Output details

Dynamic nonlinear state-space model with a neural network via improved sequential learning algorithm for an online real-time hydrological modeling

This research presents a new system to enable the hydrological modellers to overcome the technical problem of the current offline prediction system used in the industry that requires an intensive collection of historical data by helping the development of the real-time prediction system integrated with online data monitoring system for dynamic hydrological systems. This output is being applied to develop the real-time river flow forecasting system with the satellite weather data in collaboration with Korea National Research Institute (Dr Jong-Wha Ham) and rainfall recharge estimation model to groundwater with Institute of Geological and Nuclear Sciences (Mr Paul White, P.White@gns.cri.nz).