Introduction Hazardous materials are often buried in ferrometallic containers. Detection and precise location of these objects and estimation of the type and quantity of the objects are becoming increasingly important in environmental investigations worldwide. The best geophysical technique for locating and mapping the distribution of ferrometallic materials is a magnetic survey, especially when the signal-to-noise ratio of the magnetic anomalies is high. However, geophysical measurements need to be interpreted and this can be time consuming. Therefore, there is a need for a real time technique that combines the efficiency of a human interpreter with the precision and speed of a computer. One such technique may be found in the emerging field of artificial neural networks.