[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-4287":3,"related-4287":91},{"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":9,"secondary_topics":32,"classification":33,"search_phrases":67,"slug":70,"view_count":71,"doi":72,"paper":73,"created_at":90},4287,"The effect of train-test data splitting ratio on yield prediction from multispectral UAV imagery: effective reduction of training ratio with algorithm selection for single- and multi-date models","https:\u002F\u002Fdoi.org\u002F10.1007\u002Fs11119-026-10464-0","Abstract Context Optimizing the ratio of data required for training spectral grain yield (GY) prediction models is critical for efficient sampling of reference data, but has been rarely addressed so far. Given the high costs for collecting ground truth data, standard data splitting ratios which use the majority of the data for training and the rest for testing the models should be minimized, but in turn may affect prediction accuracy. Methods Therefore, this study evaluated 11 different train-test data splitting ratios (TSR), ranging from using 5% to 95% of the data for training, and the remaining portion as test sets. Models with six different machine learning algorithms were compared in winter wheat breeding trials conducted with each several thousand plots in two locations in Germany over a period of four years. The input data consisted of the (unmanned aerial vehicle) UAV-based NDRE index data from individual measurements dates as well as multi-date combinations. Results The results indicate that GY prediction remained relatively stable when decreasing TSR to about 0.30. Conversely, multi-date models tended to benefit more from higher TSR than single-date models. Support vector machine and random forest algorithms demonstrated relative advantage both for higher TSR and multi-date models, whereas partial least squares and ridge regression were the best algorithms for lowest TSR-values. Furthermore, analysis via repeated data splitting revealed minimum R² variability at a TSR of 0.30, but substantially increased variance at higher TSR values. Conclusions It is concluded that decreasing TSR while considering algorithm selection can potentially reduce costs without compromising prediction accuracy, therefore making spectral phenotyping methods more accessible and ready-to-use, whereas the absolute number of data points requires additional examination.","摘要 背景 优化光谱谷物产量（grain yield, GY）预测模型所需数据的训练-测试比例对于高效采集参考数据至关重要，但迄今鲜有研究涉及。鉴于获取地面真实数据的高昂成本，应尽量减少使用大部分数据进行模型训练、其余部分用于测试的标准数据划分比例，但这反过来可能影响预测精度。方法 因此，本研究评估了11种不同的训练-测试数据划分比例（train-test data splitting ratio, TSR），训练数据占比从5%到95%不等，剩余部分作为测试集。在德国两个地点、为期四年、每个试验包含数千个小区的冬小麦育种试验中，比较了采用六种不同机器学习算法的模型。输入数据包括来自单次测量日期的基于无人机（unmanned aerial vehicle, UAV）的NDRE指数数据以及多日期组合数据。结果 结果表明，当TSR降低至约0.30时，GY预测仍保持相对稳定。相反，多日期模型比单日期模型更倾向于从较高的TSR中获益。支持向量机（support vector machine）和随机森林（random forest）算法在较高TSR和多日期模型中均表现出相对优势，而偏最小二乘回归（partial least squares）和岭回归（ridge regression）在最低TSR值下表现最佳。此外，通过重复数据划分分析发现，TSR为0.30时R²变异性最小，但在较高TSR值下方差显著增大。结论 研究表明，在考虑算法选择的前提下降低TSR有可能在不影响预测精度的情况下减少成本，从而使光谱表型分析方法更加易于获取和实用，但数据点的绝对数量仍需进一步研究。",null,"Precision Agriculture","2026-10-05T00:00:00Z","论文",10,false,75,{"impact":17,"substance":18,"depth":19,"authority":20,"freshness":21,"relevant":22,"comment":23},12,22,18,14,9,1,"基于四年多点小麦育种试验系统评估训练集比例与算法选择对无人机多光谱产量预测的影响，方法扎实、结论实用，对降低表型数据采集成本有直接参考价值。",[25],{"name":10,"url":6},[27,28,29,30,31],"智慧农业","产量预测","机器学习","小麦育种","遥感",[],{"status":34,"locked":14,"version":35,"method":36,"evidence":37},"needs_review","2026-10-22.2","rules",{"candidates":38,"agricultural_evidence":41,"reason":66},[39,48,54,61],{"code":40,"score":13,"supported":41,"title":42,"abstract":43,"tags":47},"A2",true,[],[44,45,46],"小麦","winter