长时间序列气象数据结合随机森林法早期预测冬小麦产量
|
摘要
冬小麦生育早期的产量预测对于制定冬小麦整个生长期的精准管理决策具有重要参考意义。该文基于随机森林算法,采用1990—2015年河南省小麦平均拔节期至平均抽穗期地面观测气象数据与统计产量数据,分别提取不同穗分化期的温湿度、降水等47个气象要素和小麦种植区经纬度、高程3个空间要素,共计50个参数作为特征变量集,以实际单产、气象产量和相对气象产量分别作为目标变量,构建多种变量组合模型对冬小麦产量进行回归预测,并结合袋外数据重要性结果对产量影响因子进行分析。研究结果表明:1)使用气象产量和相对气象产量作为目标变量建模的预测效果优于单产模型,决定系数R~2均达到0.8以上,气象产量的平均绝对误差(mean absolute error,MAE)和均方根误差(root mean square error,RMSE)分别为415和558 kg/hm~2,相对气象产量的MAE和RMSE分别为0.07和0.09;2)相较于气象特征,空间特征在产量预测中起决定性作用,且小花分化期以及抽穗开花期的气象特征产量预测精度高于其他穗分化期;3)在气象特征中,利用袋外数据变量重要性得出平均温度、最低温度、负积温、最高温度在不同生育阶段对产量的影响程度。该研究结果为冬小麦生育早期产量预测提供了新的思路和方法。
Early prediction of winter wheat yield is of great significance for the formulation of precise management decisions for the whole growth period of winter wheat. The yield of winter wheat is affected by production technology level and climatic conditions. This study analyzed the feasibility of early prediction of winter wheat yield with long time series meteorological data and random forest method in Henan Province. Winter wheat was planted in a total of 106 counties(cities) in Henan province. Based on the ground observation meteorological data and the winter wheat statistical yield data from the year of1990 to 2015, we extracted 47 climatic factors such as temperature, humidity and precipitation in different growth stages from wheat jointing to heading stage, and 3 spatial factors of latitude, longitude and elevation. A total of 50 parameters were used as a set of feature variables. The actual yield, meteorological yield and relative meteorological yield were used as the target variables respectively, and a random forest yield prediction model with multiple variables was constructed. The data from the year of 1990 to 2009 were used as training samples to construct the model and the forests constructed were validated with data from the year of 2010 to 2015. The yield impact factors were analyzed by combining the data importance results outside the bag. The results showed that: 1) The prediction results by using meteorological yield and relative meteorological yield as the target variables were better than the yield model. For the meteorological yield and relative meteorological yield models, the values of determination coefficient R~2 were both above 0.8, the values of mean absolute error(MAE) and root mean square error(RMSE) of meteorological yield were 415 and 558 kg/hm~2, respectively, and the values of MAE and RMSE of relative meteorological yield were 0.07 and 0.09, respectively; 2) The spatial characteristics played an important role in the improving the random forest yield model. However, if the model included only spatial parameters, the predicted values were horizontally distributed along 1:1 line and the different yields in the same region by using random forest algorithm were predicted as the same values. The values far from 1:1 line might be affected by meteorological factors. Therefore, on this basis, adding meteorological features improved the prediction accuracy with smaller deviations, higher R~2(0.88), and smaller MAE and RMSE(0.06 and 0.08). 3) The model prediction was also affected by crop growing stages. The accuracy based on the meteorological features of winter wheat florets differentiation and heading and flowering stage was higher than the other spike differentiation periods, indicating that the environmental changes during this period have a greater impact on the final yield;The predicted results at the late drug interval had the larger deviation from the actual yield. It was because the meteorological factors had strong correlation and it weakened the impacts of spatial characteristics. 4) Based on the importance of outside the bag data, In the meteorological features, the average temperature and minimum temperature of winter wheat floret differentiation period, the spatial characteristics parameters were important. In addition, the negative accumulated temperature from the jointing to heading stage, and the maximum temperature at heading and flowering stage had great influence on yield.During the model establishment, we didn't differentiate disaster from non-disaster year because the sample sizes were small.However, during the model validation, the data were from both normal and disaster years, which could ensure the reliability of the prediction model. Thus, the winter wheat yield prediction based on random forest should consider both spatial and meteorological characteristics parameters. The results of this study provide new ideas and methods for early prediction of winter wheat yield.
