基于灰色理论—BP神经网络方法的表层土壤容重预测
|
摘要
以山西省黄土高原区15个试验点的年度跟踪监测样本为依据,利用灰色关联理论与BP神经网络相结合的方法,构建了表层土壤容重与土壤基本理化参数和累积接收水量之间的土壤传输函数预报模型。结果表明:影响表层土壤容重的7个土壤理化参数对于土壤容重的关联度均大于0.6;基于BP神经网络,以关联度较高的土壤粉粒含量、土壤砂粒含量、累积接收水量、体积含水率、有机碳含量和全盐量作为输入变量对表层土壤容重进行预测是可行的,预测值与实测值高度吻合,预测结果相对误差的平均值为0.41%,预测精度较高;检验样本预测结果相对误差的平均值为1.05%,误差完全在可接受范围内。研究结果可为黄土区土壤容重的获取提供新思路,为科学指导农田农事和灌溉管理提供理论支撑。
Based on the annual monitoring samples from the fifteen test points in Loess Plateau area of Shanxi Province,a soil transfer function prediction model between surface soil bulk density and soil physicochemical parameters and accumulated receiving water is established by combining grey correlation theory and BP neural network. The results show that the correlation between surface soil bulk density and 7 physicochemical parameters affecting surface soil bulk density is greater than 0.6; Based on BP neural network; it is feasible to select soil silt content,sand content,accumulated receiving water,organic carbon content,volumetric water content and total salt content as input variables to predict the surface soil density,and the predicted values are in good agreement with the measured values; the average relative error of the prediction is 0.41% and the prediction accuracy is high; the average relative error of the test sample prediction results is1.05%,the errors are acceptable totally. The research results can provide new ideas for obtaining soil bulk density in loess region,and provide theoretical support for scientific guidance of farmland farming and irrigation management.
Based on the annual monitoring samples from the fifteen test points in Loess Plateau area of Shanxi Province,a soil transfer function prediction model between surface soil bulk density and soil physicochemical parameters and accumulated receiving water is established by combining grey correlation theory and BP neural network. The results show that the correlation between surface soil bulk density and 7 physicochemical parameters affecting surface soil bulk density is greater than 0.6; Based on BP neural network; it is feasible to select soil silt content,sand content,accumulated receiving water,organic carbon content,volumetric water content and total salt content as input variables to predict the surface soil density,and the predicted values are in good agreement with the measured values; the average relative error of the prediction is 0.41% and the prediction accuracy is high; the average relative error of the test sample prediction results is1.05%,the errors are acceptable totally. The research results can provide new ideas for obtaining soil bulk density in loess region,and provide theoretical support for scientific guidance of farmland farming and irrigation management.
引文
[1]Rawls W J.Estimating soil bulk density from particle size analysis and organic matter content[J].Soil Science,1983,135(2):123-125.
[2]Adams W A.The effect of organic matter on the bulk and true densities of some uncultivated podzolic soils[J].European Journal of Soil Science,1973,24(1):10-17.
[3]Curtis R O,Post B W.Estimating bulk density from organic matter content in some vermont forest soils[J].Soil Science Society of America Journal,1964,28(2):285-286.
[4]Huntington T G,Johnson A H,Siccama T G.Carbon,organic matter and bulk density relationship in a forested spodosol[J].Soil Science,1989,148(5):380-386.
[5]Kaur R,Kumar S,Gueung H P.A pedo-transfer function(PTF)for estimating soil bulk density from basic soil data and its comparison with existing PTFS[J].Australian Journal of Soil Research,2002,40(5):847-857.
[6]韩光中,王德彩,谢贤健.中国主要土壤类型的土壤容重传递函数研究[J].土壤学报,2016,53(01):93-102.
[7]田耀武,黄志霖,肖文发,等.三峡库区兰陵溪流域森林土壤有机碳、有机质与容重间的回归模型[J].华南农业大学学报,2016,37(1):89-95.
