[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-2338":3,"related-2338":94},{"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":39,"search_phrases":73,"slug":76,"view_count":22,"doi":77,"paper":78,"created_at":93},2338,"An optimized machine learning approach for reliable agronomic parameter prediction in precision farming systems","https:\u002F\u002Fdoi.org\u002F10.1038\u002Fs41598-026-71592-1","Optimized machine learning models are very important for improving predictive performance in precision agriculture because they let us analyze soil and environmental data in a data-driven way. But conventional predictive methods often can’t be used to make generalizations because agronomic data is often very variable, has nonlinear interactions, and is very different from one another. The study presents an enhanced machine learning-based predictive framework for estimating agricultural parameters utilizing structured numerical soil and environmental datasets. The framework combines systematic data preprocessing, feature selection, and hyperparameter optimization to make models more stable and reliable. The model performance was evaluated using five-fold cross-validation and standard regression metrics, including the Coefficient of Determination (R 2 ), Root Mean Square Error (RMSE), and Mean Absolute Error (MAE). The average R 2 is 0.696 ± 0.148, the RMSE is 5.160 ± 1.571, and the MAE is 4.636 ± 1.545, which shows that the model can make accurate predictions across all validation folds. Further the classification of the growth stages of spinach is done with an accuracy of 84.63% and with the precision of 85% using the proposed Hybrid ensemble model. The results show that the proposed framework works well with nonlinear agricultural data and could be used for data-driven decisions in precision farming systems.","优化的机器学习模型对于提升精准农业中的预测性能至关重要，因为它使我们能够以数据驱动的方式分析土壤和环境数据。然而，传统的预测方法往往无法用于泛化，因为农艺数据通常变异性很大、具有非线性交互作用，且彼此之间差异显著。本研究提出了一种基于增强机器学习的预测框架，利用结构化数值土壤和环境数据集来估算农业参数。该框架结合了系统化的数据预处理、特征选择和超参数优化，使模型更加稳定可靠。采用五折交叉验证和标准回归指标评估模型性能，包括决定系数（R²）、均方根误差（RMSE）和平均绝对误差（MAE）。平均R²为0.696 ± 0.148，RMSE为5.160 ± 1.571，MAE为4.636 ± 1.545，表明该模型在所有验证折中均能做出准确预测。此外，利用所提出的混合集成模型对菠菜生长阶段进行分类，准确率达到84.63%，精确率达到85%。结果表明，所提出的框架能够很好地处理非线性农业数据，可用于精准农业系统中的数据驱动决策。",null,"Scientific Reports","2026-09-12T00:00:00Z","论文",10,false,67,{"impact":17,"substance":18,"depth":19,"authority":20,"freshness":21,"relevant":22,"comment":23},12,18,15,14,8,1,"该论文提出融合预处理、特征选择与超参数优化的机器学习框架，在土壤环境数据上取得R²约0.70的预测表现并以84.63%准确率识别菠菜生长期，方法扎实但属常规模型优化，产业影响有限，可作为智慧农业技术参考。",[25],{"name":10,"url":6},[27,28,29,30,31],"智慧农业","农业人工智能","机器学习","精准农业","土壤数据",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},"I2","agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai","I",[],{"status":40,"locked":14,"version":41,"method":42,"evidence":43},"classified","2026-10-22.2","rules",{"candidates":44,"agricultural_evidence":47},[45,52,58,66],{"code":33,"score":46,"supported":47,"title":48,"abstract":50,"tags":51},16,true,[49],"machine learning",[29,49],[28,29],{"code":53,"score":21,"supported":47,"title":54,"abstract":55,"tags":57},"I1",[],[30,56],"precision agriculture",[27,30],{"code":59,"score":60,"supported":47,"title":61,"abstract":62,"tags":65},"H2",7,[],[63,64],"土壤","soil",[31],{"code":67,"score":68,"supported":47,"title":69,"abstract":70,"tags":72},"I6",3,[],[71],"agricultural data",[],[74,75],"农业人工智能 土壤数据 智慧农业 机器学习","农业人工智能 土壤数据","农业人工智能土壤数据智慧农业机器学习-2338","10.1038\u002Fs41598-026-71592-1",{"doi":77,"openalex_id":79,"authors":80,"venue":10,"cited_by_count":85,"oa_url":6,"card":86,"direction":90,"ingested_from":92},"W7212396250",[81,83],{"name":82,"orcid":9},"T. Suba",{"name":84,"orcid":9},"K. Lakshmi