wheat","wheat",[30],{"code":49,"score":13,"supported":41,"title":50,"abstract":52,"tags":53},"I3",[51],"multispectral",[],[28,31],{"code":55,"score":56,"supported":41,"title":57,"abstract":58,"tags":60},"I2",7,[],[29,59],"machine learning",[29],{"code":62,"score":22,"supported":14,"title":63,"abstract":64,"tags":65},"I1",[],[],[27],"多个产业证据相当，需要确认主归属",[68,69],"无人机 多光谱 小麦 产量预测","冬小麦 育种 遥感 机器学习","无人机多光谱小麦产量预测-4287",2,"10.1007\u002Fs11119-026-10464-0",{"doi":72,"openalex_id":74,"authors":75,"venue":10,"cited_by_count":82,"oa_url":6,"card":83,"direction":87,"ingested_from":89},"W7220450104",[76,79],{"name":77,"orcid":78},"Lukas Prey","https:\u002F\u002Forcid.org\u002F0000-0001-6287-4596",{"name":80,"orcid":81},"Patrick Noack","https:\u002F\u002Forcid.org\u002F0000-0002-0226-6609",0,{"tldr":84,"method":85,"finding":86,"direction":87,"opportunity":88},"研究不同训练-测试数据划分比例对无人机多光谱小麦产量预测的影响，发现可降低训练比例。","基于德国四年两地点冬小麦育种试验，用UAV NDRE指数和六种机器学习算法比较1","训练比例降至约0.30时预测精度稳定，多时相模型更受益于高比例，SVM和随机森林较优。","农业遥感与作物表型","可探索在更低训练比例下结合主动学习或迁移学习，进一步降低地面采样成本并验证跨地点泛化性。","openalex","2026-10-06T23:30:02.110164Z",{"total":92,"page":22,"page_size":92,"items":93},6,[94,167,226,287,357,410],{"id":95,"title":96,"url":97,"summary":98,"summary_zh":99,"content":9,"source_name":100,"source_url":97,"published_at":101,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":102,"score_detail":103,"sources":106,"tags":108,"primary_topic":109,"secondary_topics":112,"classification":118,"search_phrases":141,"slug":144,"view_count":145,"doi":146,"paper":147,"created_at":166},3328,"Yield ranking of spring wheat breeding lines absent from model training within two contrasting seasons in northern Kazakhstan","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.atech.2026.102588","Reliable assessment of yield models in breeding trials requires evaluation on lines that have not contributed observations to model development. We examined this problem in an advanced spring wheat yield nursery in northern Kazakhstan during the 2024 and 2025 seasons. Of 300 plots, 176 from 22 entries formed the model development set, while 124 plots representing 31 breeding lines were completely excluded from training. Eleven variables were retained from 82 candidates using the training data alone; the candidates were derived from UAV multispectral imagery, ERA5-Land reanalysis, LiDAR-derived static plot microtopography, phenology and maturity group. LightGBM yielded a pooled R² of 0.587 for the excluded lines; resampling breeding lines within season gave a mean R² of 0.564 with a 95 % confidence interval from 0.252 to 0.776. The pooled value partly reflected the strong contrast between seasons rather than discrimination among lines within a season. Random division of plots produced an R² of 0.890, indicating that apparent predictive accuracy depended strongly on validation design. Agreement between observed and predicted line rankings was moderate, with Spearman correlations of 0.612 in 2024 and 0.650 in 2025, although uncertainty was wide because only 14 and 17 independent lines were available. Six modelling approaches produced overlapping uncertainty intervals, with no clear evidence of superiority, and the complete combination of data sources was not separable from simpler configurations retaining the multispectral block. A separate analysis in which screening, selection and fitting used 2024 data alone and evaluation used 2025 data showed a severe loss of performance, with R² = −8.81 and a Spearman correlation of −0.082 that was indistinguishable from zero. Poor transfer persisted among entries grown in both seasons, so genotype novelty alone was insufficient to explain the failure. Breeding lines absent from training could therefore be ranked with moderate consistency when both observed seasonal regimes were represented during model development, whereas prediction in an unobserved season remained unreliable. The study covers one nursery complex and two seasons, so transfer across locations and broader conditions remains to be established.","在育种试验中，要对产量模型进行可靠评估，必须在未参与模型开发的品系上进行评价。