基于BP神经网络的青藏高原土壤养分评价
详细信息    查看全文 | 推荐本文 |
  • 英文篇名:Nutrient evaluation of the soil in the Qinghai-Tibet Plateau based on BP neural network
  • 作者:杨文静 ; 王一博 ; 刘鑫 ; 孙哲
  • 英文作者:YANG Wenjing;WANG Yibo;LIU Xin;SUN Zhe;College of Earth and Environment Sciences, Lanzhou University;State Key Laboratory of Frozen Soil Engineering, Northwest Institute of Eco-Environment and Resources, Chinese Academy of Sciences;
  • 关键词:青藏高原 ; BP神经网络 ; 土壤质量 ; 海拔 ; 植被
  • 英文关键词:Qinghai-Tibet Plateau;;BP neural network;;soil quality;;elevation;;vegetation
  • 中文刊名:BCDT
  • 英文刊名:Journal of Glaciology and Geocryology
  • 机构:兰州大学资源环境学院;中国科学院西北生态环境资源研究院冻土工程国家重点实验室;
  • 出版日期:2019-02-25
  • 出版单位:冰川冻土
  • 年:2019
  • 期:v.41
  • 基金:国家自然科学基金项目(41877149; 41530752; 91547203; 41563005);; 冻土工程国家重点实验室开放基金项目(SKLFSE 201501);; 兰州大学中央高校基本科研业务费专项基金(LZUJBKY-2018-KB41)资助
  • 语种:中文;
  • 页:BCDT201901022
  • 页数:12
  • CN:01
  • ISSN:62-1072/P
  • 分类号:221-232
摘要
土壤养分在养分循环和土壤-植物关系中起着重要作用,在高海拔生态系统中,由于缺乏系统的实地观测,土壤养分在高山草原中仍然知之甚少。为了了解青藏高原多年冻土区高寒草地土壤养分的基本情况以及土壤养分的等级划分,利用青藏高原腹地西大滩至安多地区采集的154个土壤样品数据,基于BP神经网络模型建立具有3层网络, 10个中间层节点的土壤养分评价模型。在MATLAB软件中进行BP神经网络的训练和验证后,对青藏高原多年冻土区高寒草地土壤养分进行综合评价。结果表明:2009年青藏高原高寒草地的土壤养分综合评价等级为4级,属于较低水平。综合评价结果与基于主成分分析方法的土壤质量指数(SQI)基本一致,说明BP神经网络模型对青藏高原土壤养分的评价结果是合理的。对评价结果与海拔、植被盖度和植被类型的关系分析表明,海拔越高或植被盖度越高,土壤养分的评价等级越高;不同植被类型的评价等级表现出高寒沼泽草甸(2级)>高寒草甸(4级)>高寒草原(5级)的趋势。BP网络作为一种简单又准确的识别方法,不仅可以评估土壤养分等级,还可以比较不同地区的土壤养分高低状况,希望为青藏高原的土地资源管理与保护提供基本的科学依据。
        Soil nutrients play an important role in nutrient cycling and soil-plant relationships. In high-altitude ecosystems, soil nutrients are still poorly understood in alpine grasslands due to lack of systematic field observations. In order to understand the basic conditions of soil nutrients and the classification of soil nutrients in alpine grassland in the permafrost regions of the plateau, 154 soil samples collected from the Xidatan to Amdo in the hinterland of the Qinghai-Tibet Plateau were used to establish a 3-layer model based on BP neural network. After training and verifying BP neural network in MATLAB software, the soil nutrients of alpine grassland in permafrost regions of the Qinghai-Tibet Plateau were comprehensively evaluated. The results showed that in 2009, the comprehensive evaluation of soil nutrients in the alpine grassland of the plateau was Grade 4, a lower level. The comprehensive evaluation results are basically consistent with the soil quality index(SQI) based on the principal component analysis, indicating that the BP neural network model is reasonable for the evaluation of soil nutrients in the Qinghai-Tibet Plateau. The relationship between the evaluation results and altitude, vegetation coverage and vegetation types showed that the higher the altitude or the higher the vegetation coverage, the higher the evaluation level of soil nutrients; the evaluation grades of different vegetation types showed an order as alpine marsh meadow(level 2) > alpine meadow(level 4) > alpine grassland(level 5). As a simple and accurate identification method, BP network can not only assess the soil nutrient grade, but also comprehensively compare the soil nutrient level, providing a scientific basis for the management and protection of the Qinghai-Tibet Plateau.
