UV-vis spectrophotometric and artificial neural network for estimation of ammonia in aqueous environment using cobalt(ii) ions

Abstract

This paper reports the results for the quantitative determination of ammonia (NH₃) in aqueous solution by a UV-vis spectrophotometric method and artificial neural network (ANN) intelligence tool. Quantitation of NH₃ was based on the chemical reaction of NH₃ with cobalt(II) (Co²⁺) ions in basic medium to form a blue hexamminecobaltate(II) ([Co(NH₃)₆]²⁺) complex. Characterizations of Co²⁺ ion in solution included photostability, pH effect, response time, Co²⁺ ion concentration effect, dynamic linear range and reproducibility, which were performed using a UV-vis spectrophotometer. The pink cobalt species gradually changed to blue with increasing NH₃ concentration. The absorption calibration curve was linear over the NH₃ concentration range of 0.6–3.5 mM at optimum pH 8 with a reproducibility relative standard deviation (RSD) of <4.0%. The interference effect was found to be negligible for a number of foreign ions present in the reaction medium during NH₃ determination in an aqueous environment. A set of absorbance data for the [Co(NH₃)₆]²⁺ complex at selected wavelengths was input for ANN training using a back-propagation algorithm. The trained network with 22 hidden neurons, a 28 500 epoch number and 0.001% learning rate has extended the dynamic NH₃ concentration range to 0.6–5.9 mM with a calibration error as low as 0.0649 × 10⁻³. The proposed ANN electronic sensor shows promise for NH₃ estimation in unknown water samples based on pattern recognition.