Early prediction of winter wheat yield is of great significance for the formulation of precise management decisions for the whole growth period of winter wheat. The yield of winter wheat is affected by production technology level and climatic conditions. This study analyzed the feasibility of early prediction of winter wheat yield with long time series meteorological data and random forest method in Henan Province. Winter wheat was planted in a total of 106 counties(cities) in Henan province. Based on the ground observation meteorological data and the winter wheat statistical yield data from the year of1990 to 2015, we extracted 47 climatic factors such as temperature, humidity and precipitation in different growth stages from wheat jointing to heading stage, and 3 spatial factors of latitude, longitude and elevation. A total of 50 parameters were used as a set of feature variables. The actual yield, meteorological yield and relative meteorological yield were used as the target variables respectively, and a random forest yield prediction model with multiple variables was constructed. The data from the year of 1990 to 2009 were used as training samples to construct the model and the forests constructed were validated with data from the year of 2010 to 2015. The yield impact factors were analyzed by combining the data importance results outside the bag. The results showed that: 1) The prediction results by using meteorological yield and relative meteorological yield as the target variables were better than the yield model. For the meteorological yield and relative meteorological yield models, the values of determination coefficient R~2 were both above 0.8, the values of mean absolute error(MAE) and root mean square error(RMSE) of meteorological yield were 415 and 558 kg/hm~2, respectively, and the values of MAE and RMSE of relative meteorological yield were 0.07 and 0.09, respectively; 2) The spatial characteristics played an important role in the improving the random forest yield model. However, if the model included only spatial parameters, the predicted values were horizontally distributed along 1:1 line and the different yields in the same region by using random forest algorithm were predicted as the same values. The values far from 1:1 line might be affected by meteorological factors. Therefore, on this basis, adding meteorological features improved the prediction accuracy with smaller deviations, higher R~2(0.88), and smaller MAE and RMSE(0.06 and 0.08). 3) The model prediction was also affected by crop growing stages. The accuracy based on the meteorological features of winter wheat florets differentiation and heading and flowering stage was higher than the other spike differentiation periods, indicating that the environmental changes during this period have a greater impact on the final yield;The predicted results at the late drug interval had the larger deviation from the actual yield. It was because the meteorological factors had strong correlation and it weakened the impacts of spatial characteristics. 4) Based on the importance of outside the bag data, In the meteorological features, the average temperature and minimum temperature of winter wheat floret differentiation period, the spatial characteristics parameters were important. In addition, the negative accumulated temperature from the jointing to heading stage, and the maximum temperature at heading and flowering stage had great influence on yield.During the model establishment, we didn't differentiate disaster from non-disaster year because the sample sizes were small.However, during the model validation, the data were from both normal and disaster years, which could ensure the reliability of the prediction model. Thus, the winter wheat yield prediction based on random forest should consider both spatial and meteorological characteristics parameters. The results of this study provide new ideas and methods for early prediction of winter wheat yield.
引文
[1]Capa-Morocho M,Rodríguez-Fonseca Belén,Ruiz-Ramos M.Crop yield as a bioclimatic index of El Ni?o impact in Europe:Crop forecast implications[J].Agricultural and Forest Meteorology,2014,198/199:42-52.
