BP神经网络算法在河西绿洲玉米生产碳排放评估中的应用及算法有效性研究

删除或更新信息，请邮件至freekaoyan#163.com(#换成@)

本站小编 Free考研考试/2022-01-01

燕振刚^1,,,
李薇²,
YanTianhai³,
王钧¹,
陈蕾¹,
逯玉兰¹,
刘欢¹,
唐洁¹,
张磊¹,
陈玉娟¹,
常生华⁴,
侯扶江⁴
1.甘肃农业大学信息科学技术学院兰州 730070
2.甘肃农业大学财经学院兰州 730070
3.农业食品与生物科学研究所希尔斯伯勒 BT26 6DR
4.兰州大学草地农业科技学院兰州 730000
基金项目: 国家自然科学基金项目31660347

详细信息

作者简介:燕振刚, 主要研究方向为信息技术在农业中的应用。E-mail:yanzhg@gsau.edu.cn

中图分类号:TP399

计量

文章访问数:880
HTML全文浏览量:4
PDF下载量:642
被引次数:0

出版历程

收稿日期:2018-01-17
录用日期:2018-04-24
刊出日期:2018-08-01

Application and validity of BP neural networks on prediction of carbon emissions from corn production in Hexi Oasis

YAN Zhengang^1,,,
LI Wei²,
YAN Tianhai³,
WANG Jun¹,
CHEN Lei¹,
LU Yulan¹,
LIU Huan¹,
TANG Jie¹,
ZHANG Lei¹,
CHEN Yujuan¹,
CHANG Shenghua⁴,
HOU Fujiang⁴
1. College of Information & Science Technology, Gansu Agricultural University, Lanzhou 730070, China
2. College of Finance & Economics, Gansu Agricultural University, Lanzhou 730070, China
3. Agri-Food and Biosciences Institute, Hillsborough, Co. Down BT26 6DR, United Kingdom
4. College of Pastoral Agriculture Science and Technology, Lanzhou University, Lanzhou 730000, China
Funds: the National Natural Science Foundation of China31660347

More Information

Corresponding author:YAN Zhengang, E-mail: yanzhg@gsau.edu.cn

摘要
HTML全文
图(1)表(3)
参考文献(26)
相关文章
施引文献
资源附件(0)
访问统计

摘要
摘要:针对作物生产碳排放预测较为困难的实际问题，提出基于BP神经网络算法的玉米生产碳排放预测模型。选择地处河西走廊石羊河下游的民勤绿洲246家农户，面对面调查玉米种植户农场内生产投入数据，将玉米生产投入数据作为神经网络输入层；查阅和梳理国内外相似区域玉米生产环节碳排放系数，运用碳足迹生命周期法计算得到的碳排放值作为神经网络输出层；基于BP人工神经网络算法，运用试凑法确定网络隐含层节点个数，建立河西绿洲玉米生产碳排放预测模型，选择多元线性回归模型、多元非线性回归模型，对该模型有效性进行评估。研究结果表明，3层且各层节点数9、10、1的神经网络结构能够准确预测河西绿洲玉米生产碳排放，其碳排放预测值为0.763 kg（CO₂-eq）·kg^-1（DM）；9-10-1结构的神经网络预测模型的相关系数（R²=0.984 7）高于多元线性和非线性回归模型，该神经网络结构模型的均方根误差（RMSE=0.069 1）、平均绝对误差（MAE=0.051 3）均低于其他模型，BP神经网络算法预测性能明显优于其他预测模型。该研究为准确预测农业生产碳排放提供了新思路和可操作方法。
关键词:BP神经网络/
玉米生产/
碳排放/
算法有效性/
生命周期法/
预测模型
Abstract:Back-propagation (BP) neural network has been widely used in global climate change researches in recent years. There is also increasing research interests in the application of BP neural network on predicting carbon emission from agricultural lands. Hexi Oasis in the northern side of Qilian Mountain accounts for over 30% of total grain and over 70% of commercial grain production in Gansu Province, of which corn is the primary food crop. However, there has been little research in carbon emissions from corn fields in Hexi Oasis. Therefore, the objectives of this study were to predict carbon emissions from corn production in Hexi Oasis using BP neural network algorithm and to validate the performance of BP neural network algorithm against multiple linear regression and non-linear regression models. This study was done in Minqin Oasis (103°05'E, 38°38'N) located at the downstream of Shiyanghe River in Hexi Corridor. Data were collected on 246 local farms in a face-to-face questionnaire-driven survey. The data of production inputs were used as the inputs for the model in farm and the value of carbon emissions calculated using life-cycle assessment based on carbon emission factors published in the literatures about the similar regions and default figures reported by Inter-governmental Panel on Climate Change (IPCC). In order to predict carbon emissions based on BP neural network, the numbers of node in the hidden layer were calculated by trial and error. The results indicated that neural network structure with three layers predicted carbon emissions in corn productions in Hexi Oasis and the number of nodes for the input layer, hidden layer and output layer were 9, 10 and 1, respectively. The evaluated carbon emission was 0.763 kg(CO₂-eq)·kg^-1(DM) in the study area. To verify the validity of the BP neural network model, multiple linear regression and non-linear regression models were developed using the same dataset. The results indicated that the correlation coefficient (R²=0.984 7) of BP neural network model with the 9-10-1 structure was higher than that for the corresponding multiple linear regression and non-linear regression models. Also the root mean square error (RMSE=0.069 1) and mean absolute error (MAE=0.051 3) of BP model were lower than those of the corresponding multiple linear regression and non-linear regression models. Therefore, the performance of BP neural network model was better than that of the regression models. The BP neural network model developed in this study using data collected from the local farms in Hexi Oaiss combined the local practices and regional carbon emission factors, consequently providing a practical tool applicable in the prediction of carbon emissions in corn fields. Moreover, the validity of BP neural network model was also verified through comparison with multiple linear regression and non-linear regression models, which improved the reliability of its practical application. Therefore, the results of this study contributed new ideas and development methods to accurately predict carbon emissions in agricultural fields for the government and scientific community.
Key words:BP neural network/
Corn production/
Carbon emission/
Algorithm validity/
Life cycle assessment/
Prediction model

