JOURNAL OF SHANDONG UNIVERSITY(NATURAL SCIENCE) ›› 2021, Vol. 56 ›› Issue (5): 33-41.doi: 10.6040/j.issn.1671-9352.0.2021.141

Previous Articles    

Simulation of alpine wetlands CO2 flux and its influencing factors based on BP neural network optimized by genetic algorithm in Qinghai-Tibet Plateau

CAO Jia-xi1, WANG Xin2, LEI Guang-chun1*   

  1. 1. School of Ecology and Nature Conservation, Beijing Forestry University, Beijing 100083, China;
    2. Institute of Remote Sensing Science and Engineering, Faculty of Geographical Science, Beijing Normal University, Beijing 100875, China
  • Published:2021-05-13

PDF (PC)

359

Abstract: A three-layer BP neural network was constructed to simulate CO2 emission flux of wetlands ecosystem by using latent heat flux, sensible heat flux, air temperature, total radiation, effective radiation, soil temperature and soil volume water content. After determining the topological structure of BP neural network, the optimal initial threshold and weight of BP neural network training are obtained by genetic algorithm. The established BP neural network is trained and verified by normalizing 2 190 sets of measured CO2 fluxes and corresponding training data in wetlands ecosystem in Haibei alpine wetlands of Qinghai-Tibet Plateau. The validation results show that the regression coefficients of training group, validation group and test group are 0.942, 0.935 and 0.938, respectively. The overall regression coefficient is 0.941, the root mean square error between simulated and measured values is 0.92%, and the simulated CO2 flux in wetlands ecosystem is 1.207-13.767 g/(m2·d), with an average value of 6.008 g/(m2·d). Correlation analysis shows that the correlation coefficient r between CO2 flux and input neurons in alpine wetlands ecosystem is: soil temperature(0.77)> air temperature(0.72)> soil volume water content(0.39)> latent heat flux(0.30)> sensible heat flux(0.29)> total radiation(0.09)> effective radiation(0.02)(P<0.01). The dominant factors of CO2 flux in alpine wetlands ecosystem are soil temperature and air temperature, and the weights of these two factors should be increased in the subsequent modeling work.

Key words: CO2 fluxe, Matlab, genetic algorithm, BP neural network, wetlands ecosystem

CLC Number: 