我们在2024年和2025年生长季于哈萨克斯坦北部的一个高级春小麦产量圃中考察了这一问题。在300个小区中，来自22个品系的176个小区构成模型开发集，而代表31个育种品系的124个小区则完全排除在训练之外。仅使用训练数据，从82个候选变量中保留了11个变量；这些候选变量来源于无人机多光谱影像、ERA5-Land再分析数据、LiDAR衍生的静态小区微地形、物候和成熟期组。LightGBM对被排除品系给出的合并R²为0.587；在生长季内对育种品系进行重采样得到的平均R²为0.564，95%置信区间为0.252至0.776。合并值部分反映了生长季之间的强烈差异，而非生长季内品系之间的区分能力。对小区进行随机划分得到的R²为0.890，表明表观预测精度在很大程度上取决于验证设计。观测品系排名与预测品系排名之间的一致性为中等，2024年和2025年的Spearman相关系数分别为0.612和0.650，但由于仅有14个和17个独立品系可用，不确定性范围较宽。六种建模方法产生了相互重叠的不确定性区间，没有明确证据表明哪一种更优，并且完整的数据源组合与保留多光谱模块的较简单配置无法区分。另一项分析中，筛选、选择和拟合仅使用2024年数据，而评估使用2025年数据，结果显示性能严重下降，R² = −8.81，Spearman相关系数为−0.082，与零无法区分。在两个生长季均种植的品系之间，较差的迁移性依然存在，因此仅用品系新颖性不足以解释这种失败。因此，当模型开发过程中涵盖了所观测到的两种生长季情形时，未参与训练的育种品系可以以中等一致性进行排名，而在未观测生长季中的预测仍然不可靠。本研究仅涵盖一个圃系复合体和两个生长季，因此跨地点和更广泛条件下的迁移性仍有待确立。","Smart Agricultural Technology","2026-09-22T00:00:00Z",74,{"impact":17,"substance":18,"depth":19,"authority":104,"freshness":21,"relevant":22,"comment":105},13,"基于无人机多光谱与气象数据的春小麦育种品系产量预测研究，验证设计严谨、结论审慎，对智慧育种与遥感估产有参考价值，但属单点试验、地域性强，未达重大突破层级。",[107],{"name":100,"url":97},[27,28,29,30,31],{"code":40,"slug":46,"name":44,"path":110,"parent_code":111},"\u002Ftopic\u002Ffield-crops\u002Fwheat","A",[113],{"code":49,"slug":114,"name":115,"path":116,"parent_code":117},"remote-sensing","遥感与农情监测","\u002Ftopic\u002Fdigital-agriculture\u002Fremote-sensing","I",{"status":119,"locked":14,"version":35,"method":36,"evidence":120},"classified",{"candidates":121,"agricultural_evidence":41},[122,127,133,137],{"code":40,"score":123,"supported":41,"title":124,"abstract":125,"tags":126},15,[46],[44,46],[30],{"code":49,"score":128,"supported":41,"title":129,"abstract":130,"tags":132},8,[],[131,51],"无人机多光谱",[28,31],{"code":62,"score":22,"supported":14,"title":134,"abstract":135,"tags":136},[],[],[27],{"code":55,"score":22,"supported":14,"title":138,"abstract":139,"tags":140},[],[],[29],[142,143],"哈萨克斯坦 春小麦 产量预测","UAV 多光谱 育种试验","哈萨克斯坦春小麦产量预测-3328",4,"10.1016\u002Fj.atech.2026.102588",{"doi":146,"openalex_id":148,"authors":149,"venue":100,"cited_by_count":82,"oa_url":97,"card":161,"direction":87,"ingested_from":89},"W7214044328",[150,153,156,159],{"name":151,"orcid":152},"Dastan Yelubayev","https:\u002F\u002Forcid.org\u002F0000-0001-5358-7982",{"name":154,"orcid":155},"TIMUR SAVIN","https:\u002F\u002Forcid.org\u002F0000-0002-3550-647X",{"name":157,"orcid":158},"Ismail Tokbergenov","https:\u002F\u002Forcid.org\u002F0000-0002-0656-9914",{"name":160,"orcid":9},"Bakhtiyar Zhanzakov",{"tldr":162,"method":163,"finding":164,"direction":87,"opportunity":165},"评估春小麦育种品系产量模型在未参与训练品系上的跨季预测能力。","无人机多光谱、ERA5-Land、LiDAR与物候数据，LightGBM等六种模","两季均参与训练时品系排名中等一致，但预测未观测季节完全失效。","需研究跨地点、跨年份可迁移的表型预测模型与验证设计，避免随机划分高估精度。","2026-09-24T23:30:03.201775Z",{"id":168,"title":169,"url":170,"summary":171,"summary_zh":9,"content":9,"source_name":172,"source_url":9,"published_at":9,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":102,"score_detail":173,"sources":176,"tags":178,"primary_topic":181,"secondary_topics":185,"classification":186,"search_phrases":212,"slug":215,"view_count":71,"doi":9,"paper":216,"created_at":225},4477,"玉米生产精准农业系统综述：技术、应用与产量优化（2020—2026）","https:\u002F\u002Fm2.mtmt.hu\u002Fapi\u002Fpublication\u002F37500368","依据PRISMA 2020指南，系统检索Scopus与Web of Science共464篇文献，最终纳入129项研究；样本构成为田间试验（28.6%）、遥感与精准农业整合研究（25.5%）、机器学习应用（19.4%）、气候知情精准农业策略（23.4%）和土壤退化研究（3.1%）；研究表明精准农业技术通过定点管理和数据驱动决策支持，提升了玉米生产力、养分利用效率、水利用效率和产量预测准确性；指出采用精准农业仍受制于实施成本高、技术复杂、数据有限等因素。","Precision Agriculture in Maize Production Systematic Review 2026",{"impact":19,"substance":18,"depth":19,"authority":104,"freshness":174,"relevant":22,"comment":175},3,"基于PRISMA 