[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-2044":3,"related-2044":119},{"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":23,"tags":25,"primary_topic":32,"secondary_topics":37,"classification":38,"search_phrases":93,"slug":96,"view_count":97,"doi":98,"paper":99,"created_at":118},2044,"Climate-Smart Rice Production through Integrated Water and Carbon Management: Methane Mitigation, Biochar and Yield Resilience","https:\u002F\u002Fdoi.org\u002F10.9734\u002Farja\u002F2026\u002Fv19i4912","Rice production occupies a difficult position in climate-smart agriculture because flooded paddy soils support high and stable yields yet create conditions favourable to methane formation, consume substantial irrigation water, and can alter the availability of potentially toxic elements in grain. This critical narrative review evaluates whether methane mitigation, water management, biochar amendment and yield resilience can be integrated into a coherent management strategy rather than treated as separate objectives. Literature published from 2000 to 3 July 2026 was considered, with earlier foundational evidence retained selectively where necessary. The strongest and most consistent evidence supports non-continuous flooding, particularly well-managed alternate wetting and drying (AWD), as the principal near-term field lever for lowering methane emissions and irrigation demand. Across recent meta-analyses, methane reductions are substantial, but nitrous oxide commonly increases, and yield responses depend strongly on drying severity, timing, soil properties, nitrogen supply and cultivar. Mild AWD is therefore better supported than severe drying as a production-compatible mitigation practice. Biochar can improve rice yield, nitrogen-use efficiency and soil carbon status while moderating greenhouse-gas emissions, but average methane mitigation is less consistent than that achieved through water management and is highly contingent on feedstock, pyrolysis conditions, application rate, soil properties and mineral nitrogen input. Direct factorial evidence combining AWD and biochar is still limited, although several multi-year field studies indicate that biochar can partly buffer nutrient losses, contaminant trade-offs and physiological constraints associated with soil drying. Evidence that AWD itself increases yield resilience to drought or heat is mechanistically plausible but remains cultivar- and experiment-specific; it should not yet be equated with proven long-term yield stability under climate extremes. The synthesis supports a hierarchical strategy in which water regime is the primary control, biochar and nitrogen management are context-dependent modifiers, and cultivar choice provides a resilience layer. Future progress requires multi-site factorial trials, explicit life-cycle accounting, multi-contaminant grain-safety assessment and measurement frameworks that verify water status, greenhouse gases and yield stability together.","水稻生产在气候智慧型农业中处于两难境地：淹水稻田土壤虽能支撑高产稳产，却为甲烷生成创造了有利条件，消耗大量灌溉用水，并可能改变籽粒中潜在有毒元素的生物有效性。本篇批判性叙事综述评估了甲烷减排、水分管理、生物炭施用与产量韧性能否整合为协调一致的管理策略，而非被当作彼此独立的目标。文献检索范围涵盖2000年至2026年7月3日发表的文献，必要时选择性保留了更早的基础性证据。最强且最一致的证据支持非连续淹水，尤其是管理良好的干湿交替（AWD），作为近期降低甲烷排放和灌溉需求的主要田间调控手段。近期多项荟萃分析显示，甲烷减排幅度可观，但氧化亚氮排放通常增加，且产量响应在很大程度上取决于晒田强度、时机、土壤性质、氮素供应和品种。因此，轻度AWD比重度晒田更适合作为与生产兼容的减排措施。