[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-3920":3,"related-3920":111},{"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,"primary_topic":32,"secondary_topics":38,"classification":44,"search_phrases":88,"slug":91,"view_count":92,"doi":93,"paper":94,"created_at":110},3920,"Automated Leaf Color Chart (LCC)-BasedNitrogen Fertilizer Recommendation UsingPaddy Leaf Image Color Classification","https:\u002F\u002Fdoi.org\u002F10.70818\u002Fijbass.2026.v07i02.0075","The demand for accurate and timely assessment of crop health is high in precision agriculture to support proper nutrient management. In this work, we present an intelligent deep learning-based solution that evaluates the colour of paddy rice leaves to provide real-time, context-sensitive recommendations regarding the addition of nitrogen fertilizers to grow rice sustainably. For optimum nitrogen management and sustainability in the production of rice crops, an accurate assessment of the color of paddy leaves is required. Herein, we present a deep learning-based framework for paddy leaf color classification with the capability of recommending an appropriate amount of nitrogen fertilizer as needed in real-time. In this research, the Paddy Net dataset containing 12,000 augmented rice leaf images will be used for training the neural network used for classifying the rice leaf's color based on the Leaf Color Chart (LCC) system, which consists of LCC levels from 2 to 5. Additionally, several deep learning architectures were trainedand tested, specifically Custom CNNs, VGG16, ResNet50 and EfficientNetB7, to identify which architecture provided the best classification performance of rice leaf color. In terms of the experimental results, it can be concluded that the Custom CNN with a classification accuracy of 97.55% significantly outperforms the transfer learning models, VGG16 (78.89%) and EfficientNetB7 (78.67%). To also improve practicality, multimodal vision-language model LLa MA 3.2-11B Vision is integrated into the system, allowing it to provide real-time, context-based nitrogen fertilizer recommendations based on visual input images. Additionally, the proposed framework takes into account other agronomic factors such as the growth stage of the crop, type of soil, and fertilizer application history. This allows for more accurate and relevant recommendations. The proposed framework allows for precise and objective nitrogen management without the subjective use of visual assessment methods typically used by farmers. Overall, the proposed system for fertilizer application is significant for the development of precision agriculture because it increases the efficiency of the decision-making process, optimizes the use of fertilizer, and increases the practice of sustainable rice cultivation.","在精准农业中，对作物健康状况进行准确且及时评估的需求很高，以支持合理的养分管理。在这项工作中，我们提出了一种基于深度学习的智能解决方案，通过评估水稻叶片的颜色，实时提供与情境相关的氮肥添加建议，以实现水稻的可持续种植。为了实现水稻作物生产中的优化氮管理和可持续性，需要对水稻叶片颜色进行准确评估。在此，我们提出了一个基于深度学习的稻田叶片颜色分类框架，能够根据实时需求推荐适量的氮肥。在本研究中，包含12,000张增强水稻叶片图像的Paddy Net数据集将用于训练神经网络，该网络基于叶色卡（Leaf Color Chart, LCC）系统对水稻叶片颜色进行分类，LCC等级从2到5。此外，我们训练并测试了多种深度学习架构，特别是自定义CNN、VGG16、ResNet50和EfficientNetB7，以确定哪种架构在水稻叶片颜色分类中表现最佳。从实验结果可以得出结论，自定义CNN以97.55%的分类准确率显著优于迁移学习模型VGG16（78.89%）和EfficientNetB7（78.67%）。为提高实用性，系统还集成了多模态视觉语言模型LLaMA 3.2-11B Vision，使其能够基于视觉输入图像提供实时、基于情境的氮肥推荐。此外，所提出的框架还考虑了其他农艺因素，如作物生长阶段、土壤类型和施肥历史，从而提供更准确和相关的建议。该框架实现了精确、客观的氮管理，避免了农民通常采用的主观视觉评估方法。