2020的系统综述，纳入129项研究，数据规模与方法规范性强，对玉米精准农业技术路径与瓶颈有实质参考价值，但发布日期不明、时效性偏弱。",[177],{"name":172,"url":170},[27,28,29,179,180,31],"玉米","精准农业",{"code":182,"slug":183,"name":179,"path":184,"parent_code":111},"A3","maize","\u002Ftopic\u002Ffield-crops\u002Fmaize",[],{"status":119,"locked":14,"version":35,"method":36,"evidence":187},{"candidates":188,"agricultural_evidence":41},[189,193,197,202,206],{"code":62,"score":104,"supported":41,"title":190,"abstract":191,"tags":192},[180],[180],[27,180],{"code":182,"score":17,"supported":41,"title":194,"abstract":195,"tags":196},[179],[179],[179],{"code":49,"score":198,"supported":41,"title":199,"abstract":200,"tags":201},5,[],[31],[28,31],{"code":55,"score":145,"supported":41,"title":203,"abstract":204,"tags":205},[],[29],[29],{"code":207,"score":174,"supported":41,"title":208,"abstract":209,"tags":211},"H2",[],[210],"土壤",[],[213,214],"玉米 精准农业 系统综述","玉米 遥感 机器学习 产量","玉米精准农业系统综述-4477",{"doi":9,"openalex_id":9,"authors":217,"venue":9,"cited_by_count":82,"oa_url":9,"card":218,"direction":222,"ingested_from":224},[],{"tldr":219,"method":220,"finding":221,"direction":222,"opportunity":223},"系统综述2020—2026年玉米精准农业技术、应用与产量优化研究。","按PRISMA 2020检索Scopus与WoS，纳入129项研究做分类分析。","精准农业通过定点管理与数据决策提升玉米产量、养分和水利用效率。","智慧农业 \u002F 农业物联网","成本高、技术复杂与数据不足制约推广，低成本轻量化方案与本地化数据共享是研究空白。","agent","2026-10-09T00:05:02.451957Z",{"id":227,"title":228,"url":229,"summary":230,"summary_zh":231,"content":9,"source_name":232,"source_url":229,"published_at":233,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":234,"score_detail":235,"sources":239,"tags":241,"primary_topic":243,"secondary_topics":244,"classification":245,"search_phrases":266,"slug":269,"view_count":71,"doi":270,"paper":271,"created_at":286},1439,"A dictionary-based method for crop yield prediction using satellite remote sensing data","https:\u002F\u002Fdoi.org\u002F10.1080\u002F2150704x.2026.2724307","HYDRA (HYbrid Dictionary–Rocket Architecture) has shown competitive performance across several benchmark datasets in prior Time-Series Classification (TSC) studies. It is a dictionary-based method that uses static convolutional kernels as dictionary patterns. HYDRA incorporates these non-learnable kernels in its method, which form the basis of ROCKET (RandOm Convolutional KErnel Transform) method designed for TSC tasks. This work presents a machine-learning-based framework built on HYDRA to perform regression on remotely sensed satellite data for crop yield prediction. It integrates HYDRA and crop phenological features through concatenation to generate a composite feature vector for XGBoost (eXtreme Gradient Boosting), enabling within-field corn yield prediction using time-series Sentinel-2 imagery. On the 2017 and 2018 datasets derived from a 22-ha corn field in Italy, our method achieved R2 values of 0.553 and 0.696, RMSE values of 1.101 t\u002Fha and 1.013 t\u002Fha, and MAE values of 0.796 t\u002Fha and 0.708 t\u002Fha, offering a modest improvement in yield prediction performance over frameworks based solely on HYDRA and phenological features. The application of HYDRA-based features in remote-sensing-based agricultural applications shows promising results for regression tasks.","HYDRA（HYbrid Dictionary–Rocket Architecture，混合字典-火箭架构）在先前的时间序列分类（TSC）研究中，已在多个基准数据集上展现出具有竞争力的性能。它是一种基于字典的方法，使用静态卷积核作为字典模式。HYDRA在其方法中融入了这些不可学习的核，这些核构成了专为TSC任务设计的ROCKET（RandOm Convolutional KErnel Transform，随机卷积核变换）方法的基础。本研究提出了一种基于HYDRA的机器学习框架，用于对遥感卫星数据进行回归分析，以实现作物产量预测。该框架通过拼接方式整合HYDRA特征与作物物候特征，生成复合特征向量供XGBoost（eXtreme Gradient Boosting，极端梯度提升）使用，从而利用时间序列Sentinel-2影像实现田块尺度内的玉米产量预测。在源自意大利一块22公顷玉米田的2017年和2018年数据集上，我们的方法分别取得了R²值为0.553和0.696、RMSE值为1.101吨\u002F公顷和1.013吨\u002F公顷、MAE值为0.796吨\u002F公顷和0.708吨\u002F公顷的结果，相较于仅基于HYDRA和物候特征的框架，在产量预测性能上实现了适度提升。