An important and useful tracer test application is on the estimation of reservoir properties such as porosity, dispersivity, fracture width, block size, rock adsorption, layer thickness or oil saturation. In order to obtain estimations of these parameters, mathematical tracer transport models are fitted to field tracer breakthrough data. Data fitting requires the solution of the so called inverse problem. The inverse problem consists in employing regression methods to determinate the free model parameters that provide the best field data fitting. When solving the inverse problem some difficulties associated to non-linearity might appear, thus finding a solution to the inverse problem can frequently result arduous and cumbersome. In this paper, an alternative approach to solve the inverse problem is analysed.