总体而言，所提出的施肥系统对精准农业的发展具有重要意义，因为它提高了决策过程的效率，优化了肥料使用，并促进了可持续水稻种植实践。",null,"International Journal of Business Arts and Scientific Study","2026-09-30T00:00:00Z","论文",10,false,63,{"impact":17,"substance":18,"depth":19,"authority":20,"freshness":21,"relevant":22,"comment":23},12,20,17,6,8,1,"用深度学习与视觉语言模型实现水稻叶色分级与氮肥实时推荐，方法新颖、数据规模可观，但期刊影响力有限，属细分领域技术进展。",[25],{"name":10,"url":6},[27,28,29,30,31],"智慧农业","农业人工智能","精准施肥","水稻","氮肥管理",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},"F3","fertilizers","肥料与水肥一体化","\u002Ftopic\u002Finputs-equipment\u002Ffertilizers","F",[39],{"code":40,"slug":41,"name":30,"path":42,"parent_code":43},"A1","rice","\u002Ftopic\u002Ffield-crops\u002Frice","A",{"status":45,"locked":14,"version":46,"method":47,"evidence":48},"classified","2026-10-22.2","rules",{"candidates":49,"agricultural_evidence":52},[50,60,66,74,81],{"code":33,"score":51,"supported":52,"title":53,"abstract":55,"tags":59},19,true,[54],"fertilizer",[56,57,58,54],"施肥","肥料","养分管理",[31,29],{"code":40,"score":13,"supported":52,"title":61,"abstract":62,"tags":65},[],[30,63,41,64],"稻田","paddy",[30],{"code":67,"score":68,"supported":52,"title":69,"abstract":70,"tags":73},"I1",7,[],[71,72],"精准农业","precision agriculture",[27],{"code":75,"score":68,"supported":52,"title":76,"abstract":77,"tags":80},"I2",[],[78,79],"深度学习","deep learning",[28],{"code":82,"score":20,"supported":52,"title":83,"abstract":84,"tags":87},"H2",[],[85,86],"土壤","soil",[],[89,90],"水稻 叶片颜色 氮肥推荐","Paddy Net 深度学习 叶色卡","水稻叶片颜色氮肥推荐-3920",2,"10.70818\u002Fijbass.2026.v07i02.0075",{"doi":93,"openalex_id":95,"authors":96,"venue":10,"cited_by_count":102,"oa_url":6,"card":103,"direction":107,"ingested_from":109},"W7214974109",[97,99],{"name":98,"orcid":9},"Rusanara Akhter",{"name":100,"orcid":101},"Md Zahidul Islam","https:\u002F\u002Forcid.org\u002F0000-0002-4868-4945",0,{"tldr":104,"method":105,"finding":106,"direction":107,"opportunity":108},"用深度学习对水稻叶片颜色分级，并结合多模态大模型实时推荐氮肥用量。","Paddy Net 1.2万张增强叶片图像，训练Custom CNN、VGG16","Custom CNN分类准确率达97.55%，显著优于VGG16（78.89%）和Efficient","农业人工智能与决策模型","可探索轻量化模型部署到手机端，并结合多源农情数据提升跨品种、跨区域推荐泛化能力。","openalex","2026-10-01T23:30:59.367113Z",{"total":20,"page":22,"page_size":20,"items":112},[113,168,270,339,414,486],{"id":114,"title":115,"url":116,"summary":117,"summary_zh":9,"content":118,"source_name":119,"source_url":9,"published_at":120,"category":121,"cover_url":9,"hotness":13,"is_selected":14,"score":122,"score_detail":123,"sources":129,"tags":131,"primary_topic":136,"secondary_topics":137,"classification":139,"search_phrases":163,"slug":166,"view_count":102,"doi":9,"paper":9,"created_at":167},5288,"赤壁水稻智慧施肥千亩示范片区亩产突破700公斤 化肥减量、耕地地力持续提升","https:\u002F\u002Fnews.cjn.cn\u002Fzjjjdpd\u002Fxn_20064\u002F202610\u002Ft5348946.htm","10月9日湖北省农科院、省农业农村厅测产专家组赴赤壁市赤壁镇九毫村,经严格实测水稻智慧施肥千亩示范片区水稻亩产突破700公斤,片区总面积1154亩;该片区集成应用智慧科学施肥方案,推广绿色肥料、机械侧深施肥、无人机追肥、秸秆还田等先进农业技术,实现粮食稳产增产与农业绿色发展双赢;赤壁市今年水稻总产量预计可达23万吨以上。","10月9日，省农科院、省农业农村厅测产专家组赴赤壁市赤壁镇九毫村，对水稻智慧施肥千亩示范片区开展现场实收测产，经严格实测，片区水稻亩产突破700公斤。\n\n本次实收测产片区总面积1154亩。专家组现场随机选定田块，依次完成水稻脱粒、装袋、称重、籽粒含水率检测等一系列规范流程。\n\n该示范片区集成应用智慧科学施肥方案，推广绿色肥料、机械侧深施肥、无人机追肥、秸秆还田等先进农业技术。技术落地后，农田化肥投入有效减少，农业面源污染得到控制，耕地地力持续提升，实现粮食稳产增产与农业绿色发展双赢，为赤壁市乃至咸宁市秋粮稳产增产打造可复制、可推广的实践样板。\n\n近年来，赤壁市深耕科学施肥推广，以新技术、新产品、新机具“三新”集成推广为抓手，对接省农业科技服务支点建设“五大提质行动”，推动良田、良种、良机、良法深度融合，加快农业关键技术落地。全市水稻常年种植面积稳定在43万亩左右，今年水稻总产量预计可达23万吨以上。（ 见博、王智雨）","长江网(2026-10-14)","2026-10-14T00:00:00Z","报道",57,{"impact":124,"substance":125,"depth":126,"authority":20,"freshness":127,"relevant":22,"comment":128},16,18,13,4,"省级农科院测产验证的智慧施肥千亩示范实收数据，具可复制推广价值，但为地方性报道且已过一周时效。",[130],{"name":119,"url":116},[132,30,133,134,135],"绿色农业","耕地地力","化肥减量","智慧施肥",{"code":40,"slug":41,"name":30,"path":42,"parent_code":43},[138],{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},{"status":45,"locked":14,"version":46,"method":47,"evidence":140},{"candidates":141,"agricultural_evidence":52},[142,147,151,158],{"code":33,"score":143,"supported":52,"title":144,"abstract":145,"tags":146},15,[56],[56,57],[134],{"code":40,"score":17,"supported":52,"title":148,"abstract":149,"tags":150},[30],[30],[30],{"code":152,"score":153,"supported":52,"title":154,"abstract":155,"tags":157},"H5",3,[],[156],"秸秆还田",[],{"code":159,"score":22,"supported":14,"title":160,"abstract":161,"tags":162},"H8",[],[],[132],[164,165],"赤壁 水稻 智慧施肥","九毫村 水稻 测产","赤壁水稻智慧施肥-5288","2026-10-19T00:07:41.890918Z",{"id":169,"title":170,"url":171,"summary":172,"summary_zh":173,"content":9,"source_name":174,"source_url":171,"published_at":175,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":176,"score_detail":177,"sources":180,"tags":182,"primary_topic":187,"secondary_topics":188,"classification":196,"search_phrases":241,"slug":244,"view_count":22,"doi":245,"paper":246,"created_at":269},2295,"Biofilm