Ali Keshavarzi

Modeling soil cation exchange capacity using soil parameters

We modeled soil CEC using easily measured parameters.Heuristic models were applied for modeling CEC through using k-fold testing.k-fold testing assessing methodology provides much better insight about the models accuracy.Neuro-fuzzy surpasses GEP, NN and SVM in modeling CEC. Accurate knowledge about soil cation exchange capacity (CEC) is very important in land drainage and reclamation, groundwater pollution studies and modeling chemical characteristics of the agricultural lands. The present study aims at developing heuristic models, e.g. gene expression programming (GEP), neuro-fuzzy (NF), neural network (NN), and support vector machine (SVM) for modeling soil CEC using soil parameters. Soil characteristic data including soil physical parameters (e.g. silt, clay and sand content), organic carbon, and pH from two different sites in Iran were utilized to feed the applied heuristic models. The models were assessed through a k-fold test data set scanning procedures, so a complete scan of the possible train and test patterns was carried out at each site. Comparison of the models showed that the NF outperforms the other applied models in both studied sites. The obtained results revealed that the performance of the applied models fluctuated throughout the test stages and between two sites, so a reliable assessment of the model should consider a complete scan of the utilized data set, which will be a good option for preventing partially valid conclusions obtained from assessing the models based on a simple data set assignment.

Using soil easily measured parameters for estimating soil water capacity: Soft computing approaches

Abstract The current study examines the applicability of six different soft computing approaches, gene expression programming (GEP), neuro-fuzzy (NF), support vector machine (SVM), multivariate adaptive regression spline (MARS), random forest (RF), and model tree (MT) techniques in modeling two important soil water capacity parameters, field capacity (FC) and permanent wilting point (PWP). Geometric mean particle-size diameter (dg), soil bulk density (BD), clay and silt obtained from 192 soil samples were introduced as input variables to the applied techniques and k-fold testing procedure was used for better comparison of the soft computing models. The best accuracy was provided by the NF models followed by the GEP, while the MT approach gave the worst estimates. The performances accuracies of the soft computing models in estimation of PWP parameter were higher than those in the FC estimation. Further, the soft computing approaches were compared with the traditional multi-variable linear regression (MLR) as well as the previously developed pedotransfer functions (PTFs) and the better FC and PWP estimates which confirms the superiority of the soft computing approaches. The NF model increased the performance of the best PTF (Aina-Periaswamy) by 33% with respect to GMER in FC estimation while the SI statistics of the best PTF (Ghorbani-Homaee) was decreased by 50% using the soft computing model. The performance of the best PTF (Aina-Periaswamy) with respect to GMER was increased by 74% in PWP estimation while the SI statistics of the best PTF (Dijkerman) was decreased by 99% using the soft computing model.

Mapping of Spatial Distribution of Soil Salinity and Alkalinity in a Semi-arid Region

Mapping of Spatial Distribution of Soil Salinity and Alkalinity in a Semi-arid Region Spatial variability of salinity and alkalinity is important for site-specific management since they are the most important factors influencing soil quality and agricultural production. Geostatistical methods provide a means to study the heterogeneous nature of spatial distributions of soil salinity and alkalinity. The present study was carried out to evaluate the accuracy of different spatial interpolation methods including kriging, cokriging and IDW methods for prediction of spatial distribution of salinity (EC) and sodium adsorption ratio (SAR) in soils of Ziaran region in Qazvin province, Iran. The tracking of the soil profiles was done using a Garmin eTrex-H model global positioning system (GPS) receiver. Sampling was done with stratified random method and sixty soil samples from 0 to 15 cm depth were collected. After data normalization, the variograms were developed. For selecting the best model for competing on experimental variograms, the lower RSS value was used. Experimental variograms were fitted to spherical and exponential models. The best model for interpretative was selected by means of cross validation and error evaluation methods, such as RMSE method. The sum of Ca2+ + Mg2+ and Na+ concentration which were highly correlated with soil salinity and sodium adsorption ratio, respectively, are used as auxiliary parameters in this study. The results showed that kriging and cokriging methods were better than IDW method for prediction of EC and SAR. Finally, the soil EC and SAR maps were prepared, using different spatial interpolation methods in GIS environment. Mapowanie przestrzennej zmienności zasolenia na obszarach o klimacie półsuchym Artykuł przedstawia zastosowanie metod geoinformacyjnych do określania przestrzennej zmiennosści zasolenia zasadowości gleb wy-ksztalconych w klimacie półsuchym. Omówiono zastosowanie popularnych technik interpolacyjnych - metody ważonych odwrotnych odległości (Inverse Distance Weighted - IDW) oraz metod geostatystycznych krigingu i kokrigingu. W pracy przedstawiono analię błędów map wynikowych wykonanych różnymi metodami interpolacyjnymi. Metody geostatystyczne - kriging i kokriging - wykazały większą dokładność w porównaniu do metody IDW.