生物炭可提高水稻产量、氮素利用效率和土壤碳储量，同时调节温室气体排放，但其平均甲烷减排效果不如水分管理稳定，且高度依赖于原料、热解条件、施用量、土壤性质和矿质氮投入。将AWD与生物炭相结合的直接析因证据仍然有限，尽管若干多年田间研究表明，生物炭可部分缓冲与土壤干燥相关的养分损失、污染物权衡和生理限制。AWD本身能否提高水稻对干旱或高温的产量韧性，其机制虽具合理性，但仍因品种和试验条件而异；目前尚不能将其等同于在气候极端条件下已获验证的长期产量稳定性。本综述支持一种分层策略，即以水分 regime 为首要调控手段，生物炭和氮素管理为情境依赖的调节因子，品种选择则提供韧性层。未来进展需要多地点析因试验、明确的生命周期核算、多污染物籽粒安全评估，以及能够同步验证水分状态、温室气体和产量稳定性的测量框架。",null,"Asian Research Journal of Agriculture","2026-09-09T00:00:00Z","论文",10,false,79,{"impact":17,"substance":18,"depth":17,"authority":19,"freshness":20,"relevant":21,"comment":22},18,22,13,8,1,"系统综述整合水分管理与生物炭的稻田甲烷减排路径，结论可靠但属学术综述，对产业实践有中长期参考价值。",[24],{"name":10,"url":6},[26,27,28,29,30,31],"智慧农业","水稻","生物炭","气候变化","节水灌溉","甲烷减排",{"code":33,"slug":34,"name":27,"path":35,"parent_code":36},"A1","rice","\u002Ftopic\u002Ffield-crops\u002Frice","A",[],{"status":39,"locked":14,"version":40,"method":41,"evidence":42},"classified","2026-10-22.2","rules",{"candidates":43,"agricultural_evidence":45},[44,51,59,66,73,81,87],{"code":33,"score":17,"supported":45,"title":46,"abstract":47,"tags":50},true,[34],[27,48,34,49],"稻田","paddy",[27],{"code":52,"score":53,"supported":45,"title":54,"abstract":55,"tags":58},"H2",7,[],[56,57],"土壤","soil",[28],{"code":60,"score":53,"supported":45,"title":61,"abstract":62,"tags":65},"H3",[],[63,64],"灌溉","irrigation",[30],{"code":67,"score":53,"supported":45,"title":68,"abstract":69,"tags":72},"H7",[],[70,71],"干旱","drought",[29],{"code":74,"score":75,"supported":45,"title":76,"abstract":77,"tags":80},"B7",6,[],[78,79],"温室","greenhouse",[],{"code":82,"score":83,"supported":45,"title":84,"abstract":85,"tags":86},"H4",4,[],[31],[31],{"code":88,"score":83,"supported":45,"title":89,"abstract":90,"tags":92},"I1",[],[91],"smart agriculture",[26],[94,95],"智慧农业 气候变化 甲烷减排 节水灌溉","智慧农业 气候变化","智慧农业气候变化甲烷减排节水灌溉-2044",3,"10.9734\u002Farja\u002F2026\u002Fv19i4912",{"doi":98,"openalex_id":100,"authors":101,"venue":10,"cited_by_count":109,"oa_url":6,"card":110,"direction":116,"ingested_from":117},"W7212070936",[102,105,107],{"name":103,"orcid":104},"Abhishek Sinha","https:\u002F\u002Forcid.org\u002F0000-0001-7220-0691",{"name":106,"orcid":9},"Sanchita Sarkar",{"name":108,"orcid":9},"Srinivasa Rao Meesala",0,{"tldr":111,"method":112,"finding":113,"direction":114,"opportunity":115},"综述评估水稻甲烷减排、水分管理、生物炭与产量韧性的整合策略，提出以水分管理为主的分层管理框架。","2000-2026年文献综述，整合meta分析与多年田间试验证据。","适度干湿交替是近期最可靠的减排增产手段，生物炭效果依赖条件，二者联合证据有限。","农业绿色发展与碳","亟需多点多因素试验，将水分、生物炭、氮肥与品种整合，并同步验证温室气体、产量稳定性和籽粒安全。","智慧农业 \u002F 农业物联网","openalex","2026-09-10T23:30:09.553677Z",{"total":75,"page":21,"page_size":75,"items":120},[121,188,302,379,451,509],{"id":122,"title":123,"url":124,"summary":125,"summary_zh":126,"content":9,"source_name":127,"source_url":124,"published_at":128,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":129,"score_detail":130,"sources":134,"tags":136,"primary_topic":139,"secondary_topics":140,"classification":146,"search_phrases":169,"slug":172,"view_count":97,"doi":173,"paper":174,"created_at":187},2920,"Breeding rice for optimal maturity across diverse sowing windows under future climate change scenarios in Chongqing area","https:\u002F\u002Fdoi.org\u002F10.3389\u002Ffsufs.2026.1899019","Introduction It is of great significance to optimize rice cultivars for different sowing dates under future climate change for rice