引文
[1] Doran J W, Parkin T B. Defining and assessing soil quality[M]//Doran J W, Coleman D C, Bezdicek D F, et al. Defining soil quality for a sustainable environment. Madison, Wisconsin, USA: Soil Science Society of America, 1994: 3-21.
    [2] Wang Yibo, Wu Qingbai, Niu Fujun. The impact of thermokarst lake formation on soil environment of alpine meadow in permafrost regions in the Beiluhe basin of the Tibetan Plateau[J]. Journal of Glaciology and Geocryology, 2011, 33(3): 659-667. [王一博, 吴青柏, 牛富俊. 长江源北麓河流域多年冻土区热融湖塘形成对高寒草甸土壤环境的影响[J]. 冰川冻土, 2011, 33(3): 659-667.]
    [3] Harrison A F. Effects of environment and management on phosphorus cycling in terrestrial ecosystems[J]. Journal of Environment Management, 1985, 20: 163-179.
    [4] Long Xunjian, Qian Ju, Zhang Chunmin, et al. Study of the spatial heterogeneity of soil nutrients of typical landscape in alpine meadow regions[J]. Journal of Glaciology and Geocryology, 2008, 30(1): 139-146. [龙训建, 钱鞠, 张春敏, 等. 高寒草甸区典型景观单元土壤养分空间变异性研究[J]. 冰川冻土, 2008, 30(1): 139-146.]
    [5] Hu Yigang, Jiang Lili, Wang Shiping, et al. The temperature sensitivity of ecosystem respiration to climate change in an alpine meadow on the Tibet Plateau: a reciprocal translocation experiment[J]. Agricultural & Forest Meteorology, 2016, 216(9): 93-104.
    [6] Zheng Du. The system of physico-geographical regions of the Qinghai-Xizang (Tibet) Plateau[J]. Science in China: Series D, 1996, 39(4): 410-417.
    [7] Shang Wen, Wu Xiaodong, Zhao Lin, et al. Seasonal variations in labile soil organic matter fractions in permafrost soils with different vegetation types in the central Qinghai-Tibet Plateau[J]. Catena, 2016, 137: 670-678.
    [8] Yang Xuchao, Zhang Yili, Zhang Wei, et al. Climate change in Mt. Qomolangma region since 1971[J]. Journal of Geographical Science, 2006, 16(3): 326-336.
    [9] Kang Shichang, Zhang Yongjun, Qin Dahe, et al. Recent temperature increase recorded in an ice core in the source region of Yangtze River[J]. China Science Bulletin, 2007, 52(6): 825-831.
    [10] Smith L C, Sheng Yongwei, Macdonald G M, et al. Disappearing Arctic lakes[J]. Science, 2005, 308(5727): 1429.
    [11] Yang Meixue, Nelson F E, Shiklomanov N I, et al. Permafrost degradation and its environmental effects on the Tibetan Plateau: a review of recent research[J]. Earth Science Reviews, 2010, 103(1): 31-44.
    [12] Yi Shuhua, Woo M K, Arain M A. Impacts of peat and vegetation on permafrost degradation under climate warming[J]. Geophysical Research Letters, 2007, 34(16): 1445-1461.
    [13] Wang Yibo, Tian Liming, Niu Fujun, et al. Correlation of alpine vegetation degradation and soil nutrient status of permafrost in the source regions of the Yangtze River, China[J]. Environmental Earth Sciences, 2012, 67(4): 1215-1223.
    [14] Zhang Shulei, Yang Hanbo, Yang Dawen, et al. Quantifying the effect of vegetation change on the regional water balance within the Budyko framework[J]. Geophysical Research Letters, 2015, 43: 1140-1148.
    [15] Zhang Shulei, Yang Dawen, Yang Yuting, et al. Excessive afforestation and soil drying on China′s Loess Plateau[J]. Journal of Geophysical Research: Biogeosciences, 2018, 123(3): 923-935.
    [16] Chen Ge. Summary of the research and development of the artificial neural network[J]. China Science and Technology Information, 2009(17): 88-89. [陈格. 人工神经网络技术发展综述[J]. 中国科技信息, 2009(17): 88-89.]
    [17] Han Lei, Li Rui, Zhu Huili. Comprehensive evaluation model of soil nutrient based on BP neural network[J]. Transactions of the Chinese Society of Agricultural Machinery, 2011, 42(7): 109-115. [韩磊, 李锐, 朱会利. 基于BP神经网络的土壤养分综合评价模型[J]. 农业机械学报, 2011, 42(7): 109-115.]