Joshitha",0,{"tldr":87,"method":88,"finding":89,"direction":90,"opportunity":91},"提出优化机器学习框架，用土壤环境数据预测农艺参数并分类菠菜生长阶段。","数据预处理、特征选择、超参数优化，五折交叉验证与混合集成模型。","回归平均R²为0.696，菠菜生长阶段分类准确率达84.63%。","农业人工智能与决策模型","可探索跨作物、跨区域迁移学习与可解释性，提升非线性农艺数据泛化能力。","openalex","2026-09-13T23:30:43.564799Z",{"total":95,"page":22,"page_size":95,"items":96},6,[97,177,231,290,355,418],{"id":98,"title":99,"url":100,"summary":101,"summary_zh":102,"content":9,"source_name":103,"source_url":100,"published_at":104,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":105,"score_detail":106,"sources":110,"tags":112,"primary_topic":114,"secondary_topics":115,"classification":116,"search_phrases":134,"slug":137,"view_count":85,"doi":138,"paper":139,"created_at":176},5306,"A growing challenge: stakeholder perceptions of AI and ML applications in U.S. agriculture","https:\u002F\u002Fdoi.org\u002F10.1007\u002Fs11119-026-10459-x","Abstract Context The global population is expected to exceed ten billion by 2050 and food demand is projected to increase by up to 100% in the same timeframe. Agricultural management must adapt to meet the increasing global demands. Artificial intelligence (AI) and machine learning (ML) technologies can help the agricultural community respond to these needs. Aims An online survey and follow-up interviews were conducted to examine patterns of use, perceptions, and barriers among early adopting stakeholders regarding AI and ML. Methods The online survey with agricultural stakeholders (n=129) included questions regarding the participants’ views on incorporating AI and ML techniques into farming practices and individual follow-up interviews with agricultural stakeholders (n=10) were conducted to better understand their concerns toward technology use and adoption of AI-enabled tools and technologies. Key results Using a mixed-methods approach, four challenges to establishing AI-\u002FML-enabled technology in agriculture were identified. Namely, challenges related to (1) systems of systems (SoS), (2) sub-seasonal to seasonal weather (S2S) forecasts, (3) precision soil management, and (4) policy and economics. Each challenge was discussed in the context of recent literature. Conclusion Concerns were voiced clustered around four broad research themes. This brief communication brings the perspective of agricultural stakeholders to the discussion of the potential of AI\u002FML-enabled technology and the direction of their development in the agricultural sector. Implications Data collected in 2021, establish an important baseline for the early phase of AI\u002FML use in U.S. agriculture, enabling comparison of future perceptions and developments in the sector. Impact This brief communication describes a survey and follow-up interviews conducted with agricultural stakeholders on factors influencing their willingness and reluctance to incorporate AI and ML techniques into farming practices. The findings, summarized and discussed as four key challenges for AI and ML in the agricultural sector, have the potential to streamline research activities.","摘要\n\n背景 预计到2050年全球人口将超过100亿，同期粮食需求预计将增加多达100%。农业管理必须作出调整以满足不断增长的全球需求。人工智能（AI）和机器学习（ML）技术可帮助农业界应对这些需求。\n\n目的 通过开展在线调查和后续访谈，考察早期采用相关技术的利益相关者在AI和ML方面的使用模式、认知及障碍。\n\n方法 针对农业利益相关者（n=129）的在线调查包含有关参与者对将AI和ML技术纳入农业实践看法的问题，并对农业利益相关者（n=10）进行个体后续访谈，以更好地了解他们对技术使用及采用AI赋能工具和技术的顾虑。\n\n主要结果 采用混合方法，识别出在农业中建立AI\u002FML赋能技术面临的四项挑战，即与以下方面相关的挑战：（1）系统之系统（SoS），（2）次季节至季节天气（S2S）预报，（3）精准土壤管理，以及（4）政策与经济。每项挑战均结合近期文献进行了讨论。\n\n结论 所表达的顾虑集中于四个广泛的研究主题。本简报将农业利益相关者的视角引入关于AI\u002FML赋能技术潜力及其在农业部门发展方向讨论中。\n\n意义 2021年收集的数据为美国农业中AI\u002FML应用的早期阶段建立了重要基线，有助于比较该部门未来的认知和发展。\n\n影响 本简报描述了针对农业利益相关者开展的一项调查和后续访谈，内容涉及影响其愿意和不愿将AI和ML技术纳入农业实践的因素。