sustainable production in Chongqing. Methods In this study, using the APSIM-Rice model and Coupled Model Intercomparison Project Phase 6 (CMIP6) Shared Socioeconomic Pathways (SSP) scenarios, we investigated the changes of yield, water consumption and water use efficiency (WUE) across six sowing dates and three cultivars (early, normal and late-maturing cultivars) under baseline period (1981 – 2010) and future climate 2scenarios (2031-2100, SSP2-4.5 and SSP5-8.5). In this study, the climate model BCC-CSM2-MR was selected due to its reliable simulation of China’s climate and compatibility with the APSIM-Rice model. Results Results showed that rice yield with normal cultivar in the baseline period peaked on March 30, with the value of 6,310 kg ha− −1 , and reached its minimum on March 1, with the value of 4,580 kg ha− −1 . Water consumption during the rice growing period increased with the delayed sowing dates (212 mm on March 1 to 276 mm on April 20). The response trend of water use efficiency (WUE) to different sowing dates was identical to that of yield, with the maximum WUE of 23.30 kg ha− −1 mm −1 achieved when sown on March 30. Under future SSP2-4.5 and SSP5-8.5 scenarios, early sowing (March 1–20) consistently enhanced yield and WUE for normal cultivars (maximum increments were 25.40% and 29.00% for yield and WUE), while late sowing (March 30–April 20) caused severe losses (up to 26.90% and 34.60% for yield and WUE for April 10 under SSP5-8.5 in the 2060s), with water consumption rising across all sowing dates. Early-maturing cultivars reduced yield (10.60%–44.60%) and WUE (7.70%–43.90%) across all sowing dates under future scenarios, whereas late-maturing cultivars synergized with early sowing to boost yield (up to 25.62%) and WUE (up to 32.85%) but exacerbated losses for late sowing, with water consumption increasing significantly (up to 56.30% under SSP5-8.5 in the 2060s). Discussion These findings provide critical scientific support for optimizing sowing date and cultivar combinations, thereby enhancing the climate resilience and sustainability of rice production in Chongqing and similar subtropical monsoon regions. However, in the future, more climate models, extreme climate impacts, and agronomic factors should be considered","引言 优化不同播期下的水稻品种对重庆未来气候变化背景下的水稻可持续生产具有重要意义。方法 本研究利用APSIM-Rice模型和耦合模式比较计划第六阶段（CMIP6）共享社会经济路径（SSP）情景，研究了基准期（1981—2010年）和未来气候情景（2031—2100年，SSP2-4.5和SSP5-8.5）下6个播期和3个品种（早熟、中熟和晚熟品种）的产量、耗水量和水分利用效率（WUE）变化。本研究选择气候模式BCC-CSM2-MR，因其对中国气候的模拟可靠且与APSIM-Rice模型兼容。结果 结果表明，基准期中熟品种水稻产量在3月30日达到峰值，为6 310 kg ha⁻¹，在3月1日降至最低，为4 580 kg ha⁻¹。水稻生育期耗水量随播期推迟而增加（3月1日的212 mm增至4月20日的276 mm）。水分利用效率（WUE）对不同播期的响应趋势与产量一致，3月30日播种时WUE最高，为23.30 kg ha⁻¹ mm⁻¹。在未来SSP2-4.5和SSP5-8.5情景下，早播（3月1—20日）持续提高中熟品种的产量和WUE（产量和WUE的最大增幅分别为25.40%和29.00%），而晚播（3月30日—4月20日）造成严重损失（在2060年代SSP5-8.5情景下，4月10日播种的产量和WUE损失分别高达26.90%和34.60%），且所有播期的耗水量均增加。在未来情景下，早熟品种在所有播期均降低产量（10.60%—44.60%）和WUE（7.70%—43.90%），而晚熟品种与早播协同提高产量（最高25.62%）和WUE（最高32.85%），但加剧了晚播的损失，耗水量显著增加（在2060年代SSP5-8.5情景下最高达56.30%）。讨论 这些发现为优化播期和品种组合提供了关键科学支撑，从而增强重庆及类似亚热带季风区水稻生产的气候韧性和可持续性。