1. 东北林业大学林学院,黑龙江,哈尔滨,150040
2. 黑龙江省水土保持科学研究院,黑龙江,哈尔滨,150070
3. 北京林业大学林学院,北京,100083
纸质出版:2015
移动端阅览
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 Ning, LI Chao, MAN Xiuling. Prediction of Soil Erosion Modulus Based on Logistic Regression and RBF Neural Network[J]. Bulletin of Soiland Water Conservation, 2015, 35(3): 235-241.
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. DOI: 10.13961/j.cnki.stbctb.2015.03.050.
ZHOU Ning, LI Chao, MAN Xiuling. Prediction of Soil Erosion Modulus Based on Logistic Regression and RBF Neural Network[J]. Bulletin of Soiland Water Conservation, 2015, 35(3): 235-241. DOI: 10.13961/j.cnki.stbctb.2015.03.050.
[目的
]
寻求估算土壤侵蚀模数的新方法
并通过GIS实现对土壤侵蚀空间分布情况的预测。[方法
]
采用土壤侵蚀模数作为判别条件
分别验证基于Logistic回归和RBF神经网络而建立的土壤侵蚀预报模型的适用性
进而构建并验证改进模型——LOG-RBF神经网络土壤侵蚀预测模型。[结果
]
(1) Logistic回归模型判别目标土地是否发生土壤侵蚀的优势明显
未发生和发生土壤侵蚀的预测正确率分别为77.4%和97.9%
总预测正确率为94.9%。(2) RBF神经网络模型估计土壤侵蚀模数的能力较强
模拟结果的相对误差和平方和误差分别为0.612%和13.292
R
2
为0.57。(3) LOG-RBF神经网络土壤侵蚀预测模型预测结果的相对误差和平方和误差比RBF神经网络模型模拟结果分别降低了0.157%和2.601。R
2
为0.82
拟合程度上优于RBF神经网络模型。随着土壤侵蚀模数的增大
错估现象呈逐渐减少趋势。通过受试者工作特征曲线的判别
LOG-RBF神经网络模型的曲线下面积值比RBF神经网络模型大0.063
模型判断的准确性更高。[结论
]
利用LOG-RBF神经网络土壤侵蚀预测模型可更准确地估计土壤侵蚀模数
基于GIS能够预测土壤侵蚀的空间分布情况。
[Objective] To found a new approach to estimate soil erosion modulus
and achieve predictions of spatial distribution of soil erosion based on GIS. [Methods] Taking soil erosion modulus as discriminant conditions
each applicability of soil erosion prediction model built based on Logistic regression and RBF neural network was validated
and then the improved model(soil erosion prediction model) based on LOG-RBF neural network was built and validated. [Results] (1) There was obvious advantage for Logistic regression model to discriminant the occurrence of soil erosion
and the accuracy of prediction for un-occurring and occurring was 77.4% and 97.9%
respectively
the total predictive accuracy was 94.9%. (2) RBF neural network model had the stronger ability to estimate soil erosion modulus
the relative error and error sum of squares of the simulation results was 0.612% and 13.292
respectively
and R2 was 0.57. (3) Relative error and error sum of squares of the simulation results was decreased by 0.157% and 2.601
respectively based on LOG-RBF neural network model than RBF neural network model
and R2 was 0.82
so LOG-RBF neural network model had a better fitting degree
and with the soil erosion modulus increase
misjudge phenomenon showed a trend of gradual reduction. Determined by receiver operating characteristic curve
the value of area under curve based on LOG-RBF neural network model was 0.063 larger than RBF neural network model
and the accuracy was higher. [Conclusion] LOG-RBF neural network model could be used to estimate soil erosion modulus
and predict spatial distribution of soil erosion based on GIS.
Wischmeier W H, Smith D D. A universal soil-loss equation to guide conservation farm planning[J].Transactions 7th Int. Congr. Soil Sci.,1960(1):418-425.
Kirkby M J, Abraham R, McMahon M D, et al. MEDALUS soil erosion models for global change[J].Geomorphology, 1998,24(1):35-49.
De Jong S M, Paracchini M L, Bertolo F, et al. Regional assessment of soil erosion using the distributed model SEMMED and remotely sensed data[J].Catena, 1999,7(3/4):291-308.
De Vente J, Poesen J, Verstraeten G, et al. Spatially distributed modelling of soil erosion and sediment yield at regional scales in Spain[J]. Global and Planetary Change, 2008,60(3):393-415.
