ارزيابي عوامل موثر برمقاومت برشي سطح خاك در سطح زمين نما به كمك تكنيك شبكه عصبي مصنوعي

چكيده انگليسي :

103 Evaluation of factors affecting shear strength in the landscape using artificial neural networks Shaghayegh Havaee sh havayi@yahoo com 2013 01 13 Department of Soil Science College of Agriculture Isfahan University of Technology Isfahan 84156 83111 Iran Degree M Sc Language FarsiDr S Ayoubi ayoubi@cc iut ac irDr M R Mosaddeghi mosaddeghi@cc iut ac irAbstractSoil erosion is among the most important environmental problems in the world resulted fromunsustainable ecosystems It could also accelerate degradation of the ecosystems Therefore it is firstlyvital to determine soil erosion critical locations for the erosion ameliorating practices Several soilerosion models have been developed to predict soil erosion which need accurate inputs for goodestimation of soil erosion Soil surface shear strength is an important input parameter in the soil erosionmodels but its direct measurement is difficult time consuming and costly in the watershed scale Thisstudy was done to predict soil surface shear strength using artificial neural networks ANNs multiplelinear regression MLR and adaptive fuzzy system based on neural networks ANFIS It was also aimedto determine and rank the factors most effective on soil surface shear strength A direct shear box wasdesigned and constructed to measure in situ soil surface shear strength The device can determine two soilshear strength parameters i e cohesion c and angel of internal friction The study area 3500 km2 was located in Semirom region Isfahan province Soil surface shear strength was determined using theshear box at 100 locations under three land uses of grassland irrigated farming and dryland farming Soilsamples were also collected from 0 5 cm layer of the same 100 locations Particle size distribution fineclay content organic matter content OM carbonate content bulk density and gravel content weredetermined on the collected soil samples Normalized difference vegetation index NDVI was alsocalculated using satellite images Multiple linear regression MLR artificial neural networks ANNs andadaptive fuzzy system based on neural networks ANFIS were used to model predict soil surface shearstrength c and using two groups of inputs 1 easily available soil properties pedotransfer functions PTFs and 2 easily available soil properties and NDVI soil spatial prediction functions SSPFs Astrong negative correlation was found between soil c and in the studied area Positive correlations werealso obtained between c and total clay content especially fine clay content and between and sand orgravel contents The results showed that NDVI is an important factor affecting soil shear strengthparameters c and LSD mean comparisons were used to investigate the effect of land use on soilsurface shear strength and showed that dryland farming with maximum mean of clay content fine claycontent and c had also minimum mean of sand content gravel content and Also irrigated farming withmaximum mean of sand content and minimum mean of clay content had minimum mean of c However grassland and irrigated farming did not have significant differences in terms of soil c and Predictionmodels of shear strength derived in group 2 SSPFs were more accurate than those derived in group 1 PTFs In order to compare the modeling methods efficacy indices were used for evaluation of the bestresult of each method The results showed that ANN models were more feasible in predicting soil shearstrength parameters than MLR and ANFIS models The ANNs MLR and ANFIS accounted for 90 43and 37 percents of variations R2 of c respectively Corresponding values for prediction were 92 57and 52 percents respectively Therefore all three models were more successful in predicting frictionalpart than cohesive part of soil shear strength Moreover ANNs were the best models forpredicting modeling soil surface shear strength in the region because they can extract patterns and detectnonlinear trends that are too complex Results of sensitivity analysis for ANN models indicated thatN

هوائي، شقايق

ارزيابي عوامل موثر برمقاومت برشي سطح خاك در سطح زمين نما به كمك تكنيك شبكه عصبي مصنوعي

سيستم نروفازي , رگرسيون , توابع انتقالي خاك , توابع پيش بيني فضايي خاك , آنالز حساسيت