biofertilizer mitigates water stress in rice: impact on growth, yield, and grain quality","https:\u002F\u002Fdoi.org\u002F10.3389\u002Ffsufs.2026.1819208","Introduction Continuous flooding in paddy ( Oryza sativa L.) cultivation challenges sustainable agriculture and food security amid climate change. Biofilm biofertilizer (BFBF) can improve soil organic matter and nutrient content without compromising yield, but its effect on plant water use and grain quality under restricted irrigation remains untested. This study evaluated BFBF's effect on rice water consumption under progressively limited irrigation. Methods A 3-month pot experiment used wetland (At 314) and dryland (Bg 251) rice varieties under two fertilizer practices, chemical fertilizer (CF, 340 kg NPK ha −1 ) and BFBF (225 kg NPK ha −1 + 2.5 L BFBF ha −1 ), and three water treatments (flooded, 100% field capacity, 65% field capacity), in a three-factor factorial completely randomized design ( n = 3). Total water usage, water use efficiency (WUE), net assimilation rate (NAR), relative growth rate (RGR), yield components, macronutrients (carbohydrates, proteins, lipids), and heavy metal content were recorded; significance was assessed via three-factor ANOVA (variety × fertilizer × water) with Tukey’s HSD test ( p \u003C 0.05). Results Total water use was significantly reduced under BFBF only in the wetland variety (ca. 12% under flooded, 10% at 100% field capacity, and no reduction at 65% field capacity). Grain Cd and Pb fell by 34 and 81%, respectively, under BFBF. Carbohydrate, protein, and lipid contents, Fe and Zn concentrations, and yield components were unaffected by fertilizer practice, varying only by variety and\u002For water treatment. BFBF increased NAR and RGR by ca. 33 and 7%, respectively, across all water treatments. Overall, BFBF matched full-rate CF for yield and nutritional composition while reducing water use and heavy-metal accumulation under dryland, water-limited conditions. Conclusion Collectively, these results position BFBF as a candidate drought-resilience strategy for rice cultivation, reducing water demand and heavy-metal accumulation without compromising grain yield or quality, particularly for dryland, water-limited conditions. Multi-season field trials are needed to confirm these responses at scale.","引言 水稻（Oryza sativa L.）栽培中的持续淹水在气候变化背景下对可持续农业和粮食安全构成挑战。生物膜生物肥料（biofilm biofertilizer，BFBF）能够在不影响产量的前提下提高土壤有机质和养分含量，但其在限制灌溉条件下对植物水分利用和稻米品质的影响尚未得到验证。本研究评估了BFBF在逐步限制灌溉条件下对水稻耗水量的影响。方法 采用为期3个月的盆栽试验，选用湿地品种（At 314）和旱地品种（Bg 251），设置两种施肥方式——化肥（chemical fertilizer，CF，340 kg NPK ha⁻¹）和BFBF（225 kg NPK ha⁻¹ + 2.5 L BFBF ha⁻¹），以及三种水分处理（淹水、100%田间持水量、65%田间持水量），采用三因素析因完全随机设计（n = 3）。记录总用水量、水分利用效率（water use efficiency，WUE）、净同化速率（net assimilation rate，NAR）、相对生长速率（relative growth rate，RGR）、产量构成因素、大量营养素（碳水化合物、蛋白质、脂质）及重金属含量；通过三因素方差分析（品种 × 肥料 × 水分）结合Tukey's HSD检验评估显著性（p \u003C 0.05）。结果 仅在湿地品种中，BFBF显著降低了总用水量（淹水条件下约降低12%，100%田间持水量下约降低10%，65%田间持水量下无降低）。BFBF处理下稻米Cd和Pb分别降低34%和81%。碳水化合物、蛋白质和脂质含量、Fe和Zn浓度及产量构成因素不受施肥方式影响，仅随品种和\u002F或水分处理变化。在所有水分处理下，BFBF使NAR和RGR分别提高约33%和7%。总体而言，BFBF在产量和营养组成方面与全量化肥相当，同时在旱地、水分受限条件下减少了用水量和重金属积累。结论 综合来看，这些结果表明BFBF可作为水稻栽培中应对干旱的候选策略，在不影响籽粒产量或品质的前提下降低水分需求和重金属积累，尤其适用于旱地、水分受限条件。