然而，未来应考虑更多气候模式、极端气候影响和农艺因素。","Frontiers in Sustainable Food Systems","2026-09-18T00:00:00Z",78,{"impact":131,"substance":18,"depth":17,"authority":19,"freshness":132,"relevant":21,"comment":133},16,9,"基于APSIM-Rice与CMIP6情景模拟重庆水稻播期与品种组合，数据扎实、结论对区域气候适应性育种有参考价值，但属细分领域研究，影响力有限。",[135],{"name":127,"url":124},[26,27,29,137,138],"品种选育","播期优化",{"code":33,"slug":34,"name":27,"path":35,"parent_code":36},[141],{"code":67,"slug":142,"name":143,"path":144,"parent_code":145},"climate","气候适应与防灾减灾","\u002Ftopic\u002Fenvironment\u002Fclimate","H",{"status":39,"locked":14,"version":40,"method":41,"evidence":147},{"candidates":148,"agricultural_evidence":45},[149,155,160,165],{"code":67,"score":17,"supported":45,"title":150,"abstract":152,"tags":154},[151],"climate change",[29,151,153],"climate resilience",[29],{"code":33,"score":156,"supported":45,"title":157,"abstract":158,"tags":159},15,[34],[27,34],[27],{"code":161,"score":21,"supported":14,"title":162,"abstract":163,"tags":164},"F1",[],[],[137],{"code":88,"score":21,"supported":14,"title":166,"abstract":167,"tags":168},[],[],[26],[170,171],"APSIM-Rice 水稻 播期","重庆 水稻 品种 气候","APSIM-Rice水稻播期-2920","10.3389\u002Ffsufs.2026.1899019",{"doi":173,"openalex_id":175,"authors":176,"venue":127,"cited_by_count":109,"oa_url":124,"card":181,"direction":185,"ingested_from":117},"W7213555399",[177,179],{"name":178,"orcid":9},"Jianzhao Tang",{"name":180,"orcid":9},"Jianping Zhang",{"tldr":182,"method":183,"finding":184,"direction":185,"opportunity":186},"用APSIM-Rice与CMIP6情景模拟重庆不同播期和品种水稻产量、耗水与水分利用效率。","APSIM-Rice模型结合CMIP6 SSP2-4.5\u002FSSP5-8.5情景及","未来早播配晚熟品种可增产提效，晚播则大幅减产，各播期耗水均上升。","农业人工智能与决策模型","可引入多模型集合、极端气候与氮肥管理等农艺因素，优化播期-品种组合的适应策略。","2026-09-19T23:30:08.567885Z",{"id":189,"title":190,"url":191,"summary":192,"summary_zh":193,"content":9,"source_name":194,"source_url":191,"published_at":128,"category":12,"cover_url":9,"hotness":13,"is_selected":45,"score":195,"score_detail":196,"sources":202,"tags":204,"primary_topic":207,"secondary_topics":208,"classification":217,"search_phrases":254,"slug":257,"view_count":83,"doi":258,"paper":259,"created_at":301},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",89,{"impact":197,"substance":198,"depth":199,"authority":200,"freshness":132,"relevant":21,"comment":201},24,23,19,14,"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。",[203],{"name":194,"url":191},[26,27,205,30,206],"空间优化","农业减排",{"code":33,"slug":34,"name":27,"path":35,"parent_code":36},[209,212],{"code":60,"slug":64,"name":210,"path":211,"parent_code":145},"水资源与灌溉","\u002Ftopic\u002Fenvironment\u002Firrigation",{"code":74,"slug":213,"name":214,"path":215,"parent_code":216},"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":218},{"candidates":219,"agricultural_evidence":45},[220,224,228,232,239,244,250],{"code":33,"score":17,"supported":45,"title":221,"abstract":222,"tags":223},[34],[27,48,34],[27],{"code":60,"score":156,"supported":45,"title":225,"abstract":226,"tags":227},[64],[63,64],[30],{"code":74,"score":200,"supported":45,"title":229,"abstract":230,"tags":231},[79],[78,79],[],{"code":233,"score":75,"supported":45,"title":234,"abstract":235,"tags":238},"J1",[],[236,237],"农业政策","agricultural policy",[],{"code":88,"score":83,"supported":45,"title":240,"abstract":241,"tags":243},[],[242],"精准农业",[26],{"code":245,"score":97,"supported":45,"title":246,"abstract":247,"tags":249},"I2",[],[248],"机器学习",[],{"code":82,"score":21,"supported":14,"title":251,"abstract":252,"tags":253},[],[],[206],[255,256],"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":258,"openalex_id":260,"authors":261,"venue":194,"cited_by_count":109,"oa_url":191,"card":296,"direction":114,"ingested_from":117},"W7213551595",[262,264,267,270,272,274,276,278,281,283,286,289,292,294],{"name":263,"orcid":9},"Qiang