Morgan R P C, Quinton J N, Smith R E, et al. The European soil erosion model (EUROSEM):A dynamic approach for predicting sediment transport from fields and small catchments[J]. Earth Surface Processes and Landforms, 1998(23):527-544.
Kirkby M, Gobin A, Irvine B. Pan European soil erosion risk assessment(deliverable 5):PESERA Model Strategy, land use and vegetation growth[J]. European Soil Bureau, 2005,23(1):192-197.
Abbott M B, Bathurst J C, Cunge J A, et al. An introduction to the European Hydrological System-Systeme Hydrologique Europeen,"SHE"(1):History and philosophy of a physically-based, distributed modelling system[J]. Journal of Hydrology, 1986,87(1):45-59.
孙立达,洪惜英,韩熙春,等.小流域土壤流失预报方程[J].北京林学院学报,1982(4):33-40.
牟金泽,孟庆枚.降雨侵蚀土壤流失预报方程的初步研究[J].中国水土保持,1983(6):23-27.
杨艳生,史德明,吕喜玺.长江二峡区土壤流失预测方程[J].土壤,1986,18(6):313-314.
赵羽,金争平,史培军,等.内蒙占土壤侵蚀研究[M].北京:科学出版社,1989.
陈楚群.土壤侵蚀量多因子灰色模型的建立与应用:以陕北典型小流域为例[J].水土保持学报,1991,5(1):27-32.
张宪奎,许靖华.黑龙江省土壤流失方程的研究[J].水土保持通报,1992,12(4):1-9.
付炜.黄土丘陵沟壑区土壤侵蚀预测模型建立方法的研究[[J].水土保持学报,1992,6(3):6-10.
黄炎和,卢程,隆付勤,等.闽东南土壤流失预报研究[J].水土保持学报,1993,7(4):13-17.
杨子生.滇东北山区坡耕地土壤流失方程研究[J].水土保持通报,1999,19(1):1-9.
杨子生.云南省金沙江流域土壤流失方程研究[J].山地学报,2002,20(S1):1-9.
刘宝元,谢云,张科利.土壤侵蚀预报模型[M].北京:中国科学技术出版社,2001.
周宁,满秀玲,李超.黑龙江省黑土区拉林河流域土壤侵蚀强度评价方法比较[J].中国水土保持科学,2013,11(3):73-77.
周宁,李超,满秀玲.基于GIS的黑龙江省拉林河流域土壤侵蚀空间特征分析[J].水土保持研究,2014,21(6):10-15.
中华人民共和国水利部.SL446-2009黑土区水土流失综合防治技术标准[S].北京:中国水利水电出版社,2009.
龚文峰,蔡体久,范文义,等.松花江流域哈尔滨城区段土壤侵蚀时空格局及动态变化研究[J].水土保持通报,2009,29(5):56-60.
姜文亮,张晓通,李霖,等.基于GIS和空间逻辑回归模型的城市空间扩展预测:以深圳市龙岗区为例[J].测绘科学,2008,33(4):172-174.
邢秋菊,赵纯勇,高克昌,等.基于GIS的滑坡危险性逻辑回归评价研究[J].地理与地理信息科学,2004,20(3):49-51.
王海鹰,张新长,赵元.基于逻辑回归模型的城市边缘区界定方法研究[J].测绘通报,2010(10):7-10.
王静,何挺,郭旭东,等. 基于逻辑回归模型的环北京地区土地退化态势分析[J].地理科学进展,2005,24(5):23-32.
刘艺梁,殷坤龙,刘斌,等.逻辑回归和人工神经网络模型在滑坡灾害空间预测中的应用[J].水文地质工程地质,2010,37(5):92-96.
中华人民共和国水利部.SL 190-2007土壤侵蚀分类分级标准[S].北京:中国水利水电出版社,2008.
伊燕平,卢文喜,许晓鸿,等.基于RBF神经网络的土壤侵蚀预测模型研究[J].水土保持研究,2013,20(2):25-28.
黄华.基于SPSS的PCA-RBF神经网络模型的仿真试验[J].新疆农业大学学报, 2010,33(6):535-538.
张宇,谷建才,曹立颜,等.基于RS和GIS的径向基神经网络模型对森林蓄积量的估测[J].浙江林业科技,2009,29(5):51-54.
赵玉芹.基于神经网络的渭河水质定量遥感研究[D].西安:陕西师范大学,2009:28-31.
Fredric M H, Kostanic I. 神经计算原理[M].北京:机械工业出版社,2007.
王运生,谢丙炎,万方浩,等.ROC曲线分析在评价入侵物种分布模型中的应用[J].生物多样性,2007,15(4):365-372.
0
浏览量
1446
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621