基于BP神经网络的三峡库区土壤侵蚀强度模拟

doi:10.11849/zrzyxb.20161178

摘要/Abstract

摘要： 降雨侵蚀力变化是一复杂过程,其变化存在一定的随机波动性,土壤侵蚀是三峡库区生态环境脆弱最主要的影响因素之一,查明库区土壤侵蚀强度的演化过程及未来趋势是库区生态文明建设过程中急需解决的关键科学问题。论文基于三峡库区1990年侵蚀降雨特征,利用BP神经网络对2010年75个站点降雨侵蚀力进行模拟、验证,预测2030年75个站点降雨侵蚀力。选取2030年预测结果中位于库区周围的27个站点,结合2030年库区自然增长、生态保护情景下土地利用模拟数据,使用RUSLE计算2030年土壤侵蚀强度。结果表明：1）2010年库区降雨侵蚀力模拟相对误差为15%,测试样本数据相对误差为14.67%,预测相对误差为19.65%,NE系数为0.85,说明BP神经网络对库区降雨侵蚀力具有良好模拟效果;2）2010年库区土壤侵蚀强度的Kappa指数为0.75,计算结果能满足模拟与预测需求;3）在土地利用不变情况下,2030年库区轻度、中度侵蚀面积均有所增加,微度及强烈以上侵蚀面积均呈减少趋势,且侵蚀强度转变中的58%来源于相邻侵蚀强度,跨侵蚀等级区的较少;4）在降雨侵蚀力不变情况下,自然增长、生态保护情景下未来土地利用变化所导致的土壤侵蚀均呈下降趋势,后者下降的趋势更为明显;5）在降雨侵蚀力及土地利用均变化的情况下,自然增长、生态保护情景下土壤侵蚀均呈下降趋势。

关键词: BP神经网络, RUSLE, 三峡库区, 土壤侵蚀强度

Abstract: Soil erosion is one of the most important factors affecting the fragility of the ecological environment in the Three Gorges Reservoir area. The change of rainfall erosivity is a complex process and its variation has certain stochastic fluctuation. Understanding the evolution of soil erosion intensity and its future trends are the key scientific issues, which need to be resolved in the process of ecological civilization construction in the Three Gorges Reservoir area. Moreover, it is of great significance to build an appropriate ecological production paradigm, and to formulate measures to prevent and control soil erosion. Based on the characteristics of rainfall erosion in the Three Gorges Reservoir area in 1990, this paper simulated and verified the rainfall erosivity at 75 stations in 2010 using BP neural network. On this basis, the rainfall erosivity at 75 stations in 2030 was predicted. The forecast results of rainfall erosivity at 27 stations located around the Three Gorges Reservoir area were selected and interpolated with Kriging method. Combined with the simulated land use in the Three Gorges Reservoir area in the natural growth and ecological protection scenarios in 2030, the soil erosion intensity in 2030 was calculated using the revised soil loss equation (RUSLE). The results were as follows: In 2010, the relative error of rainfall erosivity simulation was 15%, the relative error of tested samples was 14.67%, the relative error of prediction was 19.65%, and the NE coefficient was 0.85, which indicated that BP neural network had a good result of rainfall erosivity simulation in the Three Gorges Reservoir area. In 2010, the Kappa index of soil erosion intensity in the Three Gorges Reservoir area was 0.75, and the overall calculation results could meet the needs of simulation and prediction. When land use does not change in the Three Gorges Reservoir area till 2030, the areas of slight and moderate erosion will both increase, the areas of micro erosion and above intensity erosion will decrease. About 58% of the change in erosion intensity happen between adjacent erosion intensity types, and less change happen across erosion grade types. Under the condition of constant rainfall erosivity, the soil erosion caused by future land use change in both natural growth scenario and ecological protection scenario has decreasing tendency, while the tendency in the latter scenario is more obvious. If both rainfall erosivity and land use change, soil erosion in both scenarios show downward trends. However, there will be a certain degree of deterioration in areas with less erosion. Therefore, the policies of “controlling severe erosion, preventing slight erosion” should be taken. It was worth noting that simulated results only show the possibility of rainfall erosivity change which are not completely deterministic.

Key words: BP neural network, RUSLE, soil erosion intensity, the Three Gorges Reservoir area

中图分类号:

S157

刘婷, 邵景安. 基于BP神经网络的三峡库区土壤侵蚀强度模拟[J]. 自然资源学报, 2018, 33(4): 669-683.