研究结果总结并讨论为农业部门AI和ML的四项关键挑战，有望优化研究活动。","Precision Agriculture","2026-10-18T00:00:00Z",77,{"impact":18,"substance":107,"depth":108,"authority":20,"freshness":21,"relevant":22,"comment":109},20,17,"基于129份问卷与10次访谈的混合方法研究，系统梳理美国农业AI\u002FML应用的四大挑战，为早期采用者认知提供基线数据，对智慧农业研究有参考价值。",[111],{"name":103,"url":100},[27,28,29,30,113],"农户认知",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[],{"status":40,"locked":14,"version":41,"method":42,"evidence":117},{"candidates":118,"agricultural_evidence":47},[119,125,129],{"code":33,"score":120,"supported":47,"title":121,"abstract":122,"tags":124},11,[],[29,49,123],"artificial intelligence",[28,29],{"code":59,"score":95,"supported":47,"title":126,"abstract":127,"tags":128},[],[63,64],[],{"code":53,"score":130,"supported":14,"title":131,"abstract":132,"tags":133},2,[],[],[27,30],[135,136],"美国农业 AI ML 调查","农业人工智能 应用障碍","美国农业AIML调查-5306","10.1007\u002Fs11119-026-10459-x",{"doi":138,"openalex_id":140,"authors":141,"venue":103,"cited_by_count":85,"oa_url":100,"card":171,"direction":90,"ingested_from":92},"W7222866367",[142,145,148,151,154,157,160,163,165,168],{"name":143,"orcid":144},"Jennifer Koch","https:\u002F\u002Forcid.org\u002F0000-0002-7067-2705",{"name":146,"orcid":147},"Andrew Fox","https:\u002F\u002Forcid.org\u002F0000-0001-6719-8902",{"name":149,"orcid":150},"Richa Bhattarai","https:\u002F\u002Forcid.org\u002F0000-0003-3827-7761",{"name":152,"orcid":153},"Hank C. Jenkins‐Smith","https:\u002F\u002Forcid.org\u002F0000-0002-5204-2726",{"name":155,"orcid":156},"Jonathan McFadden","https:\u002F\u002Forcid.org\u002F0000-0003-3762-1428",{"name":158,"orcid":159},"Audrey Reinert","https:\u002F\u002Forcid.org\u002F0000-0001-8951-702X",{"name":161,"orcid":162},"Juan Sesmero","https:\u002F\u002Forcid.org\u002F0000-0002-2669-4536",{"name":164,"orcid":9},"M. Z. Walkup",{"name":166,"orcid":167},"Wolfgang Jentner","https:\u002F\u002Forcid.org\u002F0000-0003-1045-6020",{"name":169,"orcid":170},"David S. Ebert","https:\u002F\u002Forcid.org\u002F0000-0001-6177-1296",{"tldr":172,"method":173,"finding":174,"direction":90,"opportunity":175},"通过问卷与访谈调查美国农业利益相关者对AI\u002FML应用的认知与障碍。","在线问卷129人加10人深度访谈的混合方法。","识别出系统之系统、次季节天气预报、精准土壤管理和政策经济四大挑战。","可针对四类障碍开展分区域、分作物类型的采纳意愿追踪与干预研究。","2026-10-19T23:30:02.345893Z",{"id":178,"title":179,"url":180,"summary":181,"summary_zh":182,"content":9,"source_name":183,"source_url":180,"published_at":184,"category":12,"cover_url":9,"hotness":185,"is_selected":14,"score":186,"score_detail":187,"sources":191,"tags":195,"primary_topic":197,"secondary_topics":198,"classification":199,"search_phrases":215,"slug":218,"view_count":130,"doi":219,"paper":220,"created_at":230},3282,"Design and Implementation of an Ensemble Learning Based Decision Support Model for Crop Selection in Precision Agriculture","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.22895811","Soil composition governs which crop can be grown profitably in a given field, and the relationship between soil variables and crop suitability is nonlinear, interacting and therefore poorly served by heuristic rules. This paper presents SCR-XGB, a five-layer framework that couples a disciplined data-conditioning stage with a regularised gradient-boosted tree ensemble for crop recommendation from soil and climatic parameters. The acquisition layer collects nitrogen, phosphorus and potassium concentration together with temperature, humidity, soil pH and rainfall; the conditioning layer imputes missing values and removes outliers by an interquartile filter; the feature engineering layer derives nutrient ratios, normalises and standardises the numeric fields and encodes the crop label; the ensemble layer fits an additive sequence of regression trees under a regularised objective with shrinkage and column subsampling; and the recommendation layer issues a ranked crop list with per-crop confidence. Four algorithms are specified in full, covering conditioning, feature construction, boosted training and inference, and a complexity analysis is given for each stage. Evaluated on a public corpus of soil and climate records against five baseline learners trained over the identical feature matrix, the proposed framework attains 99.31% accuracy, 100% precision, 99% recall and an F1-score of 99%, ahead of naive Bayes and random forest at 99.09%, support vector machine at 97.95%, logistic regression at 95.22% and a single decision tree at 90.00%. The 9.31 percentage point margin over the single tree, set against the 0.22 point margin over the strongest baseline, quantifies the benefit of boosting and shows where the remaining headroom on this task actually lies.","土壤组成决定了特定田块适宜种植何种作物才能获得经济效益，而土壤变量与作物适宜性之间的关系是非线性的、相互作用的，因此启发式规则难以有效处理这一问题。