仍需多季田间试验以在规模化条件下验证这些响应。","Frontiers in Sustainable Food Systems","2026-09-11T00:00:00Z",75,{"impact":143,"substance":178,"depth":125,"authority":126,"freshness":21,"relevant":22,"comment":179},21,"盆栽试验证实生物膜菌肥在限水条件下可减水降镉铅且不减产，属有数据支撑的节水抗逆新结论，但仅为单季盆栽研究，产业级影响有限。",[181],{"name":174,"url":171},[30,183,184,185,186],"节水灌溉","抗旱育种","生物膜菌肥","重金属阻控",{"code":40,"slug":41,"name":30,"path":42,"parent_code":43},[189,190],{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},{"code":191,"slug":192,"name":193,"path":194,"parent_code":195},"H7","climate","气候适应与防灾减灾","\u002Ftopic\u002Fenvironment\u002Fclimate","H",{"status":45,"locked":14,"version":46,"method":47,"evidence":197},{"candidates":198,"agricultural_evidence":52},[199,204,209,217,224,231,235],{"code":40,"score":125,"supported":52,"title":200,"abstract":201,"tags":203},[41],[30,202,41,64],"稻米",[30],{"code":33,"score":205,"supported":52,"title":206,"abstract":207,"tags":208},9,[],[56,57,54],[],{"code":191,"score":205,"supported":52,"title":210,"abstract":211,"tags":216},[],[212,213,214,215],"气候变化","干旱","climate change","drought",[],{"code":218,"score":68,"supported":52,"title":219,"abstract":220,"tags":223},"H3",[],[221,222],"灌溉","irrigation",[183],{"code":225,"score":20,"supported":52,"title":226,"abstract":227,"tags":230},"A8",[],[228,229],"粮食安全","food security",[],{"code":82,"score":20,"supported":52,"title":232,"abstract":233,"tags":234},[],[85,86],[],{"code":159,"score":20,"supported":52,"title":236,"abstract":237,"tags":240},[],[238,239],"可持续农业","sustainable agriculture",[],[242,243],"生物膜菌肥 重金属阻控 抗旱育种 节水灌溉","生物膜菌肥 重金属阻控","生物膜菌肥重金属阻控抗旱育种节水灌溉-2295","10.3389\u002Ffsufs.2026.1819208",{"doi":245,"openalex_id":247,"authors":248,"venue":174,"cited_by_count":102,"oa_url":171,"card":263,"direction":267,"ingested_from":109},"W7212303356",[249,251,253,255,258,261],{"name":250,"orcid":9},"Chamudika Gunawardhana",{"name":252,"orcid":9},"Aravindi Epa",{"name":254,"orcid":9},"Sidath Ekanayake",{"name":256,"orcid":257},"Mahesh Premarathna","https:\u002F\u002Forcid.org\u002F0000-0002-6127-3956",{"name":259,"orcid":260},"Gamini Seneviratne","https:\u002F\u002Forcid.org\u002F0000-0003-1562-4097",{"name":262,"orcid":9},"Saman Seneweera",{"tldr":264,"method":265,"finding":266,"direction":267,"opportunity":268},"盆栽试验表明生物膜菌肥可降低水稻耗水与重金属积累，且不减产。","3个月盆栽三因素试验，2品种×2施肥×3水分，测耗水、生长、产量与品质。","菌肥使湿地稻耗水降约12%，籽粒镉铅降34%和81%，产量品质与全量化肥相当。","农业绿色发展与碳","可开展多季田间验证，并探究菌肥节水降镉的微生物机制与区域适配性。","2026-09-13T23:30:07.401817Z",{"id":271,"title":272,"url":273,"summary":274,"summary_zh":275,"content":9,"source_name":174,"source_url":273,"published_at":175,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":276,"score_detail":277,"sources":279,"tags":281,"primary_topic":286,"secondary_topics":287,"classification":289,"search_phrases":309,"slug":312,"view_count":92,"doi":313,"paper":314,"created_at":338},2126,"Reduced potassium fertilization combined with magnesium application improves rice population quality and regulates grain yield and quality","https:\u002F\u002Fdoi.org\u002F10.3389\u002Ffsufs.2026.1921807","Inroduction Sichuan is a major hybrid rice-producing region, where paddy soils commonly suffer from acidification and severe magnesium leaching, resulting in low available-Mg status. Excessive potassium application intensifies K-Mg absorption antagonism and exacerbates magnesium deficiency, while blind potassium reduction accelerates plant senescence and impairs rice yield and quality. Although magnesium participates in photosynthesis and assimilate translocation, little is known about the combined effects of reduced potassium fertilization and magnesium supplementation on rice growth and agronomic performance. Methods A two-year field experiment was conducted to examine rice yield, grain quality, and nutrient uptake under varying potassium-magnesium combinations, aiming to provide fertilization references for green rice production in Sichuan hilly regions. A two-factor split-plot design was employed, with three potassium rates (0, 120, and 180 kg\u002F ha, denoted K0, K1, and K2) as main plots and three magnesium rates (0, 30, and 60 kg\u002Fha, denoted M0, M1, and M2) as sub-plots. Leaf area index, dry matter accumulation, chlorophyll content, yield components, and grain quality traits were assessed in this study. Results The results showed that the K1 treatment significantly improved grain yield, with relatively better comprehensive performance observed under the K1M2 combination. Averaged across 2 years, K1 increased grain yield by 26.55% relative to K0 and exhibited comparable yield to K2. Under K1, the M2 treatment further increased yield by 6.21% relative to M1. Moreover, K1M2 significantly enhanced leaf area index and chlorophyll content, while improving milling and appearance quality and reducing grain chalkiness and amylose content. Discussion These findings offer a theoretical and practical basis for improving rice yield and grain quality and promoting green, high-quality and efficient rice cultivation in the hilly regions of Sichuan.","引言 四川是杂交水稻主产区，稻田土壤普遍存在酸化与镁素淋溶严重的问题，导致土壤有效镁含量偏低。