The Study of Three Multivariate Regression, Neural Network and Neuro-Fuzzy Models Efficiency in Splash Erosion Estimation (Published)
The application of artificial intelligence in soil properties prediction has been progressing and developing in recent years. Determination of aggregate stability properties as indices against soil erodibility is time consuming and difficult. The predictability of three multivariate linear regression, neural network and neuro-fuzzy models efficiency in splash erosion prediction has been tested in this study. Due to low correlation of some properties of the soil, only four input parameters of Sodium Absorption Ratio (SAR), Porosity, Geometric Mean Diameter (GMD) of aggregates and runoff height have been analyzed as input variables in splash erosion prediction. The results indicated the priority of neuro-fuzzy method compared to others. Coefficient of determination of 0.798 in gauss2mf membership function with 3 membership functions and Hybrid Learning Algorithm have been obtained in adaptive neuro-fuzzy inference method. The small number of available data, in addition to samples distribution and spatial changes of samples led to low accuracy of multivariate linear regression method in splash erosion prediction.
Keywords: Aggregate Stability, Artificial Intelligence, Geometric Mean Diameter (GMD), Soil Erodibility
Assessment of Some Soil Erodibility Indices on Agricultural Land Uses in Fadan Kagoma Area of Jema’a Local Government Area, Kaduna State, Northern Nigeria (Published)
A field study was carried out in Fadan Kagoma, Kaduna State to assess some erodibility indices on different agricultural land uses. Five plots made up of Yam, Beans, Groundnut, Ginger and Fallow were selected. 80 soil samples were collected in all at a depth of 0-22.5cm. 16 samples from each site, out of which 4 composite samples were generated and analyzed for pH, electric conductivity, particle size distribution, organic carbon, exchangeable acidity and bases (exch. Na, Ca, and K) using standard laboratory procedures. While the soil erodibility indices were derived from the results of data from laboratory. Analysis of Variance compared erodibility indices amongst and between agricultural land use types was carried out at α = 0.05 significance level. Result showed, Clay Ratio (CR), Modified Clay Ratio (MCR) and Critical Level of Soil Organic Matter concentration (St) did not significantly vary with the agricultural land uses. Results also showed mean values of 4.96% and 4.01% for critical level of soil organic matter content in Yam and Beans plots respectively, these results imply that there was loose soil structure and high susceptibility of the soils to erosion; the Fallow plot had an St value of 7.05% implying an unstable structure and erosion risk while the mean values of G/nut and Ginger implied stable structure and lesser susceptibility to erosion with 11.36% and 10.52% respectively. Soil erodibility indices further showed mean values of 7.58% for critical level of soil organic matter content, 11.48 for clay ratio and 9.41 for modified clay ratio. Communal tree planting, farming across the slopes, crop rotation and grass fallowing were among the recommendations proffered.
Keywords: Agricultural Landuse, Soil Erodibility, Soil Erodibility Indices