Modeling water consumption of Populus bolleana by artificial neural network based on fuzzy rules

doi:10.13287/j.1001-9332.202005.005

Abstract

Abstract: To explore the water consumption characteristics of trees, the thermal dissipation probe technology was used to monitor sap flow of Populus bolleana in east sandy land of Yellow River, from July to November in 2017. Microclimate variables were monitored. We analyzed the diurnal and seasonal variations of water consumption, and proposed the models for water consumption with back propagation neural network (BPNN) and Elman neural network (ENN) based on fuzzy rules. Results showed that the average sap flow rate of P. bolleana was 4.98 g·cm^-2·h^-1 in growing season (July to October), with solar radiation (R_s), temperature (T), vapor pressure deficit (VPD) and relative humidity (RH) as the main factors affecting sap flow. Due to the influence of meteorological factors, water consumption was characterized by obvious seasonal variation, with that in summer (July-August) being 1.4 times of that in autumn (September-October). BPNN and ENN models based on fuzzy rules were used to simulate water consumption of P. euphratica. The optimal parameter calibration of two models explained more than 80% of the total variation, which indicated that these two models could more accurately simulate water consumption. Compared with the BP neural network model, the simulated results of ENN model showed that the relative error was reduced by 27.0%, RMSE was reduced by 24.3%, Nash-Sutclife efficiency coefficient increased by 67.9%, R² was higher than 0.80. The ENN model performed better than BPNN model with a higher efficiency and goodness of fitness. ENN model effectively improved the simulating accuracy of water consumption. Therefore, it could be used as an optimal model to estimate water consumption of P. bolleana in east sandy land of Yellow River.

Key words: sap flow, water consumption, neural network, Populus bolleana

HAN Yong-gui, GAO Yang, HAN Lei, HUANG Xiao-yu. Modeling water consumption of Populus bolleana by artificial neural network based on fuzzy rules[J]. Chinese Journal of Applied Ecology, 2020, 31(5): 1525-1534.