[2]王静,李新.基于作物生长模型和多源数据的融合技术研究进展[J].遥感技术与应用,2015,30(2):209-219.Wang Jing,Li Xin.Research progress of fusion technology based on crop growth model and multi-source data[J].Remote Sensing Technology and Application,2015,30(2):209-219(in Chinese with English abstract)
[3]黄健熙,贾世灵,马鸿元,等.基于WOFOST模型的中国主产区冬小麦生长过程动态模拟[J].农业工程学报,2017,33(10):222-228.Huang Jianxi,Jia Shiling,Ma Hongyuan,et al.Dynamic simulation of growth process of winter wheat in main production areas of China based on WOFOST model[J].Transactions of the Chinese Society of Agricultural Engineering(Transactions of the CSAE),2017,33(10):222-228.(in Chinese with English abstract)
[4]Brown J N,Zvi H,Dean H,et al.Seasonal climate forecasts provide more definitive and accurate crop yield predictions[J]Agricultural and Forest Meteorology,2018,260/261:247-254.
[5]Basist A,Dinar A,Blankespoor B,et al.Use of satellite information on wetness and temperature for crop yield prediction and river resource planning[J].Climate Smart Agriculture,2018,52:77-104.
[6]Zhang S,Liu L.The potential of the MERIS Terrestrial Chlorophyll Index for crop yield prediction[J].Remote Sensing Letters,2014,5(8):10.
[7]黎锐,李存军,徐新刚,等.基于支持向量回归(SVR)和多时相遥感数据的冬小麦估产[J].农业工程学报,2009,25(7):114-117.Li Rui,Li Cunjun,Xu Xingang,et al.Winter wheat yieldestimation based on suport vector machine regression andmulti-temporal remote sensing data[J].Transactions of the Chinese Society of Agricultural Engineering(Transactions of the CSAE),2009,25(7):114-117.(in Chinese with English abstract)
[8]Zai Songmei,Jia Yanhui,Wen Ji,et al.Study on grain yield prediction of irrigation district based on least squares support vector machine[J].Agricultural Science and Technology,2009,10(6):1-3,6.
[9]姜新.河南省粮食产量影响因素和预测方法研究[J].中国农学通报,2019,35(1):154-158.Jiang Xin.Study on the factors affecting grain yield and forecasting methods in henan province[J].Chinese Agricultural Science Bulletin,2019,35(1):154-158.(in Chinese with English abstract)
[10]Pandey A,Mishra A.Application of artificial neural networks in yield prediction of potato crop[J].Russian Agricultural Sciences,2017,43(3):266-272.
[11]Kaul M,Hill R L,Walthall C.Artificial neural networks for corn and soybean yield prediction[J].Agricultural Systems,2005,85(1):1-18.
[12]Uno Y,Prasher S O,Lacroix R,et al.Artificial neural networks to predict corn yield from compact airborne spectrographic imager data[J].Computer and Electronics in Agriculture,2005,47(2):149-161.
[13]Breiman L.Random forests[J].Machine Learning,2001,45(1):5-32.
[14]方匡南,吴见彬.随机森林方法研究综述[J].统计与信息论坛,2011,26(3):32-38.Fang Kuangnan,Wu Jianbin.A review of random forest method research[J].Statistics and Information Forum,2011,26(3):32-38.
[15]Anna Chlingaryan,Salah Sukkarieh,Brett Whelan.Machine learning approaches for crop yield prediction and nitrogen status estimation in precision agriculture:Areview[J].Computers and Electronics in Agriculture,2018,151:61-69.
[16]Dhivya Elavarasan,Durai Raj Vincent,Vishal Sharma,et al.Forecasting yield by integrating agrarian factors and machine learning models:A survey[J].Computers and Electronics in Agriculture,2018,155:257-282.
[17]Everingham Y,Sexton J,Skocaj D,et al.Accurate prediction of sugarcane yield using a random forest algorithm[J].Agronomy for Sustainable Development,2016,36(2):1-9.
[18]Tulbure M G,Wimberly M C,Boe A,et al.Climatic and genetic controls of yields of switchgrass,a model bioenergy species[J].Agriculture Ecosystems and Environment,2012,146(1):121-129.
[19]河南省统计局.河南农村统计年鉴1990-2015[M].北京:中国统计出版社,2016.
