-
oa Statistical Modeling of Radioactinide Activity with Cesium-137 and Strontium-90 using the ANS Neural Network
- Publisher: European Association of Geoscientists & Engineers
- Source: Conference Proceedings, 18th International Conference Monitoring of Geological Processes and Ecological Condition of the Environment, Apr 2025, Volume 2025, p.1 - 4
Abstract
Summary
The use of ANS neural networks in statistical modeling of radioactinide activity prediction are highly effective. Using both of radiocesium and radiostrontium as input parameters has several advantages: in man-made pollution their content is higher than the content of transuranic radionuclides; they are more sensitive indicators of vertical and surface transport; their identification requires less expensive and more accessible analytics. The incorporation in the statistical model such a qualitative indicator “sampling layer” significantly improves the reliability of the initial data. It takes into account the high spatial migration ability of cesium-137 and strontium-90 that provides 98–99% efficiency of the regression model.
EAGE Publications BV © 2025 The Authors © European Association of Geoscientists and Engineers