":19,"supported":13,"title":396,"abstract":397,"tags":398},[],[],[88,25],[400,401],"美国农业 AI ML 调查","农业人工智能 应用障碍","美国农业AIML调查-5306","10.1007\u002Fs11119-026-10459-x",{"doi":403,"openalex_id":405,"authors":406,"venue":322,"cited_by_count":112,"oa_url":371,"card":436,"direction":125,"ingested_from":127},"W7222866367",[407,410,413,416,419,422,425,428,430,433],{"name":408,"orcid":409},"Jennifer Koch","https:\u002F\u002Forcid.org\u002F0000-0002-7067-2705",{"name":411,"orcid":412},"Andrew Fox","https:\u002F\u002Forcid.org\u002F0000-0001-6719-8902",{"name":414,"orcid":415},"Richa Bhattarai","https:\u002F\u002Forcid.org\u002F0000-0003-3827-7761",{"name":417,"orcid":418},"Hank C. Jenkins‐Smith","https:\u002F\u002Forcid.org\u002F0000-0002-5204-2726",{"name":420,"orcid":421},"Jonathan McFadden","https:\u002F\u002Forcid.org\u002F0000-0003-3762-1428",{"name":423,"orcid":424},"Audrey Reinert","https:\u002F\u002Forcid.org\u002F0000-0001-8951-702X",{"name":426,"orcid":427},"Juan Sesmero","https:\u002F\u002Forcid.org\u002F0000-0002-2669-4536",{"name":429,"orcid":8},"M. Z. Walkup",{"name":431,"orcid":432},"Wolfgang Jentner","https:\u002F\u002Forcid.org\u002F0000-0003-1045-6020",{"name":434,"orcid":435},"David S. Ebert","https:\u002F\u002Forcid.org\u002F0000-0001-6177-1296",{"tldr":437,"method":438,"finding":439,"direction":125,"opportunity":440},"通过问卷与访谈调查美国农业利益相关者对AI\u002FML应用的认知与障碍。","在线问卷129人加10人深度访谈的混合方法。","识别出系统之系统、次季节天气预报、精准土壤管理和政策经济四大挑战。","可针对四类障碍开展分区域、分作物类型的采纳意愿追踪与干预研究。","2026-10-19T23:30:02.345893Z",{"id":443,"title":444,"url":445,"summary":446,"summary_zh":447,"content":8,"source_name":448,"source_url":445,"published_at":449,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":450,"score_detail":451,"sources":454,"tags":456,"primary_topic":459,"secondary_topics":460,"classification":461,"search_phrases":472,"slug":475,"view_count":112,"doi":476,"paper":477,"created_at":507},5153,"Real-Time UAV scheduling under hazardous weather conditions using an integrated fuzzy logic and machine learning framework","https:\u002F\u002Fdoi.org\u002F10.1007\u002Fs43926-026-00489-2","The use of Unmanned Aerial Vehicles (UAVs) in precision agriculture, specifically palm farm management, is perpetually challenged by dynamic and extreme weather. From sudden wind gusts and thermal stress to destructive regional events like sandstorms and flash floods, these hazards severely constrict operational windows. This paper proposes a robust, hybrid scheduling framework that integrates fuzzy logic inference with an ensemble of machine learning classifiers to enhance real-time UAV flight reliability. The primary novelty of this research lies not in a new mathematical paradigm, but in its specialized application: the holistic integration of region-specific agricultural hazards into a real-time, decision-fusion architecture. The framework classifies takeoff viability into three categories (SAFE, CAUTION, and UNSAFE) automatically issuing alerts to trigger preventative measures and preserve hardware. By leveraging both short-term farm datasets and a decade of historical weather records, the fuzzy logic