[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-5292":3,"related-5292":62},{"id":4,"title":5,"url":6,"summary":7,"summary_zh":8,"content":9,"source_name":10,"source_url":8,"published_at":11,"category":12,"cover_url":8,"hotness":13,"is_selected":14,"score":15,"score_detail":16,"sources":23,"tags":25,"primary_topic":31,"secondary_topics":37,"classification":38,"search_phrases":56,"slug":59,"view_count":60,"doi":8,"paper":8,"created_at":61},5292,"福建省农科院联合开展福清三星村\"生态种植\"实验 三年渐进破解库区水质与种粮矛盾","https:\u002F\u002Fwww.faas.cn\u002Fcms\u002Fhtml\u002Ffjsnykxy\u002F2026-10-15\u002F1462192328.html","2023年7月福建\"一闸三线\"工程全线通水,东张水库从灌溉型水库升级为向平潭供水的调节库,水质要求从农业灌溉标准跃升为饮用水标准;由自然部东南丘陵土地整治野外科学观测研究站、福建省农科院资环所罗旭辉团队制定\"第一年无肥无药、第二年控肥控药,第三年逐步恢复产能\"的渐进式技术路线,形成\"政府+企业+科研+合作社\"四方协作模式。",null,"三星村稻田的试验，不只是简单的农业经济账，更是生态账、社会账。三星村，人均耕地仅有0.2-0.3亩。单纯依靠卖稻谷，农业对家庭收入贡献有限。项目最大的难点，不是施肥用药的技术参数，而是转变村民固有认知。\n\n项目实施以来，农户看着一批批游客慕名来到家门口，想法渐渐从追求最高产量，转向兼顾田间环境与水库水质。“田间环境，本身就是宝贵资源，守护库区水质也与村庄发展息息相关。生态种植方式需要一个长期的过程，如果能在期间提升群众获得感，我们后续的技术落地、环境管护都会顺畅很多。”罗旭辉说。\n\n对于“无废乡村”理念，团队也在这片田野开展了实践。据罗旭辉介绍，乡村层面主要聚焦几大指标，涵盖化肥农药减量、粪污资源化利用、农药包装废弃物回收转运体系、秸秆综合利用等。谈及这套模式未来如何持续，他提出两个基础前提：第一，水稻生态种植必须持续开展，网红流量依托稻田本体，田地不能改作他用；第二，村庄人居环境要长期维护，守住干净整洁底色。在此基础上，持续叠加体验业态，拉长游览周期，进一步把流量做稳。\n\n种植本土作物打造打卡点，核心逻辑是把生态治理、粮食生产、乡村发展三者结合，推动群众思想观念转变。据了解，福建省农科院现有一百余个科技示范基地，将推动更多示范点实现技术落地、群众认可，让乡村找到保护与发展的平衡点。（资环所通讯员：陈钟佃）","福建省农业科学院(2026-10-15)","2026-10-15T00:00:00Z","报道",10,false,62,{"impact":17,"substance":18,"depth":19,"authority":19,"freshness":20,"relevant":21,"comment":22},16,14,13,6,1,"省级科研机构主导的生态种植与库区水质协同试验，有实地进展与理念转变细节，但属单点示范，公共影响有限，可作一般资讯而非每日精选。",[24],{"name":10,"url":6},[26,27,28,29,30],"水稻","生态种植","库区水质","无废乡村","科技示范基地",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},"H3","irrigation","水资源与灌溉","\u002Ftopic\u002Fenvironment\u002Firrigation","H",[],{"status":39,"locked":14,"version":40,"method":41,"evidence":42},"classified","2026-10-22.2","rules",{"candidates":43,"agricultural_evidence":46},[44,51],{"code":32,"score":45,"supported":46,"title":47,"abstract":48,"tags":50},3,true,[],[49],"灌溉",[],{"code":52,"score":21,"supported":14,"title":53,"abstract":54,"tags":55},"A1",[],[],[26],[57,58],"福建省农科院 福清三星村 生态种植","东张水库 水稻 生态种植","福建省农科院福清三星村生态种植-5292",0,"2026-10-19T00:07:42.151069Z",{"total":20,"page":21,"page_size":20,"items":63},[64,159,227,319,436,492],{"id":65,"title":66,"url":67,"summary":68,"summary_zh":69,"content":8,"source_name":70,"source_url":67,"published_at":71,"category":72,"cover_url":8,"hotness":13,"is_selected":14,"score":73,"score_detail":74,"sources":80,"tags":82,"primary_topic":87,"secondary_topics":93,"classification":95,"search_phrases":135,"slug":138,"view_count":60,"doi":139,"paper":140,"created_at":158},5496,"Multi-Crop Irrigation Need Classification Based on Machine Learning with an Indonesian-Language GenAI-UX Recommendation Layer","https:\u002F\u002Fdoi.org\u002F10.30871\u002Fjaic.v10i5.13774","Inefficient irrigation water use remains a critical challenge in Indonesian agriculture, and the complexity of raw sensor data hinders adoption by smallholder farmers who lack data-analysis skills. This study develops an intelligent irrigation Decision Support System that integrates interpretable Machine Learning with an Indonesian-language GenAI-UX recommendation layer, using a publicly available multi-crop irrigation scheduling dataset (501 records, nine crops) with an analytical focus on paddy and maize. Four components are combined into one pipeline: (i) irrigation-need classification compared across six algorithms; (ii) regression of a continuous water-requirement score; (iii) sensor-anomaly detection using Isolation Forest cross-validated with the Interquartile Range method; and (iv) a rule-based natural-language recommendation layer whose operating point is optimized by a Genetic Algorithm. Validity was safeguarded through stratified five-fold cross-validation and leakage-controlled preprocessing. Gradient