基于HYDRA的特征在遥感农业应用中的使用，为回归任务展现了有前景的结果。","Remote Sensing Letters","2026-09-01T00:00:00Z",67,{"impact":17,"substance":236,"depth":237,"authority":17,"freshness":56,"relevant":22,"comment":238},20,16,"基于HYDRA的遥感作物产量预测方法在意大利玉米田取得较好精度，为农业遥感应用提供新思路。",[240],{"name":232,"url":229},[27,242,28,29,31],"农业人工智能",{"code":49,"slug":114,"name":115,"path":116,"parent_code":117},[],{"status":119,"locked":14,"version":35,"method":36,"evidence":246},{"candidates":247,"agricultural_evidence":41},[248,253,258,262],{"code":49,"score":104,"supported":41,"title":249,"abstract":251,"tags":252},[250],"remote sensing",[31],[28,31],{"code":182,"score":92,"supported":41,"title":254,"abstract":255,"tags":257},[],[179,256],"corn",[],{"code":55,"score":198,"supported":41,"title":259,"abstract":260,"tags":261},[],[29],[242,29],{"code":62,"score":22,"supported":14,"title":263,"abstract":264,"tags":265},[],[],[27],[267,268],"农业人工智能 产量预测 智慧农业 机器学习","农业人工智能 产量预测","农业人工智能产量预测智慧农业机器学习-1439","10.1080\u002F2150704x.2026.2724307",{"doi":270,"openalex_id":272,"authors":273,"venue":232,"cited_by_count":82,"oa_url":9,"card":281,"direction":87,"ingested_from":89},"W7204870154",[274,276,279],{"name":275,"orcid":9},"M.R. Najam",{"name":277,"orcid":278},"Hasnat Khurshid","https:\u002F\u002Forcid.org\u002F0000-0001-8722-5904",{"name":280,"orcid":9},"Faisal Akram",{"tldr":282,"method":283,"finding":284,"direction":87,"opportunity":285},"提出基于HYDRA字典方法的机器学习框架，结合物候特征预测玉米产量。","HYDRA特征与物候特征拼接，输入XGBoost回归，使用Sentinel-2时","在意大利玉米田上R²达0.696，优于单独使用HYDRA或物候特征。","HYDRA在遥感回归中潜力大，可探索多作物、多区域及与其他时序特征融合。","2026-09-02T23:30:51.479183Z",{"id":288,"title":289,"url":290,"summary":291,"summary_zh":292,"content":9,"source_name":293,"source_url":290,"published_at":294,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":295,"score_detail":296,"sources":298,"tags":300,"primary_topic":301,"secondary_topics":302,"classification":304,"search_phrases":324,"slug":327,"view_count":71,"doi":328,"paper":329,"created_at":356},1307,"Estimation of the Comprehensive High Photosynthetic-Efficiency Phenotypic Index in Winter Wheat Based on UAV Multimodal Remote Sensing Data","https:\u002F\u002Fdoi.org\u002F10.3390\u002Fplants15172674","Accurate monitoring of photosynthetic phenotypes is fundamental for breeding high photosynthetic-efficiency wheat cultivars, and UAV remote sensing provides an effective approach for their large-scale identification. However, single photosynthetic parameters are limited in comprehensively evaluating crop photosynthetic efficiency. This study integrated multiple photosynthetic phenotypic parameters using principal component analysis (PCA) and the CRITIC objective weighting method (PCA-CRITIC) to construct a Comprehensive High Photosynthetic-Efficiency Phenotypic Index (CHPPI) for winter wheat. Concurrently, multispectral vegetation indices (MSVI), RGB vegetation indices (RGBVI), texture features (TF), and their combination, Comprehensive Multispectral-Visible-Texture Features (CMVTF), were extracted from UAV multimodal remote sensing data. Based on these features, four feature selection methods, namely PCC, VIP, SPA, and UVE, were evaluated in combination with five machine learning algorithms, including KNN, DT, SVR, RF, and XGBoost, to precisely estimate the CHPPI across key growth stages. The results demonstrated that the CHPPI exhibited significant cultivar variations across growth stages. Cultivars SH06144 and Liangxing19 consistently maintained high photosynthetic efficiency levels. The fused feature set CMVTF derived from multimodal remote sensing data outperformed individual feature categories, and the feature subset selected by the UVE method most significantly enhanced model accuracy. Regarding algorithms, the ensemble-based XGBoost and RF models markedly surpassed traditional machine learning algorithms. Specifically, the CMVTF-UVE-XGBoost model achieved the optimal comprehensive performance, yielding an R2 of 0.862, an RMSE of 0.032, and an MAE of 0.027 on the testing set, with its spatial distribution estimations highly consistent with measured values. This study provides robust technical support for the rapid and large-scale screening of high photosynthetic-efficiency wheat breeding materials.","光合表型精准监测是培育高光效小麦品种的基础，无人机遥感为其大规模鉴定提供了有效途径。