[20]王绍中,田云峰,郭天财,等.河南小麦栽培学[M].北京:中国统计出版社,2011.
[21]崔金梅,郭天财.小麦的穗[M].北京:中国农业出版社,2006.
[22]房世波.分离趋势产量和气候产量的方法探讨[J].自然灾害学报,2011,20(6):13-18.Fang Shibo.Discussion on methods of separating trend yield and climate yield[J].Journal of Natural Disasters,2011,20(6):13-18.(in Chinese with English abstract)
[23]Jamieson P D,Porter J R,Wilson D R.A test of the computer simulation model ARCWHEAT1 on wheat crops grown in New Zealand[J].Field Crops Research,1991,27(4):337-350.
[24]Zhu Y,Li Y,Feng W,et al.Monitoring leaf nitrogen in wheat using canopy reflectance spectra[J].Canadian Journal of Plant Science,2006,86(4):1037-1046.
[25]Zhou Zhihua,Ji Feng.Deep forest:Towards an alternative to deep neural networks[J].Machine Learning,2017,497:3553-3559.
[26]张荣荣,宁晓菊,秦耀辰,等.1980年以来河南省主要粮食作物产量对气象变化的敏感性分析[J].资源科学,2018,40(1):137-149.Zhang Rongrong,Ning Xiaoju,Qin Yaochen,et al.Sensitivity analysis of main grain crop yields to climate change in Henan Province since 1980[J].Resources Science,2018,40(1):137-149.(in Chinese with English abstract)
[27]成林,李彤霄,刘荣花.主要生育期气象变化对河南省冬小麦生长及产量的影响[J].中国生态农业学报,2017,25(6):931-940.Cheng Lin,Li Tongxiao,Liu Ronghua.Effects of climate change during main growth period on winter wheat growth and yield in Henan Province[J].Chinese Journal of Eco-Agriculture,2017,25(6):931-940.(in Chinese with English abstract)
[28]冯玉香,何维勋,孙忠富,等.我国冬小麦霜冻害的气候分析[J].作物学报,1999,25(3):335-340.Feng Yuxiang,He Weixun,Sun Zhongfu,et al.Climatological study onfrost damage of winter wheat in China[J].Acta Agronomy Sinica,1999,25(3):335-340.(in Chinese with English abstract)
[29]张雪芬,郑有飞,王春乙,等.冬小麦晚霜冻害时空分布与多时间尺度变化规律分析[J].气象学报,2009,67(2):321-330.Zhang Xuefeng,Zheng Youfei,Wang Chunyi,et al.Spatial-temporal distribution and multiple-temporal scale variationanalyses of winter wheat late freezing injury[J].Acta Meteorologica Sinica,2009,67(2):321-330.(in Chinese with English abstract)
[30]朱虹晖,武永峰,宋吉青,等.基于多因子关联的冬小麦晚霜冻害分析:以河南省为例[J].中国农业气象,2018,39(1):59-68.Zhu Honghui,Wu Yongfeng,Song Jiqing,et al.Analysis of winter frost damage of winter wheat based on multi-factor correlation:A case study of Henan Province[J].Chinese Journal of Agricultural Meteorology,2018,39(1):59-68.(in Chinese with English abstract)
[31]Gislason P,Benediktsson J.Random forests for land cover classification[J].Pattern Recognition Letters,2006,27(4):294-300.
[32]Mo X,Liu S,Lin Z,et al.Prediction of crop yield,water consumption and water use efficiency with a SVAT-crop growth model using remotely sensed data on the North China Plain[J].Ecological Modelling,2005,183(2/3):301-322.
[33]Krupnik T J,Ahmed Z U,Timsina J,et al.Untangling crop management and environmental influences on wheat yield variability in Bangladesh:An application of non-parametric approaches[J].Agricultural Systems,2015,139:166-179.