HTML全文

图1基于BP神经网络的玉米生产碳排放预测模型
Figure1.Prediction model of carbon emissions of corn production based on BP neural network

下载: 全尺寸图片幻灯片

表1玉米生产过程各环节的碳排放系数
Table1.Carbon emission factors of agricultural inputs in corn production

项目?Item	子项目?Sub-item	排放系数?Emission factor	文献?Reference
劳动力?Labor [kg(CO₂-eq)·h^-1]	—	0.115	[12]
种子?Seed [kg(CO₂-eq)·hm^-2]	—	3.850	[11]
化肥?Fertilizer [kg(CO₂-eq)·hm^-2]	N	6.380	[13-14]
	P	0.733	[14-15]
	K	0.550	[14-15]
施氮肥? N fertilization [kg(CO₂-eq)·kg^-1]	CO₂排放?CO₂ emission	0.633	[16-17]
	N₂O排放?N₂O emission	6.205	[17]
农家肥? Farmyard manure [kg(CO₂-eq)·kg^-1]	羊粪? Sheep manure	6.12×10^-6	[18]
	鸡粪?Poultry manure	2.00×10^-4	[18]
地膜?Plastic film [kg(CO₂-eq)·kg^-1]	—	18.993	[14]
燃油?Fuel [kg(CO₂-eq)·L^-1]	柴油?Diesel oil for machine	2.629	[14]
农药?Pesticides [kg(CO₂-eq)·kg^-1]	除草剂?Herbicide	23.100	[12, 19]
	杀虫剂?Insecticide	18.700	[12, 19]
	杀菌剂?Fungicide	13.933	[12, 19]
电力?Electricity [t(CO₂-eq)·(kW·h)^-1]	灌溉用电?Electricity for irrigation	0.917	[11]

下载: 导出CSV
表2单隐含层不同节点数中BP神经网络预测模型的训练集与验证集玉米生产碳排放的均方根误差(RMSE)、平均绝对误差(MAE)、R²和均方误差(MSE)
Table2.Root mean square error (RMSE), mean absolute error (MAE), R² and mean square error (MSE) statistics of carbon emission of corn production of the BP network prediction model for training and validation sets with various numbers of neurons in simple hidden layer

