Empirical relationships between Arias Intensity and peak ground acceleration for western China

There is little available attenuation relationship for Arias Intensity (AI) in China. Empirical relationships between AI and peak ground acceleration (PGA) provide another option for predicting AI. We establish empirical relationships for AI and PGA for western China, utilizing 3,169 horizontal and 979 vertical strong motion records with PGA >= 0.01 g from 274 earthquakes (M S 4.0-8.0), originating in eight provinces in southwest (Yunnan, Sichuan) and northwest China (Gansu, Shaanxi, Ningxia, Qinghai, Inner Mongolia, and Xinjiang). The influences of M S epicenter distance, and site conditions indicators VS30, generic site classes (i.e., rock and soil) are explored. The results show that the logarithm of AI increases linearly with the increase of the logarithm of PGA and M S, and decreases with the logarithm of VS30. However, the influence of site conditions on AI-PAG relationships can't be recognized by the simple generic rock and soil site classes. The epicenter distance has little effect on the AI-PAG relationships. Empirical relationships are developed to estimate horizontal or vertical AI as a function of PGA (basic model), PGA and MS (model 2) for southwest, northwest, and western China, using all the records. Empirical relationships for AI as a function of PGA, MS, and VS30 (model 1) are established using the 2,248 horizontal (70.9% of the total) and 670 vertical (68.4% of the total) records with VS30 between 148 and 841m/s. The notable disparity between model 1 of the southwest and northwest regions is chiefly attributed to local site conditions, indicating that the AI-PGA correlation is region-dependent. These findings enable one way of estimating AI for western China and will contribute to a better understanding of AI attenuation.