    [18] Sun Yan, Wang Yibo, Sun Zhe, et al. Impact of soil organic matter on water hold capacity in permafrost active layer in the Tibetan Plateau[J]. Journal of Glaciology and Geocryology, 2017, 37(2): 288-295. [孙岩, 王一博, 孙哲, 等. 有机质对青藏高原多年冻土活动层土壤持水性能的影响[J]. 冰川冻土, 2017, 37(2): 288-295.]
    [19] Tian Liming, Zhao Lin, Wu Xiaodong, et al. Vertical patterns and controls of soil nutrients in alpine grassland: implications for nutrient uptake[J]. Science of the Total Environment, 2017, 607: 855-864.
    [20] Tian Liming, Zhao Lin, Wu Xiaodong, et al. Soil moisture and texture primarily control the soil nutrient stoichiometry across the Tibetan grassland[J]. Science of the Total Environment, 2018, 622/623: 192-202.
    [21] Zhao Lin, Sheng Yu, Nan Zhuotong, et al. Permafrost survey manual[M]. Beijing: Science Press, 2015. [赵林, 盛煜, 南卓铜, 等. 多年冻土调查手册[M]. 北京: 科学出版社, 2015.]
    [22] Nelson D W, Sommers L E. Total carbon, organic carbon, and organic matter 1[J]. Methods of Soil Analysis, 1982, 9: 539-579.
    [23] Dai Yuming. Research progress of soil total nitrogen analysis[J]. Shanghai Agricultural Science and Technology, 1989(2): 39-40. [戴育明. 土壤全氮分析的研究进展[J]. 上海农业科技, 1989(2): 39-40.]
    [24] Jackson P E. Ion chromatography in environmental analysis[J/OL]. Encyclopedia of Analytical Chemistry, 2006. [2018-09-07]. https://onlinelibrary.wiley.com/doi/full/10.1002/9780470027318.a0835.
    [25] Lu Rukun. Soil and agricultural chemistry analysis method[M]. Beijing: China Agriculture Science and Technique Press, 2000: 133-137. [鲁如坤. 土壤农业化学分析方法[M]. 北京: 中国农业科技出版社, 2000: 133-137.]
    [26] Chen Yanguang. Analysis of geographical data based on MATLAB[M]. Beijing: Higher Education Press, 2012. [陈彦光. 基于MATLAB的地理数据分析[M]. 北京: 高等教育出版社, 2012.]
    [27] Wan Jiashan, Wu Yunzhi, Zhang Youhua, et al. Model of grading farmland soil nutrient based on LM-BP neural network: a case of south Anhui mountains areas[J]. Chinese Agricultural Science Bulletin, 2015, 31(26): 255-260. [万家山, 吴云志, 张友华, 等. 基于LM-BP神经网络的耕地土壤养分等级划分模型: 以皖南山区为例[J]. 中国农学通报, 2015, 31(26): 255-260.]
    [28] Zhang Guangliang, Bai Junhong, Xi Min, et al. Soil quality assessment of coastal wetlands in the Yellow River Delta of China based on the minimum data set[J]. Ecological Indicators, 2016, 66: 458-466.
    [29] Zhao Yujie, Shi Rongguang, Gao Huaiyou, et al. Assessment method for soil environmental quality based on BP neural network[J]. Journal of Agro-Environment Science, 2006, 25(1): 186-189. [赵玉杰, 师荣光, 高怀友, 等. 基于MATLAB 6.x 的BP人工神经网络的土壤环境质量评价方法研究[J]. 农业环境科学学报, 2006, 25(1): 186-189.]
    [30] He Yongxiu, Pang Yuexia, Zhang Qi, et al. Comprehensive evaluation of regional clean energy development levels based on principal component analysis and rough set theory[J]. Renewable Energy, 2018, 122: 643-653.
    [31] Liebig M A, Varvel G, Doran J. A simple performance-based index for assessing multiple agroecosystem functions[J]. Agronomy Journal, 2001, 93(2): 313-318.
    [32] Guo L, Sun Z, Ouyang Z, et al. A comparison of soil quality evaluation methods for Fluvisol along the lower Yellow River[J]. Catena, 2017, 152: 135-143.
    [33] Masto R E, Chhonkar P K, Singh D, et al. Alternative soil quality indices for evaluating the effect of intensive cropping, fertilisation and manuring for 31 years in the semi-arid soils of India[J]. Environmental monitoring and assessment, 2008, 136(1/2/3): 419-435.