隐含层节点数No. of nodes	训练集Training set				验证集Validation set
隐含层节点数No. of nodes	RMSE	MAE	R²	MSE	RMSE	MAE	R²	MSE
1	0.158 1	0.128 9	0.899 8	4.66E-04	0.142 1	0.114 4	0.946 9	7.94E-04
2	0.135 4	0.109 9	0.932 5	2.92E-04	0.156 6	0.119 1	0.904 0	4.81E-04
3	0.174 9	0.124 9	0.890 8	4.27E-04	0.134 7	0.111 1	0.926 6	6.21E-04
4	0.115 5	0.095 0	0.944 7	2.68E-04	0.130 6	0.108 2	0.947 8	9.50E-04
5	0.092 1	0.067 1	0.970 6	3.41E-04	0.102 4	0.076 0	0.959 6	3.48E-04
6	0.088 7	0.069 2	0.973 9	2.63E-04	0.134 2	0.080 2	0.920 1	5.53E-04
7	0.087 8	0.064 0	0.970 7	2.65E-04	0.088 4	0.065 4	0.962 9	5.25E-04
8	0.118 1	0.094 7	0.946 5	2.23E-04	0.134 5	0.108 2	0.919 4	3.70E-04
9	0.128 9	0.103 1	0.938 6	2.21E-04	0.122 5	0.098 6	0.952 4	2.69E-04
10¹⁾	0.063 8	0.043 6	0.985 8	1.49E-04	0.067 1	0.050 7	0.984 2	2.51E-04
11	0.093 8	0.072 8	0.970 0	2.97E-04	0.096 0	0.076 8	0.959 7	4.53E-04
12	0.101 0	0.064 9	0.963 9	2.67E-04	0.093 9	0.055 8	0.970 7	6.01E-04
13	0.087 4	0.062 5	0.972 0	3.11E-04	0.079 1	0.054 8	0.979 1	4.76E-04
14	0.125 4	0.095 4	0.954 4	3.26E-04	0.114 2	0.088 8	0.949 6	4.51E-04
15	0.096 9	0.064 1	0.966 3	2.83E-04	0.117 7	0.071 9	0.952 1	6.46E-04
1)最优BP结构。1) The best topology.

下载: 导出CSV
表3测试集BP神经网络、非线性回归和线性回归模型预测玉米生产碳排放的根误差(RMSE)、平均绝对误差(MAE)和R²统计值
Table3.Root mean square error (RMSE), mean absolute error (MAE), and R² statistics of carbon emission of corn production estimated by BP network prediction model, nonlinear regression and multiple linear regression models for the test data

模型?Model	RMSE	MAE	R²
BP神经网络 BP neural network¹⁾	0.069 1	0.051 3	0.984 7
多元线性回归 Multiple linear regression	0.173 4	0.154 5	0.929 3
多元非线性回归-1 Multiple nonlinear regression-1	0.158 8	0.112 6	0.904 4
多元非线性回归-2 Multiple nonlinear regression-2	0.188 5	0.146 9	0.883 1
1)最优模型。1) The best model.

下载: 导出CSV

参考文献(26)