过量施钾会加剧钾镁吸收拮抗，加重镁素缺乏，而盲目减钾则会加速植株衰老，损害水稻产量与品质。尽管镁参与光合作用与同化物转运，但关于减钾配施镁对水稻生长及农艺性状的联合效应尚不清楚。方法 通过两年田间试验，研究不同钾镁配施组合下水稻产量、稻米品质及养分吸收特征，旨在为四川丘陵区水稻绿色生产提供施肥参考。采用两因素裂区设计，以3个钾水平（0、120、180 kg\u002Fha，记为K0、K1、K2）为主区，3个镁水平（0、30、60 kg\u002Fha，记为M0、M1、M2）为裂区。本研究测定了叶面积指数、干物质积累量、叶绿素含量、产量构成因素及稻米品质性状。结果 结果表明，K1处理显著提高籽粒产量，其中K1M2组合综合表现相对较优。两年平均而言，K1较K0使籽粒产量提高26.55%，且产量与K2相当。在K1条件下，M2处理较M1进一步增产6.21%。此外，K1M2显著提高叶面积指数与叶绿素含量，同时改善碾磨品质与外观品质，降低籽粒垩白度与直链淀粉含量。讨论 这些研究结果为提高水稻产量与稻米品质、促进四川丘陵区水稻绿色优质高效栽培提供了理论与实践依据。",76,{"impact":143,"substance":178,"depth":19,"authority":126,"freshness":13,"relevant":22,"comment":278},"两年田间试验数据扎实，为四川丘陵区水稻减钾配镁施肥提供实证参考，但属区域性栽培技术研究，产业影响有限。",[280],{"name":174,"url":273},[30,282,283,284,285],"科学施肥","绿色种植","钾镁配施","四川丘陵",{"code":40,"slug":41,"name":30,"path":42,"parent_code":43},[288],{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},{"status":45,"locked":14,"version":46,"method":47,"evidence":290},{"candidates":291,"agricultural_evidence":52},[292,296,301,305],{"code":40,"score":125,"supported":52,"title":293,"abstract":294,"tags":295},[41],[30,202,63,41,64],[30],{"code":33,"score":143,"supported":52,"title":297,"abstract":299,"tags":300},[298],"fertilization",[56,298],[282],{"code":82,"score":153,"supported":52,"title":302,"abstract":303,"tags":304},[],[85],[],{"code":159,"score":22,"supported":14,"title":306,"abstract":307,"tags":308},[],[],[283],[310,311],"四川丘陵 科学施肥 绿色种植 钾镁配施","四川丘陵 科学施肥","四川丘陵科学施肥绿色种植钾镁配施-2126","10.3389\u002Ffsufs.2026.1921807",{"doi":313,"openalex_id":315,"authors":316,"venue":174,"cited_by_count":102,"oa_url":273,"card":333,"direction":267,"ingested_from":109},"W7212147499",[317,319,321,323,325,327,329,331],{"name":318,"orcid":9},"Jianming Ding",{"name":320,"orcid":9},"Xiaotian Jiang",{"name":322,"orcid":9},"Ran Wang",{"name":324,"orcid":9},"Keyuan Zhang",{"name":326,"orcid":9},"Lubing Jia",{"name":328,"orcid":9},"Yuetong Mo",{"name":330,"orcid":9},"Rongping Zhang",{"name":332,"orcid":9},"Peng Ma",{"tldr":334,"method":335,"finding":336,"direction":267,"opportunity":337},"研究减钾配施镁对四川丘陵水稻产量和品质的影响。","两年田间裂区试验，设3个钾水平和3个镁水平。","减钾至120 kg\u002Fha配施60 kg\u002Fha镁可增产并改善稻米品质。","可探究减钾配镁下土壤-植株镁钾互作机制及适宜区域阈值。","2026-09-11T23:30:07.632874Z",{"id":340,"title":341,"url":342,"summary":343,"summary_zh":344,"content":9,"source_name":345,"source_url":342,"published_at":346,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":347,"score_detail":348,"sources":351,"tags":353,"primary_topic":356,"secondary_topics":357,"classification":364,"search_phrases":394,"slug":397,"view_count":102,"doi":398,"paper":399,"created_at":413},5394,"Rice Yield Prediction Using Multi-Modal Regression Learning with Optimized Ensemble Models","https:\u002F\u002Fdoi.org\u002F10.3390\u002Feng7100572","Accurate rice yield estimation is important for agricultural planning, resource allocation, and food security assessment, but yield depends on interacting climatic, vegetation, remote sensing, seasonal, and crop growth factors. This study presents a Multi-Modal Regression Learning (MMRL) framework for continuous rice yield prediction. The framework integrates rainfall, temperature, humidity, normalized difference vegetation index (NDVI), VH synthetic aperture radar (SAR) backscatter, season, rice cultivation area, and leaf wetness information. Predictor relevance is assessed before model development, and multiple regression learners are trained using