    [34] Andrews S S, Karlen D L, Mitchell J P. A comparison of soil quality indexing methods for vegetable production systems in Northern California[J]. Agriculture, Ecosystems & Environment, 2002, 90(1): 25-45.
    [35] Andrews S S, Flora C B, Mitchell J P, et al. Growers′ perceptions and acceptance of soil quality indices[J]. Geoderma, 2003, 114(3/4): 187-213.
    [36] Liu Xin, Wang Yibo, Lü Mingxia, et al. Soil quality assessment of alpine grassland in permafrost region of Tibetan Plateau based on principal component analysis[J]. Journal of Glaciology and Geocryology, 2018, 40(3): 469-479. [刘鑫, 王一博, 吕明侠, 等. 基于主成分分析的青藏高原多年冻土区高寒草地土壤质量评价[J]. 冰川冻土, 2018, 40(3): 469-479.]
    [37] Liu Shiliang, Fu Bojie, Lü Yihe, et al. Assessment of soil quality in relation to land use and landscape position on slope[J]. Acta Ecologica Sinica, 2003, 23(3): 414-420. [刘世梁, 傅伯杰, 吕一河, 等. 坡面土地利用方式与景观位置对土壤质量的影响[J]. 生态学报, 2003, 23(3): 414-420.]
    [38] K?rner C. The use of ‘altitude’ in ecological research[J]. Trends in Ecology & Evolution, 2007, 22: 569-574.
    [39] Sexton J P, Mcintyre P J, Angert A L, et al. Evolution and ecology of species range limits[J]. Annual Review of Ecology Evolution & Systematics, 2009, 40: 415-436.
    [40] Atkin O K, Dan B, Hurry V M, et al. The hot and the cold: unravelling the variable response of plant respiration to temperature[J]. Functional Plant Biology, 2005, 32(2): 87-105.
    [41] Wang Ao, Wang Xue, Tognetti R, et al. Elevation alters carbon and nutrient concentrations and stoichiometry in Quercus aquifolioides in southwestern China[J]. Science of the Total Environment, 2018, 622: 1463-1475.
    [42] Ma Lüyi, Zhai Mingpu, Lin Ping. Analysis of soil physi-chemical properties of Beijing Xishan Mountain[J]. Journal of Beijing Forestry University, 1999, 21(1): 32-37. [马履一, 翟明普, 林平. 京西山地土壤理化性质的分布[J]. 北京林业大学学报, 1999, 21(1): 32-37.]
    [43] Chen Z Z, Wang S P. Typical steppe ecosystem of China[M]. Beijing: Science Press, 2000: 15-20.
    [44] Wang Genxu, Cheng Guodong, Shen Yongping, et al. Impact to the alpine meadow soil from the change of the soil cover[J]. Chinese Science Bulletin, 2002, 47(23): 1771-1777. [王根绪, 程国栋, 沈永平, 等. 土地覆盖变化对高山草甸土壤特性的影响[J]. 科学通报, 2002, 47(23): 1771-1777.]
    [45] Wang Yibo, Wang Genxu, Zhang Chunmin, et al. Response of soil physicochemical properties to the changes of the vegetation ecosystem on the Tibetan Plateau[J]. Journal of Glaciology and Geocryology, 2007, 29(6): 921-927. [王一博, 王根绪, 张春敏, 等. 高寒植被生态系统变化对土壤物理化学性状的影响[J]. 冰川冻土, 2007, 29(6): 921-927.]
    [46] Luo Yayong, Meng Qingtao, Zhang Jinghui, et al. Species diversity and biomass in relation to soil properties of alpine meadows in the eastern Tibetan Plateau in different degradation stages[J]. Journal of Glaciology and Geocryology, 2014, 36(5): 1298-1305. [罗亚勇, 孟庆涛, 张静辉, 等. 青藏高原东缘高寒草甸退化过程中植物群落物种多样性、 生产力与土壤特性的关系[J]. 冰川冻土, 2014, 36(5): 1298-1305.]
    [47] Ma Suhui, Mou Cuicui, Guo Hong, et al. Distribution features of permafrost organic carbon density on different vegetation types in the upper reaches of Heihe River, Qilian Mountains[J]. Journal of Glaciology and Geocryology, 2018, 40(3): 426-433. [马素辉, 牟翠翠, 郭红, 等. 祁连山黑河上游多年冻土区不同植被类型土壤有机碳密度分布特征[J]. 冰川冻土, 2018, 40(3): 426-433.]

© 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