Xu",{"name":265,"orcid":266},"Fan Yao","https:\u002F\u002Forcid.org\u002F0000-0002-4393-7296",{"name":268,"orcid":269},"Dan Wei","https:\u002F\u002Forcid.org\u002F0000-0003-4401-567X",{"name":271,"orcid":9},"Hui Gao",{"name":273,"orcid":9},"Min Jiang",{"name":275,"orcid":9},"Wenya Chen",{"name":277,"orcid":9},"Yourui Cao",{"name":279,"orcid":280},"Peng Zhang","https:\u002F\u002Forcid.org\u002F0000-0002-3036-1507",{"name":282,"orcid":9},"A. I. Abdo",{"name":284,"orcid":285},"Liujun Xiao","https:\u002F\u002Forcid.org\u002F0000-0002-1900-1586",{"name":287,"orcid":288},"Hao Liang","https:\u002F\u002Forcid.org\u002F0000-0002-9955-6492",{"name":290,"orcid":291},"Xiaoqing Cui","https:\u002F\u002Forcid.org\u002F0000-0002-1970-5145",{"name":293,"orcid":9},"Xia Liang",{"name":295,"orcid":9},"Huiqing Bai",{"tldr":297,"method":298,"finding":299,"direction":114,"opportunity":300},"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","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":303,"title":304,"url":305,"summary":306,"summary_zh":307,"content":9,"source_name":308,"source_url":305,"published_at":309,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":129,"score_detail":310,"sources":313,"tags":315,"primary_topic":319,"secondary_topics":320,"classification":327,"search_phrases":359,"slug":362,"view_count":109,"doi":363,"paper":364,"created_at":378},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",{"impact":17,"substance":18,"depth":17,"authority":311,"freshness":20,"relevant":21,"comment":312},12,"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。",[314],{"name":308,"url":305},[26,316,27,317,318],"农业人工智能","产量预测","遥感",{"code":33,"slug":34,"name":27,"path":35,"parent_code":36},[321],{"code":322,"slug":323,"name":324,"path":325,"parent_code":326},"I3","remote-sensing","遥感与农情监测","\u002Ftopic\u002Fdigital-agriculture\u002Fremote-sensing","I",{"status":39,"locked":14,"version":40,"method":41,"evidence":328},{"candidates":329,"agricultural_evidence":45},[330,334,339,346,351,355],{"code":33,"score":156,"supported":45,"title":331,"abstract":332,"tags":333},[34],[27,34],[27],{"code":322,"score":20,"supported":45,"title":335,"abstract":336,"tags":338},[],[318,337],"remote sensing",[317,318],{"code":340,"score":75,"supported":45,"title":341,"abstract":342,"tags":345},"A8",[],[343,344],"粮食安全","food security",[],{"code":233,"score":97,"supported":45,"title":347,"abstract":348,"tags":350},[],[349],"农业规划",[],{"code":88,"score":21,"supported":14,"title":352,"abstract":353,"tags":354},[],[],[26],{"code":245,"score":21,"supported":14,"title":356,"abstract":357,"tags":358},[],[],[316],[360,361],"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":363,"openalex_id":365,"authors":366,"venue":308,"cited_by_count":109,"oa_url":305,"card":372,"direction":376,"ingested_from":117},"W7222942064",[367,369],{"name":368,"orcid":9},"Nayana Venkatesh",{"name":370,"orcid":371},"Evangelin Geetha