Boosting achieved the best classification performance (F1-score 0.980; cross-validated F1 0.963), Random Forest Regressor reached R square of 0.807, Isolation Forest agreed with IQR outliers at 95.2%, and the Genetic Algorithm attained a confidence of 0.993 within realistic agronomic bounds. In an illustrative usability evaluation, the GenAI-UX interface obtained the highest System Usability Scale score (Good category). The results indicate that pairing accurate, interpretable models with a language-based delivery layer can transform complex sensor data into actionable irrigation recommendations, lowering the adoption barrier for non-technical users. Field validation with real respondents and edge deployment are identified as the next steps.","灌溉用水效率低下仍是印度尼西亚农业面临的一项关键挑战，而原始传感器数据的复杂性阻碍了缺乏数据分析技能的小农户采用相关技术。本研究开发了一种智能灌溉决策支持系统（Decision Support System），将可解释的机器学习与印度尼西亚语生成式人工智能用户体验（GenAI-UX）推荐层相结合，使用公开可用的多作物灌溉调度数据集（501条记录，九种作物），并以水稻和玉米为分析重点。四个组件被整合为一条流水线：（i）在六种算法之间比较灌溉需求分类；（ii）对连续需水量得分进行回归；（iii）使用孤立森林（Isolation Forest）进行传感器异常检测，并与四分位距（IQR）方法交叉验证；（iv）基于规则的自然语言推荐层，其操作点由遗传算法优化。通过分层五折交叉验证和防泄漏预处理保障了有效性。梯度提升（Gradient Boosting）取得了最佳分类性能（F1分数0.980；交叉验证F1为0.963），随机森林回归器（Random Forest Regressor）达到R平方0.807，孤立森林与IQR异常值的一致率为95.2%，遗传算法在现实农艺范围内达到0.993的置信度。在一项示例性可用性评估中，GenAI-UX界面获得了最高的系统可用性量表（System Usability Scale）得分（良好类别）。结果表明，将准确、可解释的模型与基于语言的交付层相结合，能够将复杂的传感器数据转化为可操作的灌溉建议，从而降低非技术用户的采用门槛。与真实受访者进行田间验证以及边缘部署被确定为下一步工作。","Journal of Applied Informatics and Computing","2026-10-19T00:00:00Z","论文",69,{"impact":75,"substance":76,"depth":77,"authority":75,"freshness":78,"relevant":21,"comment":79},12,20,17,8,"方法组合完整、指标扎实的农业AI决策支持论文，但属印尼小农户场景的实验室级研究，公共影响有限，适合作为技术参考而非每日精选头条。",[81],{"name":70,"url":67},[83,84,26,85,86],"智慧农业","农业人工智能","玉米","灌溉决策",{"code":88,"slug":89,"name":90,"path":91,"parent_code":92},"I2","agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai","I",[94],{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},{"status":39,"locked":14,"version":40,"method":41,"evidence":96},{"candidates":97,"agricultural_evidence":46},[98,106,111,117,123,130],{"code":88,"score":99,"supported":46,"title":100,"abstract":102,"tags":105},18,[101],"machine learning",[103,101,104],"机器学习","decision support",[84],{"code":32,"score":107,"supported":46,"title":108,"abstract":109,"tags":110},15,[33],[49,33],[86],{"code":52,"score":112,"supported":46,"title":113,"abstract":114,"tags":116},7,[],[26,115],"paddy",[26],{"code":118,"score":112,"supported":46,"title":119,"abstract":120,"tags":122},"A3",[],[85,121],"maize",[85],{"code":124,"score":20,"supported":46,"title":125,"abstract":126,"tags":129},"G2",[],[127,128],"小农户","smallholder",[],{"code":131,"score":21,"supported":14,"title":132,"abstract":133,"tags":134},"I1",[],[],[83],[136,137],"印尼 多作物 灌溉决策","GenAI 灌溉推荐","印尼多作物灌溉决策-5496","10.30871\u002Fjaic.v10i5.13774",{"doi":139,"openalex_id":141,"authors":142,"venue":70,"cited_by_count":60,"oa_url":67,"card":150,"direction":156,"ingested_from":157},"W7223016583",[143,146,148],{"name":144,"orcid":145},"Muhammad Rusdi","https:\u002F\u002Forcid.org\u002F0000-0002-1048-5000",{"name":147,"orcid":8},"Zaenuddin Zaenuddin",{"name":149,"orcid":8},"Hendra Sanjaya",{"tldr":151,"method":152,"finding":153,"direction":154,"opportunity":155},"构建融合可解释机器学习与印尼语GenAI推荐层的智能灌溉决策支持系统。","六种分类算法、回归、孤立森林异常检测与遗传算法优化规则推荐层。","梯度提升分类F1达0.980，GenAI界面可用性最佳，降低非技术用户使用门槛。","智慧农业 \u002F 农业物联网","可探索多语言本地化GenAI推荐层与边缘部署，并开展真实农户田间验证。","农业人工智能与决策模型","openalex","2026-10-21T23:30:46.441864Z",{"id":160,"title":161,"url":162,"summary":163,"summary_zh":8,"content":8,"source_name":164,"source_url":8,"published_at":165,"category":72,"cover_url":8,"hotness":13,"is_selected":14,"score":166,"score_detail":167,"sources":171,"tags":173,"primary_topic":177,"secondary_topics":181,"classification":188,"search_phrases":214,"slug":217,"view_count":45,"doi":8,"paper":218,"created_at":226},4159,"Dynamic regulation of grid-scale high-efficiency precision irrigation for rice under climate variability（基于气候变化的网格尺度水稻精准灌溉动态调控）","https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs44264-026-00172-7","Dong Wenhao、Xu YaoWen、Zhangzhong Lili、Xu Xianghui、Wei Shiyu、Sun Ziqiang、Chen Yingshan、Zhang Pingan、Li Mo（npj Sustainable Agriculture 2026, 4(1): 61）。