基于聚类法筛选历史相似气象数据的玉米产量DSSAT-CERES-Maize预测

陈 上; 窦子荷; 蒋腾聪; 李华龙; 马海姣; 冯 浩; 于 强; 何建强

doi:10.11975/j.issn.1002-6819.2017.19.019

基于聚类法筛选历史相似气象数据的玉米产量DSSAT-CERES-Maize预测

陈上^1,2,
窦子荷^1,2,
蒋腾聪^1,2,
李华龙^1,2,
马海姣^1,2,
冯浩^2,3,
于强³,
何建强^1,2,3

1.
西北农林科技大学旱区农业水土工程教育部重点实验室，杨凌 712100
2.
西北农林科技大学中国旱区节水农业研究院，杨凌 712100
3.
中国科学院水利部水土保持研究所，杨凌 712100

基金项目: 国家高技术研究发展计划（863计划）（2013AA102904）；陕西省科技统筹创新工程计划项目（2016KTZDNY03-06）；黄土高原土壤侵蚀与旱地农业国家重点实验室开放基金（A314021402-1611）；西北农林科技大学人才专项资金（千人计划项目）；高等学校学科创新引智计划（111计划）（B12007）

计量
- 文章访问数: 2130
- HTML全文浏览量: 0
- PDF下载量: 1098
出版历程
- 收稿日期: 2017-02-20
- 修回日期: 2017-08-09
- 发布日期: 2017-09-30

Maize yield forecast with DSSAT-CERES-Maize model driven by historical meteorological data of analogue years by clustering algorithm

1.
Key Laboratory for Agricultural Soil and Water Engineering in Arid Area of Ministry of Education, Northwest A&F University, Yangling 712100, China
2.
Institute of Water-Saving Agriculture in Arid Areas of China, Northwest AandF University, Yangling 712100, China
3.
Institute of Water and Soil Conservation, Chinese Academy of Science and Ministry of Water Resource,Yangling 712100, China