Developing Pedotransfer Functions for Estimating Field Capacity and Permanent Wilting Point Using Fuzzy Table Look-up Scheme

Study of soil properties like field capacity (F.C) and permanent wilting point (P.W.P) plays important roles in study of soil moisture retention curve. Pedotransfer functions (PTFs) provide an alternative by estimating soil parameters from more readily available soil data. In this study, a new approach is proposed as a modification to a standard fuzzy modeling method based on the table look-up scheme. 70 soil samples were collected from different horizons of 15 soil profiles located in the Ziaran region, Qazvin province, Iran. Then, fuzzy table look-up scheme was employed to develop pedotransfer functions for predicting F.C and P.W.P using easily measurable characteristics of clay, silt, O.C, S.P, B.D and CaCO3. In order to evaluate the models, root mean square error (RMSE) and R 2 were used. The value of RMSE and R 2 derived by fuzzy table look-up scheme for F.C and P.W.P were (1.65, 0.87) and (1.03, 0.83), respectively.

Assessment of soil properties from catchment areas of Ravi and Beas rivers: a review

ABSTRACT Soil is a substantive environmental medium that is subjected to various physiochemical challenges derived by natural, as well as human activities. The present review attempts to summarize the pollution status of soil from the catchments areas of Beas and Ravi Rivers in Punjab, India, as reported by different workers. Principal component analysis (PCA) showed that anthropogenic activities and lithogenic factors are the major sources of metals. The average values of heavy metals of Beas River for heavy metals, Cr, Cu, Co, and Cd, were lower than the values suggested by Awasthi, European Union, and Ewers. The average values of C (0.29%), P (0.05 mg/g), and N (0.13 mg/g) were found for the Beas River, whereas for Ravi River the average values recorded were C (0.32%), P (0.01 mg/g), and N (0.16 mg/g). The results of contamination factor (CF) indicate that soil of Beas River is less contaminated by the metals. The results of ecological risk index indicate that metals showed low ecological risk in the soils of Beas River.

Evaluation of groundwater quality and its suitability for drinking and irrigation using GIS and geostatistics techniques in semiarid region of Neyshabur, Iran

Groundwater is a vital source for drinking and agricultural purposes in semiarid region of Neyshabur area (Iran). The present study assessed the groundwater quality and mapped the spatial variation of water samples in terms of suitability for drinking and irrigation purposes. A total 402 groundwater samples were collected from the field with global positioning system (GPS) from 2010 to 2013 and analyzed for pH, calcium (Ca2+), magnesium (Mg2+), sodium (Na+), potassium, bicarbonate, sulfate, chloride, sodium adsorption ratio (SAR), electrical conductivity (EC), total dissolved solids, and total hardness (TH). A GIS-based ordinary kriging method with best fit semivariogram models was used for preparation of thematic maps of groundwater quality parameters. The results were evaluated and compared with WHO (2011) recommended water quality standard. Results showed that 68.40% of SAR, 25% of Mg2+, 32.62% of Na+, and 1.74% of TH of the total groundwater samples are suitable for the irrigation purpose. Consequently, 55.57% of EC, 89.19% of TDS, 0.75% of pH, and 6.25% of K+ of the total groundwater samples are suitable for the drinking purpose as per the WHO standard. The groundwater quality in the study area is very hard and slightly alkaline in nature. The spatial distribution map of groundwater quality showed 80% of the area suitable for drinking purpose; whereas, 90% of the area demarcated for irrigation purpose.