Generalized spatiotemporally-decoupled framework for reconstructing the source of non-constant atmospheric radionuclide releases

Abstract. Determining the source location and release rate are critical in assessing the environmental consequences of atmospheric radionuclide releases, but remain challenging because of the huge multi-dimensional solution space. We propose a generalized spatiotemporally-decoupled two-step framework to reduce the dimension of the solution space in each step and improves the reconstruction accuracy, which is applicable to non-constant releases. The decoupling process is conducted by applying a temporal sliding-window average filter to the observations, thereby reducing the influence of temporal variations in the release rate and ensuring that the features of the filtered data are dominated by the source location. A machine learning model is trained to link these features to the source location, enabling independent source localization. Then the release rate is determined using projected alternating minimization with the L1-norm and total variation regularization algorithm. Validation using SCK-CEN ⁴¹Ar experimental data demonstrates that the localization error is less than 1 %, and the temporal variations, peak release rate, and total release are reconstructed accurately. The proposed method exhibits higher accuracy and a smaller uncertainty range than the correlation-based and Bayesian methods. Furthermore, it achieves stable performance with different hyperparameters and produces low error levels even with only a single observation site.