摘要

摘要: 根据陕西杨凌、合阳、长武3个站点各2 a玉米试验，在对玉米生长模拟模型CERES-Maize进行调试、验证的基础上，探索在生育期内进行动态产量预测的方法并验证。研究将目标生育期内未知气象数据分别用试验地的多年历史同期数据代替，结合生育期实时数据对应生成多个完整的气象数据序列运行模型预测产量。随着生育期的推进，逐日在气象数据序列中融入目标年实测的气象数据，从播种至收获动态模拟玉米产量。此外该研究使用改进前后的K-NN算法从历史气象年份中筛选目标年的气象相似年份进而预测产量。通过对3种方法预测精度及预测效率对比，确定改进的K-NN算法最优。研究表明，玉米生育前期产量预测可靠性和准确率均较差，抽雄后预测精度迅速提高；利用改进的K-NN算法在3个站点全生育期预测产量的平均绝对相对误差的均值分别为9.9%、19.8%、17.9%，抽雄后预测产量的平均绝对相对误差在0.2%～12.6%之间，相比于使用全部历史年份数据进行全生育期产量预测，模拟所需时间从61 min缩短至25 min。对该方法中降雨因子的筛选进一步改进可提高预报精度，未来有望达到业务应用水平。
- 聚类 /
- 气象预报 /
- 模型 /
- 玉米 /
- 产量预测 /
- CERES-Maize /
- K-NN
Abstract: Abstract: Crop growth simulation models can simulate the processes of crop growth, development, yield formation, and its response to environment, which provides an effective method for crop yield forecast. However, how to select suitable weather data for the forecast is still an open question. In this study, we established a method for maize yield forecast based on maize growth simulation model of CERES-Maize and historical weather data from the year of 1956 to 2015. Two year's experimental data from 3 sites of Yangling (2014 and 2015), Heyang (2009 and 2011) and Changwu (2010 and 2011) in Shaanxi Province were used to test the reliable and accuracy of the method established. The weather data needed for model simulation were divided into 2 different groups including the known weather data and unknown weather data during the whole growth season of spring maize. The known weather data were obtained from local weather stations, while unknown data were supplemented with historical weather data of multiple years in the local experimental sites. Multiple complete climatic data series were then created and used to run the CERES-Maize model to forecast maize yield for a given year. As the advancing of maize growth season, the daily weather data were gradually merged into the observed weather data in a target year. Consequently, the daily maize yield was forecasted from sowing day to harvest. In addition, in order to reduce the times of model runs and reduce the uncertainties in yield forecasts, this study compared the daily meteorological data of historical and target years with normal K nearest neighbor (K-NN) and a modified K-NN algorithm to select several historical analogue years whose weather data were similar to the target year. The results showed that: 1) the model was suitable for the yield simulation since the absolute relative error was smaller than 15%; 2) the data distribution of predicted yields began to converge and the uncertainty decreased rapidly after the tasseling stage. For example, the predicted yield after 30, 60 and 90 days (the tasseling stage) of sowing was 3 531-14 461, 3 413-14 828 and 961-13 210 kg/hm2, respectively. But, the yield was 49 33-10 826, 8 484-10 565 kg/hm2, respectively after 100 and 130 days of sowing. The coefficient of variation had a sudden fall around the tasseling stage; 3) Yield forecast accuracy was generally lower than expectation for the method based on all historical data and climatic analogue years selected with historical data. The model run cost 61 min for a yield prediction during a complete growth stage of spring maize, indicting a necessary change in the prediction method optimization; 4) Among the 3 methods, the modified K-NN method showed a higher prediction accuracy and shorter run time than the other methods. The coefficient of variation was 11.7%-23.8% for the modified K-NN method, 15.1%-29.1% for the historical data, and 14.7%-26.9% for the K-NN method, respectively. To complete the yield prediction of a growth stage of spring maize, the modified K-NN method only took 14 min, which was shorter than the normal K-NN method. Thus, the modified K-NN method in this study had a big potential for the yield prediction by the CERES-Maize model. The study provides an effective method for selecting precipitation factor used for the yield prediction by crop models.
- clustering algorithms /
- weather forecasting /
- models /
- maize /
- yield forecasting /
- CERES-Maize /
- K-NN

HTML全文

参考文献(54)