Devaraj","https:\u002F\u002Forcid.org\u002F0000-0002-7253-4314",{"tldr":373,"method":374,"finding":375,"direction":376,"opportunity":377},"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":380,"title":381,"url":382,"summary":383,"summary_zh":384,"content":9,"source_name":385,"source_url":382,"published_at":386,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":387,"score_detail":388,"sources":390,"tags":392,"primary_topic":395,"secondary_topics":396,"classification":397,"search_phrases":433,"slug":436,"view_count":109,"doi":437,"paper":438,"created_at":450},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":17,"substance":18,"depth":17,"authority":19,"freshness":132,"relevant":21,"comment":389},"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。",[391],{"name":385,"url":382},[26,316,27,393,394],"数字孪生","病虫害预警",{"code":33,"slug":34,"name":27,"path":35,"parent_code":36},[],{"status":39,"locked":14,"version":40,"method":41,"evidence":398},{"candidates":399,"agricultural_evidence":45},[400,406,410,417,421,428],{"code":88,"score":199,"supported":45,"title":401,"abstract":403,"tags":405},[402],"digital twin",[242,393,404,402],"precision agriculture",[393,26],{"code":33,"score":17,"supported":45,"title":407,"abstract":408,"tags":409},[49],[27,48,34,49],[27],{"code":411,"score":75,"supported":45,"title":412,"abstract":413,"tags":416},"F4",[],[414,415],"农药","pesticide",[],{"code":60,"score":75,"supported":45,"title":418,"abstract":419,"tags":420},[],[63,64],[],{"code":422,"score":75,"supported":45,"title":423,"abstract":424,"tags":427},"I5",[],[425,426],"物联网","IoT",[],{"code":245,"score":83,"supported":45,"title":429,"abstract":430,"tags":432},[],[431],"decision support",[316],[434,435],"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":437,"openalex_id":439,"authors":440,"venue":385,"cited_by_count":109,"oa_url":9,"card":445,"direction":116,"ingested_from":117},"W7222969403",[441,443],{"name":442,"orcid":9},"Jyoti Rani",{"name":444,"orcid":9},"Dr.  Narendra S.  Jadhav",{"tldr":446,"method":447,"finding":448,"direction":185,"opportunity":449},"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。","2026-10-20T23:30:12.636299Z",{"id":452,"title":453,"url":454,"summary":455,"summary_zh":456,"content":9,"source_name":457,"source_url":454,"published_at":458,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":387,"score_detail":459,"sources":461,"tags":463,"primary_topic":466,"secondary_topics":467,"classification":472,"search_phrases":488,"slug":491,"view_count":109,"doi":492,"paper":493,"created_at":508},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":17,"substance":18,"depth":17,"authority":19,"freshness":132,"relevant":21,"comment":460},"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。",[462],{"name":457,"url":454},[26,316,27,464,465],"病虫害识别","联邦学习",{"code":33,"slug":34,"name":27,"path":35,"parent_code":36},[468],{"code":245,"slug":469,"name":470,"path":471,"parent_code":326},"agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai",{"status":39,"locked":14,"version":40,"method":41,"evidence":473},{"candidates":474,"agricultural_evidence":45},[475,479,484],{"code":33,"score":156,"supported":45,"title":476,"abstract":477,"tags":478},[49],[27,49],[27],{"code":245,"score":311,"supported":45,"title":480,"abstract":481,"tags":483},[],[248,482,431],"machine