Self-organizing map artificial neural network application in multidimensional soil data analysis

Because of the complex nonlinear relationships between soil variables and their multivariable aspects, classical analytic, deterministic, or linear statistical methods are unreliable and cause difficulty to present or visualize the results. Using intelligent techniques, which have ability to analyze the multidimensional soil data with an intricate visualization technique, is crucial for nutrient and water management in soil, consequently, for sustainable agriculture and groundwater management. In this study, first, the Kohonen self-organizing feature maps (KSOFM) neural network was applied to analyze the effects of soil physical properties on soil chemical/hydraulic processes, and to diagnose the inter-relationships of the multivariable soil data in vadose zone. The inter-relationships among the soil variables were extracted and interpreted using the pattern analysis visualized in component planes. Then K-means clustering algorithm was used to determine the optimal number of clusters by using the Silhouette clustering validity index, resulting in six clusters or groups for soil variables. In conclusion, the KSOFM technique is an effective tool for analyzing and diagnosing the dynamics in soil and extracting information from the multidimensional soil data. These results suggest that this technique has a potential to monitor and diagnose not only soil physical/chemical/hydraulic processes, but also soil morphological and microbiological processes.