[2]王静,李新.基于作物生长模型和多源数据的融合技术研究进展[J].遥感技术与应用,2015,30(2):209-219.Wang Jing,Li Xin.Research progress of fusion technology based on crop growth model and multi-source data[J].Remote Sensing Technology and Application,2015,30(2):209-219(in Chinese with English abstract)
[3]黄健熙,贾世灵,马鸿元,等.基于WOFOST模型的中国主产区冬小麦生长过程动态模拟[J].农业工程学报,2017,33(10):222-228.Huang Jianxi,Jia Shiling,Ma Hongyuan,et al.Dynamic simulation of growth process of winter wheat in main production areas of China based on WOFOST model[J].Transactions of the Chinese Society of Agricultural Engineering(Transactions of the CSAE),2017,33(10):222-228.(in Chinese with English abstract)
[4]Brown J N,Zvi H,Dean H,et al.Seasonal climate forecasts provide more definitive and accurate crop yield predictions[J]Agricultural and Forest Meteorology,2018,260/261:247-254.
[5]Basist A,Dinar A,Blankespoor B,et al.Use of satellite information on wetness and temperature for crop yield prediction and river resource planning[J].Climate Smart Agriculture,2018,52:77-104.
[6]Zhang S,Liu L.The potential of the MERIS Terrestrial Chlorophyll Index for crop yield prediction[J].Remote Sensing Letters,2014,5(8):10.
[7]黎锐,李存军,徐新刚,等.基于支持向量回归(SVR)和多时相遥感数据的冬小麦估产[J].农业工程学报,2009,25(7):114-117.Li Rui,Li Cunjun,Xu Xingang,et al.Winter wheat yieldestimation based on suport vector machine regression andmulti-temporal remote sensing data[J].Transactions of the Chinese Society of Agricultural Engineering(Transactions of the CSAE),2009,25(7):114-117.(in Chinese with English abstract)
[8]Zai Songmei,Jia Yanhui,Wen Ji,et al.Study on grain yield prediction of irrigation district based on least squares support vector machine[J].Agricultural Science and Technology,2009,10(6):1-3,6.
[9]姜新.河南省粮食产量影响因素和预测方法研究[J].中国农学通报,2019,35(1):154-158.Jiang Xin.Study on the factors affecting grain yield and forecasting methods in henan province[J].Chinese Agricultural Science Bulletin,2019,35(1):154-158.(in Chinese with English abstract)
[10]Pandey A,Mishra A.Application of artificial neural networks in yield prediction of potato crop[J].Russian Agricultural Sciences,2017,43(3):266-272.
[11]Kaul M,Hill R L,Walthall C.Artificial neural networks for corn and soybean yield prediction[J].Agricultural Systems,2005,85(1):1-18.
[12]Uno Y,Prasher S O,Lacroix R,et al.Artificial neural networks to predict corn yield from compact airborne spectrographic imager data[J].Computer and Electronics in Agriculture,2005,47(2):149-161.
[13]Breiman L.Random forests[J].Machine Learning,2001,45(1):5-32.
[14]方匡南,吴见彬.随机森林方法研究综述[J].统计与信息论坛,2011,26(3):32-38.Fang Kuangnan,Wu Jianbin.A review of random forest method research[J].Statistics and Information Forum,2011,26(3):32-38.
[15]Anna Chlingaryan,Salah Sukkarieh,Brett Whelan.Machine learning approaches for crop yield prediction and nitrogen status estimation in precision agriculture:Areview[J].Computers and Electronics in Agriculture,2018,151:61-69.
[16]Dhivya Elavarasan,Durai Raj Vincent,Vishal Sharma,et al.Forecasting yield by integrating agrarian factors and machine learning models:A survey[J].Computers and Electronics in Agriculture,2018,155:257-282.
[17]Everingham Y,Sexton J,Skocaj D,et al.Accurate prediction of sugarcane yield using a random forest algorithm[J].Agronomy for Sustainable Development,2016,36(2):1-9.
[18]Tulbure M G,Wimberly M C,Boe A,et al.Climatic and genetic controls of yields of switchgrass,a model bioenergy species[J].Agriculture Ecosystems and Environment,2012,146(1):121-129.