针对气候变化与区域水量供需失衡，文章提出「模拟-优化」协同的网格尺度水稻精准灌溉调度框架：使用WOFOST模型结合Sobol敏感性分析与粒子群优化，与多目标优化模型耦合生成可动态调整的灌溉策略。在黑龙江省三江平原与松嫩平原（332,500 km²）应用：模型精度提高，区域产量提升1.5%、灌溉用水减少8.0%；动态调度策略相比传统灌溉节水10.1%。","npj Sustainable Agriculture 2026, 4(1): 61","2026-09-28T00:00:00Z",83,{"impact":168,"substance":169,"depth":99,"authority":18,"freshness":20,"relevant":21,"comment":170},22,23,"核心期刊论文，提出模拟-优化协同的网格尺度水稻精准灌溉框架，在三江平原等区域验证节水增产效果，方法新颖、数据规模大，对智慧农业与气候适应有参考价值。",[172],{"name":164,"url":162},[83,26,174,175,176],"气候适应","精准灌溉","三江平原",{"code":52,"slug":178,"name":26,"path":179,"parent_code":180},"rice","\u002Ftopic\u002Ffield-crops\u002Frice","A",[182,183],{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},{"code":184,"slug":185,"name":186,"path":187,"parent_code":36},"H7","climate","气候适应与防灾减灾","\u002Ftopic\u002Fenvironment\u002Fclimate",{"status":39,"locked":14,"version":40,"method":41,"evidence":189},{"candidates":190,"agricultural_evidence":46},[191,195,199,204,210],{"code":52,"score":76,"supported":46,"title":192,"abstract":193,"tags":194},[26,178],[26],[26],{"code":32,"score":76,"supported":46,"title":196,"abstract":197,"tags":198},[49,33],[49],[175],{"code":184,"score":75,"supported":46,"title":200,"abstract":202,"tags":203},[201],"气候变化",[201],[174],{"code":205,"score":45,"supported":46,"title":206,"abstract":207,"tags":209},"H8",[],[208],"sustainable agriculture",[],{"code":131,"score":21,"supported":14,"title":211,"abstract":212,"tags":213},[],[],[83],[215,216],"三江平原 水稻 精准灌溉","WOFOST 水稻 灌溉调度","三江平原水稻精准灌溉-4159",{"doi":8,"openalex_id":8,"authors":219,"venue":8,"cited_by_count":60,"oa_url":8,"card":220,"direction":154,"ingested_from":225},[],{"tldr":221,"method":222,"finding":223,"direction":154,"opportunity":224},"提出模拟-优化协同的网格尺度水稻精准灌溉调度框架，实现动态调控。","WOFOST作物模型、Sobol敏感性分析、粒子群优化与多目标优化耦合。","区域产量提升1.5%、灌溉用水减少8.0%，动态调度较传统灌溉节水10.1%。","可探索将网格尺度灌溉调度与实时物联网墒情监测、遥感数据同化结合，实现气候变率下的在线滚动优化。","agent","2026-10-04T00:09:10.154416Z",{"id":228,"title":229,"url":230,"summary":231,"summary_zh":232,"content":8,"source_name":233,"source_url":230,"published_at":234,"category":72,"cover_url":8,"hotness":13,"is_selected":14,"score":235,"score_detail":236,"sources":238,"tags":240,"primary_topic":245,"secondary_topics":246,"classification":253,"search_phrases":294,"slug":297,"view_count":60,"doi":298,"paper":299,"created_at":318},3168,"Spatial and Temporal Analysis of Rice Yield Using the DSSAT Model in the Kommamuru Canal Command Area, Guntur (Dist), Andhra Pradesh, India","https:\u002F\u002Fdoi.org\u002F10.9734\u002Fjeai\u002F2026\u002Fv48i104524","Rice is the predominant crop cultivated in the Kommamuru Canal Command Area of Guntur district, Andhra Pradesh. Rice productivity is strongly influenced by irrigation water availability and climatic conditions. The present study aimed to analyse the spatial and temporal variability of rice productivity using the DSSAT-CERES Rice model integrated with Sentinel-2 remote sensing data during the kharif seasons of 2022, 2023 and 2024. Rice-cultivated areas were mapped using multi-temporal Sentinel-2 imagery, while weather, soil, crop management and cultivar data were used as inputs for DSSAT simulations. The model was calibrated and validated using field observations and yield data collected from representative locations within the command area. Simulated rice yields showed considerable variation among mandals and across years, ranging from 1,560.58 to 4,111.06 kg ha⁻¹. The highest productivity was observed in 2024 due to favourable rainfall distribution, adequate canal water supply and improved crop growth conditions, whereas