component reacts to rapid environmental shifts while establishing safety baselines. Simultaneously, tree-based ensemble models (Gradient Boosting, XGBoost, LightGBM, and CatBoost) analyze non-linear atmospheric interactions, achieving up to 99.67% accuracy in predicting safe windows. Comprehensive sensitivity analyses, including evaluations without SMOTE and seasonal temporal holdout validations, confirm the model’s robustness against class imbalance and unseen extremes. Empirical benchmarking demonstrates the framework's superiority over existing hybrid approaches, highlighting the necessity of combining adaptive fuzzy reasoning with deep historical learning for smart farming.","无人机（UAV）在精准农业尤其是棕榈农场管理中的应用，始终受到动态极端天气的困扰。从突发阵风和热应激到沙尘暴和山洪等破坏性区域事件，这些灾害严重压缩了作业窗口。本文提出了一种稳健的混合调度框架，将模糊逻辑推理与机器学习分类器集成相结合，以提升无人机实时飞行的可靠性。本研究的主要创新点不在于新的数学范式，而在于其专门化应用：将区域特定的农业灾害整体集成到实时决策融合架构中。该框架将起飞可行性分为三类（安全、 caution、不安全），自动发出警报以触发预防措施并保护硬件。通过利用短期农场数据集和十年历史天气记录，模糊逻辑组件能够对快速环境变化作出反应，同时建立安全基线。与此同时，基于树的集成模型（梯度提升、XGBoost、LightGBM和CatBoost）分析非线性大气相互作用，在预测安全窗口方面达到高达99.67%的准确率。全面的敏感性分析，包括无SMOTE的评估和季节性时间留出验证，证实了模型对类别不平衡和未见极端情况的稳健性。实证基准测试表明，该框架优于现有的混合方法，凸显了将自适应模糊推理与深度历史学习相结合对于智慧农业的必要性。","Discover Internet of Things","2026-10-15T00:00:00Z",76,{"impact":18,"substance":452,"depth":17,"authority":139,"freshness":81,"relevant":20,"comment":453},21,"将模糊逻辑与集成学习融合用于极端天气下的农业无人机实时调度，方法扎实、验证充分，对智慧农业作业安全有实际参考价值。",[455],{"name":448,"url":445},[88,89,457,25,458],"农业无人机","气象预警",{"code":30,"slug":31,"name":32,"path":33,"parent_code":34},[],{"status":37,"locked":13,"version":38,"method":39,"evidence":462},{"candidates":463,"agricultural_evidence":44},[464,468],{"code":30,"score":249,"supported":44,"title":465,"abstract":466,"tags":467},[166],[46,166],[89],{"code":58,"score":43,"supported":44,"title":469,"abstract":470,"tags":471},[],[88,25,106],[88,25],[473,474],"无人机 精准农业 极端天气","UAV 棕榈园 调度","无人机精准农业极端天气-5153","10.1007\u002Fs43926-026-00489-2",{"doi":476,"openalex_id":478,"authors":479,"venue":448,"cited_by_count":112,"oa_url":501,"card":502,"direction":234,"ingested_from":127},"W7166891579",[480,483,486,488,490,493,495,498],{"name":481,"orcid":482},"Ahmad B. Alkhodre","https:\u002F\u002Forcid.org\u002F0000-0001-6168-3552",{"name":484,"orcid":485},"Adnan Ahmed Abi Sen","https:\u002F\u002Forcid.org\u002F0000-0003-2960-5807",{"name":487,"orcid":8},"Abdelouahab Abid",{"name":489,"orcid":8},"Nour Mahmoud Bahbouh",{"name":491,"orcid":492},"Adel Ben Mnaouer","https:\u002F\u002Forcid.org\u002F0000-0003-3617-7636",{"name":494,"orcid":8},"Mohamed Benaida",{"name":496,"orcid":497},"Yazed Alsaawy","https:\u002F\u002Forcid.org\u002F0000-0001-5031-3388",{"name":499,"orcid":500},"Hani Almoamari","https:\u002F\u002Forcid.org\u002F0000-0002-3550-8977","https:\u002F\u002Flink.springer.com\u002Fcontent\u002Fpdf\u002F10.1007\u002Fs43926-026-00489-2.pdf",{"tldr":503,"method":504,"finding":505,"direction":234,"opportunity":506},"提出融合模糊逻辑与机器学习分类器的无人机实时调度框架，在恶劣天气下保障精准农业飞行安全。","模糊逻辑推理结合梯度提升、XGBoost、LightGBM、CatBoost集成","框架将起飞可行性分为安全、警告、不安全三级，预测安全窗口准确率最高达99.67%，优于现有混合方法。","可将区域特定灾害（沙尘暴、山洪）纳入实时决策融合，并扩展到多机协同调度与边缘端轻量化部署研究。","2026-10-17T23:30:08.889571Z"]