We have developed artificial neural network (ANN) based models for simulating two application examples of hydrodynamic cavitation (HC) namely, biomass pre-treatment to enhance biogas and degradation of organic pollutants in water. The first case reports data on influence of number of passes through HC reactor on bio-methane generation from bagasse. The second case reports data on influence of HC reactor scale on degradation of dichloroaniline (DCA). Similar to most of the HC based applications, the availability of experimental data for these two applications is rather limited. In this work a systematic methodology for developing ANN model is presented. The models were shown to describe the experimental data very well. The ANN models were then evaluated for their ability to interpolate and extrapolate. Despite the limited data, the ANN models were able to simulate and interpolate the data for two very different and complex HC applications very well. The extrapolated results of biomethane generation in terms of number of passes were consistent with the intuitive understanding. The extrapolated results in terms of elapsed time were however not consistent with the intuitive understanding. The ANN model was able to generate intuitively consistent extrapolated results for degradation of DCA in terms of number of passes as well as scale of HC reactor. The results will be useful for developing quantitative models of complex HC applications.