本文提出SCR-XGB，一个五层框架，将规范化的数据调理阶段与正则化梯度提升树集成相结合，用于基于土壤和气候参数的作物推荐。采集层收集氮、磷、钾浓度以及温度、湿度、土壤pH值和降雨量；调理层通过四分位距滤波器插补缺失值并剔除异常值；特征工程层推导养分比率，对数值字段进行归一化和标准化，并对作物标签进行编码；集成层在带有收缩和列子采样的正则化目标函数下拟合加性回归树序列；推荐层输出带有每种作物置信度的排序作物列表。本文完整给出了四种算法，涵盖调理、特征构建、提升训练和推理，并对每个阶段进行了复杂度分析。在公开的土壤和气候记录语料库上，与在相同特征矩阵上训练的五个基线学习器进行对比评估，所提框架达到了99.31%的准确率、100%的精确率、99%的召回率和99%的F1分数，优于朴素贝叶斯和随机森林的99.09%、支持向量机的97.95%、逻辑回归的95.22%以及单棵决策树的90.00%。相较于单棵决策树9.31个百分点的优势，与相较于最强基线0.22个百分点的优势相比，量化了提升方法的收益，并揭示了该任务上剩余提升空间的实际所在。","Zenodo (CERN European Organization for Nuclear Research)","2026-09-22T00:00:00Z",25,71,{"impact":17,"substance":188,"depth":108,"authority":17,"freshness":189,"relevant":22,"comment":190},21,9,"方法完整、对比基线充分，但属常规机器学习应用论文，公共价值有限，可作主题聚合素材而非每日精选。",[192,193],{"name":183,"url":180},{"name":183,"url":194},"https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.22895812",[27,28,30,196,31],"作物推荐",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[],{"status":40,"locked":14,"version":41,"method":42,"evidence":200},{"candidates":201,"agricultural_evidence":47},[202,206,211],{"code":53,"score":13,"supported":47,"title":203,"abstract":204,"tags":205},[56],[],[27,30],{"code":33,"score":189,"supported":47,"title":207,"abstract":209,"tags":210},[208],"decision support",[],[28],{"code":59,"score":60,"supported":47,"title":212,"abstract":213,"tags":214},[],[63,64],[31],[216,217],"SCR-XGB 作物推荐 土壤","集成学习 精准农业 选种","SCR-XGB作物推荐土壤-3282","10.5281\u002Fzenodo.22895811",{"doi":219,"openalex_id":221,"authors":222,"venue":183,"cited_by_count":85,"oa_url":180,"card":225,"direction":90,"ingested_from":92},"W7214043002",[223],{"name":224,"orcid":9},"Prof. Nagendra Patel Sahil Verma",{"tldr":226,"method":227,"finding":228,"direction":90,"opportunity":229},"提出SCR-XGB五层框架，用梯度提升树集成从土壤和气候参数推荐作物。","基于土壤气候数据，采用正则化梯度提升树集成，含缺失值插补、异常值过滤和特征工程。","模型准确率达99.31%，优于朴素贝叶斯、随机森林等基线，比单决策树提升9.31个百分点。","可探索将模型部署到田间实时决策，并融合遥感与物联网数据提升泛化能力。","2026-09-23T23:30:35.342497Z",{"id":232,"title":233,"url":234,"summary":235,"summary_zh":236,"content":9,"source_name":183,"source_url":234,"published_at":184,"category":12,"cover_url":9,"hotness":185,"is_selected":14,"score":237,"score_detail":238,"sources":242,"tags":246,"primary_topic":247,"secondary_topics":248,"classification":249,"search_phrases":274,"slug":277,"view_count":130,"doi":278,"paper":279,"created_at":289},3271,"A Systematic Study of Supervised and Ensemble Learning Approaches for Crop Selection in Smart Agriculture","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.22896343","Selecting the crop best matched to a field’s soil and climate is one of the highest-leverage decisions in agriculture, and one that farmers have traditionally made by intuition or inherited practice. Soil pH together with nitrogen, phosphorus and potassium concentration, and the local temperature, humidity and rainfall regime, jointly determine which crop will flourish and which will fail, and the relationship between those variables and crop performance is neither linear nor independent. Machine learning has therefore become the dominant approach to automated crop recommendation. This paper reviews the field across four technique families — classical supervised learning, ensemble and boosting methods, deep learning and metaheuristic hybrids, and IoT and deployment-oriented systems — and compares twenty-four representative studies published between 2016 and 2026 in terms of method, data source, reported accuracy, advantage and limitation. A generic seven-stage recommendation