然而，单一光合参数难以全面评价作物光合效率。本研究利用主成分分析(PCA)与CRITIC客观赋权法(PCA-CRITIC)整合多个光合表型参数，构建了冬小麦高光效综合表型指数(CHPPI)。同时，从无人机多模态遥感数据中提取多光谱植被指数(MSVI)、RGB植被指数(RGBVI)、纹理特征(TF)及其融合特征——多光谱-可见光-纹理综合特征(CMVTF)。基于上述特征，评估了PCC、VIP、SPA和UVE四种特征选择方法，并结合KNN、DT、SVR、RF和XGBoost五种机器学习算法，对关键生育期的CHPPI进行精准估算。结果表明，CHPPI在不同生育期表现出显著的品种间差异，品种SH06144和良星19始终保持较高的光合效率水平。基于多模态遥感数据构建的融合特征集CMVTF优于单一特征类别，且UVE方法筛选的特征子集对模型精度的提升最为显著。在算法方面，基于集成的XGBoost和RF模型明显优于传统机器学习算法。具体而言，CMVTF-UVE-XGBoost模型取得了最优的综合性能，在测试集上R²为0.862，RMSE为0.032，MAE为0.027，其空间分布估算结果与实测值高度一致。本研究为高光效小麦育种材料的快速大规模筛选提供了有力的技术支撑。","Plants","2026-08-31T00:00:00Z",73,{"impact":19,"substance":18,"depth":19,"authority":104,"freshness":71,"relevant":22,"comment":297},"基于无人机多模态遥感构建小麦光合效率综合指数，方法新颖且模型精度高，对育种筛选有实用价值。",[299],{"name":293,"url":290},[27,29,30,31],{"code":40,"slug":46,"name":44,"path":110,"parent_code":111},[303],{"code":49,"slug":114,"name":115,"path":116,"parent_code":117},{"status":119,"locked":14,"version":35,"method":36,"evidence":305},{"candidates":306,"agricultural_evidence":41},[307,312,316,320],{"code":40,"score":308,"supported":41,"title":309,"abstract":310,"tags":311},26,[45,46],[44,45,46],[30],{"code":49,"score":19,"supported":41,"title":313,"abstract":314,"tags":315},[250],[31,250,51],[31],{"code":55,"score":56,"supported":41,"title":317,"abstract":318,"tags":319},[],[29,59],[29],{"code":62,"score":22,"supported":14,"title":321,"abstract":322,"tags":323},[],[],[27],[325,326],"小麦育种 智慧农业 机器学习 遥感","小麦育种 智慧农业","小麦育种智慧农业机器学习遥感-1307","10.3390\u002Fplants15172674",{"doi":328,"openalex_id":330,"authors":331,"venue":293,"cited_by_count":82,"oa_url":290,"card":351,"direction":87,"ingested_from":89},"W7204845072",[332,334,336,338,340,342,344,346,348],{"name":333,"orcid":9},"Ning Yang",{"name":335,"orcid":9},"Dayong Cui",{"name":337,"orcid":9},"Songming Lin",{"name":339,"orcid":9},"Changliang Du",{"name":341,"orcid":9},"Liwen Wang",{"name":343,"orcid":9},"Fei Zhang",{"name":345,"orcid":9},"Zhu Shi",{"name":347,"orcid":9},"Bingqian Hou",{"name":349,"orcid":350},"Junke Zhu","https:\u002F\u002Forcid.org\u002F0009-0005-7778-9614",{"tldr":352,"method":353,"finding":354,"direction":87,"opportunity":355},"基于无人机多模态遥感数据，构建综合高光效表型指数并精准估算，用于小麦育种材料筛选。","PCA-CRITIC构建CHPPI，提取多模态特征，结合UVE特征选择与XGBo","CMVTF-UVE-XGBoost模型表现最优，测试集R²=0.862，可快速大规模筛选高光效小麦。","可探索将CHPPI估算模型推广至其他作物或不同环境，并引入深度学习或时序数据提升泛化能力。","2026-09-01T23:30:16.317443Z",{"id":358,"title":359,"url":360,"summary":361,"summary_zh":362,"content":9,"source_name":363,"source_url":360,"published_at":364,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":234,"score_detail":365,"sources":368,"tags":370,"primary_topic":372,"secondary_topics":376,"classification":378,"search_phrases":395,"slug":397,"view_count":82,"doi":398,"paper":399,"created_at":409},5570,"Evaluation of Counterfactual Explanation Robustness for Computer Vision Agriculture Yield-Forecast Models Under Satellite Cloud-Mask Gaps: An Interpretability Reliability Bound for Cooperative Storage Decisions","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23545079","Counterfactual explanations are increasingly proposed as the interface through which cooperative storage managers interrogate computer-vision yield-forecast models, yet their reliability under the satellite cloud-mask gaps that routinely afflict agricultural remote sensing has not been bounded. The bound is derived from a Lipschitz continuity assumption on the forecast model and a masking-operator perturbation analysis, and it is expressed as a function of the cloud-mask gap fraction, the model's local