learning",[316,464,465],{"code":88,"score":21,"supported":14,"title":485,"abstract":486,"tags":487},[],[],[26],[489,490],"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":492,"openalex_id":494,"authors":495,"venue":457,"cited_by_count":109,"oa_url":502,"card":503,"direction":116,"ingested_from":117},"W7221522859",[496,499],{"name":497,"orcid":498},"B Johnson","https:\u002F\u002Forcid.org\u002F0009-0009-8281-4051",{"name":500,"orcid":501},"Chandrakumar Thangavel","https:\u002F\u002Forcid.org\u002F0000-0002-1186-5988","https:\u002F\u002Fdergipark.org.tr\u002Fen\u002Fdownload\u002Farticle-file\u002F5486058",{"tldr":504,"method":505,"finding":506,"direction":185,"opportunity":507},"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",{"id":510,"title":511,"url":512,"summary":513,"summary_zh":9,"content":514,"source_name":515,"source_url":9,"published_at":516,"category":517,"cover_url":9,"hotness":13,"is_selected":14,"score":518,"score_detail":519,"sources":521,"tags":523,"primary_topic":527,"secondary_topics":528,"classification":535,"search_phrases":584,"slug":587,"view_count":580,"doi":9,"paper":9,"created_at":588},4529,"给稻田做\"体检\"，开数字化\"处方\"（秋收进行时·田间探新）","https:\u002F\u002Ffinance.people.com.cn\u002Fn1\u002F2026\u002F1009\u002Fc1004-40810929.html","人民日报\"秋收进行时·田间探新\"专栏报道宁波市鄞州区田间数字化变量施肥实践。种粮大户黄佳科依托鄞州区农技推广站变量施肥技术，通过测土、卫星遥感和低空无人机巡田对600余亩水稻精准\"开处方\"，实现底肥减少10%、增产超3%、亩均增收50斤，并带动其由单纯种地拓展到为周边农户提供技术培训和农机售后服务。该报道指出，浙江正以\"数据驱动\"改写传统经验种植，越来越多新农人用变量施肥、无人机巡田、智能灌溉等数字化工具守护粮食安全。文章同时引述鄞州区农技推广站试点示范做法，强调通过降低使用门槛、整合农机服务、形成\"一码通\"数字档案，让农户从会种地到\"慧种地\"。","由于营养供给均衡，空瘪粒有效减少、千粒重增加，亩均还能增收50斤左右。\"而且人还轻松了，时间也省出来了。\"黄佳科说。鄞州区农技推广站在本地开展试验示范，实打实展示科技种田的效果，让更多农户亲眼看到节肥、增产、提质的好处，慢慢接受并用上变量施肥新技术。黄佳科也开展了农机服务业务，从单纯种地拓展到为周边农户提供技术培训和农机售后服务。暮色四合，曾经堆满锄头和草帽的仓库，如今整齐码放着各式智能农机。\"科技让我更懂土地——就像父辈懂节气、看云识天气一样，我们这代人用数据守护粮食安全。\"黄佳科说。《 人民日报 》（ 2026年10月09日 02 版）","《人民日报》2026 年 10 月 09 日 02 版 经济·科技","2026-10-08T23:00:00Z","报道",66,{"impact":200,"substance":156,"depth":200,"authority":156,"freshness":20,"relevant":21,"comment":520},"央媒实地报道变量施肥在鄞州水稻上的节肥增产效果，有农户信源与具体数据，但属地方试验示范，影响层级有限。",[522],{"name":515,"url":512},[524,26,27,525,526],"数字农业","变量施肥","农机服务",{"code":33,"slug":34,"name":27,"path":35,"parent_code":36},[529],{"code":530,"slug":531,"name":532,"path":533,"parent_code":534},"J4","seasonal-agriculture","农时与节庆活动","\u002Ftopic\u002Fpolicy\u002Fseasonal-agriculture","J",{"status":39,"locked":14,"version":40,"method":41,"evidence":536},{"candidates":537,"agricultural_evidence":45},[538,542,548,555,561,565,571,575,579],{"code":33,"score":311,"supported":45,"title":539,"abstract":540,"tags":541},[48],[27],[27],{"code":530,"score":543,"supported":45,"title":544,"abstract":546,"tags":547},11,[545],"秋收",[545],[],{"code":549,"score":75,"supported":45,"title":550,"abstract":551,"tags":554},"G1",[],[552,553],"农技推广","技术培训",[],{"code":556,"score":83,"supported":45,"title":557,"abstract":558,"tags":560},"F3",[],[559],"施肥",[525],{"code":340,"score":97,"supported":45,"title":562,"abstract":563,"tags":564},[],[343],[],{"code":566,"score":97,"supported":45,"title":567,"abstract":568,"tags":570},"F5",[],[569],"农机",[],{"code":60,"score":97,"supported":45,"title":572,"abstract":573,"tags":574},[],[63],[],{"code":322,"score":97,"supported":45,"title":576,"abstract":577,"tags":578},[],[318],[],{"code":88,"score":580,"supported":14,"title":581,"abstract":582,"tags":583},2,[],[],[524,26],[585,586],"鄞州区 变量施肥 水稻","宁波 智慧农业 稻田体检","鄞州区变量施肥水稻-4529","2026-10-10T00:14:53.135917Z"]