a common feature set. Their validation predictions are combined through non-negative ensemble weights constrained to sum to one, thereby producing a single optimized prediction. Experiments were performed on a modeled spatio-temporal agricultural dataset representing Karnataka conditions, with 10,000 observations used for the regression comparison. The proposed MMRL ensemble achieved an R2 of 0.9515, an RMSE of 0.6334 tons\u002Fha, an MAE of 0.5075 tons\u002Fha, and an MAPE of 9.81%, outperforming the evaluated individual regression models. Diagnostic plots further indicated close agreement between predicted and reference yields across most of the evaluated range. The MMRL workflow was also evaluated on a separately reconstructed synthetic dataset generated with fully specified distributions, sampling rules, noise terms, a yield generation equation, and fixed random seeds.","准确的水稻产量估算对农业规划、资源配置和粮食安全评估具有重要意义，但产量取决于气候、植被、遥感、季节和作物生长等多种因素的相互作用。本研究提出了一种用于连续水稻产量预测的多模态回归学习（Multi-Modal Regression Learning，MMRL）框架。该框架整合了降雨量、温度、湿度、归一化植被指数（NDVI）、VH合成孔径雷达（SAR）后向散射、季节、水稻种植面积和叶片湿润信息。在模型开发之前评估预测变量的相关性，并使用共同特征集训练多个回归学习器。其验证预测结果通过约束为和等于1的非负集成权重进行组合，从而生成单一优化预测。实验在代表卡纳塔克邦条件的建模时空农业数据集上进行，使用10,000个观测值进行回归比较。所提出的MMRL集成模型实现了R²为0.9515、RMSE为0.6334吨\u002F公顷、MAE为0.5075吨\u002F公顷、MAPE为9.81%，优于所评估的各个回归模型。诊断图进一步表明，在大多数评估范围内，预测产量与参考产量高度一致。MMRL工作流程还在一个单独重建的合成数据集上进行了评估，该数据集使用完全指定的分布、采样规则、噪声项、产量生成方程和固定随机种子生成。","Eng—Advances in Engineering","2026-10-18T00:00:00Z",78,{"impact":125,"substance":349,"depth":125,"authority":17,"freshness":21,"relevant":22,"comment":350},22,"多模态回归集成方法在水稻估产上取得较高精度，方法新颖、数据规模明确，对农业信息化有参考价值，但属学术论文且数据集为模拟数据，产业影响有限。",[352],{"name":345,"url":342},[27,28,30,354,355],"产量预测","遥感",{"code":40,"slug":41,"name":30,"path":42,"parent_code":43},[358],{"code":359,"slug":360,"name":361,"path":362,"parent_code":363},"I3","remote-sensing","遥感与农情监测","\u002Ftopic\u002Fdigital-agriculture\u002Fremote-sensing","I",{"status":45,"locked":14,"version":46,"method":47,"evidence":365},{"candidates":366,"agricultural_evidence":52},[367,371,376,380,386,390],{"code":40,"score":143,"supported":52,"title":368,"abstract":369,"tags":370},[41],[30,41],[30],{"code":359,"score":21,"supported":52,"title":372,"abstract":373,"tags":375},[],[355,374],"remote sensing",[354,355],{"code":225,"score":20,"supported":52,"title":377,"abstract":378,"tags":379},[],[228,229],[],{"code":381,"score":153,"supported":52,"title":382,"abstract":383,"tags":385},"J1",[],[384],"农业规划",[],{"code":67,"score":22,"supported":14,"title":387,"abstract":388,"tags":389},[],[],[27],{"code":75,"score":22,"supported":14,"title":391,"abstract":392,"tags":393},[],[],[28],[395,396],"水稻 产量预测 多模态","NDVI SAR 水稻估产","水稻产量预测多模态-5394","10.3390\u002Feng7100572",{"doi":398,"openalex_id":400,"authors":401,"venue":345,"cited_by_count":102,"oa_url":342,"card":407,"direction":411,"ingested_from":109},"W7222942064",[402,404],{"name":403,"orcid":9},"Nayana Venkatesh",{"name":405,"orcid":406},"Evangelin Geetha Devaraj","https:\u002F\u002Forcid.org\u002F0000-0002-7253-4314",{"tldr":408,"method":409,"finding":410,"direction":411,"opportunity":412},"构建多模态回归学习框架，融合气候、遥感与作物因子，实现水稻产量连续预测。","融合降雨、温度、NDVI、SAR后向散射等多源特征，用非负权重集成多个回归器。","集成模型R²达0.9515，RMSE为0.6334吨\u002F公顷，优于各单一回归模型。","农业遥感与作物表型","可引入真实田间多时相遥感与深度时序模型，验证合成数据结论在真实产区的泛化性。","2026-10-20T23:30:19.292634Z",{"id":415,"title":416,"url":417,"summary":418,"summary_zh":419,"content":9,"source_name":420,"source_url":417,"published_at":421,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":422,"score_detail":423,"sources":425,"tags":427,"primary_topic":430,"secondary_topics":431,"classification":432,"search_phrases":467,"slug":470,"view_count":102,"doi":471,"paper":472,"created_at":485},5388,"A digital twin framework for proactive disease management in paddy cultivation using spatio-temporal graph neural networks","https:\u002F\u002Fdoi.org\u002F10.1080\u002F20421338.2026.2707951","Rice production is highly affected by disease outbreaks, particularly in