Collecting very large amount of data from experimental measurement is a common practice in almost every scientific domain. There is a great need to have specific techniques capable of extracting synthetic information, which is essential to understand and model the specific phenomena. The Proper Orthogonal Decomposition (POD) is one of the most powerful data-analysis methods for multivariate and nonlinear phenomena. Generally, POD is a procedure that takes a given collection of input experimental or numerical data and creates an orthogonal basis constituted by functions estimated as the solutions of an integral eigenvalue problem known as a Fredholm equation. By utilising POD to identify flow structure in horizontal pipeline, specially, for slag, plug and wavy stratified air-water flow regimes, this paper proposes a novel approach, in which POD technique extends the current evaluation procedure of electrical impedance tomography applied on air-water flow measurement [32] . This extension is provided by implementation of the POD as an identifier of typical horizontal multiphase flow regimes. The POD snapshot matrices are reconstructed for electrical thomography measurement domain and specific flow conditions. Direct POD method introduced by Lumley and Snapshot POD method introduced by Sirovich are applied. It is expected that this study may provide new knowledge on two phase flow dynamics in a horizontal pipeline and supportive information for further prediction of multiphase flow regime.