Assessment of the variation of soil trace metals using artificial intelligence: A case study from Eastern Province, Saudi Arabia
Soils may preserve metals from different sources that might pollute the environment. Hence, it is very important to assess the concentration of the geochemical elements of areas where intensified agriculture and industrial activities. This study involved the spatial assessment of topsoil contamination with trace metals in selected areas in Eastern Province, Saudi Arabia. To achieve this objective, more than 130 samples of topsoil from residential, industrial, and agricultural areas were collected and analysed. Inductively coupled plasma - optical emission spectroscopy (ICP-OES) was used to analyse the samples for various trace metals. Moreover, different artificial intelligence (AI) models such as artificial neural network (ANN) were applied to estimation the zinc (Zn), copper (Cu), chromium (Cr), and lead (Pb) using feature-based input selection. The experimental results depicted that the average concentration levels of HMs were as follows: Chromium (Cr) (31.79±37.9 mg/kg), Copper (Cu) (6.76±12.54 mg/kg), Lead (Pb) (6.34±14.55 mg/kg), and Zinc (Zn) (23.44±84.43 mg/kg). The modelling accuracy showed that agricultural and industrial stations performance merit with goodness-of-fit ranges of 51-91% and 80-99%, respectively. This study concluded that AI models might be successfully applied for the quick estimation of soil trace metals and for decision support system.