2014
EMSS 2014 Proceeding
Empirical modeling and simulation for discharge dynamics enabling catchment-scale water quality management
Authors: Huma Zia, Nick R. Harris, Geoff V. Merrett
Abstract
Excessive or poorly timed application of irrigation and fertilizers, coupled with inherent inefficiency of nutrient uptake by crops result in nutrient fluxes into the water system. Due to the recent adoption of WSNs in precision agriculture, it is proposed that existing networked agricultural activities can be leveraged into an integrated mechanism by sharing information about discharges and predicting their impact, allowing dynamic decision making for irrigation strategies. Since resource constraints on network nodes (e.g. battery life, computing power etc.) require a simplified predictive model, low-dimensional model parameters are derived from the existing National Resource Conservation Method (NRCS). An M5 decision tree algorithm is then used to develop predictive models for depth (Q), response-time (t1) and duration (td) of the discharge. 10- fold cross-validation of these models demonstrates RRMSE of 10.2%, 30% and 9.6% for Q, t1 and td respectively. Furthermore, performance of these models is validated using multiple linear regression method.
I3M Scientific Sponsors
I3M Industrial Sponsors
I3M Media Sponsors