[1]	中华人民共和国国家统计局. 中国统计年鉴[M]. 北京：中国统计出版社，2016.
[2]	代立芹，吴炳方，李强子，等. 作物单产预测方法研究进展[J]. 农业网络信息，2006(4)：24－27.Dai Liqin, Wu Bingfang, Li Qiangzi, et al. Overview of technique used by crop yield for ecasting[J]. Agricultural Network Information, 2006(4): 24－27. (in Chinese with English abstract)
[3]	甘一忠，刘流. 特征展开模糊推理模式在农作物产量预报中的应用[J]. 模糊系统与数学，2002，16(1)：104－109.Gan Yizhong, Liu Liu. Application of character spread faintness consequence model to forecast the output of crop[J]. Fuzzy Systems and Mathematics, 2002, 16(1): 104－109. (in Chinese with English abstract)
[4]	许清海，孟令尧，阳小兰，等. 应用花粉分析预报板栗产量的研究[J]. 植物生态学报，1999，23(4)：370－378.Xu Qinghai, Meng Lingyao, Yang Xiaolan, et al. Prediction yield of castanea mollissima with pollen concentration[J]. Acta Phytoecologica Sinica, 1999, 23(4): 370－378. (in Chinese with English abstract)
[5]	陈锡康，杨翠红. 农业复杂巨系统的特点与全国粮食产量预测研究[J]. 系统工程理论与实践，2002，22(6)：108－112.Chen Xikang, Yang Cuihong. Characteristic of agricultural complex giant system and national grain output prediction[J]. Systems Engineering Theory and Practice, 2002, 22(6): 108－112. (in Chinese with English abstract)
[6]	吴炳方. 全国农情监测与估产的运行化遥感方法[J]. 地理学报，2000，55(1)：25－35.Wu Bingfang. Operational remote sensing methods for agricultural statistics[J]. Acta Geographica Sinica, 2000, 55(1): 25－35. (in Chinese with English abstract)
[7]	刘布春，刘文萍，梅旭荣，等. 我国农业气象业务引入作物生长模型的前景[J]. 气象，2006，32(12)：10－15.Liu Buchun, Liu Wenping, Mei Xurong, et al. Prospects for crop growth models introduced into agrometeorology services in china[J]. Meteorological Monthly, 2006, 32(12): 10－15. (in Chinese with English abstract)
[8]	吴蕾，柏军华，肖青，等. 作物生长模型与定量遥感参数结合研究进展与展望[J]. 农业工程学报，2017，33(9)：155－166.Wu Lei, Bai Junhua, Xiao Qing, et al. Research process and prospect on combining crop groth models with paramerers derived from quantitative remote sensing[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2017, 33(9): 155－166. (in Chinese with English abstract)
[9]	曹宏鑫，赵锁劳，葛道阔，等. 作物模型发展探讨[J]. 中国农业科学，2011，44(17)：3520－3528.Cao Hongxin, Zhao Suolao, Ge Daokuo, et al. Discussion on development of crop models[J]. Scientia Agricultura Sinica, 2011, 44(17): 3520－3528. (in Chinese with English abstract)
[10]	王亚莉，贺立源. 作物生长模拟模型研究和应用综述[J]. 华中农业大学学报，2005，24(5)：529－535.Wang Yali, He Liyuan. A review on the research and application of crop simulation model[J]. Journal of Huazhong Agricultural University, 2005, 24(5): 529－535. (in Chinese with English abstract)
[11]	Jones J W, Hoogenboom G, Porter C H, et al. The DSSAT cropping system model[J]. European Journal Agronomy, 2003, 18(3): 235－265.
[12]	Hoogenboom G, Jones J, Wilkens P, et al. Decision Support System for Agrotechnology Transfer (DSSAT) Version 4.5[M]. Honolulu: University of Hawaii, 2010.
[13]	Jones C A, Kiniry J R, Dyke P T. CERES-Maize: A Simulation Model of Maize Growth and Development[M]. Texas: TexasA and? M University, 1986.
[14]	He J, Dukes M D, Hochmuth G J, et al. Evaluation of sweet corn yield and nitrogen leaching with CERES-Maize considering input parameter uncertainties[J]. Transactions of the ASABE, 2011, 54(4): 1257－1268.
[15]	Jing Q, Shang J, Huffman T, et al. Using the CSM-CERES- Maize model to assess the gap between actual and potential yields of grain maize[J]. Journal of Agricultural Science, 2016, 155(2): 1－22.
[16]	Kassie B T, Ittersum M K V, Hengsdijk H, et al. Climate-induced yield variability and yield gaps of maize (Zea mays L.) in the Central Rift Valley of Ethiopia[J]. Field Crops Research, 2014, 160(4):41－53.