Lipschitz constant, and the counterfactual search tolerance. A replication-based evaluation of the before-after-control-impact estimator was conducted to characterise the operating characteristics of the design under a declared variance structure (between-cluster SD = 6.0, residual SD = 4.5, intraclass correlation = 0.64), with power estimated across 2000 design cells. The reliability bound degrades non-linearly as the gap fraction rises, and that the intraclass correlation of 0.64 implies that cooperative-level aggregation of counterfactual recourse is necessary to preserve explanation stability. The contribution is a decision-relevant reliability bound that storage cooperatives can use to set a maximum tolerable cloud-mask gap before counterfactual recourse is suspended.","反事实解释日益被提出作为合作式仓储管理者质询计算机视觉产量预测模型的接口，然而在农业遥感中经常出现的卫星云掩膜缺口条件下，其可靠性尚未得到界定。该界基于预测模型上的Lipschitz连续性假设和掩膜算子扰动分析推导得出，并表示为云掩膜缺口比例、模型局部Lipschitz常数和反事实搜索容差的函数。对前后对照影响估计量进行了基于重复的评估，以表征该设计在给定方差结构（组间标准差=6.0，残差标准差=4.5，组内相关系数=0.64）下的运行特征，并在2000个设计单元中估计了检验效能。可靠性界随缺口比例上升呈非线性退化，且组内相关系数0.64意味着需要对反事实救济进行合作社层面的聚合，以保持解释的稳定性。本文的贡献在于提供了一个与决策相关的可靠性界，仓储合作社可据此设定在暂停反事实救济之前可容忍的最大云掩膜缺口。","Zenodo (CERN European Organization for Nuclear Research)","2026-10-21T00:00:00Z",{"impact":128,"substance":236,"depth":366,"authority":17,"freshness":13,"relevant":22,"comment":367},17,"该论文提出反事实解释在卫星云掩膜缺口下的可靠性边界，方法新颖且结论可用于合作社决策，但属细分方法学研究，产业影响有限。",[369],{"name":363,"url":360},[27,242,28,31,371],"可解释性",{"code":55,"slug":373,"name":374,"path":375,"parent_code":117},"agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai",[377],{"code":49,"slug":114,"name":115,"path":116,"parent_code":117},{"status":119,"locked":14,"version":35,"method":36,"evidence":379},{"candidates":380,"agricultural_evidence":41},[381,387,391],{"code":55,"score":17,"supported":41,"title":382,"abstract":384,"tags":386},[383],"computer vision",[385],"计算机视觉",[242],{"code":49,"score":128,"supported":41,"title":388,"abstract":389,"tags":390},[],[31,250],[28,31],{"code":62,"score":22,"supported":14,"title":392,"abstract":393,"tags":394},[],[],[27],[396,268],"农业人工智能 产量预测 可解释性 智慧农业","农业人工智能产量预测可解释性智慧农业-5570","10.5281\u002Fzenodo.23545079",{"doi":398,"openalex_id":400,"authors":401,"venue":363,"cited_by_count":82,"oa_url":360,"card":404,"direction":87,"ingested_from":89},"W7223114002",[402],{"name":403,"orcid":9},"Kadiatou Barry",{"tldr":405,"method":406,"finding":407,"direction":87,"opportunity":408},"推导卫星云掩膜缺口下反事实解释可靠性的理论界，并评估其对合作社储粮决策的影响。","基于Lipschitz连续性假设与掩膜扰动分析推导可靠性界，并用2000个设计单","缺口比例上升使可靠性非线性下降；ICC=0.64表明需合作社层级聚合以保持解释稳定。","可研究不同作物区云掩膜统计特性下的自适应解释暂停阈值与聚合策略。","2026-10-22T11:20:39.240791Z",{"id":411,"title":412,"url":413,"summary":414,"summary_zh":415,"content":9,"source_name":416,"source_url":413,"published_at":417,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":418,"score_detail":419,"sources":421,"tags":423,"primary_topic":426,"secondary_topics":431,"classification":432,"search_phrases":455,"slug":458,"view_count":82,"doi":459,"paper":460,"created_at":474},5561,"Growth Stage and Cultivar Influence the Interpretation of UAV-Derived NDVI for Potato Yield Assessment","https:\u002F\u002Fdoi.org\u002F10.1007\u002Fs11540-026-10161-5","Abstract Single-date UAV vegetation indices are widely used to assess potato crop performance and estimate yield. However, whether their biological interpretation remains consistent across cultivars and growth stages is rarely examined. This study investigated how the relationships between UAV-derived multispectral and thermal canopy indicators and potato yield changed during crop development under contrasting irrigation in two cultivars with contrasting maturity classes (Anouk and Celandine). UAV surveys were conducted in July and August, and canopy metrics were related to final yield and tuber traits. The relationship between