The paper aims to forecast the Philippine storm frequencies using nonlinear Poisson model. More specifically, the nonlinear kernel of the model is defined by the Artificial Neural Network (ANN) with one hidden layer and at least two output neurons. The model is trained to simultaneously forecast two semesters ahead for a given input. Further, the covariates studied were the Average Sea Surface Temperatures in the NINO3.4 region (5°-5°S, 170°-120°W), and the Average Sea Surface Temperatures in the eastern pole (0°10°S, 90°-110°E) of the Dipole Mode Index. The data, taken from the Japan Meteorological Agency’s Regional Specialized Meteorological Center, with time points running from 1950 to October 2021, is modeled at a semester-level granularity. The estimation is done using Maximum Likelihood Estimation by minimizing the negative log-likelihood function. Further, the proposed model is studied for different activation functions and different number of hidden neurons. Lastly, out of the 12 candidate models, the best model captures well the characteristics of the data both in terms of the point forecast and the associated uncertainties.