Prediction of ammonia concentration in piggery based on ARIMA and BP neural network
LIU Chun-hong1,2, YANG Liang1, DENG He1, GUO Yu-chen1, LI Dao-liang1,2, DUAN Qing-ling1,2
1. College of Information and Electrical Engineering, China Agricultural University, Beijing 100083, China;
2. Beijing Engineering and Technology Research Center for Internet of Things in Agriculture, Beijing 100083, China
In order to reduce ammonia emissions from the source during pig breeding and reduce the ammonia concentration in piggery, this paper proposed a combination prediction method based on ARIMA-BP neural network for the concentration of ammonia in piggery, and compared with the combined prediction method based on ARIMA-BP neural network, from the perspective of optimal weight and residual optimization. The proposed prediction method was applied to the prediction of ammonia concentration in a piggery in Yixing, Jiangsu province. The results of the prediction experiments showed that the prediction accuracy of the combination prediction method based on ARIMA-BP neural network residual optimization was the highest. Compared with the BP neural network, ARIMA prediction method and the optimal weight combination prediction method based on the ARIMA-BP neural network, the evaluation indexes MAE, MAPE and RMSE were 0.0319, 0.1580% and 0.0365respectively.The ammonia prediction method proposed in this paper can be used as a scientific basis for the precise control and management of piggery environment in order to reduce the ecological environmental pollution caused by ammonia emission from piggery.
刘春红, 杨亮, 邓河, 郭昱辰, 李道亮, 段青玲. 基于ARIMA和BP神经网络的猪舍氨气浓度预测[J]. 中国环境科学, 2019, 39(6): 2320-2327.
LIU Chun-hong, YANG Liang, DENG He, GUO Yu-chen, LI Dao-liang, DUAN Qing-ling. Prediction of ammonia concentration in piggery based on ARIMA and BP neural network. CHINA ENVIRONMENTAL SCIENCECE, 2019, 39(6): 2320-2327.
于洪康,吴建寨,王亚辉,等.我国生猪养殖产业现状、模式与区域布局分析[J]. 中国猪业, 2018,(1):23-26.Yu H K, Wu J Z, Wang Y H. Analysis on the current situation, model and regional distribution of pig breeding industry in China[J]. China Swine Industry, 2018,(1):23-26.
[2]
李新建,吕刚,任广志.影响猪场氨气排放的因素及控制措施[J]. 家畜生态学报, 2012,33(1):86-93.Li X J, Lv G, Ren G Z. Influencing factors of ammonia emissions from pig houses and mitigation techniques[J]. Acta Ecologiae Animalis Domastici, 2012,33(1):86-93.
[3]
程龙,郭秀锐,程水源,等.京津冀农业源氨排放对PM2.5的影响[J]. 中国环境科学, 2018,38(4):1579-1588.Cheng L, Guo X R, Cheng S Y, et al. Effect of ammonia emission from agriculture in Beijing-Tianjin-Hebei on PM2.5[J]. China Environmental Science, 2018,38(4):1579-1588.
[4]
武志敏,郑炜,任永鑫,等.北方规模化猪场周环境空气中NH3的监测分析[J]. 中国兽医杂志, 2017,53(9):91-93.Wu Z M, Zheng W, Ren Y X, et al. Monitoring analysis on ammonia of the air around pig farm in the northeast[J]. Chinese Journal of Veterinary Medicine, 2017,53(9):91-93.
[5]
王悦,赵同科,邹国元,等.畜禽养殖舍氨气排放特性及减排技术研究进展[J]. 动物营养学报, 2017,29(12):4249-4259.Wang Y, Zhao T K, Zou G Y, et al. Research statues of ammonia emission characteristics and mitigation technologies from livestock houses[J]. Chinese Journla of Animal Nutrition, 2017,29(12):4249-4259.
[6]
朱海生,董红敏.猪舍氨气排放预测模型的研究现状[J]. 农业工程学报, 2006,22(S2):187-192.Zhu H S, Dong H M. Research progress of models for predicting ammonia emision in swine houses[J]. Transcations of the CSAE, 2006, 22(S2):187-192.