relatively lower productivity was recorded in 2023 owing to moisture stress and irregular irrigation availability. Spatial yield maps generated through the integration of DSSAT outputs and GIS-based rice maps identified high- and low-productivity zones across the command area. The study demonstrated the usefulness of combining crop simulation modelling and remote sensing techniques for rice yield assessment, irrigation planning, yield forecasting and sustainable water resource management in canal command areas. The study confirmed that the DSSAT-CERES Rice model effectively simulated rice productivity in the Kommamuru Canal Command Area during 2022-2024. Overall, the study provides a reliable framework for sustainable rice production and efficient water management in canal command areas and can be applied for future agricultural planning and decision-making. The validation results showed low percentage deviation values ranging from 0.94% to 4.39%, indicating good agreement between simulated and actual farmer yields. Low percentage deviation values between simulated and actual yields indicated good model accuracy and reliability for yield prediction. The integration of DSSAT, GIS and remote sensing techniques was useful for sustainable rice production planning and efficient irrigation management.","水稻是安得拉邦贡土尔县科马穆鲁灌区种植的主要作物。水稻生产力受灌溉可用水量和气候条件的强烈影响。本研究旨在利用DSSAT-CERES水稻模型结合Sentinel-2遥感数据，分析2022年、2023年和2024年kharif季水稻生产力的时空变异性。利用多时相Sentinel-2影像绘制水稻种植区，同时将气象、土壤、作物管理和品种数据作为DSSAT模拟的输入。利用从灌区内代表性地点收集的田间观测数据和产量数据对模型进行校准和验证。模拟水稻产量在不同mandal和年份间表现出相当大的变异，范围为1,560.58至4,111.06 kg ha⁻¹。2024年由于有利的降雨分布、充足的渠水供应和改善的作物生长条件，生产力最高；而2023年由于水分胁迫和不规律的灌溉可用性，生产力相对较低。通过整合DSSAT输出和基于GIS的水稻分布图生成的空间产量图，识别出灌区内的高产区和低产区。研究表明，将作物模拟模型与遥感技术相结合，对于灌区水稻产量评估、灌溉规划、产量预测和可持续水资源管理具有实用价值。研究证实，DSSAT-CERES水稻模型有效模拟了2022-2024年科马穆鲁灌区的水稻生产力。总体而言，本研究为灌区可持续水稻生产和高效水资源管理提供了可靠的框架，可应用于未来的农业规划和决策。验证结果显示，百分比偏差值较低，范围为0.94%至4.39%，表明模拟产量与实际农民产量之间具有良好的一致性。模拟产量与实际产量之间较低的百分比偏差值表明模型在产量预测方面具有良好的准确性和可靠性。DSSAT、GIS和遥感技术的整合有助于可持续水稻生产规划和高效灌溉管理。","Journal of Experimental Agriculture International","2026-09-22T00:00:00Z",72,{"impact":75,"substance":76,"depth":77,"authority":19,"freshness":13,"relevant":21,"comment":237},"印度区域尺度的DSSAT与Sentinel-2融合估产研究，方法成熟、验证可靠，对遥感估产与灌溉管理有参考价值，但属区域性案例，公共影响有限。",[239],{"name":233,"url":230},[26,241,242,243,244],"产量预测","遥感","作物模型","灌溉管理",{"code":52,"slug":178,"name":26,"path":179,"parent_code":180},[247,248],{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},{"code":249,"slug":250,"name":251,"path":252,"parent_code":92},"I3","remote-sensing","遥感与农情监测","\u002Ftopic\u002Fdigital-agriculture\u002Fremote-sensing",{"status":39,"locked":14,"version":40,"method":41,"evidence":254},{"candidates":255,"agricultural_evidence":46},[256,260,266,271,278,284,290],{"code":52,"score":107,"supported":46,"title":257,"abstract":258,"tags":259},[178],[26,178],[26],{"code":32,"score":13,"supported":46,"title":261,"abstract":262,"tags":265},[],[49,263,33,264],"水资源","water resource",[244],{"code":249,"score":78,"supported":46,"title":267,"abstract":268,"tags":270},[],[242,269],"remote sensing",[241,242],{"code":272,"score":20,"supported":46,"title":273,"abstract":274,"tags":277},"H2",[],[275,276],"土壤","soil",[],{"code":279,"score":45,"supported":46,"title":280,"abstract":281,"tags":283},"I4",[],[282],"GIS",[],{"code":285,"score":45,"supported":46,"title":286,"abstract":287,"tags":289},"J1",[],[288],"农业规划",[],{"code":88,"score":21,"supported":14,"title":291,"abstract":292,"tags":293},[],[],[243],[295,296],"DSSAT CERES Rice 水稻","Sentinel-2 水稻 遥感估产","DSSATCERESRice水稻-3168","10.9734\u002Fjeai\u002F2026\u002Fv48i104524",{"doi":298,"openalex_id":300,"authors":301,"venue":233,"cited_by_count":60,"oa_url":230,"card":312,"direction":316,"ingested_from":157},"W7213966772",[302,304,306,308,310],{"name":303,"orcid":8},"Rana Prathap",{"name":305,"orcid":8},"G. Ravi Babu",{"name":307,"orcid":8},"V. Muthayya