利用Stacking集成学习估算柑橘叶片氮含量
S127; 准确估算柑橘叶片氮含量对于科学合理的施肥具有重要的指导作用,该研究利用Landsat8 OLI卫星遥感影像和地面采样实测数据,以K-近邻(K-Nearest Neighbors,KNN),随机森林(Random Forest,RF)和自适应增强(Adaptive boosting,Adaboost)模型为基础,构建Stacking集成学习框架,实现对柑橘叶片氮含量(Leaf Nitrogen Content,LNC)的估算.首先分析不同氮含量下的光谱反射特征,构建植被指数(Vegetation Indices,VIs)并计算其与柑橘LNC的相关系数;接着利用格网搜索、交叉验证训练模...
Saved in:
| Published in | 农业工程学报 Vol. 37; no. 13; pp. 163 - 171 |
|---|---|
| Main Authors | , , , , , , , |
| Format | Journal Article |
| Language | Chinese |
| Published |
河海大学水文水资源学院,南京 210098%河海大学地球科学与工程学院,南京 211100%新平褚氏农业有限公司,新平 653407
01.07.2021
|
| Subjects | |
| Online Access | Get full text |
| ISSN | 1002-6819 |
| DOI | 10.11975/j.issn.1002-6819.2021.13.019 |
Cover
| Abstract | S127; 准确估算柑橘叶片氮含量对于科学合理的施肥具有重要的指导作用,该研究利用Landsat8 OLI卫星遥感影像和地面采样实测数据,以K-近邻(K-Nearest Neighbors,KNN),随机森林(Random Forest,RF)和自适应增强(Adaptive boosting,Adaboost)模型为基础,构建Stacking集成学习框架,实现对柑橘叶片氮含量(Leaf Nitrogen Content,LNC)的估算.首先分析不同氮含量下的光谱反射特征,构建植被指数(Vegetation Indices,VIs)并计算其与柑橘LNC的相关系数;接着利用格网搜索、交叉验证训练模型,最后将Stacking模型与包括Bagging(Bootstrap Aggregating,Bagging)、人工神经网络(Artificial Neural Network,ANN)在内的多个经典机器学习模型试验结果进行对比分析,并生成柑橘果园的氮含量分布图.结果表明:1)构建的光谱指数与LNC具有较好的相关性,大部分指数相关系数在0.55以上;2)相比KNN、RF、Adaboost等多个单一模型,Stacking模型的估算效果最佳,决定系数达到0.761,均方根误差为1.366 g/kg,平均绝对百分比误差为3.494％;同时,Stacking模型的赤池信息准则(Akaike Information Criterion,AIC)值最低,是观测期内LNC估算的最优模型;3)研究区内LNC值整体上处于30.5～31.5 g/kg左右,接近柑橘种植的理想区间,模型估算与实测值趋于一致.总体上,该研究采用的光谱特征能够有效表征柑橘冠层叶片氮含量,并证明Stacking集成学习能综合多个基模型的优点,提高模型的准确性,为利用卫星遥感展开作物参数估算提供新的思路. |
|---|---|
| AbstractList | S127; 准确估算柑橘叶片氮含量对于科学合理的施肥具有重要的指导作用,该研究利用Landsat8 OLI卫星遥感影像和地面采样实测数据,以K-近邻(K-Nearest Neighbors,KNN),随机森林(Random Forest,RF)和自适应增强(Adaptive boosting,Adaboost)模型为基础,构建Stacking集成学习框架,实现对柑橘叶片氮含量(Leaf Nitrogen Content,LNC)的估算.首先分析不同氮含量下的光谱反射特征,构建植被指数(Vegetation Indices,VIs)并计算其与柑橘LNC的相关系数;接着利用格网搜索、交叉验证训练模型,最后将Stacking模型与包括Bagging(Bootstrap Aggregating,Bagging)、人工神经网络(Artificial Neural Network,ANN)在内的多个经典机器学习模型试验结果进行对比分析,并生成柑橘果园的氮含量分布图.结果表明:1)构建的光谱指数与LNC具有较好的相关性,大部分指数相关系数在0.55以上;2)相比KNN、RF、Adaboost等多个单一模型,Stacking模型的估算效果最佳,决定系数达到0.761,均方根误差为1.366 g/kg,平均绝对百分比误差为3.494％;同时,Stacking模型的赤池信息准则(Akaike Information Criterion,AIC)值最低,是观测期内LNC估算的最优模型;3)研究区内LNC值整体上处于30.5～31.5 g/kg左右,接近柑橘种植的理想区间,模型估算与实测值趋于一致.总体上,该研究采用的光谱特征能够有效表征柑橘冠层叶片氮含量,并证明Stacking集成学习能综合多个基模型的优点,提高模型的准确性,为利用卫星遥感展开作物参数估算提供新的思路. |