LIU Ting, SHAO Jing-an. Simulation of Soil Erosion Intensity in the Three Gorges Reservoir Area Using BP Neural Network[J]. JOURNAL OF NATURAL RESOURCES, 2018, 33(4): 669-683.

参考文献

[1] WU J G, HUANG J H, HAN X G, et al.The Three Gorges Dam—Experiment in habitat fragmentation?[J] Science, 2003, 300(5623): 1239-1240.
[2] MORGAN T K K B, SARDELIC D N, WARETINI A F. The Three Gorges Project: How sustainable? [J]. Journal of Hydrology, 2012, 460/461(16): 1-12.
[3] 张广纳, 邵景安, 王金亮, 等. 三峡库区重庆段农村面源污染时空格局演变特征[J]. 自然资源学报, 2015, 30(7): 1197-1209.
[ZHANG G N, SHAO J A, WANG J L, et al.Spatial and temporal variations of agricultural non-point source pollution in Three Gorges Reservoir Area of Chongqing. Journal of Natural Resources, 2015, 30(7): 1197-1209. ]
[4] 吕明权, 吴胜军, 陈春娣, 等. 三峡消落带生态系统研究文献计量分析[J]. 生态学报, 2015, 35(11): 3504-3518.
[LÜ M Q, WU S J, CHEN C D, et al.A review of studies on water level fluctuating zone (WLFZ) of the Three Gorges Reservoir (TRG) based on bibliometric perspective. Acta Ecologica Sinica, 2015, 35(11): 3504-3518. ]
[5] 范建容, 刘飞, 郭芬芬, 等. 基于遥感技术的三峡库区土壤侵蚀量评估及影响因子分析[J]. 山地学报, 2011, 29(3): 306-311.
[FAN J R, LIU F, GUO F F, et al.Soil erosion assessment and cause analysis in the Three Gorges Reservoir area based on remote sensing. Journal of Mountain Science, 2011, 29(3): 306-311. ]
[6] 李天宏, 郑丽娜. 基于RUSLE模型的延河流域2001—2010年土壤侵蚀动态变化[J]. 自然资源学报, 2012, 27(7): 1164-1175.
[LI T H, ZHANG L N.Soil erosion changes in the Yanhe watershed from 2001 to 2010 based on RUSLE model. Journal of Natural Resources, 2012, 27(7): 1164-1175. ]
[7] WISCHMEIER W H, SMITH D D.Predicting Rainfall Erosion Losses from Cropland East of the Rocky Mountains[M]. Agriculture Handbook No. 282. Washington D C: US Department of Agriculture, 1965.
[8] RENARD K G, FOSTER G R, WEESIES G A, et al.Predicting Soil Erosion by Water: A Guide to Conservation Planning with the Revised Universal Soil Loss Equation (RUSLE)[M]. Washington D C: US Department of Agriculture, 1997.
[9] FOSTER G R, LANE L J.User Requirements: USDA WaterErosion Prediction Project (WEPP)[M]. NSERL Report No. 1. West Lafayette, Indiana: USDA-ARS National Soil Erosion Research Laboratory, 1987.
[10] DE ROO A P J. The L ISEM project: An introduction[J]. Hydrological Processes, 1996, 10(8): 1021-1025.
[11] 董婷婷, 左丽君, 张增祥. 基于Ann-CA模型的土壤侵蚀时空演化分析[J]. 地球信息科学学报, 2009, 11(1): 133-137.
[DONG T T, ZUO L J, ZHANG Z X.A study on space time evolution of soil erosion based on Ann-CA model. Journal of Geo-Information Science, 2009, 11(1): 133-137. ]
[12] 李德成, 徐彬彬, 石晓日. 利用马氏过程模拟和预测土壤侵蚀的动态演变——以安徽省岳西县为例[J]. 环境遥感, 1995, 10(2): 89-96.
[LI D C, XU B B, SHI X R.Simulation and prediction of soil using Markov process dynamic evolution of erosion—A case study of Yuexi County, Anhui Province. Remote Sensing of Environment, 1995, 10(2): 89-96. ]
[13] PHEERAWAT P, MUKAND S B, ROBERTO S C, et, al. Simulating the impact of future land use and climate change on soil erosion and deposition in the Mae Nam Nan Sub-Catchment, Thailand[J]. Sustainability, 2013, 5: 3244-3274.