References

[1] 汤世珍. 白杨河流域水资源可利用量与生态耗水分析. 干旱区资源与环境, 2010, 24(4): 90-93 [Tang S-Z. Water resources availability and ecological water consumption analysis for Baiyang River basin. Journal of Arid Land Resources and Environment, 2010, 24(4): 90-93]
[2] Granier A, Bobay V, Gash JH, et al. Vapour flux density and transpiration rate comparisons in a stand of Mari-time pine (Pinus pinaster Ait.) in Les Landes forest. Agricultural and Forest Meteorology, 1990, 51: 309-319
[3] 王云霓, 曹恭祥, 王彦辉, 等. 六盘山南侧华北落叶松人工林冠层蒸腾及其影响因子的坡位差异. 应用生态学报, 2018, 29(5): 1503-1514 [Wang Y-N, Cao G-X, Wang Y-H, et al. Canopy transpiration of Larix principis-rupprechtii plantation and its impact factors in different slope locations at the south side of Liupan Mountains, China. Chinese Journal of Applied Ecology, 2018, 29(5): 1503-1514]
[4] 党宏忠, 却晓娥, 冯金超, 等. 晋西黄土区苹果树边材液流速率对环境驱动的响应. 应用生态学报, 2019, 30(3): 823-831 [Dang H-Z, Que X-E, Feng J-C, et al. Response of sap flow rate of apple trees to environmental factors in Loess Plateau of Western Shanxi Province, China. Chinese Journal of Applied Ecology, 2019, 30(3): 823-831]
[5] 卢森堡, 陈云明, 唐亚坤, 等. 黄土丘陵区混交林中油松和沙棘树干液流对降雨脉冲的响应. 应用生态学报, 2017, 28(11): 3469-3478 [Lu S-B, Chen Y-M, Tang Y-K, et al. Sap flux density in response to rainfall pulses for Pinus tabuliformis and Hippophaer hamnoides from mixed plantation in hilly Loess Plateau. Chinese Journal of Applied Ecology, 2017, 28(11): 3469-3478]
[6] 周翠鸣, 顾大形, 赵平, 等. 液流径向变化对尾巨桉单株日蒸腾量估算的影响. 应用生态学报, 2017, 28(8): 2445-2451 [Zhou C-M, Gu D-X, Zhao P, et al. Effect of sap flow radial variation on daily transpiration estimation of Eucalyptus urophylla × Eucalyptus grandis. Chinese Journal of Applied Ecology, 2017, 28(8): 2445-2451]
[7] 刘泽勇, 马长明, 刘春鹏, 等. 华北石质山区山杏耗水预测模型的构建与验证. 中南林业科技大学学报, 2019, 39(9): 21-27 [Liu Z-Y, Ma C-M, Liu C-P, et al. Construction and validation of water-consumption prediction model for Prunus sibirica in the rocky mountainous area of north China. Journal of Central South University of Forestry and Technology, 2019, 39(9): 21-27]
[8] 张慧玲, 丁亚丽, 陈洪松, 等. 喀斯特出露基岩生境两种典型乔木的树干液流特征. 应用生态学报, 2017, 28(8): 2431-2437 [Zhang H-L, Ding Y-L, Chen H-S, et al. Characteristics of sap flow of two typical trees in exposed bedrock habitat of Karst region, China. Chinese Journal of Applied Ecology, 2017, 28(8): 2431-2437]
[9] 廖明, 詹总谦, 呙维, 等. 动态数据驱动模式下的湖泊流域降雨径流模拟. 遥感学报, 2019, 23(5): 911-923 [Liao M, Zhan Z-Q, Guo W, et al. Study on rainfall-runoff simulation and prediction in lake basin based on dynamic data-driven deep recurrent network. Journal of Remote Sensing, 2019, 23(5): 911-923]
[10] 崔宁博, 魏俊, 赵璐, 等. 基于MEA-BPNN的西北旱区参考作物蒸散量预报模型. 农业机械学报, 2018, 49(8): 228-236 [Cui N-B, Wei J, Zhao L, et al. Reference crop evapotranspiration prediction model of arid areas of Northwest China based on MEA-BPNN. Transactions of the Chinese Society for Agricultural Machinery, 2018, 49(8): 228-236]
[11] 陈昌华, 谭俊, 尹健康, 等. 基于PCA-RBF神经网络的烟田土壤水分预测. 农业工程学报, 2010, 26(8): 85-90 [Chen C-H, Tan J, Yin J-K, et al. Prediction for soil moisture in tobacco fields based on PCA and RBF neural network. Transactions of the Chinese Society of Agricultural Engineering, 2010, 26(8): 85-90]
[12] Tu J, Wei XH, Huang BB, et al. Improvement of sap flow estimation by including phenological index and time-lag effect in back-propagation neural network models. Agricultural and Forest Meteorology, 2019, 276/277: 107608
[13] 苏里坦, 阿迪力·吐拉尔别克, 王兴勇, 等. 地下变水位条件下塔里木河下游河岸胡杨林蒸腾模型. 干旱区地理, 2014, 37(5): 916-921 [Su L-T, Tulaerbieke A, Wang X-Y, et al. Transpiration model of Populous euphratica in the lower reaches of Tarim River under groundwater fluctuation. Arid Land Geography, 2014, 37(5): 916-921]
[14] 徐星, 田坤云, 李凤琴, 等. 基于GA-Elman神经网络的煤矿突水水源判别. 西南大学学报: 自然科学版, 2018, 40(4): 170-179 [Xu X, Tian K-Y, Li F-Q, et al. Discriminating mine water inrush sources based on GA-Elman neural network. Journal of Southwest University: Natural Science, 2018, 40(4): 170-179]
[15] 卢志宏, 武晓东, 郭利彪, 等. 基于Elman神经网络的阿拉善荒漠啮齿动物群落组成物种数量预测研究. 生态环境学报, 2015, 24(12): 1976-1982 [Lu Z-H, Wu X-D, Guo L-B, et al. Prediction of the number of rodent community composition species based on Elman neural network in Alasan Desert. Ecology and Environmental Sciences, 2015, 24(12): 1976-1982]
