RESEARCH ARTICLE Using the combined model of gamma test and neuro-fuzzy system for modeling and estimating lead bonds in reservoir sediments Ali Akbar Mohammadi 1 & Mahmood Yousefi 2 & Jaber Soltani 3 & Ahmad Gholamalizadeh Ahangar 4 & Safoura Javan 1 Received: 7 April 2018 /Accepted: 20 August 2018 # Springer-Verlag GmbH Germany, part of Springer Nature 2018 Abstract Heavy metals attract a great deal of attention nowadays due to their potential accumulation in living creatures and transference in the food chain. Sediments of water reservoirs are considered to be a source of accumulation of these metals that develop in response to human activities and soil erosion. This study collected 180 samples of the surface sediments of water reservoir 1 at Chahnimeh in Sistan. Efficiency of the ANFIS model was evaluated to estimate the five bonds following the measurement of parameters in the laboratory. The following results were obtained for the parameters: organic carbon (OC) %, 0.31; cation exchange capacity (CEC), 37.07 Cmol kg; total Pb, 25.19 mg/kg; clay %, 45.87; and silt %, 39.02. These parameters were used as input for the training model. In the output layer, lead bonds were chosen as modeling targets in the following way: Pb f1 (4.61); Pb f2 (0.54); Pb f3 (16.28); Pb f4 (3.42); and Pb f5 (0.38) mg/kg. The best input compound in this model was chosen using the gamma test. From a total of 180, 88 data were considered for the model training section. Eventually, the neural-fuzzy model (subtractive clustering), developed for the prediction of lead bonds in the studied region, was able to account for over 99% of lead bonds in the sediments; considering statistical criteria of root mean squares error or RMSE (0.0337–0.0813) and determination coefficient or R 2 (0.92– 0.99), this model showed good performance with regard to prediction. Keywords Sediments . Gamma test . M-test . ANFIS . Zabol, Iran Introduction Suspended sediments in a water resource play an important role in aquatic ecosystems and contribute strongly to water quality with implications on human and environmental health (Duan et al. 2013a, b, 2016). Heavy metals are one of the most serious and dangerous environmental contaminations due to their toxicity and stability (Macfarlane and Burchett 2000; Defew et al. 2005; Javan et al. 2015). Lead is a heavy metal naturally found mainly in bivalent form and, also, in combination with carbonate and hydroxide (Aboud et al. 2009). Lead and its compounds are used across various industries including dye production, pipe making, de- velopment of lead bullets, battery making, preparation of dif- ferent alloys, crystal making, pottery, ceramics, tile making, and pesticide production (Mielke et al. 1991). One way of being exposed to lead is through its transference from remote areas (Malakootian and Khashi 2014). This metal causes seri- ous damage to the brain and can lead to mental retardation, behavioral disorders, memory problems, and mood changes (Mosaferi et al. 2008). The most important effects of lead are manifested in the growth of children. In adults, it can also cause hypertension (WHO 2004, 2006). Lead is also consid- ered to be a carcinogenic agent in the digestive system (Corcoran et al. 2003). Artificial intelligence models are a powerful computational technique for modeling nonlinear combinations, especially for unknown parameters of the explicit relationship between Responsible editor: Marcus Schulz * Safoura Javan javans1@nums.ac.ir 1 Department of Environmental Health Engineering, Neyshabur University of Medical Sciences, Neyshabur, Iran 2 Department of Environmental Health Engineering, School of Public Health, Tehran University of Medical Sciences, Tehran, Iran 3 Irrigation and Drainage Engineering Department, Abouraihan Campus, University of Tehran, Tehran, Iran 4 Department of Soil Science, Faculty of Soil and Water University of Zabol, Zabol, Iran Environmental Science and Pollution Research https://doi.org/10.1007/s11356-018-3026-7