[7]
Yu S H, Zhang J F, Ou J Y. Quantitative detection model of pernicious gases in pig house based on BP neural network[J]. Animal Husbandry and Feed Science, 2009,1(3):40-43,48.
[8]
Canh T T, Aarnink A J A. Influence of electrolyte balance and acidifying calcium salts in the diet of growing-finishing pigs On urinary pH, slurry pH and ammonia volatilization from slurry[J]. Livestock Production Science, 1998,56:1-13.
[9]
彭红芳.不同季节不同类型猪舍环境参数监测及对仔猪生产性能影响的研究[D]. 保定:河北农业大学, 2015.Peng H F. Monitoring of the Environmental parameter of different seasons and different types pig house and the effect on the production performance of piglets.[D]. Baoding:Agricultural University of Heibei, 2014.
[10]
许稳,刘学军,孟令敏,等.不同养殖阶段猪舍氨气和颗粒物污染特征及其动态[J]. 农业环境科学学报, 2018,37(6):1248-1254.Xu W, Liu X J, Meng L M, et al. Dynamics and pollution features of ammonia and particulate matter during different pig breeding stages[J]. Journal of Agro-Environment Science, 2018,37(6):1248-1254.
[11]
汪开英,代小蓉,李震宇,等.不同地面结构的育肥猪舍NH3排放系数[J]. 农业机械学报, 2010,41(1):163-166.Wang K Y, Dai X R, Li Z Y, et al. NH3 Emission factor of fattening pig buildings with different floor systems[J].Transactions of the Chinese Socity for Agricultural Machinery, 2010,41(1):163-166.
[12]
Lowry A. Harper, Ron R. Sharpe, John D. Simmons. Ammonia emissions from swine houses in the Southeastern United States[J]. Journal of Environment Quality, 2004,33:449-457.
[13]
Michael J H, Anders Peter S A, Poul P, et al. Prediction of odor from pig production based on chemical odorants[J]. Journal of Environment Quality, 2012,41(2):436-443.
[14]
Patra A K. Prediction of enteric methane emission from cattle using linear and non-linear statistical models in tropical production systems[J]. Mitigation and Adaptation Strategies for Global Change, 2017, 22(4):629-650.
[15]
周茁.生猪养殖环境监测及氨气浓度预警模型研究[D]. 长沙:湖南农业大学, 2014.Zhou Z. Research of pig breeding environment monitoring and early warning model of ammonia concentration[D]. Changsha:Hunan Agricultural University, 2014.
[16]
Rafiu O Y, Zainura Z N, Ahmad H A, et al. Predicting methane emissions from livestock in Malaysia using the ARIMA model[J]. Management of Environmental Quality An International Journal, 2014,25(5):584-599.
[17]
Sun G, Hoff S J, Zelle, B C, et al. Development and comparison of backpropagation and generalized regression neural network models to predict diurnal and seasonal gas and PM10 concentrations and emissions from swine buildings[J]. Transactions of the ASABE, 2008, 51(2):685-694.
[18]
俞守华,张洁芳,区晶莹.基于BP神经网络的猪舍有害气体定量检测模型研究[J]. 安徽农业科学研究, 2009,37(23):11316-11317.Yu S H, Zhang J F, Qu J Y. Quantitative detection model of pernicious gases in pig house based on BP neural network[J]. Journal of Anhui Agricultural Sciences, 2009,37(23):11316-11317.
[19]
Lidija J S, Davor Z A, MirjanaD R, et al. Modeling of methane emissions using artificial neural network approach[J]. Journal of the Serbian Chemical Society, 2015,80(3):421-433.
[20]
Roberto B, Tamara A, Antonio O, et al. Prediction of carbon dioxide concentration in weaned piglet buildings by wavelet neural network models[J]. Computers and Electronics in Agriculture, 2017,(143):201-207.
[21]
谢秋菊,罗文博,李妍,等.基于神经网络猪舍氨气浓度预测方法研究[J]. 东北农业大学学报, 2016,47(10):83-92.Xie Q J, Luo W B, Li Y, et al. Study on prediction method ammonia concentrations in pig house using Neural Network[J]. Journal of Northeast Agricultural University, 2016,47(10):83-92.