Chowdary",{"name":309,"orcid":8},"K.Krupavathi",{"name":311,"orcid":8},"K. Chandrasekhar",{"tldr":313,"method":314,"finding":315,"direction":316,"opportunity":317},"用DSSAT-CERES水稻模型结合Sentinel-2遥感，分析印度Guntur灌区2022-20","DSSAT-CERES水稻模型、Sentinel-2多时相影像、GIS空间制图与","模拟产量1560-4111 kg\u002Fha，2024年最高、2023年因水分胁迫最低，验证偏差仅0.94","农业遥感与作物表型","可引入机器学习同化遥感与作物模型，提升灌区尺度产量预报精度并支撑灌溉决策。","2026-09-22T23:30:22.711640Z",{"id":320,"title":321,"url":322,"summary":323,"summary_zh":324,"content":8,"source_name":325,"source_url":322,"published_at":326,"category":72,"cover_url":8,"hotness":13,"is_selected":46,"score":327,"score_detail":328,"sources":333,"tags":335,"primary_topic":339,"secondary_topics":340,"classification":348,"search_phrases":387,"slug":390,"view_count":373,"doi":391,"paper":392,"created_at":435},2912,"Spatial optimization of water-saving irrigation in Chinese rice paddies: Balancing yield, greenhouse gases, and cost using NSGA-II","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.agsy.2026.104976","CONTEXT Optimizing the spatial allocation of water-saving irrigation (WSI) promotion is critical for balancing rice production, greenhouse gas (GHG) mitigation, and economic costs, yet remains challenging at a national scale due to computational intractability. OBJECTIVE This study aims to develop a spatially explicit optimization framework to identify WSI promotion pathways across China's rice paddies that simultaneously maximize yield gain, maximize GHG reduction, and minimize implementation cost. METHODS We coupled K-means clustering with a multi-objective evolutionary algorithm (NSGA-II). Based on machine-learning predicted yield and GHG emissions for 157,417 flooded irrigation grids, we first clustered these grids into 500 environmentally and agronomically homogeneous groups. We then formulated a continuous optimization problem with cluster-level conversion rates as decision variables, simultaneously maximizing national yield gain, maximizing GHG reduction, and minimizing implementation cost. RESULTS AND CONCLUSIONS The Pareto front comprised 100 non-dominated solutions spanning promotion rates from 61.8% to 80.3%. The optimal solution, selected by normalized scoring, achieved 6.47 Mt. yield gain and 63.5 Mt. CO 2 e GHG reduction at a cost of 10.14 billion CNY, corresponding to a national promotion rate of 80.3%. Cluster-scale conversion rates exhibited significant spatial heterogeneity and positive correlation with cluster size ( r = 0.23), revealing economies of scale in WSI promotion. Compared with a random promotion strategy at 90% adoption, our optimized solution delivered 74% higher yield gain with 9.7 percentage points lower promotion effort while achieving comparable GHG reduction. SIGNIFICANCE Our framework provides a spatially explicit decision-support tool for precision agricultural policy, demonstrating that smart spatial allocation can substantially enhance the efficiency of limited resources in scaling climate-smart agricultural practices.","背景 优化节水灌溉（WSI）推广的空间配置对于平衡水稻生产、温室气体（GHG）减排和经济成本至关重要，但由于计算上的不可处理性，在全国尺度上仍具挑战性。目的 本研究旨在开发一个空间显式优化框架，以识别中国稻田的WSI推广路径，同时最大化产量增益、最大化GHG减排并最小化实施成本。方法 我们将K-means聚类与多目标进化算法（NSGA-II）相结合。基于机器学习预测的157,417个淹水灌溉网格的产量和GHG排放，我们首先将这些网格聚类为500个在环境和农艺上同质的组。然后，我们构建了一个以组级转换率为决策变量的连续优化问题，同时最大化全国产量增益、最大化GHG减排并最小化实施成本。结果与结论 Pareto前沿包含100个非支配解，推广率从61.8%到80.3%不等。通过归一化评分选出的最优解实现了6.47 Mt的产量增益和63.5 Mt CO₂e的GHG减排，成本为101.4亿元人民币，对应全国推广率为80.3%。组尺度转换率表现出显著的空间异质性，并与组规模呈正相关（r = 0.23），揭示了WSI推广中的规模经济。与90%采纳率的随机推广策略相比，我们的优化方案在推广力度低9.7个百分点的情况下实现了高出74%的产量增益，同时实现了相当的GHG减排。