NDVI and yield differed markedly between cultivars and growth stages. In the early-maturing cultivar Anouk, July NDVI showed a strong positive correlation with yield ( r = 0.87, p = 0.002), whereas August NDVI was not informative. In the late-maturing cultivar Celandine, the relationship reversed from a positive correlation in July ( r = 0.56) to a strong negative correlation in August ( r = −0.80, p = 0.009), indicating that greater late-season canopy greenness was associated with lower yield. Exploratory LOOCV Random Forest models achieved the highest yield prediction accuracy using July features for Anouk ( R 2 = 0.72) and August features for Celandine ( R 2 = 0.47), while multi-temporal features provided similar predictive performance. Greater temporal declines in NDVI were associated with higher yield in both cultivars, consistent with the change in canopy greenness acting as a phenological indicator of the transition from vegetative growth to tuber bulking. These results demonstrate that the interpretation of UAV-derived vegetation indices is strongly dependent on cultivar maturity and growth stage. A single UAV acquisition may therefore provide misleading assessments of crop performance when canopy phenology is not considered. Rather than serving as fixed proxies for yield, canopy vegetation indices should be interpreted within cultivar-specific and temporal contexts when used for potato monitoring and agronomic decision-making.","摘要 单期无人机植被指数被广泛用于评估马铃薯作物表现和估算产量。然而，其生物学解释在不同品种和生育期之间是否保持一致，鲜有研究加以检验。本研究探讨了在两种成熟性类别不同的品种（Anouk和Celandine）中，不同灌溉条件下，无人机获取的多光谱与热红外冠层指标与马铃薯产量之间的关系在作物发育过程中如何变化。无人机调查于7月和8月进行，并将冠层指标与最终产量及块茎性状进行关联分析。NDVI与产量之间的关系在品种和生育期之间差异显著。在早熟品种Anouk中，7月NDVI与产量呈强正相关（r = 0.87，p = 0.002），而8月NDVI则不具有指示意义。在晚熟品种Celandine中，该关系由7月的正相关（r = 0.56）转变为8月的强负相关（r = −0.80，p = 0.009），表明后期冠层绿度越高与产量越低相关。探索性留一交叉验证（LOOCV）随机森林模型在使用Anouk的7月特征（R² = 0.72）和Celandine的8月特征（R² = 0.47）时取得了最高的产量预测精度，而多时相特征提供了相似的预测表现。两个品种中NDVI随时间下降幅度越大均与产量越高相关，这与冠层绿度变化作为从营养生长向块茎膨大转变的物候指示相一致。这些结果表明，无人机获取的植被指数的解释强烈依赖于品种成熟性和生育期。因此，在未考虑冠层物候的情况下，单次无人机采集可能对作物表现作出误导性评估。冠层植被指数不应作为产量的固定替代指标，而应在品种特异性和时间背景下加以解释，方可用于马铃薯监测和农艺决策。","Potato Research","2026-10-20T00:00:00Z",79,{"impact":237,"substance":18,"depth":19,"authority":20,"freshness":21,"relevant":22,"comment":420},"该研究揭示UAV-NDVI与马铃薯产量的关系随品种熟期和生育阶段而反转，对智慧农业遥感监测具有实质方法学与决策参考价值。",[422],{"name":416,"url":413},[27,424,28,31,425],"马铃薯","作物表型",{"code":427,"slug":428,"name":429,"path":430,"parent_code":111},"A5","tubers-grains","薯类与杂粮","\u002Ftopic\u002Ffield-crops\u002Ftubers-grains",[],{"status":119,"locked":14,"version":35,"method":36,"evidence":433},{"candidates":434,"agricultural_evidence":41},[435,440,447,451],{"code":427,"score":123,"supported":41,"title":436,"abstract":438,"tags":439},[437],"potato",[424,437],[424],{"code":441,"score":92,"supported":41,"title":442,"abstract":443,"tags":446},"H3",[],[444,445],"灌溉","irrigation",[],{"code":49,"score":92,"supported":41,"title":448,"abstract":449,"tags":450},[],[51],[28,425,31],{"code":62,"score":22,"supported":14,"title":452,"abstract":453,"tags":454},[],[],[27],[456,457],"UAV NDVI 马铃薯 产量","马铃薯 品种 生育期 遥感","UAVNDVI马铃薯产量-5561","10.1007\u002Fs11540-026-10161-5",{"doi":459,"openalex_id":461,"authors":462,"venue":416,"cited_by_count":82,"oa_url":468,"card":469,"direction":222,"ingested_from":89},"W7223067378",[463,466],{"name":464,"orcid":465},"Jiangsan Zhao","https:\u002F\u002Forcid.org\u002F0000-0003-3916-7388",{"name":467,"orcid":9},"Jaroslaw S. Grodek","https:\u002F\u002Flink.springer.com\u002Fcontent\u002Fpdf\u002F10.1007\u002Fs11540-026-10161-5.pdf",{"tldr":470,"method":471,"finding":472,"direction":87,"opportunity":473},"研究不同品种和生育期下无人机NDVI与马铃薯产量的关系差异。","两个熟期品种、多时相无人机多光谱与热红外冠层指标，结合随机森林建模。","NDVI与产量的关系随品种和时期反转，晚熟品种8月NDVI与产量强负相关。","可构建融合品种熟期与冠层物候期的时相自适应产量估算模型，避免单次飞行误判。","2026-10-22T11:20:21.975818Z"]