[22]
Bai Y, Li Y, Wang X X, et al. Air pollutants concentrations forecasting using back propagation neural network based on wavelet decomposition with meteorological conditions[J]. Atmospheric Pollution Research, 2016,7(3):557-566.
[23]
Zhu K H, Wu S Y, Li Q. Prediction model for piggery ammonia concentration based on genetic algorithm and optimized BP neural network[J]. Metallurgical & Mining Industry, 2015,(11):6-12.
[24]
Xie Q J, Ni J Q, Su Z B. A prediction model of ammonia emission from a fattening pig room based on the indoor concentration using adaptive neuro fuzzy inference system[J]. Journal of Hazardous Materials, 2017,(325):301-309.
[25]
Wang F, Su H Z, Jing K. Dam safety monitoring model based on ARIMA-ANN[J]. Engineering Journal of Wuhan University, 2010, 43(5):585-588.
[26]
尧姚,陶静,李毅.基于ARIMA-BP组合模型的民航旅客运输量预测[J]. 计算机技术与发展, 2015,25(12):147-151.Yao Y, Tao J, Li Y. Prediction of civil aviation passenger transport volume based on ARIMA-BP combined model[J]. Computer Technology and Development, 2015,25(12):147-151.
[27]
张娣,景元书,李亚春,等.基于ARMA-BP集成的藻类叶绿素a预测研究[J]. 气象科学, 2015,35(3):312-316.Zhang D, Jing Y S, Li Y C, et al. Prediction on algal chlorophyll a by integrating ARIMAand BP neural network[J]. Journal of the Meteorological Sciences, 2015,35(3):312-316.
[28]
徐涛,苏瀚,杨国庆.基于空间拟合和神经网络的机场噪声预测集成模型[J]. 中国环境科学, 2016,36(4):1250-1257.Xu T, Su H, Yang G Q. Airport noise prediction ensemble model based on space fitting and neural network[J]. China Environmental Science, 2016,36(4):1250-1257.
[29]
郑剑锋,焦继东,孙力平.基于神经网络的城市内湖水华预警综合建模方法研究[J]. 中国环境科学, 2017,37(5):1872-1878.Zhang J F, Jiao J D, Sn L P. A modeling approach for early-warning of water bloom risk in urban lake based on neural network[J]. China Environmental Science, 2017,37(5):1872-1878.
[30]
Zeng Q S, Quan S P, Jin Z Q. Short-term traffic flow's forecasting by fusing BP neural network and ARIMA[J]. Journal of Zhengzhou University Engineering Science, 2015,32(4):60-3.
[31]
宋国君,国潇丹,杨啸,等.沈阳市PM2.5浓度ARIMA-SVM组合预测研究[J]. 中国环境科学, 2018,38(11):4031-4039.Song G J, Guo X D, Yang X, et al. ARIMA-SVM combination prediction of PM2.5 concentration in Shenyang[J]. China Environmental Science, 2018,38(11):4031-4039.
[32]
吴静,李振波,朱玲,等.融合ARIMA模型和GAWNN的溶解氧含量预测方法[J]. 农业机械学报, 2017,48(S1):205-210.Wu J, Li Z B, Zhu L, et al. Hybrid Model of ARIMA Model and GAWNN for dissolved oxygen content prediction[J]. Transactions of The Chinese Society of Agricultural Machinery, 2017,48(S1):205-210.
[33]
刘东君,邹志红.最优加权组合预测法在水质预测中的应用研究[J]. 环境科学学报, 2012,32(12):3128-3132.Liu D J, Zou Z H. Application of weighted combination model on forecasting water quality[J]. Acta Scientiae Circumstantiae, 2012, 32(12):3128-3132.
[34]
Wang J, Sun L, Zhao H, et al. ARIMA-BP integrated intelligent algorithm for China's consumer price index forecasting and its applications[J]. Journal of Intelligent & Fuzzy Systems, 2016,31(4):2187-2193.