pipeline is presented and each family is situated within it. The comparison shows that reported accuracy on the standard nutrient-and-climate benchmark has converged in a narrow band between roughly 98 and 99.5 per cent, that boosting and ensemble methods occupy the upper part of that band, and that further gains on the benchmark are no longer the binding constraint on the field. The gaps that remain open are instead the absence of socio-economic and market variables from the decision, the lack of region-specific and long-horizon environmental validation, dataset narrowness and geographic bias, limited interpretability, and the accessibility of these systems to small and resource-poor farmers. These are consolidated into a set of research directions for future work.","选择与田块土壤和气候最匹配的作物是农业中杠杆效应最高的决策之一，而农民传统上依靠直觉或世代相传的经验来做出这一决策。土壤pH值以及氮、磷、钾浓度，加上当地的气温、湿度和降雨状况，共同决定了哪种作物能够茁壮成长、哪种会歉收，而这些变量与作物表现之间的关系既非线性也非相互独立。因此，机器学习已成为自动化作物推荐的主流方法。本文从四个技术族系——经典监督学习、集成与提升方法、深度学习与元启发式混合方法，以及物联网与面向部署的系统——对该领域进行了综述，并从方法、数据来源、报告精度、优势和局限性方面比较了2016年至2026年间发表的二十四项代表性研究。本文提出了一个通用的七阶段推荐流程，并将每个技术族系置于该流程中加以定位。比较结果表明，在标准养分与气候基准上的报告精度已收敛于约98%至99.5%的狭窄区间内，提升与集成方法占据该区间的上端，而在该基准上进一步提升已不再是该领域的约束瓶颈。真正尚未填补的空白在于：决策中缺乏社会经济和市场变量，缺少针对特定区域和长期环境验证，数据集狭窄且存在地理偏差，可解释性有限，以及这些系统对小型和资源匮乏农户的可及性不足。这些空白被归纳为未来工作的一系列研究方向。",78,{"impact":46,"substance":239,"depth":18,"authority":240,"freshness":189,"relevant":22,"comment":241},22,13,"系统综述24项研究并指出基准精度已趋饱和，真正瓶颈转向社会经济变量与可解释性，对智慧农业选种方向有参考价值。",[243,244],{"name":183,"url":234},{"name":183,"url":245},"https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.22896344",[27,28,29,30,196],{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[],{"status":40,"locked":14,"version":41,"method":42,"evidence":250},{"candidates":251,"agricultural_evidence":47},[252,258,263,267],{"code":33,"score":120,"supported":47,"title":253,"abstract":254,"tags":257},[],[255,29,49,256],"深度学习","deep learning",[28,29],{"code":53,"score":13,"supported":47,"title":259,"abstract":261,"tags":262},[260],"smart agriculture",[],[27,30],{"code":59,"score":95,"supported":47,"title":264,"abstract":265,"tags":266},[],[63,64],[],{"code":268,"score":95,"supported":47,"title":269,"abstract":270,"tags":273},"I5",[],[271,272],"物联网","IoT",[],[275,276],"农业人工智能 作物推荐 智慧农业 机器学习","农业人工智能 作物推荐","农业人工智能作物推荐智慧农业机器学习-3271","10.5281\u002Fzenodo.22896343",{"doi":278,"openalex_id":280,"authors":281,"venue":183,"cited_by_count":85,"oa_url":234,"card":283,"direction":288,"ingested_from":92},"W7214002748",[282],{"name":224,"orcid":9},{"tldr":284,"method":285,"finding":286,"direction":90,"opportunity":287},"系统综述2016-2026年24项作物推荐研究，比较四类机器学习方法并指出基准精度已趋饱和。","综述监督学习、集成提升、深度学习与元启发式、物联网部署四类方法及七阶段流程。","标准基准精度收敛于98%-99.5%，提升集成法最优，但精度已非领域瓶颈。","将社会经济与市场变量、区域长期环境验证及可解释性纳入作物推荐，服务小农户。","智慧农业 \u002F 农业物联网","2026-09-23T23:30:09.369987Z",{"id":291,"title":292,"url":293,"summary":294,"summary_zh":295,"content":9,"source_name":10,"source_url":293,"published_at":296,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":297,"score_detail":298,"sources":300,"tags":302,"primary_topic":304,"secondary_topics":305,"classification":306,"search_phrases":329,"slug":332,"view_count":333,"doi":334,"paper":335,"created_at":354},2802,"Advanced olive leaf area prediction using machine learning methods","https:\u002F\u002Fdoi.org\u002F10.1038\u002Fs41598-026-71390-9","Abstract Accurate leaf area estimation is essential for understanding olive tree physiology, productivity, and stress adaptationThis study developed and evaluated machine learning models for non-destructive olive leaf area prediction using linear measurements (length and width) from 30 diverse cultivars at the Tarom Olive Research Station, Iran. Six machine learning algorithms, Artificial Neural Network (ANN), Support Vector Regression (SVR), Random Forest, Decision Tree, AdaBoost, and XGBoost were optimized using Bayesian optimization, Genetic Algorithm (GA), and Particle Swarm Optimization (PSO). Results demonstrated that PSO consistently outperformed other optimization methods across most models. The ANN model optimized with PSO achieved the highest prediction accuracy (R 2 = 0.9828, RMSE = 0.3009 cm 2 ). External validation using eight additional cultivars confirmed model generalizability, with the universal ANN model maintaining R 2 > 0.98. This study provides a robust, non-destructive methodology for olive leaf area estimation applicable across diverse cultivars, offering practical implications for precision agriculture, phenotyping, and orchard management under changing climatic conditions.","摘要 准确的叶面积估算对于理解油橄榄树的生理特性、生产力及逆境适应性至关重要。本研究在伊朗塔罗姆油橄榄研究站，利用来自30个不同品种的线性测量数据（长度和宽度），开发并评估了用于无损油橄榄叶面积预测的机器学习模型。采用贝叶斯优化、遗传算法（GA）和粒子群优化（PSO）对六种机器学习算法——人工神经网络（ANN）、支持向量回归（SVR）、随机森林、决策树、AdaBoost和XGBoost——进行了优化。结果表明，在大多数模型中，PSO始终优于其他优化方法。经PSO优化后的ANN模型取得了最高的预测精度（R² = 0.9828，RMSE = 0.3009 cm²）。利用另外八个品种进行的外部验证证实了模型的泛化能力，通用ANN模型保持R² > 0.98。本研究为适用于不同品种的油橄榄叶面积估算提供了一种稳健的无损方法，为气候变化条件下的精准农业、表型分析和果园管理提供了实际应用价值。","2026-09-17T00:00:00Z",73,{"impact":17,"substance":107,"depth":108,"authority":20,"freshness":13,"relevant":22,"comment":299},"基于30个品种的机器学习叶片面积无损预测研究，方法新颖、验证充分，对精准农业与表型分析有实用价值，但属细分领域技术进展，影响范围有限。",[301],{"name":10,"url":293},[27,28,29,30,303],"表型分析",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[],{"status":40,"locked":14,"version":41,"method":42,"evidence":307},{"candidates":308,"agricultural_evidence":47},[309,313,317,323],{"code":33,"score":46,"supported":47,"title":310,"abstract":311,"tags":312},[49],[29,49],[28,29],{"code":53,"score":21,"supported":47,"title":314,"abstract":315,"tags":316},[],[30,56],[27,30],{"code":318,"score":68,"supported":47,"title":319,"abstract":320,"tags":322},"B2",[],[321],"orchard",[],{"code":324,"score":68,"supported":47,"title":325,"abstract":326,"tags":328},"H7",[],[327],"气候变化",[],[330,331],"农业人工智能 智慧农业 机器学习 精准农业","农业人工智能 智慧农业","农业人工智能智慧农业机器学习精准农业-2802",4,"10.1038\u002Fs41598-026-71390-9",{"doi":334,"openalex_id":336,"authors":337,"venue":10,"cited_by_count":85,"oa_url":293,"card":348,"direction":90,"ingested_from":92},"W7213449017",[338,341,343,345],{"name":339,"orcid":340},"Ahmad Reza Dadras","https:\u002F\u002Forcid.org\u002F0000-0001-8591-5813",{"name":342,"orcid":9},"Hossein Sabouri",{"name":344,"orcid":9},"Ali Tanhaei",{"name":346,"orcid":347},"Sayed Javad Sajadi","https:\u002F\u002Forcid.org\u002F0000-0002-6555-080X",{"tldr":349,"method":350,"finding":351,"direction":352,"opportunity":353},"用机器学习基于叶长宽非破坏性预测30个橄榄品种叶面积，PSO优化ANN精度最高。","30个品种叶长宽数据，六种ML算法结合贝叶斯、GA、PSO优化。","PSO优化ANN最优（R²=0.9828），外部8品种验证R²>0.98，通用性好。","农业遥感与作物表型","可拓展至多物种、多环境及无人机\u002F手机图像自动测量，构建通用叶面积表型平台。","2026-09-17T23:30:59.169744Z",{"id":356,"title":357,"url":358,"summary":359,"summary_zh":360,"content":9,"source_name":361,"source_url":358,"published_at":362,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":363,"score_detail":364,"sources":366,"tags":368,"primary_topic":369,"secondary_topics":370,"classification":379,"search_phrases":400,"slug":402,"view_count":130,"doi":403,"paper":404,"created_at":417},2509,"Artificial Intelligence-Based Crop Recommendation Using Soil and Climate Data: A Comprehensive Review of Machine Learning, Deep Learning, and Smart Agriculture Approaches","https:\u002F\u002Fdoi.org\u002F10.64388\u002Firev10i3-1722922","Crop recommendation systems that integrate soil and climate data with artificial intelligence (AI) have expanded rapidly since 2020, spanning classical machine learning (ML), ensemble methods, deep learning, explainable AI (XAI), and Internet of Things (IoT)-enabled sensing. This review critically synthesizes 35 sources — 33 peer-reviewed journal articles and conference papers plus 2 preprints retained only for background context — comprising 12 studies verified in full against their primary text and 23 studies verified at the