  • X171
[1] GASBARRO F, IRALDO F, DADDI T. The drivers of multinational enterprises climate change strategies: a quantitative study on climate-related risks and opportunities[J]. Journal of Cleaner Production, 2017, 160(1):8-26.
[2] 裴朔. 辽宁省碳排放影响因素分析及趋势预测[D].大连: 大连理工大学, 2020. PEI Shuo. Influencing factor and prediction of carbon emissions in Liaoning Provice[D]. Dalian: Dalian University of Technology, 2020.
[3] FEARNSIDE P. Greenhouse-gas emissions from Amazonian hydroelectric reservoirs: the example of Brazils Tucurui Dam as compared to fossil fuel alternatives[J]. Environmental Conservation, 1997, 24(1):64-75.
[4] WATSON R T. Third assesssment report of the intergovernmental panel on climate change[M] //Climate Change 2001: Synthesis Report. Cambridge:Cambridge University Press, 2001.
[5] BURNETT W, HARRISON M, FROLKING S, et al. Greenhouse gas balance over thaw-freeze cycles in discontinuous zone permafrost[J]. Journal of Geophysical Research Biogeosciences, 2017, 122(2):387-404.
[6] WANG Jiaoyue, SONG Changchun, HOU Aixin, et al. Methane emission potential from freshwater marsh soils of Northeast China: response to simulated freezing-thawing cycles[J]. Wetlands, 2017, 37(3):437-445.
[7] MONTENY G, BANNINK A, CHADWICK D. Greenhouse gas abatement strategies for animal husbandry[J]. Agriculture Ecosystems & Environment, 2006, 112(2):163-170.
[8] 张荣涛,付晓宇,王康,等.三江平原小叶章湿地碳排放对雪被变化的短期响应[J]. 应用生态学报, 2020,31(4):262-270. ZHANG Rongtao, FU Xiaoyu, WANG Kang, et al. Short-term response of carbon emission to snow cover change in Calamagrostis angustifolia wetlands of Sanjiang Plain, Northeast China[J]. Journal of Applied Ecology, 2020, 31(4):262-270.
[9] 孟焕,王琳,张仲胜,等.气候变化对中国内陆湿地空间分布和主要生态功能的影响研究[J]. 湿地科学, 2016,14(5):710-716. MENG Huan, WANG Lin, ZHANG Zhongsheng, et al. Research on the impacts of climate change on spatial distribution and main ecology functions of inland wetlands ecosystem in China[J]. Wetlands Science, 2016, 14(5):710-716.
[10] 胡保安. 天鹅湖高寒湿地CO2,CH4和N2O排放对水分变化的响应[D]. 乌鲁木齐:新疆农业大学, 2017. HU Baoan. Response of CO2,CH4 and N2O emission to water change in the alpine wetland of Swan Lake[D]. Urumqi: Xinjiang Agricultural University, 2017.
[11] 刘春颖,丁喜菊,谢丽君,等.湿地生态系统影响气候变化的活性气体交换通量的研究进展[J]. 中国海洋大学学报(自然科学版), 2020,50(3):8-18. LIU Chunying, DING Xiju, XIE Lijun, et al. Research progress on exchange fluxe of active gases effecting climate change in wetland ecosystem[J]. Journal of Ocean University of China(Natural Science Edition), 2020, 50(3):8-18.
[12] 赵金元,马振,唐海亮.BP神经网络和多元线性回归模型对碳排放预测的比较[J]. 科技和产业, 2020,20(11):172-176. ZHAO Jinyuan, MA Zhen, TANG Hailiang. Comparison of BP neural network and multiple linear regression models for carbon emissions prediction[J]. Journal of technology and industry, 2020, 20(11):172-176.
[13] 宋杰鲲,张宇.基于BP神经网络的我国碳排放情景预测[J].科学技术与工程, 2011,11(17):4108-4111. SONG Jiekun, ZHANG Yu. Scenario prediction of carbon emissions in China based on BP neural network[J]. Science Technology and Engineering, 2011, 11(17):4108-4111.
[14] 张发明,王艳旭. 融合系统聚类与BP神经网络的世界碳排放预测模型研究[J]. 数学的实践与认识, 2016,46(1):77-84. ZHANG Faming, WANG Yanyu. Study on world carbon emission prediction model based on system clustering and BP neural network[J]. Mathematics in Practice and Theory, 2016, 46(1):77-84.
[15] RAHMAN M, BALA B. Modelling of jute production using artificial neural networks[J]. Biosystems Engineering, 2010, 105(3):350-356.