[19]河南省统计局.河南农村统计年鉴1990-2015[M].北京:中国统计出版社,2016.
[20]王绍中,田云峰,郭天财,等.河南小麦栽培学[M].北京:中国统计出版社,2011.
[21]崔金梅,郭天财.小麦的穗[M].北京:中国农业出版社,2006.
[22]房世波.分离趋势产量和气候产量的方法探讨[J].自然灾害学报,2011,20(6):13-18.Fang Shibo.Discussion on methods of separating trend yield and climate yield[J].Journal of Natural Disasters,2011,20(6):13-18.(in Chinese with English abstract)
[23]Jamieson P D,Porter J R,Wilson D R.A test of the computer simulation model ARCWHEAT1 on wheat crops grown in New Zealand[J].Field Crops Research,1991,27(4):337-350.
[24]Zhu Y,Li Y,Feng W,et al.Monitoring leaf nitrogen in wheat using canopy reflectance spectra[J].Canadian Journal of Plant Science,2006,86(4):1037-1046.
[25]Zhou Zhihua,Ji Feng.Deep forest:Towards an alternative to deep neural networks[J].Machine Learning,2017,497:3553-3559.
[26]张荣荣,宁晓菊,秦耀辰,等.1980年以来河南省主要粮食作物产量对气象变化的敏感性分析[J].资源科学,2018,40(1):137-149.Zhang Rongrong,Ning Xiaoju,Qin Yaochen,et al.Sensitivity analysis of main grain crop yields to climate change in Henan Province since 1980[J].Resources Science,2018,40(1):137-149.(in Chinese with English abstract)
[27]成林,李彤霄,刘荣花.主要生育期气象变化对河南省冬小麦生长及产量的影响[J].中国生态农业学报,2017,25(6):931-940.Cheng Lin,Li Tongxiao,Liu Ronghua.Effects of climate change during main growth period on winter wheat growth and yield in Henan Province[J].Chinese Journal of Eco-Agriculture,2017,25(6):931-940.(in Chinese with English abstract)
[28]冯玉香,何维勋,孙忠富,等.我国冬小麦霜冻害的气候分析[J].作物学报,1999,25(3):335-340.Feng Yuxiang,He Weixun,Sun Zhongfu,et al.Climatological study onfrost damage of winter wheat in China[J].Acta Agronomy Sinica,1999,25(3):335-340.(in Chinese with English abstract)
[29]张雪芬,郑有飞,王春乙,等.冬小麦晚霜冻害时空分布与多时间尺度变化规律分析[J].气象学报,2009,67(2):321-330.Zhang Xuefeng,Zheng Youfei,Wang Chunyi,et al.Spatial-temporal distribution and multiple-temporal scale variationanalyses of winter wheat late freezing injury[J].Acta Meteorologica Sinica,2009,67(2):321-330.(in Chinese with English abstract)
[30]朱虹晖,武永峰,宋吉青,等.基于多因子关联的冬小麦晚霜冻害分析:以河南省为例[J].中国农业气象,2018,39(1):59-68.Zhu Honghui,Wu Yongfeng,Song Jiqing,et al.Analysis of winter frost damage of winter wheat based on multi-factor correlation:A case study of Henan Province[J].Chinese Journal of Agricultural Meteorology,2018,39(1):59-68.(in Chinese with English abstract)
[31]Gislason P,Benediktsson J.Random forests for land cover classification[J].Pattern Recognition Letters,2006,27(4):294-300.
[32]Mo X,Liu S,Lin Z,et al.Prediction of crop yield,water consumption and water use efficiency with a SVAT-crop growth model using remotely sensed data on the North China Plain[J].Ecological Modelling,2005,183(2/3):301-322.
[33]Krupnik T J,Ahmed Z U,Timsina J,et al.Untangling crop management and environmental influences on wheat yield variability in Bangladesh:An application of non-parametric approaches[J].Agricultural Systems,2015,139:166-179.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |