The High Energy Particle Detector (HEPD-02) is one of the scientific payloads of the China Seismo-Electromagnetic Satellite (CSES-02) aimed to measure particle precipitation due to short-time perturbations in the radiation belts caused by solar and terrestrial phenomena. Developed by the CSES-Limadou collaboration, HEPD-02 will measure particle flux and energy spectrum in a wide range of energies and was designed to improve the performance of the 1st generation detector. We report on the Geant4 Monte Carlo simulation developed to study the response of the new detector. In addition to the detailed simulation, a parametric approach was also developed in order to reduce simulation time without losing performance or precision. An event reconstruction software is used to estimate the arrival direction, energy, and identity of the incoming particles. Moreover, specifically designed neural networks are trained using the ADC signals from the calorimeter and the particle impact position and direction to better reconstruct the deposited energy, correcting for the energy lost in the inert materials obtained from simulation.