[16] 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(3):120-127.
[17] SONG Ding, YAO Guodang, XUE Meili, et al. Forecasting Chinese CO2 emissions from fuel combustion using a novel grey multivariable model[J]. Journal of Cleaner Production, 2017, 162(20):1527-1538.
[18] LIU Xi, MAO Guozhu, REN Jing, et al. How might China achieve its 2020 emissions target? a scenario analysis of energy consumption and CO2 emissions using the system dynamics model[J]. Journal of Cleaner Production, 2015, 103(15):401-410.
[19] SUN Wei, LIU Mohan. Prediction and analysis of the three major industries and residential consumption CO2 emissions based on least squares support vector machine in China[J]. Journal of Cleaner Production, 2016, 122(20):144-153.
[20] 陈明. MATLAB神经网络原理与实例精解[M]. 北京:清华大学出版社, 2013. CHEN Ming. Principle of MATLAB neural network and exact solution of examples[M]. Beijing: Tsinghua University Press, 2013.
[21] 杨帆. 基于BP神经网络的CO2通量预测模型研究[D].哈尔滨: 东北林业大学, 2017. YANG Fan. Study on CO2 flux prediction model based on BP neural network[D]. Harbin: Northeast Forestry University, 2017.
[22] 陈召月,段巍巍. 旱地农田N2O、CO2排放主要影响因素及减排措施研究进展[J]. 现代农业科技, 2020(24):140-142. CHEN Zhaoyue, DUAN Weiwei. Research progress on main influencing factors and emission reduction measures of N2O and CO2 emission in dryland farmland[J]. Modern Agricultural Science and Technology, 2020(24):140-142.
[23] 杨轶宁. 基于BP神经网络的点焊接头疲劳寿命预测研究[D].昆明: 昆明理工大学, 2016. YANG Yining. Study on fatigue life prediction of spot welding joint based on BP neural network[D]. Kunming: Kunming University of Science and Technology, 2016.
[24] 张雅晶,董文彬,杨拓宇,等. 基于BP神经网络的激光弯曲成形工艺参数优化[J]. 塑性工程学报, 2020(8):66-71. ZHANG Yajin, DONG Wenbin, YANG Tuoyu, et al. Optimization of laser bending process parameters based on BP neural network[J]. Journal of Plastic Engineering, 2020(8):66-71.
[25] 邹伟,王荣吉,张立强,等. 基于BP神经网络的奥贝球铁的热处理工艺优化[J]. 热加工工艺, 2020, 532(6):139-142. ZOU Wei, WANG Ringji, ZHANG Liqiang, et al. Optimization of heat treatment process of ADI based on BP neural network[J]. Hot Working Technology, 2020, 532(6):139-142.
[26] 王小川. MATLAB神经网络43个案例分析[M]. 北京:北京航空航天大学出版社, 2013. WANG Xiaochuan. Analysis of 43 cases of MATLAB neural network[M]. Beijing: Beihang University Press, 2013.
[27] 王顺科,李艳红,李发东,等. 新疆典型淡水湖和咸水湖芦苇湿地土壤CO2、CH4和N2O排放研究[J]. 干旱区研究, 2020,37(5):1183-1193. WANG Shunke, LI Yanhong, LI Fadong, et al. Study on CO2, CH4 and N2O emission from reed wetland soil of typical freshwater lake and saltwater lake in Xinjiang[J]. Arid Area Research, 2020, 37(5):1183-1193.
[28] 王莉莉,李艳红,吴浠. 艾比湖湿地土壤CO2、CH4和N2O排放通量及其影响因素研究[J]. 江西农业, 2019(24):126-129. WANG Lili, LI Yanhong, WU Xi. Study on emission fluxes of CO2, CH4 and N2O and their influencing factors in Ebinur Lake wetland soil[J]. Jiangxi Agriculture, 2019(24):126-129.
[29] 王俊峰,王根绪,吴青柏. 青藏高原腹地不同退化程度高寒沼泽草甸生长季节CO2排放通量及其主要环境控制因子研究[J]. 冰川冻土, 2008,30(3):408-414. WANG Junfeng, WANG Genxu, WU Qingbai. Study on CO2 emission flux and its main environmental control factors in alpine swamp meadow with different degradation degrees in the hinterland of Qinghai-Tibet Plateau during growing season[J]. Journal of Glaciology and Geocryology, 2008, 30(3):408-414.
[30] 张海宏,李林,周秉荣,等. 青藏高原高寒湿地CO2通量特征及影响因子分析[J]. 冰川冻土, 2017,39(1):54-60. ZHANG Haihong, LI Lin, ZHOU Bingrong, et al. Analysis of CO2 flux characteristics and influencing factors in alpine wetland of Qinghai-Tibet Plateau[J]. Journal of Glaciology and Geocryology, 2017, 39(1):54-60.