[17]	Jin Zhiqing, Zhu Dawei. Impacts of changes in climate and its variability on food production in northeast china[J]. Acta Agronomica Sinica, 2008, 34(9): 1588－1597.
[18]	Guo Ruiping, Lin Zhonghui, Mo Xingguo, et al. Responses of crop yield and water use efficiency to climate change in the North China Plain[J]. Agricultural Water Management, 2010, 97(8): 1185－1194.
[19]	黄晚华，薛昌颖，李忠辉，等. 基于作物生长模拟模型的产量预报方法研究进展[J]. 中国农业气象，2009，30(S1)：140－143.Huang Wanhua, Xue Changyin, Li Zhonghui, et al. Research progresses in yield forecasting method based on crop growth simulation model in china[J]. Chinese Journal of Agrometeorology, 2009, 30(S1): 140－143. (in Chinese with English abstract)
[20]	Zinyengere N, Mhizha T, Mashonjowa E, et al. Using seasonal climate forecasts to improve maize production decision support in Zimbabwe[J]. Agricultural and Forest Meteorology, 2012, 151(12): 1792-1799.
[21]	Porter J R, Semenov M A. Crop responses to climatic variation[J]. Philosophical Transactions of the Royal Society of London, 2005, 360(1463): 2021.
[22]	Semenov M A, Barrow E M. Use of a stochastic weather generator in the development of climate change scenarios[J]. Climatic Change, 1997, 35(4): 397－414.
[23]	Hoogenboom G. Contribution of agrometeorology to the simulation of crop production and its applications[J]. Agricultural and Forest Meteorology, 2000, 103(1): 137－157.
[24]	Hyndman R J, Koehler A B. Another look at measures of forecast accuracy[J]. International Journal of Forecasting, 2005, 22(4): 679－688.
[25]	Goel S, Dash S K. Response of model simulated weather parameters to round-off-errors on different systems[J]. Environmental Modelling and Software, 2007, 22(8): 1164－1174.
[26]	Geng S, Penning de Vries F W T , Supit I. A simple method for generating daily rainfall data[J]. Agricultural and Forest Meteorology, 1986, 36(4): 363－376.
[27]	Kilsby C G, Jones P D, Burton A, et al. A daily weather generator for use in climate change studies[J]. Environmental Modelling and Software, 2007, 22(12): 1705－1719.
[28]	Jones P G, Thornton P K. MarkSim: Software to generate daily weather data for Latin America and Africa.[J]. Agronomy Journal, 2000, 92(3): 445－453.
[29]	Richardson C W. Stochastic simulation of daily precipitation, temperature, and solar radiation[J]. Water Resources Research, 1981, 17(1): 182－190.
[30]	Nicks A D, Harp J F. Stochastic generation of temperature and solar radiation data[J]. Journal of Hydrology, 1980, 48(1/2): 1－17.
[31]	Hartkamp A D, White J W, Hoogenboom G. Comparison of three weather generators for crop modeling: A case study for subtropical environments[J]. Agricultural Systems, 2003, 76(2): 539－560.
[32]	Semenov M A, Brooks R J, Barrow E M, et al. Comparison of the WGEN and LARS-WG stochastic weather generators for diverse climates[J]. Climate Research, 1998, 10(2): 95－107.
[33]	Sharif M, Burn D H. Simulating climate change scenarios using an improved K-Nearest Neighbor model[J]. Journal of Hydrology, 2006, 325(1): 179－196.
[34]	Brandsma T, K?nnen G P. Application of nearest-neighbor resampling for homogenizing temperature records on a daily to sub-daily level[J]. International Journal of Climatology, 2010, 26(26): 75－89.
[35]	彭思岭. 气象要素时空插值方法研究[D]. 长沙：中南大学，2010.Peng Siling. Developments of Spatio-temporal Interpolation Methods for Meteorological Elements[D]. Changsha: Zhongnan University, 2010. (in Chinese with English abstract)