bibliographic level, to examine what has been attempted, which data and algorithms have been used, and how reliable the reported results are. The reviewed literature shows convergent use of a narrow feature set (nitrogen, phosphorus, potassium, temperature, humidity, pH, and rainfall) and recurring near-ceiling accuracy, including cases at or above 98% [1], [5], [6] and, in one case, a reported 1.00 across accuracy, precision, recall, and F1-score following class-balancing [7]. Cross-examination of dataset descriptions across studies reveals inconsistent provenance and documentation: structurally similar seven-feature datasets are described with different national contexts and reported sample sizes ranging from 2,100 to 3,000 records [5], [6], [9]. Validation practice is dominated by random hold-out or k-fold cross-validation; among the studies examined in full, only one tested spatial cross-validation, reporting a substantial performance decline (AUC 0.89 to 0.55–0.62) relative to random-split results [4]. Explainable AI and uncertainty quantification remain minority practices in the reviewed literature. A prior conference proceedings paper self-described as a","自2020年以来，将土壤和气候数据与人工智能（AI）相结合的作物推荐系统迅速扩展，涵盖经典机器学习（ML）、集成方法、深度学习、可解释人工智能（XAI）以及物联网（IoT）赋能的传感技术。本综述批判性地综合了35个来源——33篇同行评审期刊论文和会议论文，以及2篇仅用于背景参考的预印本——其中包括12项经全文核实的研究和23项经书目层面核实的研究，以考察已尝试的研究方向、所使用的数据和算法，以及所报告结果的可靠性。所综述的文献显示，特征集使用趋同且范围狭窄（氮、磷、钾、温度、湿度、pH和降雨量），准确率反复接近上限，包括达到或超过98%的案例[1], [5], [6]，以及一例在类别平衡后准确率、精确率、召回率和F1分数均报告为1.00的研究[7]。对各项研究中数据集描述的交叉审查揭示了来源和文档记录的不一致：结构相似的七特征数据集被描述为不同的国家背景，报告的样本量从2,100到3,000条记录不等[5], [6], [9]。验证实践以随机留出法或k折交叉验证为主；在经全文审查的研究中，仅有一项测试了空间交叉验证，报告称相对于随机划分结果，性能显著下降（AUC从0.89降至0.55–0.62）[4]。可解释人工智能和不确定性量化在所综述文献中仍属少数实践。一篇先前会议论文集中自述为","Iconic Research and Engineering Journals","2026-09-14T00:00:00Z",61,{"impact":17,"substance":18,"depth":46,"authority":95,"freshness":189,"relevant":22,"comment":365},"系统综述揭示作物推荐模型普遍存在数据集来源混乱与验证方法单一（仅一项空间交叉验证即大幅掉点）的问题，对智慧农业AI落地有实质警示价值，但期刊影响力有限。",[367],{"name":361,"url":358},[27,28,30,196,31],{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[371,375],{"code":59,"slug":64,"name":372,"path":373,"parent_code":374},"土壤健康与改良","\u002Ftopic\u002Fenvironment\u002Fsoil","H",{"code":268,"slug":376,"name":377,"path":378,"parent_code":37},"agricultural-iot","物联网传感与边缘计算","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-iot",{"status":40,"locked":14,"version":41,"method":42,"evidence":380},{"candidates":381,"agricultural_evidence":47},[382,387,391,395],{"code":33,"score":383,"supported":47,"title":384,"abstract":385,"tags":386},34,[49,256,123],[255,29,49,256,123],[28],{"code":59,"score":19,"supported":47,"title":388,"abstract":389,"tags":390},[64],[63,64],[31],{"code":53,"score":13,"supported":47,"title":392,"abstract":393,"tags":394},[260],[],[27,30],{"code":268,"score":189,"supported":47,"title":396,"abstract":397,"tags":399},[],[271,398,272],"internet of things",[],[401,276],"农业人工智能 作物推荐 土壤数据 智慧农业","农业人工智能作物推荐土壤数据智慧农业-2509","10.64388\u002Firev10i3-1722922",{"doi":403,"openalex_id":405,"authors":406,"venue":361,"cited_by_count":85,"oa_url":411,"card":412,"direction":288,"ingested_from":92},"W7212594050",[407,409],{"name":408,"orcid":9},"Snehal Sanjay Raut",{"name":410,"orcid":9},"Yogesh V. Chimate","https:\u002F\u002Fwww.irejournals.com\u002Fformatedpaper\u002F1722922.pdf",{"tldr":413,"method":414,"finding":415,"direction":90,"opportunity":416},"综述AI作物推荐研究，指出高准确率多源于数据与验证缺陷。","系统综述35篇文献，对比ML、DL、XAI与IoT方法及验证方式。","常用7特征数据集来源不一，随机验证致准确率虚高，空间验证性能骤降。","需建立标准化数据集并推广空间交叉验证与不确定性量化，提升模型真实泛化能力。","2026-09-15T23:30:08.397298Z",{"id":419,"title":420,"url":421,"summary":422,"summary_zh":423,"content":9,"source_name":424,"source_url":421,"published_at":425,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":426,"score_detail":427,"sources":429,"tags":431,"primary_topic":433,"secondary_topics":434,"classification":435,"search_phrases":459,"slug":461,"view_count":68,"doi":462,"paper":463,"created_at":478},2179,"Comparative