意义 我们的框架为精准农业政策提供了一个空间显式的决策支持工具，表明智能空间配置可以显著提高有限资源在推广气候智慧型农业实践中的效率。","Agricultural Systems","2026-09-18T00:00:00Z",89,{"impact":329,"substance":169,"depth":330,"authority":18,"freshness":331,"relevant":21,"comment":332},24,19,9,"基于NSGA-II的全国稻田节水灌溉空间优化框架，数据规模大、结论具体，对气候智慧型农业政策有决策参考价值。",[334],{"name":325,"url":322},[83,26,336,337,338],"空间优化","节水灌溉","农业减排",{"code":52,"slug":178,"name":26,"path":179,"parent_code":180},[341,342],{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},{"code":343,"slug":344,"name":345,"path":346,"parent_code":347},"B7","protected-horticulture","设施园艺与植物工厂","\u002Ftopic\u002Fhorticulture\u002Fprotected-horticulture","B",{"status":39,"locked":14,"version":40,"method":41,"evidence":349},{"candidates":350,"agricultural_evidence":46},[351,356,360,366,372,378,382],{"code":52,"score":99,"supported":46,"title":352,"abstract":353,"tags":355},[178],[26,354,178],"稻田",[26],{"code":32,"score":107,"supported":46,"title":357,"abstract":358,"tags":359},[33],[49,33],[337],{"code":343,"score":18,"supported":46,"title":361,"abstract":363,"tags":365},[362],"greenhouse",[364,362],"温室",[],{"code":285,"score":20,"supported":46,"title":367,"abstract":368,"tags":371},[],[369,370],"农业政策","agricultural policy",[],{"code":131,"score":373,"supported":46,"title":374,"abstract":375,"tags":377},4,[],[376],"精准农业",[83],{"code":88,"score":45,"supported":46,"title":379,"abstract":380,"tags":381},[],[103],[],{"code":383,"score":21,"supported":14,"title":384,"abstract":385,"tags":386},"H4",[],[],[338],[388,389],"中国稻田 节水灌溉 空间优化","NSGA-II 水稻 温室气体 减排","中国稻田节水灌溉空间优化-2912","10.1016\u002Fj.agsy.2026.104976",{"doi":391,"openalex_id":393,"authors":394,"venue":325,"cited_by_count":60,"oa_url":322,"card":429,"direction":433,"ingested_from":157},"W7213551595",[395,397,400,403,405,407,409,411,414,416,419,422,425,427],{"name":396,"orcid":8},"Qiang Xu",{"name":398,"orcid":399},"Fan Yao","https:\u002F\u002Forcid.org\u002F0000-0002-4393-7296",{"name":401,"orcid":402},"Dan Wei","https:\u002F\u002Forcid.org\u002F0000-0003-4401-567X",{"name":404,"orcid":8},"Hui Gao",{"name":406,"orcid":8},"Min Jiang",{"name":408,"orcid":8},"Wenya Chen",{"name":410,"orcid":8},"Yourui Cao",{"name":412,"orcid":413},"Peng Zhang","https:\u002F\u002Forcid.org\u002F0000-0002-3036-1507",{"name":415,"orcid":8},"A. I. Abdo",{"name":417,"orcid":418},"Liujun Xiao","https:\u002F\u002Forcid.org\u002F0000-0002-1900-1586",{"name":420,"orcid":421},"Hao Liang","https:\u002F\u002Forcid.org\u002F0000-0002-9955-6492",{"name":423,"orcid":424},"Xiaoqing Cui","https:\u002F\u002Forcid.org\u002F0000-0002-1970-5145",{"name":426,"orcid":8},"Xia Liang",{"name":428,"orcid":8},"Huiqing Bai",{"tldr":430,"method":431,"finding":432,"direction":433,"opportunity":434},"构建空间优化框架，为中国稻田节水灌溉推广寻找兼顾产量、温室气体与成本的路径。","耦合K-means聚类与NSGA-II多目标进化算法，基于15.7万网格的机器学","最优方案增产6.47 Mt、减排63.5 Mt CO2e，成本101.4亿元，推广率80.3%，存在","农业绿色发展与碳","可将该空间优化框架扩展到其他气候智慧型农业技术，并耦合农户采纳行为与政策激励。","2026-09-19T23:30:05.508592Z",{"id":437,"title":438,"url":439,"summary":440,"summary_zh":441,"content":8,"source_name":442,"source_url":439,"published_at":443,"category":72,"cover_url":8,"hotness":13,"is_selected":14,"score":73,"score_detail":444,"sources":446,"tags":448,"primary_topic":451,"secondary_topics":452,"classification":454,"search_phrases":474,"slug":477,"view_count":60,"doi":478,"paper":479,"created_at":491},5591,"Hierarchical Conformal Risk Control for Artificial Intelligence Agriculture Irrigation Scheduling Under Unmodeled Infiltration: A Computer Safety-Guarantee Evaluation","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23543665","Irrigation scheduling algorithms that rely on soil-moisture forecasts are vulnerable to unmodeled infiltration, the process by which water bypasses the root zone through preferential pathways that resistance-based soil models cannot represent. The framework is evaluated through a replication-based design study that characterises the operating characteristics of the before-after-control-impact estimator used to audit scheduler performance, under a declared variance structure with between-cluster standard deviation 6.0, residual standard deviation 4.5 and intraclass correlation 0.64. Power was estimated across 2000 design cells spanning cluster counts of 8, 16, 24 and 32 and effect sizes of 3, 5 and 8 percentage points. The analysis indicates that 54 clusters are required to detect a 5-percentage-point effect at 80% power, and that the minimum detectable effect declines steeply as cluster count rises from 8 to 32. The contribution is a formal safety guarantee for irrigation decision support that remains valid when the infiltration model is wrong, together with an audit design that makes the guarantee empirically checkable.","依赖土壤湿度预报的灌溉调度算法容易受到未建模入渗的影响，即水分通过优先路径绕过根区的过程，而基于阻力的土壤模型无法表征这一过程。