[36]	王连喜，陈怀亮，李琪，等. 农业气候区划方法研究进展[J]. 中国农业气象，2010，31(2)：277－281.Wang Lianxi, Chen Huailiang, Li Qi, et al. Research progress on agricultural climatic division method in China[J]. Chinese Journal of Agrometeology, 2010, 31(2): 227－281. (in Chinese with English abstract)
[37]	王雪姣，潘学标，王森，等. 基于COSIM模型的新疆棉花产量动态预报方法[J]. 农业工程学报，2017，33(8)：160－165.Wang Xuejiao, Pan Xuebiao, Wang Sen, et al. Dynamic prediction method for cotton yield based on COSIM model in Xinjiang[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2017, 33(8): 160－165. (in Chinese with English abstract)
[38]	易雪，王建林，宋迎波，等. 早稻产量动态集成预报方法研究[J]. 中国水稻科学，2011，25(3)：307－313.Yi Xue, Wang Jianlin, Song Yingpo, et al. Study on dynamic integrated prediction of early rice yield[J]. Chinese Journal of Rice Science, 2011, 25(3): 307－313. (in Chinese with English abstract)
[39]	王建林，宋迎波. 棉花产量动态预测方法研究[J]. 中国棉花，2002，29(9)：5－8.Wang Jianlin, Song Yingbo. Study on dynamic predictionmethod for cotton yield[J]. China Cotton, 2002, 29(9): 5－7. (in Chinese with English abstract)
[40]	陈艳春，李鸿怡，赵红. 山东棉花引种的农业气候相似诊断分析[J]. 气象，1997，23(3)：42－45.Chen Yanchun, Li Hongyi, Zhao Hong. Agroclimatic similarity diagnosic analysis for introduction of cotton varieties in Shandong province[J]. Meteorological Monthly, 1997, 23(3): 42－45
[41]	Young K C. A multivariate chain model for simulating climatic parameters from daily data[J]. Journal of Applied Meteorology, 2010, 33(6): 661－671.
[42]	Rajagopalan B, Lall U. A k-nearest-neighbor simulator for daily precipitation and other weather variables[J]. Water Resources Research, 1999, 35(10): 3089－3101.
[43]	Buishand T A, Brandsma T. Multisite simulation of daily precipitation and temperature in the Rhine basin by nearest-neighbor resampling[J]. Water Resources Research, 2001, 37(11): 2761－2776.
[44]	Bannayan M, Hoogenboom G. Weather analogue: A tool for real-time prediction of daily weather data realizations based on a modified k-nearest neighbor approach[J]. Environmental Modelling and Software, 2008, 23(6): 703－713.
[45]	Hoogenboom G, Jones J, Wilkens P, et al. Decision Support System for Agrotechnology Transfer (DSSAT) version 4.6.1.0[M] Washington: DSSAT Foundation, 2015.
[46]	Jones C A, Ritchie J T, Kiniry J R, et al. The CERES wheat and maize models[C]//Proceedings of the International Symposium on Minimum Data Sets for Agrotechnology Transfer, ICRISAT Center, India,1983: 95－100.
[47]	Ritchie J R, Otter S. Description and performance of CERES-Wheat: A user-oriented wheat yield model[R]. USA: ARS-United States Department of Agriculture, 1985: 159－175.
[48]	刘海波，袁靖. CERES玉米模拟模式评价及其应用[J]. 黑龙江气象，1997(1)：22－25.
[49]	Cover T, Hart P. Nearest neighbor pattern classification[J]. IEEE Transactions on Information Theory, 1967, 13(1): 21－27.
[50]	王石立，马玉平. 作物生长模拟模型在我国农业气象业务中的应用研究进展及思考[J]. 气象，2008，34(6)：3－10.Wang Shili, Ma Yuping. The progress in application of crop growth simulation models to agro-meteorological services in china[J]. Meteorological Monthly, 2008, 34(6): 3－10. (in Chinese with English abstract)
[51]	Lawless C, Semenov M A. Assessing lead-time for predicting wheat growth using a crop simulation model[J]. Agricultural and Forest Meteorology, 2005, 135(1): 302－313.
[52]	于振文. 作物栽培学各论[M]. 北京：中国农业出版社，2003.
[53]	刘铁梅，谢国生. 农业系统分析与模拟[M]. 北京：科学出版社，2010.
[54]	郭建平. 农业气象灾害监测预测技术研究进展[J]. 应用气象学报，2016，27(5)：620－630.Guo Jianping. Research progress on agricultural meteorological disaster monitoring and forecast[J]. Journal of Applied Meteorological Science, 2016, 27(5): 620－630. (in Chinese with English abstract)