| Author | 刘凌杰 庄翠珍 李勇 席顺忠 袁晓慧 吴彤 葛莹 任孟杰 |
| AuthorAffiliation | 河海大学水文水资源学院,南京 210098%河海大学地球科学与工程学院,南京 211100%新平褚氏农业有限公司,新平 653407 |
| AuthorAffiliation_xml | – name: 河海大学水文水资源学院,南京 210098%河海大学地球科学与工程学院,南京 211100%新平褚氏农业有限公司,新平 653407 |
| Author_FL | Ren Mengjie Zhuang Cuizhen Li Yong Xi Shunzhong Yuan Xiaohui Wu Tong Ge Ying Liu Lingjie |
| Author_FL_xml | – sequence: 1 fullname: Wu Tong – sequence: 2 fullname: Li Yong – sequence: 3 fullname: Ge Ying – sequence: 4 fullname: Liu Lingjie – sequence: 5 fullname: Xi Shunzhong – sequence: 6 fullname: Ren Mengjie – sequence: 7 fullname: Yuan Xiaohui – sequence: 8 fullname: Zhuang Cuizhen |
| Author_xml | – sequence: 1 fullname: 吴彤 – sequence: 2 fullname: 李勇 – sequence: 3 fullname: 葛莹 – sequence: 4 fullname: 刘凌杰 – sequence: 5 fullname: 席顺忠 – sequence: 6 fullname: 任孟杰 – sequence: 7 fullname: 袁晓慧 – sequence: 8 fullname: 庄翠珍 |
| BookMark | eNo9j8tKAzEYRrOoYK19DHE18f-TzCVLKd6g4EJdl8xMMkyVFIyivoCtq1YQFFzoSixi6UoQfJzODH0LK4qrA9_ifJwVUrM9qwlZQ6CIMvQ3ujR3zlIEYF4QoaQMGFLkFFDWSP1_XyZN5_IYfOQhgMA68YvBuLp7PThTyXFus_njdTkYFe8vs8_n2de0mtyXT7fl-KEYflQ3_XI6KUZv8_5wlSwZdeJ0848NcrS9ddja9dr7O3utzbbnEJj00gRCFkPAAyG0lmkIWmqeqiDxuTBcMSFEJDRTRsaR1oghKGMSn4U-QoQxb5D1X--FskbZrNPtnZ_axWPHXmXJZfyTiXwRyb8Bp95b0w |
| ClassificationCodes | S127 |
| ContentType | Journal Article |
| Copyright | Copyright © Wanfang Data Co. Ltd. All Rights Reserved. |
| Copyright_xml | – notice: Copyright © Wanfang Data Co. Ltd. All Rights Reserved. |
| DBID | 2B. 4A8 92I 93N PSX TCJ |
| DOI | 10.11975/j.issn.1002-6819.2021.13.019 |
| DatabaseName | Wanfang Data Journals - Hong Kong WANFANG Data Centre Wanfang Data Journals 万方数据期刊 - 香港版 China Online Journals (COJ) China Online Journals (COJ) |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Agriculture |