[14] 周宁, 李超, 满秀玲. 基于Logistic回归和RBF神经网络的土壤侵蚀模数预测[J]. 水土保持通报, 2015, 35(3): 235-241.
[ZHOU N, LI C, MAN X L.Prediction of soil erosion modulus based on logistic regression and RBF neural network. Bulletin of Soil and Water Conservation, 2015, 35(3): 235-241. ]
[15] 董杰, 杨达源, 周彬, 等. ¹³⁷Cs示踪三峡库区土壤侵蚀速率研究[J]. 水土保持学报, 2006, 20(6): 1-5.
[DONG J, YANG D Y, ZHOU B, et al.Study on soil erosion rates in the Three Gorges Reservoir area using ¹³⁷Cs tracing method. Journal of Soil and Water Conservation, 2006, 20(6): 1-5. ]
[16] 冯利华. 基于ANN的土壤侵烛研究[J]. 水土保持学报, 1999, 5(6): 105-109.
[FENG L H.Ann-based investigation on soil involving. Journal of Soil and Water Conservation, 1999, 5(6): 105-109. ]
[17] 王尧, 蔡运龙, 潘懋. 贵州省乌江流域土壤侵蚀模拟——基于GIS、RUSLE和ANN技术的研究[J]. 中国地质, 2014, 41(5): 1735-1747.
[WANG Y, CAI Y L, PAN M, et al.Soil erosion simulation of the Wujiang River Basin in Guizhou Province based on GIS, RUSLE and ANN. Geology in China, 2014, 41(5): 1735-1747. ]
[18] 张坤, 丁新, 洪伟, 等. BP神经网络在降雨侵蚀力预测预报中的应用研究[J]. 水土保持研究, 2009, 16(1): 43-46.
[ZHANG K, DING X, HONG W, et al.Application of prediction for rainfall erosivity based on BP neural network. Research of Soil and Water Conservation, 2009, 16(1): 43-46. ]
[19] 中华人民共和国水利部. SL 190—2007 土壤侵蚀分类及分级标准 [S]. 北京: 中国水利水电出版社, 2008: 1-20.
[Ministry of Water Resources of the People’s Republic of China. Classification and grading criteria of soil erosion (SL 190-2007). Beijing: China Water Conservancy and Hydropower Press, 2008: 1-20. ]
[20] 施开放, 刁承泰, 孙秀锋. 基于熵权可拓决策模型的重庆三峡库区水土资源承载力评价[J]. 环境科学学报, 2013, 33(2): 609-616.
[SHI K F, DIAO C T, SUN X F.Evaluation of soil-water resources carrying capacity based on entropy weight extension decision model in the Three Gorges Reservoir region of Chongqing. Acta Scientiae Circumstantiae, 2013, 33(2): 609-616. ]
[21] 虞孝感. 长江流域生态环境的意义及生态功能区段的划分[J]. 长江流域资源与环境, 2002, 11(4): 323-326.
[YU X G.Economic significance of eco-environmental protection and the delineation of ecological functional zones in Yangtze River Valley. Resources and Environment in the Yangtze Basin, 2002, 11(4): 323-326. ]
[22] 刘春霞, 李月臣, 杨华, 等. 三峡库区重庆段生态与环境敏感性综合评价[J]. 地理学报, 2011, 66(5): 631-642.
[LIU C X, LI Y C, YANG H, et al.RS and GIS-based assessment for eco-environmental sensitivity of the Three Gorges Reservoir area of Chongqing. Acta Geographica Sinica, 2011, 66(5): 631-642. ]
[23] 王金亮, 邵景安, 李阳兵. 近20 a三峡库区农林第利用变化图谱特征分析[J]. 自然资源学报, 2015, 30(2): 235-247.
[WANG J L, SHAO J A, LI Y B.Analysis on characteristic of utilization patterns of agricultural and forestry land in Three Gorges Reservoir area in recent 20 years. Journal of Natural Resources, 2015, 30(2): 235-247. ]
[24] 于慧, 邓伟, 刘邵全. 地势起伏度对三峡库区人口及经济发展水平的影响[J]. 长江流域资源与环境, 2013, 22(6): 686-690.
[YU H, DENG W, LIU S Q.Impact of relief amplitude on population and economic development in the Three Gorges Reservoir. Resources and Environment in the Yangtze Basin, 2013, 22(6): 686-690. ]
[25] 刘睿, 周李磊, 彭瑶, 等. 三峡库区重庆段土壤保持服务时空分布格局研究[J]. 长江流域资源与环境, 2016, 25(6): 932-942.