[8]刘继红,兰传宾,陈杰.区域土壤容重转换函数构建与预测结果评价——以河南省封丘县为例[J].土壤通报,2013,44(1):77-82.
[9]李昊哲,樊贵盛.盐碱土壤Kostiakov入渗模型参数的BP预报模型[J].中国农村水利水电,2017,(7):49-53
[10]侯泽宇,卢文喜,陈社明.基于小波神经网络方法的降水量预测研究[J].节水灌溉,2013,(3):31-34.
[11]王巧利,林剑辉,许彦峰.基于BP神经网络的土壤容重预测模型[J].中国农学通报,2014,30(24):237-245.
[12]程诗念,樊贵盛.玉米生育期内不同覆膜对黄土表层容重变化特性的影响[J].节水灌溉,2017,(6):26-29.
[13]WANG S Q,ZHOU C H,LIU J Y.Carbon storage in northeast China as estimated from vegetation and soil inventories[J].Environmental Pollution,2002,116(1):157-165.
[14]南京农学院.土壤农化分析[M].北京:中国农业出版社,1980.
[15]郝彬彬,李冲,王春红.灰色关联度在矿井突水水源判别中的应用[J].中国煤炭,2010,36(6):20-22.
[16]赵西宁,王万忠,吴普特,等.坡面入渗的人工神经网络模型研究[J].农业工程学报,2004,20(3):48-50.
[2]Adams W A.The effect of organic matter on the bulk and true densities of some uncultivated podzolic soils[J].European Journal of Soil Science,1973,24(1):10-17.
[3]Curtis R O,Post B W.Estimating bulk density from organic matter content in some vermont forest soils[J].Soil Science Society of America Journal,1964,28(2):285-286.
[4]Huntington T G,Johnson A H,Siccama T G.Carbon,organic matter and bulk density relationship in a forested spodosol[J].Soil Science,1989,148(5):380-386.
[5]Kaur R,Kumar S,Gueung H P.A pedo-transfer function(PTF)for estimating soil bulk density from basic soil data and its comparison with existing PTFS[J].Australian Journal of Soil Research,2002,40(5):847-857.
[6]韩光中,王德彩,谢贤健.中国主要土壤类型的土壤容重传递函数研究[J].土壤学报,2016,53(01):93-102.
[7]田耀武,黄志霖,肖文发,等.三峡库区兰陵溪流域森林土壤有机碳、有机质与容重间的回归模型[J].华南农业大学学报,2016,37(1):89-95.
[8]刘继红,兰传宾,陈杰.区域土壤容重转换函数构建与预测结果评价——以河南省封丘县为例[J].土壤通报,2013,44(1):77-82.
[9]李昊哲,樊贵盛.盐碱土壤Kostiakov入渗模型参数的BP预报模型[J].中国农村水利水电,2017,(7):49-53
[10]侯泽宇,卢文喜,陈社明.基于小波神经网络方法的降水量预测研究[J].节水灌溉,2013,(3):31-34.
[11]王巧利,林剑辉,许彦峰.基于BP神经网络的土壤容重预测模型[J].中国农学通报,2014,30(24):237-245.
[12]程诗念,樊贵盛.玉米生育期内不同覆膜对黄土表层容重变化特性的影响[J].节水灌溉,2017,(6):26-29.
[13]WANG S Q,ZHOU C H,LIU J Y.Carbon storage in northeast China as estimated from vegetation and soil inventories[J].Environmental Pollution,2002,116(1):157-165.
[14]南京农学院.土壤农化分析[M].北京:中国农业出版社,1980.
[15]郝彬彬,李冲,王春红.灰色关联度在矿井突水水源判别中的应用[J].中国煤炭,2010,36(6):20-22.
[16]赵西宁,王万忠,吴普特,等.坡面入渗的人工神经网络模型研究[J].农业工程学报,2004,20(3):48-50.