Activity analysis to environmental sample γ-spectrum with OLAM net

Based on the learning mechanism of OLAM net-work and the theory of γ-spectrum analysis, an artificial neural net-work to carry out the activity analysis of nuclides was constructed. For getting γ-spectrum of the nuclide of a simple substance to train the net, the characteristic spectra of the nuclide were simulated with the scale equations given in the spectrum analysis software. The well-trained net was used to calculate the activities of nuclides 238U, 226Ra, 232Th, 40K and 137Cs in the samples of environmental soil. By comparing the results with the SPAS-G calculation, the average relative deviation is 2.24%, and this indicates that both the net construction and the characteristic spectrum simulation are successful. (authors)