[LIU R, ZHOU L L, PENG Y, et al.Spatio-temporal variations of soil conservation services in the Three Gorges Reservoir area of Chongqing. Resources and Environment in the Yangtze Basin, 2016, 25(6): 932-942. ]
[26] 邓华, 邵景安, 王金亮, 等. 多因素耦合下三峡库区土地利用未来情景模拟[J]. 地理学报, 2016, 71(11): 1979-1997.
[DENG H, SHAO J A, WANG J L, et al.Land use driving forces and its future scenario simulation in the Three Gorges Reservoir Area using CLUE-S model. Acta Geographica Sinica, 2016, 71(11): 1979-1997. ]
[27] VERBURG P H, BERKEL D B, DOORN A M, et al.Trajectories of land use change in Europe: A model-based exploration of rural futures[J]. Landscape Ecology, 2010, 25: 217-232.
[28] 陈彦光. 基于MATLAB的地理数据分析 [M]. 北京: 高等教育出版社, 2012: 359-359.
[CHEN Y G.Analysis of Geographic Data Based on MATLAB. Beijing: Higher Education Press, 2012: 359-359. ]
[29] OPENSHAW S.Neural network genetic and fuzzy logic models of spatial interaction[J]. Environment and Planning A, 1998, 30: 1857-1872.
[30] 张宏, 马岩, 李勇, 等. 基于遗传BP神经网络的核桃破裂功预测模型[J]. 农业工程学报, 2014, 30(18): 78-84.
[ZHANG H, MA Y, LI Y, et al.Rupture energy prediction model for walnut shell breaking based on genetic BP neural network. Transactions of the CSAE, 2014, 30(18): 78-84. ]
[31] 龙天渝, 乔敦, 安强, 等. 基于GIS和RULSE的三峡库区土壤侵蚀量估算分析[J]. 灌溉排水学报, 2012, 31(2): 33-37.
[LONG T Y, QIAO D, AN Q, et al.Estimating soil erosion in Three Gorges Reservoir area based on GIS and RUSLE. Journal of Irrigation Drainage, 2012, 31(2): 33-37. ]
[32] 吴昌广, 曾毅, 周志翔, 等. 三峡库区土壤可蚀性K值研究[J]. 中国水土保持科学, 2010, 8(3): 8-12.
[WU C G, ZENG Y, ZHOU Z X, et al.Soil erodibility K value in Three Gorges Reservoir Area. Science of Soil and Water Conservation, 2010, 8(3): 8-12. ]
[33] 章文波, 谢云, 刘元宝. 用雨量和雨强计算次降雨侵蚀力[J]. 地理科学, 2002, 21(3): 384-390.
[ZHANG W B, XIE Y, LIU Y B.Estimation of rainfall erosivity using rainfall amount and rainfall intensity. Scientia Geographica Sinica, 2002, 21(3): 384-390. ]
[34] 吴昌广, 吕华丽, 周志翔, 等. 三峡库区土壤侵蚀空间分布特征[J]. 中国水土保持科学, 2012, 10(3): 15-21.
[WU C G, LÜ H L, ZHOU Z X, et al.Spatial distribution analysis of soil erosion in the Three Gorges Reservoir area. Science of Soil and Water Conservation, 2012, 10(3): 15-21. ]
[35] 刘爱霞, 王静, 刘正军. 三峡库区土壤侵蚀遥感定量监测——基于GIS和修正通用土壤流失方程的研究[J]. 自然灾害学报, 2009, 18(4): 25-30.
[LIU A X, WANG J, LIU Z J.Remote sensing quantitative monitoring of soil erosion in Three Gorges Reservoir area: A GIS/RUSLE-based research. Journal of Natural Disaster, 2009, 18(4): 25-30. ]
[36] 蔡崇法, 丁树文, 史志华, 等. 应用USLE模型与地理信息系统IDRISI预测小流域土壤侵蚀量的研究[J]. 水土保持学报, 2000, 14(2): 19-24.
[CAI C F, DING S W, SHI Z H, et al.Study of applying USLE and geographical information system IDRISI to predict soil erosion in small watershed. Journal of Soil and Water Conservation, 2009, 14(2): 19-24. ]
[37] NASH J E, SUTCLIFFE J V.River flow forecasting through conceptual models: A discussion of principles[J]. Journal of Hydrology, 1970, 10(3): 280-292.
[38] XIU X B, TAN Y, YANG G S.Environmental impact assessments of the Three Gorges Project in China: Issues and interventions[J]. Earth-Science Reviews, 2013, 124: 115-125.