该框架通过一项基于重复的设计研究进行评估，该研究刻画了用于审计调度器性能的前后对照影响估计量的运行特性，其所依据的声明方差结构为：组间标准差6.0、残差标准差4.5、组内相关系数0.64。功效估计覆盖2000个设计单元，涵盖聚类数8、16、24和32以及效应量3、5和8个百分点。分析表明，在80%功效下检测5个百分点效应需要54个聚类，且最小可检测效应随聚类数从8增至32而急剧下降。本文的贡献在于为灌溉决策支持提供了一种正式的安全保证，该保证在入渗模型错误时仍然有效，同时提出了一种使该保证可经实证检验的审计设计。","Zenodo (CERN European Organization for Nuclear Research)","2026-10-21T00:00:00Z",{"impact":78,"substance":168,"depth":99,"authority":75,"freshness":331,"relevant":21,"comment":445},"该研究提出在入渗模型失配条件下仍有效的灌溉决策安全保证框架，并给出可审计的试验设计，方法新颖、结论可靠，但属细分方法学研究，产业影响有限，适合作为专业精选而非头条。",[447],{"name":442,"url":439},[83,84,86,449,450],"安全保证","试验设计",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[453],{"code":88,"slug":89,"name":90,"path":91,"parent_code":92},{"status":39,"locked":14,"version":40,"method":41,"evidence":455},{"candidates":456,"agricultural_evidence":46},[457,461,466,470],{"code":32,"score":107,"supported":46,"title":458,"abstract":459,"tags":460},[33],[49,33],[86],{"code":88,"score":75,"supported":46,"title":462,"abstract":464,"tags":465},[463],"artificial intelligence",[104],[84],{"code":272,"score":20,"supported":46,"title":467,"abstract":468,"tags":469},[],[275,276],[],{"code":131,"score":21,"supported":14,"title":471,"abstract":472,"tags":473},[],[],[83],[475,476],"灌溉调度 安全保证","农业人工智能 安全保证 智慧农业 灌溉决策","灌溉调度安全保证-5591","10.5281\u002Fzenodo.23543665",{"doi":478,"openalex_id":480,"authors":481,"venue":442,"cited_by_count":60,"oa_url":439,"card":486,"direction":156,"ingested_from":157},"W7223131205",[482,484],{"name":483,"orcid":8},"Nassima Benkhelifa",{"name":485,"orcid":8},"Yacine Aït Ahmed",{"tldr":487,"method":488,"finding":489,"direction":156,"opportunity":490},"提出分层保形风险控制，为未建模入渗下的灌溉调度提供安全保证。","分层保形风险控制与基于重复设计的BACI审计，2000个设计单元功效分析。","检测5个百分点效应需54个集群，最小可检测效应随集群数增加陡降。","可将保形风险控制扩展到其他未建模扰动下的农业决策安全保证与审计设计。","2026-10-22T11:21:10.283561Z",{"id":493,"title":494,"url":495,"summary":496,"summary_zh":497,"content":8,"source_name":498,"source_url":495,"published_at":499,"category":72,"cover_url":8,"hotness":13,"is_selected":14,"score":500,"score_detail":501,"sources":503,"tags":505,"primary_topic":511,"secondary_topics":512,"classification":513,"search_phrases":535,"slug":538,"view_count":60,"doi":539,"paper":540,"created_at":555},5575,"Wetland vegetation dynamics and its linkage with climatic, hydrological, and land-use\u002F land cover changes in the Foket floodplain of the Fetam River Watershed, Northwestern Ethiopia","https:\u002F\u002Fdoi.org\u002F10.1007\u002Fs44274-026-01136-x","Timely monitoring of wetland changes is vital for effective conservation and management of the landscape. This study, therefore, examines vegetation dynamics and their climatic, hydrological, and land-use drivers in the Foket floodplain wetland, Upper Blue Nile basin, Ethiopia. The LULC analysis was employed based on 1985, 2002, and 2020 cloud-free Landsat images. The maximum likelihood classification algorithm was applied to classify the images into eight LULC classes. The spatial and temporal dynamics of the floodplain’s surface water were further analyzed using the Global Surface Water Explorer (1984–2020), focusing on water occurrence, seasonality, transitions, and changes in surface-water dynamics. The Normalized Difference Vegetation Index (NDVI) was used to assess the temporal dynamics of wetland vegetation, while annual rainfall, temperature, and evapotranspiration data were used to examine the climatic