施引文献(39)

期刊类型引用(22)

1.	郭维红，蒋非非，马静，朱新华，陈浮. 2000—2020年中国耕地旱改水空间格局演变及其适应性管理. 农业工程学报. 2024(04): 292-303 . 本站查看
2.	左小康，刘嘉骏，冯胜梅，郭殿繁，李苗. 基于GEE云平台的三江平原水稻种植区作物提取与监测研究. 遥感技术与应用. 2024(05): 1284-1294 . 百度学术
3.	王翔宇，张学霞，胡韵哲，穆微，方华军. 基于地理探测器的耕地土壤肥力及影响因子. 环境科学. 2024(12): 7378-7389 . 百度学术
4.	杨喆，褚琳，肖燚彬，王晨，谭婉怡，王天巍，蔡崇法. 2017—2021年东北地区主要粮食作物覆盖类型时空演变及其影响因素. 资源科学. 2023(05): 966-979 . 百度学术
5.	陈志昂，孙颖娜，慕丰宇. 三江平原地下水补给利用研究现状与进展. 绿色科技. 2023(12): 232-237 . 百度学术
6.	周璐红，张康. 2000—2020年延安市植被覆盖时空变化及其影响因素. 水土保持通报. 2023(04): 356-365 . 百度学术
7.	谢宇轩，梁鑫源. 苏州市水田破碎化时空演变研究. 地域研究与开发. 2023(05): 127-133 . 百度学术
8.	吴大放，马佩芳，李龙，李昭铖，梁逸璇. 基于地理探测器的区域土地利用转型时空演变及因子探测——以珠海市为例. 华南师范大学学报(自然科学版). 2023(04): 50-61 . 百度学术
9.	孙博，吴雨珂，闫白冰，牛继强. 1990—2020年淮河生态经济带耕地资源分布变化特征与驱动机制. 农业工程学报. 2023(23): 247-258 . 本站查看
10.	罗晓虹，王蓥燕，王舒，郑杰炳，王丹，王子芳，高明. 1990-2015年三峡库区重庆段水田时空分布及演变特征. 中国农业资源与区划. 2022(01): 71-80 . 百度学术
11.	解帅，殷冠羿，娄毅，魏玮. 1990—2020年中国耕地利用的“水旱分异”格局及机制分析. 中国土地科学. 2022(06): 113-124 . 百度学术
12.	尤李俊，王少丽，刘长荣，张兴波，樊林生，陶园，彭舟. 1957-2019年三江平原降雨洪涝特征分析——以绥滨县为例. 水资源与水工程学报. 2022(04): 40-49 . 百度学术
13.	刘波，樊成芳，束龙仓，王文鹏，胡鑫. 气候变化与人类活动对三江平原典型区地下水埋深影响预估. 灌溉排水学报. 2022(08): 63-69 . 百度学术
14.	于凤荣，孙嘉曼，春香. 基于垦区/农区对比分析的三江平原水田变化分析. 现代化农业. 2022(10): 22-26 . 百度学术
15.	孔胃，梁勇，吴闯，王长鹏，田家宽，崔健. 基于地理探测器的济南市生态环境评价及影响因素分析. 测绘与空间地理信息. 2022(12): 45-48+52 . 百度学术
16.	金翠，李欣涛，佟欣羽，曾令辉，李凤秀. 三江平原水田景观对局地热环境的影响. 生态学报. 2021(05): 1766-1776 . 百度学术
17.	周洋，赵小敏，郭熙，韩逸. 基于地理探测器的寻乌县土壤微量元素影响因子分析. 核农学报. 2021(06): 1420-1432 . 百度学术
18.	张红梅，宋戈. 黑龙江省典型县耕地种植结构空间分异特征与影响因素. 农业机械学报. 2021(05): 239-248 . 百度学术
19.	田爽，罗光杰，李阳兵，廖晶晶，罗旭玲，王权. 典型传统村落集聚地土地利用演变特征及驱动因素. 长江流域资源与环境. 2021(11): 2682-2692 . 百度学术
20.	刘园，周清波，余强毅，吴文斌. 基于遥感数据的大尺度区域水田空间格局及生态服务价值变化分析. 智慧农业(中英文). 2020(01): 43-57 . 百度学术
21.	宋戈，张文琦. 粮食作物种植视角下东北粮食主产区耕地利用的时空分化特征. 农业工程学报. 2020(15): 1-8 . 本站查看
22.	杨春霞，郑华，欧阳志云. 三江平原土地利用变化、效应与驱动力. 环境保护科学. 2020(05): 99-104 . 百度学术