Low gas-saturation reservoirs are gas bearing intervals whose gas saturation is less than 47%. They are common in the Quaternary of the Sanhu area in the Qaidam Basin. Due to the complex genesis mechanisms and special geological characteristics, the logging curves of low gas-saturation reservoirs are characterized by ambiguity and diversity, namely without significant log response characteristics. Therefore, it is particularly difficult to identify the low gas-saturation reservoirs in the study area. In addition, the traditional methods such as using the relations among lithology, electrical property, physical property and gas bearing property, as well as their threshold values, can not effectively identify low gassaturation reservoirs. To solve this problem, we adopt the decision tree, support vector machine and rough set methods to establish a predictive model of low gas-saturation reservoirs, which is capable of classifying a mass of multi-dimensional and fuzzy data. According to the transparency of learning processes and the understandability of learning results, the predictive model was also revised by absorbing the actual reservoir characteristics. Practical applications indicate that the predictive model is effective in identifying low gas-saturation reservoirs in the study area.