evaluation of classical machine learning and deep learning models for early weed detection in precision agriculture","https:\u002F\u002Fdoi.org\u002F10.1007\u002Fs44163-026-02195-y","Unless treated and controlled early, weeds considerably impede the growth of crops as they compete over vital factors (resources) like nutrients, water, and light. To overcome this problem, an automated weed species early detection and classification system using machine learning-based image analysis is suggested. The framework integrates classical machine learning algorithms Support Vector Machines (SVM), Random Forests and k-Nearest Neighbors (k-NN), using handcrafted features like texture, shape, and color with deep learning models, Convolutional Neural Networks (CNNs) which automatically learn discriminative features in the data. The study comparatively evaluates classical ML and deep learning models. In order to test the experiments, a publicly available Sugar Beet dataset was used, as well as a custom maize seedling dataset. To enhance generalization and robustness, some preprocessing steps were performed, including normalization, background removal, and augmentation. Common metrics used to assess the performance of the models are F1-score and Intersection over Union (IoU). The experimental results show deep learning models outperforming the traditional machine learning methods, especially CNNs The CNN model also exhibited a classification accuracy of 98.7%. These results demonstrate the promise of deep learning to quickly, reliably, and in large scale detect weeds in the early stages of precision agriculture. This study highlights the feasibility of machine learning systems in proactive management of weed as well as in supporting healthy crop growth at the early stages of development.","除非在早期进行处理和控制，否则杂草会争夺养分、水分和光照等关键因素（资源），从而严重阻碍作物生长。为解决这一问题，提出了一种基于机器学习的图像分析自动化杂草物种早期检测与分类系统。该框架整合了经典机器学习算法——支持向量机（SVM）、随机森林和k近邻（k-NN），利用纹理、形状和颜色等手工特征，并结合深度学习模型——卷积神经网络（CNN），后者可自动学习数据中的判别性特征。本研究对经典机器学习和深度学习模型进行了对比评估。为验证实验，使用了公开的甜菜数据集以及自建的玉米幼苗数据集。为增强泛化性和鲁棒性，执行了一些预处理步骤，包括归一化、背景去除和数据增强。用于评估模型性能的常用指标为F1分数和交并比（IoU）。实验结果表明，深度学习模型优于传统机器学习方法，尤其是CNN。CNN模型的分类准确率达到了98.7%。这些结果证明了深度学习在精准农业中快速、可靠且大规模地早期检测杂草的潜力。本研究凸显了机器学习系统在杂草主动管理以及支持作物早期健康生长方面的可行性。","Discover Artificial Intelligence","2026-09-10T00:00:00Z",72,{"impact":46,"substance":107,"depth":46,"authority":17,"freshness":21,"relevant":22,"comment":428},"对比经典机器学习与深度学习在作物早期杂草检测中的表现，CNN 分类准确率达 98.7%，方法扎实、结论明确，对精准农业智能除草有参考价值。",[430],{"name":424,"url":421},[27,28,29,432,30],"杂草识别",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[],{"status":40,"locked":14,"version":41,"method":42,"evidence":436},{"candidates":437,"agricultural_evidence":47},[438,443,447,454],{"code":33,"score":439,"supported":47,"title":440,"abstract":441,"tags":442},27,[49,256],[255,29,49,256],[28,29],{"code":53,"score":46,"supported":47,"title":444,"abstract":445,"tags":446},[56],[30,56],[27,30],{"code":448,"score":95,"supported":47,"title":449,"abstract":450,"tags":453},"A3",[],[451,452],"玉米","maize",[],{"code":455,"score":22,"supported":14,"title":456,"abstract":457,"tags":458},"F4",[],[],[432],[460,331],"农业人工智能 智慧农业 机器学习 杂草识别","农业人工智能智慧农业机器学习杂草识别-2179","10.1007\u002Fs44163-026-02195-y",{"doi":462,"openalex_id":464,"authors":465,"venue":424,"cited_by_count":85,"oa_url":421,"card":473,"direction":90,"ingested_from":92},"W7212111551",[466,469,471],{"name":467,"orcid":468},"Rajeev Kumar","https:\u002F\u002Forcid.org\u002F0000-0001-8414-3778",{"name":470,"orcid":9},"P. K. Singh",{"name":472,"orcid":9},"Rohit Kumar Tiwari",{"tldr":474,"method":475,"finding":476,"direction":90,"opportunity":477},"对比经典机器学习与深度学习模型在精准农业早期杂草检测中的性能。","用SVM、随机森林、k-NN及CNN，基于甜菜和玉米幼苗图像数据集。","CNN分类准确率达98.7%，显著优于传统机器学习方法。","可探索轻量化模型在田间边缘设备实时检测杂草的部署与跨物种泛化能力。","2026-09-11T23:30:52.642134Z"]