context of vegetation change. The results reveal that the area coverage of water body and wetland decreased by 63.2% and 29%, respectively, over the study period. In contrast, cultivated land, settlement, and eucalyptus plantation had expanded by 39.8%, 280.6%, and 380%, respectively, at the expense of wetland, woodland, and shrubland. Surface-water dynamics showed a substantial decline in seasonally inundated areas and changes in the spatial distribution and persistence of surface water. This indicates the reduction of the floodplain’s hydrological connectivity. The NDVI analysis also revealed a significant increasing of wetland vegetation over 1985–2020\u002F21. Vegetation growth was very fast during 1985–2000, slowed down between 2001 and 2012, and dropped slightly from 2013 to 2020\u002F21. Analysis of climatic variables showed no major change in annual rainfall or evapotranspiration, whereas temperature exhibited a significant upward trend. The overall findings revealed the association of the floodplain vegetation dynamics with land-use land cover, hydrological, and climatic changes. This indicates that land-use land cover, hydrological, and climatic changes have contributed to the degradation of the floodplain vegetation, highlighting the urgent need for integrated management interventions that regulate agricultural expansion, grazing, and water diversion while maintaining hydrological connectivity and wetland vegetation. Clinical trial number Not applicable (NA).","及时监测湿地变化对于景观的有效保护和管理至关重要。因此，本研究考察了埃塞俄比亚上青尼罗河流域福凯特洪泛平原湿地的植被动态及其气候、水文和土地利用驱动因素。基于1985年、2002年和2020年无云Landsat影像进行土地利用\u002F土地覆盖（LULC）分析，采用最大似然分类算法将影像分为八个LULC类别。进一步利用全球地表水探索器（1984—2020年）分析洪泛平原地表水的时空动态，重点关注水的出现频率、季节性、转换及地表水动态变化。采用归一化差异植被指数（NDVI）评估湿地植被的时间动态，同时利用年降水量、气温和蒸散发数据考察植被变化的气候背景。结果表明，研究期间水体和湿地的面积覆盖率分别下降了63.2%和29%。相比之下，耕地、居民点和桉树种植园分别扩张了39.8%、280.6%和380%，侵占了湿地、林地和灌丛。地表水动态显示季节性淹没区域大幅减少，地表水的空间分布和持续性发生变化，表明洪泛平原水文连通性降低。NDVI分析还揭示1985—2020\u002F21年间湿地植被显著增加。植被生长在1985—2000年间非常迅速，2001—2012年间放缓，2013—2020\u002F21年间略有下降。气候变量分析显示年降水量或蒸散发无重大变化，而气温呈显著上升趋势。总体研究结果揭示了洪泛平原植被动态与土地利用\u002F土地覆盖、水文和气候变化的关联。这表明土地利用\u002F土地覆盖、水文和气候变化共同导致了洪泛平原植被退化，凸显了迫切需要综合管理干预措施，以调控农业扩张、放牧和引水，同时维持水文连通性和湿地植被。临床试验编号：不适用（NA）。","Discover Environment","2026-10-20T00:00:00Z",65,{"impact":78,"substance":76,"depth":17,"authority":75,"freshness":331,"relevant":21,"comment":502},"基于Landsat与NDVI的湿地植被动态实证研究，数据扎实但属区域案例，国际参考价值有限，不宜进入每日精选。",[504],{"name":498,"url":495},[506,507,508,509,510],"NDVI","埃塞俄比亚","土地利用变化","湿地遥感","水文连通性",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[],{"status":39,"locked":14,"version":40,"method":41,"evidence":514},{"candidates":515,"agricultural_evidence":46},[516,522,526,531],{"code":32,"score":20,"supported":46,"title":517,"abstract":518,"tags":521},[],[519,520],"蒸散发","evapotranspiration",[],{"code":184,"score":45,"supported":46,"title":523,"abstract":524,"tags":525},[],[201],[],{"code":527,"score":21,"supported":14,"title":528,"abstract":529,"tags":530},"H6",[],[],[508],{"code":249,"score":21,"supported":14,"title":532,"abstract":533,"tags":534},[],[],[506],[536,537],"土地利用变化 埃塞俄比亚 水文连通性 湿地遥感","土地利用变化 埃塞俄比亚","土地利用变化埃塞俄比亚水文连通性湿地遥感-5575","10.1007\u002Fs44274-026-01136-x",{"doi":539,"openalex_id":541,"authors":542,"venue":498,"cited_by_count":60,"oa_url":549,"card":550,"direction":316,"ingested_from":157},"W7223064056",[543,546],{"name":544,"orcid":545},"Workiyie Worie Assefa","https:\u002F\u002Forcid.org\u002F0000-0002-4029-9022",{"name":547,"orcid":548},"Belachew Getnet Eneyew","https:\u002F\u002Forcid.org\u002F0000-0003-1196-9004","https:\u002F\u002Flink.springer.com\u002Fcontent\u002Fpdf\u002F10.1007\u002Fs44274-026-01136-x.pdf",{"tldr":551,"method":552,"finding":553,"direction":316,"opportunity":554},"分析埃塞俄比亚Foket洪泛湿地植被动态及其气候、水文与土地利用驱动因素。","用Landsat影像做最大似然分类，结合全球地表水数据与NDVI及气候数据分析。","水体与湿地面积大幅减少，耕地、居民点和桉树种植扩张，温度显著上升。","可结合多源遥感与水文连通性指标，量化湿地退化对农业灌溉与乡村生态服务的影响。","2026-10-22T11:20:42.476484Z"]