Asian agricultural systems, resulting in major yield losses and excessive pesticide usage. This study proposes a digital twin framework for paddy cultivation that integrates predictive disease modelling with real-time crop phenology simulation to support proactive disease management. The framework utilizes historical phenological records, IoT-based microclimatic sensor data, irrigation information, and field management records collected from 150 hectares of paddy fields in Maharashtra, India. A Spatio-Temporal Graph Neural Network (ST-GNN), integrating Graph Convolutional Networks (GCNs) and Long Short-Term Memory (LSTM) networks, is employed to model spatial disease propagation and temporal crop dynamics for predicting blast, brown planthopper, and bacterial leaf blight outbreaks up to 14 days in advance. Experimental results demonstrate 87.3% prediction accuracy, 23.7% reduction in pesticide usage, and 31.2% reduction in crop losses, while outperforming traditional Random Forest and SVM models in F1-score performance. The proposed framework enables real-time decision support for sustainable precision agriculture and optimized resource management.","水稻生产极易受到病害暴发的影响，在亚洲农业体系中尤为突出，造成重大产量损失和农药过度使用。本研究提出一个水稻栽培数字孪生（digital twin）框架，将预测性病害建模与实时作物物候模拟相结合，以支持主动式病害管理。该框架利用从印度马哈拉施特拉邦150公顷稻田采集的历史物候记录、基于物联网的微气候传感器数据、灌溉信息及田间管理记录。采用融合图卷积网络（Graph Convolutional Networks, GCN）与长短期记忆网络（Long Short-Term Memory, LSTM）的时空图神经网络（Spatio-Temporal Graph Neural Network, ST-GNN），对病害空间传播与作物时序动态进行建模，以提前14天预测稻瘟病、褐飞虱和白叶枯病的暴发。实验结果表明，预测准确率达87.3%，农药使用量减少23.7%，作物损失减少31.2%，且在F1分数上优于传统随机森林（Random Forest）和支持向量机（SVM）模型。所提框架可为可持续精准农业和优化资源管理提供实时决策支持。","African Journal of Science Technology Innovation and Development","2026-10-19T00:00:00Z",80,{"impact":125,"substance":349,"depth":125,"authority":126,"freshness":205,"relevant":22,"comment":424},"方法新颖、数据规模明确且量化效果显著，属智慧农业细分领域实质进展，值得进入每日精选。",[426],{"name":420,"url":417},[27,28,30,428,429],"数字孪生","病虫害预警",{"code":40,"slug":41,"name":30,"path":42,"parent_code":43},[],{"status":45,"locked":14,"version":46,"method":47,"evidence":433},{"candidates":434,"agricultural_evidence":52},[435,440,444,451,455,462],{"code":67,"score":51,"supported":52,"title":436,"abstract":438,"tags":439},[437],"digital twin",[71,428,72,437],[428,27],{"code":40,"score":125,"supported":52,"title":441,"abstract":442,"tags":443},[64],[30,63,41,64],[30],{"code":445,"score":20,"supported":52,"title":446,"abstract":447,"tags":450},"F4",[],[448,449],"农药","pesticide",[],{"code":218,"score":20,"supported":52,"title":452,"abstract":453,"tags":454},[],[221,222],[],{"code":456,"score":20,"supported":52,"title":457,"abstract":458,"tags":461},"I5",[],[459,460],"物联网","IoT",[],{"code":75,"score":127,"supported":52,"title":463,"abstract":464,"tags":466},[],[465],"decision support",[28],[468,469],"水稻 病害预测 数字孪生","ST-GNN 水稻 病虫害","水稻病害预测数字孪生-5388","10.1080\u002F20421338.2026.2707951",{"doi":471,"openalex_id":473,"authors":474,"venue":420,"cited_by_count":102,"oa_url":9,"card":479,"direction":484,"ingested_from":109},"W7222969403",[475,477],{"name":476,"orcid":9},"Jyoti Rani",{"name":478,"orcid":9},"Dr.  Narendra S.  Jadhav",{"tldr":480,"method":481,"finding":482,"direction":107,"opportunity":483},"构建水稻数字孪生框架，用时空图神经网络提前14天预测病害。","融合物联网微气候、物候与管理数据，用GCN+LSTM的ST-GNN建模。","预测准确率87.3%，农药减23.7%、损失减31.2%，优于RF与SVM。","可探索多尺度时空图建模与数字孪生闭环决策，并迁移至其他作物与区域。","智慧农业 \u002F 农业物联网","2026-10-20T23:30:12.636299Z",{"id":487,"title":488,"url":489,"summary":490,"summary_zh":491,"content":9,"source_name":492,"source_url":489,"published_at":493,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":422,"score_detail":494,"sources":496,"tags":498,"primary_topic":501,"secondary_topics":502,"classification":507,"search_phrases":524,"slug":527,"view_count":102,"doi":528,"paper":529,"created_at":544},4802,"A Privacy-Preserving Federated Learning Framework for Paddy Leaf Disease Detection Using an Enhanced Pretrained Novel EfficientNet-Lite4 