Application of machine-learning models for diagnosing health hazard of nitrate toxicity in shallow aquifers

Abstract

There is a growing concern about health hazards linked to nitrate (NO3) toxicity in groundwater due to overuse of nitrogen fertilizers in rice production systems of northern Iran. Simple-cost-effective methods for quick and reliable prediction of NO3 contamination in groundwater of such agricultural systems can ensure sustainable rural development. Using 10-year time series data, the capability of adaptive neuro-fuzzy inference system (ANFIS) and support vector machine (SVM) models as well as six geostatistical models was assessed for predicting NO3 concentration in groundwater and its noncarcinogenic health risk. The dataset comprised 9360 water samples representing 26 different wells monitored for 10 years. The best predictions were found by SVM models which decreased prediction errors by 42–73 % compared with other models. However, using well locations and sampling date as input parameters led to the best performance of SVM model for predicting NO3 with RMSE = 4.75–8.19 mg l−1 and MBE = 3.3–5.2 mg l−1. ANFIS models ranked next with RMSE = 8.19–25.1 mg l−1 and MBE = 5.2–13.2 mg l−1 while geostatistical models led to the worst results. The created raster maps with SVM models showed that NO3 concentration in 38–97 % of the study area usually exceeded the human-affected limit of 13 mg l−1 during different seasons. Generally, risk probability went beyond 90 % except for winter when groundwater quality was safe from nitrate viewpoint. Noncarcinogenic risk exceeded the unity in about 1.13 and 6.82 % of the study area in spring and summer, respectively, indicating that long-term use of groundwater poses a significant health risk to local resident. Based on the results, SVM models were suitable tools to identify nitrate-polluted regions in the study area. Also, paddy fields were the principal source of nitrate contamination of groundwater mainly due to unmanaged agricultural activities emphasizing the importance of proper management of paddy fields since a considerable land in the world is devoted to rice cultivation.