[16] 张瑜, 汪小旵, 孙国祥, 等. 基于集合经验模态分解与Elman神经网络的线椒株高预测. 农业工程学报, 2015, 31(18): 169-174 [Zhang Y, Wang X-C, Sun G-X, et al. Prediction of cayenne pepper plant height based on ensemble empirical mode decomposition and Elman neural network. Transactions of the Chinese Society of Agricultural Engineering, 2015, 31(18): 169-174]
[17] 邓继峰, 丁国栋, 赵媛媛, 等. 盐池地区三种典型树种蒸腾速率的研究. 干旱区资源与环境, 2014, 28(7): 161-165 [Deng J-F, Ding G-D, Zhao Y-Y, et al. The transpiration rates of three typical trees in Yanchi district. Journal of Arid Land Resources and Environment, 2014, 28(7): 161-165]
[18] 屈艳萍, 康绍忠, 王素芬. 甘肃石羊河流域人工种植新疆杨耗水规律研究. 中国水利水电科学研究院学报, 2014, 12(2): 130-137 [Qu Y-P, Kang S-Z, Wang S-F. Study on water consumption of irrigated Populus alba var. pyramidalis in Shiyang River basin. Journal of China Institute of Water Resources and Hydropower Research, 2014, 12(2): 130-137]
[19] 韩磊, 何俊, 齐拓野, 等. 宁夏河东沙区侧柏冠层气孔导度对环境因子的响应及其模拟. 生态学杂志, 2018, 37(9): 2862-2868 [Han L, He J, Qi T-Y, et al. Responses and modeling of canopy stomatal conduc-tance of Platycladus orientalis to environmental factors in Hedong sandy land, Ningxia. Chinese Journal of Eco-logy, 2018, 37(9): 2862-2868]
[20] Granier A. Evaluation of transpiration in a Douglas-fir stand by means of sap flow measurements. Tree Physio-logy, 1987, 3: 309-320
[21] Mirchandani G, Cao W. On hidden nodes for neural nets. IEEE Transactions on Circuits and Systems, 1989, 36: 661-664
[22] 荣莉莉, 王众托. 基于知识的阶层型神经网络结构及参数的一种确定方法. 计算机研究与发展, 2003, 40(2): 169-176 [Rong L-L, Wang Z-T. A method to determine the structure and parameters of BP neural network from knowledge. Journal of Computer Research and Development, 2003, 40(2): 169-176]
[23] 范嘉智, 王丹, 胡亚林, 等. 最优气孔行为理论和气孔导度模拟. 植物生态学报, 2016, 40(6): 631-642 [Fan J-Z, Wang D, Hu Y-L, et al. Optimal stomatal behavior theory for simulating stomatal conductance. Chinese Journal of Plant Ecology, 2016, 40(6): 631-642]
[24] 付伟锋, 邹维宝. 深度学习在遥感影像分类中的研究进展. 计算机应用研究, 2018, 35(12): 3521-3525 [Fu W-F, Zou W-B. Review of remote sensing image classification based on deep learning. Application Research of Computers, 2018, 35(12): 3521-3525]
[25] Chen X, Zhao P, Hu YT, et al. Canopy transpiration and its cooling effect of three urban tree species in a subtropical city—Guangzhou, China. Urban Forestry and Urban Greening, 2019, 43: 126368
[26] 李建明, 樊翔宇, 闫芳芳, 等. 基于蒸腾模型决策的灌溉量对甜瓜产量及品质的影响. 农业工程学报, 2017, 33(21): 156-162 [Li J-M, Fan X-Y, Yan F-F, et al. Effect of different irrigation amount based on transpiration model on yield and quality of muskmelon. Transactions of the Chinese Society of Agricultural Engineering, 2017, 33(21): 156-162]
[27] 王磊, 曹福亮, 吴家胜. 分根区交替渗灌对银杏苗木生长及生理的影响. 林业科学, 2013, 49(6): 52-59 [Wang L, Cao F-L, Wu J-S. Effects of alternative partial root-zone irrigation on growth and physiology of Gin-kgo biloba seedlings. Scientia Silvae Sinicae, 2013, 49(6): 52-59]
[28] Chang XX, Zhao WZ, Liu H, et al. Qinghai spruce (Picea crassifolia) forest transpiration and canopy conductance in the upper Heihe River Basin of arid northwestern China. Agricultural and Forest Meteorology, 2014, 198/199: 209-220
[29] 孟祥武, 王凡, 史艳翠, 等. 移动用户需求获取技术及其应用. 软件学报, 2014, 25(3): 439-456 [Meng X-W, Wang F, Shi Y-C, et al. Mobile user requirements acquisition techniques and their applications. Journal of Software, 2014, 25(3): 439-456]
[30] 田震, 荆双喜, 赵丽娟, 等. 基于粒子群优化BP神经网络的采煤机可靠性预测. 河南理工大学学报: 自然科学版, 2020, 39(1): 68-74 [Tian Z, Jing S-X, Zhao L-J, et al. Reliability prediction of shearer based on BP neural network optimized by particle swarm. Journal of Henan Polytechnic University: Natural Science, 2020, 39(1): 68-74]
[31] 苏里坦, 玉米提, 宋郁东. 基于改进BP神经网络的干旱区芦苇腾发量预测模型. 干旱区地理, 2011, 34(4): 551-557 [Su L-T, Yu M-T, Song Y-D. Prediction modeling for evapotranspiration of Phragmites aus-tralis base on the modified BP neural network in arid regions. Arid Land Geography, 2011, 34(4): 551-557]
[32] 钱家忠, 吕纯, 赵卫东, 等. Elman与BP神经网络在矿井水源判别中的应用. 系统工程理论与实践, 2010, 30(1): 145-150 [Qian J-Z, Lyu C, Zhao W-D, et al. Comparison of application on Elman and BP neural networks in discriminating water bursting source of coal mine. Systems Engineering-Theory and Practice, 2010, 30(1): 145-150]
[33] 曾润喜, 杜换霞, 王君泽. 网络舆情指标体系、方法与模型比较研究. 情报杂志, 2014, 33(4): 96-101 [Zeng R-X, Du H-X, Wang J-Z. Comparative study of internet public opinion index system, method and model. Journal of Intelligence, 2014, 33(4): 96-101]