Model","https:\u002F\u002Fdoi.org\u002F10.15832\u002Fankutbd.1837705","The correct and prompt detection of leaf diseases in paddy crops remains essential for protecting agricultural output and yield stability and reducing major losses that occur during severe disease outbreaks. The widespread use of conventional centralized machine learning techniques becomes impractical for real-world agricultural applications, as their effectiveness diminishes under three main conditions: data privacy limitations, delayed transmission of information, along with reduced performance accuracy from non-independent and identically distributed (non-IID) data properties across different agro-climatic regions. This research develops a decentralized diagnostic system which combines Federated Learning with an Enhanced Pretrained Novel EfficientNet-Lite4 model designed for paddy leaf disease classification. The Paddy Doctor dataset served as training material for the system which contained 16,225 RGB images that classified 12 disease types alongside healthy categories. The proposed model reached 98.7% classification accuracy and 98.5% precision and 98.6% F1-score while maintaining a final loss of 0.21 after 100 communication rounds. The system underwent field testing which demonstrated its ability to generate accurate diagnostic results in real time in various working conditions. The study demonstrates how privacy preserving AI-based paddy disease management works in practice and recommends local agricultural institutions to build decentralized learning systems. The suggested system will give farmers direct access to field level decision support and facilitate the creation of sustainable digital pest management systems required to ensure food supply.","正确且及时地检测水稻作物叶片病害，对于保护农业产出和产量稳定、减少病害严重暴发期间发生的重大损失仍然至关重要。传统集中式机器学习技术的广泛使用在现实农业应用中变得不切实际，因为在三种主要条件下其有效性会下降：数据隐私限制、信息传输延迟，以及不同农业气候区域间非独立同分布（non-IID）数据特性导致的性能准确率降低。本研究开发了一种去中心化诊断系统，将联邦学习与一种增强的预训练新型高效网络模型EfficientNet-Lite4相结合，用于水稻叶片病害分类。Paddy Doctor数据集作为该系统的训练材料，包含16,225张RGB图像，涵盖12种病害类型以及健康类别。所提出的模型在100轮通信后达到了98.7%的分类准确率、98.5%的精确率和98.6%的F1分数，同时最终损失保持在0.21。该系统经过实地测试，证明其能够在各种工作条件下实时生成准确的诊断结果。该研究展示了基于隐私保护人工智能的水稻病害管理如何在实践中运作，并建议地方农业机构构建去中心化学习系统。所建议的系统将为农民提供直接的田间决策支持，并促进建立确保粮食供应所需的可持续数字病虫害管理系统。","Tarım Bilimleri Dergisi","2026-10-12T00:00:00Z",{"impact":125,"substance":349,"depth":125,"authority":126,"freshness":205,"relevant":22,"comment":495},"将联邦学习与轻量级EfficientNet-Lite4结合用于水稻叶病识别，兼顾隐私保护与98.7%高精度，对智慧农业落地有参考价值。",[497],{"name":492,"url":489},[27,28,30,499,500],"病虫害识别","联邦学习",{"code":40,"slug":41,"name":30,"path":42,"parent_code":43},[503],{"code":75,"slug":504,"name":505,"path":506,"parent_code":363},"agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai",{"status":45,"locked":14,"version":46,"method":47,"evidence":508},{"candidates":509,"agricultural_evidence":52},[510,514,520],{"code":40,"score":143,"supported":52,"title":511,"abstract":512,"tags":513},[64],[30,64],[30],{"code":75,"score":17,"supported":52,"title":515,"abstract":516,"tags":519},[],[517,518,465],"机器学习","machine learning",[28,499,500],{"code":67,"score":22,"supported":14,"title":521,"abstract":522,"tags":523},[],[],[27],[525,526],"Paddy Doctor 数据集 水稻病害","EfficientNet-Lite4 水稻叶片病害","PaddyDoctor数据集水稻病害-4802","10.15832\u002Fankutbd.1837705",{"doi":528,"openalex_id":530,"authors":531,"venue":492,"cited_by_count":102,"oa_url":538,"card":539,"direction":484,"ingested_from":109},"W7221522859",[532,535],{"name":533,"orcid":534},"B Johnson","https:\u002F\u002Forcid.org\u002F0009-0009-8281-4051",{"name":536,"orcid":537},"Chandrakumar Thangavel","https:\u002F\u002Forcid.org\u002F0000-0002-1186-5988","https:\u002F\u002Fdergipark.org.tr\u002Fen\u002Fdownload\u002Farticle-file\u002F5486058",{"tldr":540,"method":541,"finding":542,"direction":107,"opportunity":543},"提出联邦学习结合改进EfficientNet-Lite4的水稻叶片病害检测框架，兼顾隐私与精度。","联邦学习+预训练EfficientNet-Lite4，用Paddy Doctor","12类病害分类准确率达98.7%，100轮通信后损失0.21，支持实时诊断。","可探索非IID数据下联邦聚合优化与轻量化模型在边缘设备的部署研究。","2026-10-13T23:30:08.809781Z"]