[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-2271":3},{"id":4,"title":5,"url":6,"summary":7,"summary_zh":8,"content":8,"source_name":9,"source_url":8,"published_at":10,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":14,"score_detail":15,"sources":23,"tags":25,"view_count":31,"doi":8,"paper":32,"created_at":41},2271,"MDPI Agriculture 16(17):1932 厄瓜多尔农场级玉米产量模型空间可迁移性研究","https:\u002F\u002Fwww.mdpi.com\u002F2077-0472\u002F16\u002F17\u002F1932","MDPI Agriculture刊载厄瓜多尔马纳比省农场记录级玉米产量预测模型研究,基于518份数据评估Elastic Net、随机森林和直方图梯度提升模型。结果显示所有模型配置产生负的合并R2值,空间交叉验证显示空间乐观偏差,提示农场管理数据不足以支持对未见地区单作物记录的可靠产量预测。",null,"MDPI Agriculture 16(17):1932","2026-09-06T16:00:00Z","论文",10,false,63,{"impact":16,"substance":17,"depth":18,"authority":19,"freshness":20,"relevant":21,"comment":22},8,20,16,13,6,1,"基于518份农场记录检验多种机器学习模型的跨区域可迁移性，得出负面结论，对农业数据驱动产量预测的适用边界有实质警示价值，但属细分方法学研究，影响范围有限。",[24],{"name":9,"url":6},[26,27,28,29,30],"智慧农业","产量预测","机器学习","玉米","空间迁移",0,{"doi":8,"openalex_id":8,"authors":33,"venue":8,"cited_by_count":31,"oa_url":8,"card":34,"direction":38,"ingested_from":40},[],{"tldr":35,"method":36,"finding":37,"direction":38,"opportunity":39},"评估三种机器学习模型在厄瓜多尔农场级玉米产量预测中的空间可迁移性。","基于518份农场记录，用Elastic Net、随机森林和直方图梯度提升做空间交","所有模型合并R2为负，存在空间乐观偏差，农场管理数据不足以可靠预测未见地区产量。","农业人工智能与决策模型","可探索融合遥感、气象与土壤等多源数据，提升小农户农场级产量模型的空间泛化能力。","agent","2026-09-13T00:04:04.999192Z"]