[1]	LIU Z L, PENG C H, XIANG W H, et al. Application of artificial neural networks in global climate change and ecological research:An overview[J]. Chinese Science Bulletin, 2010, 55(34):3853-3863 doi: 10.1007/s11434-010-4183-3
[2]	ERMIS K, MIDILLI A, DINCER I, et al. Artificial neural network analysis of world green energy use[J]. Energy Policy, 2007, 35(3):1731-1743 doi: 10.1016/j.enpol.2006.04.015
[3]	CLAIR T A, EHRMAN J M. Variations in discharge and dissolved organic carbon and nitrogen export from terrestrial basins with changes in climate:A neural network approach[J]. Limnology and Oceanography, 1996, 41(5):921-927 doi: 10.4319/lo.1996.41.5.0921
[4]	VIOTTI P, LIUTI G, GENOVA P D. Atmospheric urban pollution:Applications of an artificial neural network (ANN) to the city of Perugia[J]. Ecological Modelling, 2002, 148(1):27-46 doi: 10.1016/S0304-3800(01)00434-3
[5]	KHOSHNEVISAN B, RAFIEE S, OMID M, et al. Application of artificial neural networks for prediction of output energy and GHG emissions in potato production in Iran[J]. Agricultural Systems, 2014, 123:120-127 doi: 10.1016/j.agsy.2013.10.003
[6]	陈喜, 吴敬禄, 王玲.人工神经网络模型预测气候变化对博斯腾湖流域径流影响[J].湖泊科学, 2005, 17(3):207-212 http://www.cnki.com.cn/Article/CJFDTOTAL-ZSUX200911077.htm CHEN X, WU J L, WANG L. Prediction of climate change impacts on streamflow of lake Bosten using artificial neural network model[J]. Journal of Lake Sciences, 2005, 17(3):207-212 http://www.cnki.com.cn/Article/CJFDTOTAL-ZSUX200911077.htm
[7]	MELESSE A M, HANLEY R S. Artificial neural network application for multi-ecosystem carbon flux simulation[J]. Ecological Modelling, 2005, 189(3/4):305-314 https://www.sciencedirect.com/science/article/pii/S0304380005002061
[8]	纪广月.基于灰色关联分析的BP神经网络模型在中国碳排放预测中的应用[J].数学的实践与认识, 2014, 44(14):243-249 http://www.cqvip.com/QK/93074X/201414/661780409.html JI G Y. Application of BP neural network model in the prediction of China's carbon emissions based on grey correlation analysis[J]. Mathematics in Practice and Theory, 2014, 44(14):243-249 http://www.cqvip.com/QK/93074X/201414/661780409.html
[9]	李明峰, 董云社, 耿元波, 等.农业生产的温室气体排放研究进展[J].山东农业大学学报:自然科学版, 2003, 34(2):311-314 doi: 10.11867/j.issn.1001-8166.2007.10.1076 LI M F, DONG Y S, GENG Y B, et al. Progress of study on emissions of greenhouse gases of agriculture[J]. Journal of Shandong Agricultural University:Natural Science, 2003, 34(2):311-314 doi: 10.11867/j.issn.1001-8166.2007.10.1076
[10]	陈昌毓.河西走廊粮仓的生态环境代价[J].大自然, 2013, (6):21-22 http://www.cnki.com.cn/Article/CJFDTotal-DZRA201306009.htm CHEN C Y. The cost of ecological environment for granary in Hexi Oasis[J]. China Nature, 2013, (6):21-22 http://www.cnki.com.cn/Article/CJFDTotal-DZRA201306009.htm
[11]	史磊刚, 陈阜, 孔凡磊, 等.华北平原冬小麦-夏玉米种植模式碳足迹研究[J].中国人口·资源与环境, 2011, 21(9):93-98 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=zgrkzyyhj201109016 SHI L G, CHEN F, KONG F L, et al. The carbon footprint of winter wheat-summer maize cropping pattern on North China Plain[J]. China Population Resources and Environment, 2011, 21(9):93-98 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=zgrkzyyhj201109016
[12]	LAL R. Soil carbon sequestration impacts on global climate change and food security[J]. Science, 2004, 304(5677):1623-1627 doi: 10.1126/science.1097396
[13]	逯非, 王效科, 韩冰, 等.中国农田施用化学氮肥的固碳潜力及其有效性评价[J].应用生态学报, 2008, 19(10):2239-2250 http://www.cnki.com.cn/Article/CJFDTOTAL-YYSB200810023.htm LU F, WANG X K, HAN B, et al. Assessment on the availability of nitrogen fertilization in improving carbon sequestration potential of China's cropland soil[J]. Chinese Journal of Applied Ecology, 2008, 19(10):2239-2250 http://www.cnki.com.cn/Article/CJFDTOTAL-YYSB200810023.htm
