At present, pipeline transportation is a very common mode in the long-distance transportation of liquid materials such as oil. Compared with other transportation ways, pipeline transportation is not only high-throughput and continuous, but it is also reliable and of low energy consumption. Although the probability of pipeline leakage is low, the result of leakage is catastrophic, including economic losses, personal safety, and environmental pollution. Once the liquid pipeline leakage occurs, risk assessment and emergency repair measures are urgent. The key to these is to determine the leakage parameters of the pipeline. However, many current leakage detection methods are based on physical mechanism and hydraulic calculations with assumptions, resulting in poor accuracy and a high false alarm rate. Therefore, from the perspective of data-driven, the relationship between leakage parameters and the operational flow rate and pressure is mined in this paper. First, due to the limited leakage accidents for one pipeline, a large amount of leakage data is generated through experimental simulation. For every second, the pressure and flow rate in upstream as well as downstream should be recorded, making it hard for common deep learning algorithms to cope with such a high-dimensional complex dataset. To overcome the dimensionality problem, a conditional generative adversarial network is then introduced to treat the dimensional data as labels when the leakage parameters model is trained. After training the leakage data, the leakage parameters can be estimated based on the detected data, when the leakage occurs. Finally, four examples of pipeline leakage are tested to demonstrate our superiority over two traditional algorithms, i.e. artificial neural network and support vector machine. Thus, this method has a potential prospect in the estimation of leakage parameters, and can effectively guide site management when the leakage occurs.