[31] 柴曦,李英年,段呈. 青藏高原高寒灌丛草甸和草原化草甸CO2通量动态及其限制因子[J]. 植物生态学报, 2018,42(1):6-19. CHAI Xi, LI Yingnian, DUAN Cheng. Dynamics of CO2 flux and its limiting factors in alpine shrub meadow and grassland meadow in Qinghai-Tibet Plateau[J]. Journal of Plant Ecology, 2018, 42(1):6-19.
[32] 吴建国,周巧富. 青海南部高原积雪期与生长季高寒草甸土壤CO2、CH4和N2O通量的观测[J]. 环境科学, 2016,37(8):2914-2923. WU Jianguo, ZHOU Qiaofu. Observation of CO2, CH4 and N2O fluxes in alpine meadow soil during snow cover and growing season in Southern Qinghai Plateau[J]. Environmental Sciences, 2016, 37(8):2914-2923.
[33] 王世杰,李子涵,罗维均. 喀斯特常绿落叶阔叶混交林旱季CO2通量特征及其影响因子[J]. 地球与环境, 2020, 337(5):4-15. WANG Shijie, LI Zihan, LUO Weijun. Characteristics of CO2 flux and its influencing factors in dry season of karst evergreen deciduous broad-leaved mixed forest[J]. Earth and Environment, 2020, 337(5):4-15.
[34] 李伟成,盛海燕,蒋跃平,等. 基塘系统不同竹林土壤CO2通量特征及其影响因子[J]. 林业科学, 2018, 54(8):13-22. LI Weicheng, SHENG Haiyan, JIANG Yuepin, et al. Characteristics and influencing factors of soil CO2 flux in different bamboo forests in the pond system[J]. Journal of Forest Science, 2018, 54(8):13-22.
[35] 张雷,王琳琳,张旭东,等. 随机森林算法基本思想及其在生态学中的应用:以云南松分布模拟为例[J]. 生态学报, 2014,34(3):650-659. ZHANG Lei, WANG Linlin, ZHANG Xudong, et al. The basic principle of random forest and its applications in ecology: a case study of Pinus yunnanensis[J]. Journal of Ecology, 2014, 34(3):650-659.
[1] ZHANG Jing, XIAO Zhi-bin, RONG Hui, CUI Yi. An improved genetic algorithm in the application of Web spider [J]. JOURNAL OF SHANDONG UNIVERSITY(NATURAL SCIENCE), 2015, 50(05): 1-6.
[2] DU Xiao-jun, LIN Bo-gang, LIN Zhi-yuan, LI Ying. Research on multiple population genetic algorithm in security software fuzzy test [J]. J4, 2013, 48(7): 79-84.
[3] SUN Fei, WANG Peng-jun*, YU Hai-zhen, WANG Di-sheng. Ternary FPRM circuit area optimization based on genetic algorithm [J]. J4, 2013, 48(05): 51-56.
[4] MA Yu-hong1,2, SUN Shu-fen2. A multi-product transport problem with transfer and  sent straight and its genetic algorithm [J]. J4, 2012, 47(7): 121-126.
[5] WU Da-hua, HE Zhen-feng*. Improvement of cluster-based genetic segmentation of time series algorithm [J]. J4, 2010, 45(7): 45-49.
[6] XU Min-Li, SUN Cai-Qun. A multi-location inventory model for service parts with lateral transshipment and waiting time constraints [J]. J4, 2010, 45(3): 61-65.
[7] DING Ran, LI Qi-Qiang, LIANG Tao. Short-term scheduling formulation with decomposition structurefor multi-purpose batch plants [J]. J4, 2010, 45(1): 73-79.
[8] LIU Bing, LIU Wei-Ji, YANG Guo-Sheng. QSRR of alkyl-nitrophenols in gas chromatography by genetic algorithms [J]. J4, 2009, 44(9): 8-11.
[9] . Researches on post VRPTW based on genetic algorithm [J]. J4, 2009, 44(6): 46-50.
[10] . The optimized algorithm of optical threedimensional 
measurement for phaseshift technique [J]. J4, 2009, 44(6): 40-45.
[11] HE Ai-xiang,ZHANG Yong . Classification rules for mining tumors and normal tissues using genetic algorithms and decision trees [J]. J4, 2007, 42(9): 91-95 .
[12] HONG Xiao-fang,CHEN Di* and WU Shi-jun . Design of an active RC filter based on game theory and genetic algorithm [J]. J4, 2007, 42(5): 30-33 .
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
Copyright 2018 © Editorial office of JOURNAL OF SHANDONG UNIVERSITY(NATURAL SCIENCE)
Supported by Beijing Magtech Co.Ltd