[14]	CHENG K, PAN G X, SMITH P, et al. Carbon footprint of China's crop production-An estimation using agro-statistics data over 1993-2007[J]. Agriculture, Ecosystems and Environment, 2011, 142(3/4):231-237 https://www.deepdyve.com/lp/elsevier/carbon-footprint-of-china-s-crop-production-an-estimation-using-agro-S2RM5710Mt
[15]	DUBEY A, LAL R. Carbon footprint and sustainability of agricultural production systems in Punjab, India, and Ohio, USA[J]. Journal of Crop Improvement, 2009, 23(4):332-350 doi: 10.1080/15427520902969906
[16]	ADOM F, MAES A, WORKMAN C, et al. Regional carbon footprint analysis of dairy feeds for milk production in the USA[J]. The International Journal of Life Cycle Assessment, 2012, 17(5):520-534 doi: 10.1007/s11367-012-0386-y
[17]	Intergovernmental Panel on Climate Change (IPCC). 2006 IPCC Guidelines for National Greenhouse Gas Inventories[M]. Hayama, Japan:Institute for Global Environmental Strategies, 2006
[18]	柯水发, 李彪, 杨育红, 等.林场运营碳足迹及林木资源碳储量测算——以内蒙古赤峰市旺业甸林场为例[J].林业经济, 2013, (9):93-101 http://www.cnki.com.cn/Article/CJFDTOTAL-LYJJ201309020.htm KE S F, LI B, YANG Y H, et al. The evaluation of carbon footprint from the operation of forest farm and carbon storage by forest resources-Based on the Wangyedian Forest Farm in Chifeng of Inner Mongolia[J]. Forestry Economics, 2013, (9):93-101 http://www.cnki.com.cn/Article/CJFDTOTAL-LYJJ201309020.htm
[19]	曾宪芳, 赵世伟, 李晓晓, 等.宁夏回族自治区平罗县主要农作物碳足迹研究[J].水土保持通报, 2012, 32(5):61-65 http://cdmd.cnki.com.cn/Article/CDMD-10183-2010106861.htm ZENG X F, ZHAO S W, LI X X, et al. Main crops carbon footprint in Pingluo County of the Ningxia Hui Autonomous Region[J]. Bulletin of Soil and Water Conservation, 2012, 32(5):61-65 http://cdmd.cnki.com.cn/Article/CDMD-10183-2010106861.htm
[20]	TOPUZ A. Predicting moisture content of agricultural products using artificial neural networks[J]. Advances in Engineering Software, 2010, 41(3):464-470 doi: 10.1016/j.advengsoft.2009.10.003
[21]	樊振宇. BP神经网络模型与学习算法[J].软件导刊, 2011, 10(7):66-68 http://ufldl.stanford.edu/wiki/index.php/反向传导算法 FAN Z Y. The model and algorithm of BP neural network[J]. Software Guide, 2011, 10(7):66-68 http://ufldl.stanford.edu/wiki/index.php/反向传导算法
[22]	赵松山, 白雪梅.关于多重共线性检验方法的研究[J].中国煤炭经济学院学报, 2001, 15(4):296-300 http://mall.cnki.net/magazine/Article/TJJC201310025.htm ZHAO S S, BAI X M. Research on the test for multi-co linearity[J]. Journal of China Coal Economic College, 2001, 15(4):296-300 http://mall.cnki.net/magazine/Article/TJJC201310025.htm
[23]	沈花玉, 王兆霞, 高成耀, 等. BP神经网络隐含层单元数的确定[J].天津理工大学学报, 2008, 24(5):13-15 http://www.cnki.com.cn/Article/CJFDTOTAL-TEAR200805006.htm SHEN H Y, WANG Z X, GAO C Y, et al. Determining the number of BP neural network hidden layer units[J]. Journal of Tianjin University of Technology, 2008, 24(5):13-15 http://www.cnki.com.cn/Article/CJFDTOTAL-TEAR200805006.htm
[24]	?AKMAK G, YILDIZ C. The prediction of seedy grape drying rate using a neural network method[J]. Computers and Electronics in Agriculture, 2011, 75(1):132-138 https://www.researchgate.net/publication/251524294_The_prediction_of_seedy_grape_drying_rate_using_a_neural_network_method
[25]	梁修如. 我国出口谷物产品的碳足迹分析[D]. 合肥: 中国科学技术大学, 2015: 22-23 http://cdmd.cnki.com.cn/Article/CDMD-10358-1015723237.htm LIANG X R. Carbon footprint of Chinese export grains[D]. Hefei: University of Sciences and Technology of China, 2015: 22-23 http://cdmd.cnki.com.cn/Article/CDMD-10358-1015723237.htm
[26]	MA B L, LIANG B C, BISWAS D K, et al. The carbon footprint of maize production as affected by nitrogen fertilizer and maize-legume rotations[J]. Nutrient Cycling in Agroecosystems, 2012, 94(1):15-31 doi: 10.1007/s10705-012-9522-0