| DocumentTitle_FL | Estimation of nitrogen contents in citrus leaves using Stacking ensemble learning |
| EndPage | 171 |
| ExternalDocumentID | nygcxb202113019 |
| GrantInformation_xml | – fundername: ("十三五"国家重点研发计划项目); (国家自然科学基金); (云南省重大科技专项计划项目资助) funderid: ("十三五"国家重点研发计划项目); (国家自然科学基金); (云南省重大科技专项计划项目资助) |
| GroupedDBID | -04 2B. 4A8 5XA 5XE 92G 92I 93N ABDBF ABJNI ACGFO ACGFS ACUHS AEGXH AIAGR ALMA_UNASSIGNED_HOLDINGS CCEZO CHDYS CW9 EOJEC FIJ IPNFZ OBODZ PSX RIG TCJ TGD TUS U1G U5N |
| ID | FETCH-LOGICAL-s1029-dc072b063644ee9d70e9e3da6c534f3a244484e2af9b8ee1170affc52751081b3 |
| ISSN | 1002-6819 |
| IngestDate | Thu May 29 04:08:36 EDT 2025 |
| IsPeerReviewed | false |
| IsScholarly | true |
| Issue | 13 |
| Keywords | Stacking 模型 植被指数 遥感 柑橘 卫星 氮 |
| Language | Chinese |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-s1029-dc072b063644ee9d70e9e3da6c534f3a244484e2af9b8ee1170affc52751081b3 |
| PageCount | 9 |
| ParticipantIDs | wanfang_journals_nygcxb202113019 |
| PublicationCentury | 2000 |
| PublicationDate | 2021-07-01 |
| PublicationDateYYYYMMDD | 2021-07-01 |
| PublicationDate_xml | – month: 07 year: 2021 text: 2021-07-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationTitle | 农业工程学报 |
| PublicationTitle_FL | Transactions of the Chinese Society of Agricultural Engineering |
| PublicationYear | 2021 |
| Publisher | 河海大学水文水资源学院,南京 210098%河海大学地球科学与工程学院,南京 211100%新平褚氏农业有限公司,新平 653407 |
| Publisher_xml | – name: 河海大学水文水资源学院,南京 210098%河海大学地球科学与工程学院,南京 211100%新平褚氏农业有限公司,新平 653407 |
| SSID | ssib051370041 ssj0041925 ssib001101065 ssib023167668 |
| Score | 2.4132657 |
| Snippet | S127; 准确估算柑橘叶片氮含量对于科学合理的施肥具有重要的指导作用,该研究利用Landsat8 OLI卫星遥感影像和地面采样实测数据,以K-近邻(K-Nearest Neighbors,KNN),随机森林(Random Forest,RF)和自适应增强(Adaptive... |
| SourceID | wanfang |
| SourceType | Aggregation Database |
| StartPage | 163 |
| Title | 利用Stacking集成学习估算柑橘叶片氮含量 |
| URI | https://d.wanfangdata.com.cn/periodical/nygcxb202113019 |
| Volume | 37 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV3NaxQxFB9KC6IH8RPrFz2YU9l1PjKT5JjszlIEPbXQk2VnNlNPK7Rb0P4Btp5aQVDwoCexiKUnQfDP6W7pf-F7b7K7s7Xa6mXJJi_v_ZJfyMsLmcTzHtg2h7jC5jXRoa0baWtZVuCV-9xmcce3ir56f_wkWVjij5bj5anpp5VTSxu9rJ5vnvpdyf-wCnnAK34l-w_MjpRCBqSBX_gFhuH3XByzNGZSMq1YKpjiTEtYO-a4-c1SxZRhMmFpgiLKR1ndZBpyODOKaZ8SDWZ8rK1TpgQKqxZTASZAq5JkocVMgjJSMUkyUAXkoQjUaoO2IF9OnBCkiqCtQVYAgMYcA4ZiMieZNBVIAFJD0ZB-p9twqgQifFwCSptMknlQMfajLJWIHFoNCSg3qqoN-6BsDSBtOC3Gr256hMHogGw5TKmpITMRJQg9IoZ-FhPQTYkUVCbjDsIcibUkFRk9yQF0LnAQwggnUE3qfY5iujEPAbIPaMP4fAhi7OaSRrAhI-pgQTRWOZeu1_5IwhmY8No_h0lRE1GXInASMSHFlA8D5hT26S8ModJM2RkSbDeGY0yS4ZPK55M44uWTxc55ondNpHOBzrtGojqLRBVfGTjPVi67gvIlnt89uhIxuXQ0UR-ZqOOoqAdR3XfmJi9N775czV9kKANrNLwVeCYUAo9xzGjTNK1xwBDgnsjIo4V4L0QyDsDjIMLnH0aHxvDIREznJxyMCx4bgnz4N4j0SWC3aHdXK6vXxSveZRd2zulyDrnqTW0-u-Zd0qtr7uode92L-9t7R2-_DGeQ4w-vBtu7_W-fD398Ovx5cLT_bvDxzWDvfX_n-9HrrcHBfn_36_HWzg1vqZUuNhZq7lGV2nqAR906uS_CDAITCISsVR0B07GNOu0kBzaLqA3LfS65DduFyqS1-DBVuyjyOBTgvSHGjW56093nXXvLm6PbSHmeFFCXF4WUAc-E6Kicy1wUcTHrzblGr7hJc33lBDG3zxa5410czwB3vene2oa9B4FAL7vv2PwFaJ-3PQ |
| linkProvider | EBSCOhost |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=%E5%88%A9%E7%94%A8Stacking%E9%9B%86%E6%88%90%E5%AD%A6%E4%B9%A0%E4%BC%B0%E7%AE%97%E6%9F%91%E6%A9%98%E5%8F%B6%E7%89%87%E6%B0%AE%E5%90%AB%E9%87%8F&rft.jtitle=%E5%86%9C%E4%B8%9A%E5%B7%A5%E7%A8%8B%E5%AD%A6%E6%8A%A5&rft.au=%E5%90%B4%E5%BD%A4&rft.au=%E6%9D%8E%E5%8B%87&rft.au=%E8%91%9B%E8%8E%B9&rft.au=%E5%88%98%E5%87%8C%E6%9D%B0&rft.date=2021-07-01&rft.pub=%E6%B2%B3%E6%B5%B7%E5%A4%A7%E5%AD%A6%E6%B0%B4%E6%96%87%E6%B0%B4%E8%B5%84%E6%BA%90%E5%AD%A6%E9%99%A2%2C%E5%8D%97%E4%BA%AC+210098%25%E6%B2%B3%E6%B5%B7%E5%A4%A7%E5%AD%A6%E5%9C%B0%E7%90%83%E7%A7%91%E5%AD%A6%E4%B8%8E%E5%B7%A5%E7%A8%8B%E5%AD%A6%E9%99%A2%2C%E5%8D%97%E4%BA%AC+211100%25%E6%96%B0%E5%B9%B3%E8%A4%9A%E6%B0%8F%E5%86%9C%E4%B8%9A%E6%9C%89%E9%99%90%E5%85%AC%E5%8F%B8%2C%E6%96%B0%E5%B9%B3+653407&rft.issn=1002-6819&rft.volume=37&rft.issue=13&rft.spage=163&rft.epage=171&rft_id=info:doi/10.11975%2Fj.issn.1002-6819.2021.13.019&rft.externalDocID=nygcxb202113019 |
| thumbnail_s | http://utb.summon.serialssolutions.com/2.0.0/image/custom?url=http%3A%2F%2Fwww.wanfangdata.com.cn%2Fimages%2FPeriodicalImages%2Fnygcxb%2Fnygcxb.jpg |