The application of multivariate calibration analysis is very useful in water environmental geochemistry, it can be used to process and analyze complicated data, disclose the relation between water quality condition and pollutant discharges, establish models for assessing and predicting water quality, which is fundamental in water pollution control. The paper reviews various multivariate calibration analysis methods including principal component analysis, partial least squares regression and artificial neural networks, as well as their application, progress and outlook in water environmental geochemistry.