Miniature Multi-Ion Sensor Integrated With Artificial Neural Network

Low-cost, accurate monitoring of macronutrient ions in soils, plants, and water is highly desired to improve fertilizer management for maximum profitability and minimum negative environmental impacts. Traditional ion-selective electrodes (ISEs) suffer from interference from nontarget ions. This paper reports the integration of artificial neural networks (ANNs) and a miniature sensor containing an array of three ISE-based sensing elements to improve accuracy of the sensor in detecting and quantifying target nitrate (NO3-), phosphate (H2PO4-), and potassium (K+) ions in the environment. The sensor outputs of NO3-, H2PO4-, and K+ ion concentrations are used to train and optimize ANNs. The optimized neural networks are applied to classify and estimate concentrations of the target ions in the presence of interfering ions. The ANN- assisted array of sensing elements reduces cross-sensitivity between these elements. The present sensor is validated with measurements of NO3-, H2PO4-, and K+ ions in soil solution, plant sap, and tile drainage water from crop fields.

Automated summary

Low-cost and accurate monitoring of macronutrient ions in soils, plants, and water is achieved by integrating artificial neural networks with a miniature sensor containing three ISE-based sensing elements. The optimized neural networks improve the sensor's accuracy in detecting and quantifying target ions in the presence of interfering ions. This sensor introduces a new approach to reducing cross-sensitivity between sensing elements for improved ion concentration estimation.