Empirical modeling and simulation for discharge dynamics enabling catchment-scale water quality management

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 RRSE 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

[1]  Seok Hwan Hwang,et al.  A new measure for assessing the efficiency of hydrological data-driven forecasting models , 2012 .

[2]  Christian W. Dawson,et al.  An artificial neural network approach to rainfall-runoff modelling , 1998 .

[3]  Richard H. Hawkins,et al.  The NRCS Curve Number , a New Look at an Old Tool , 2001 .

[4]  Dimitri P. Solomatine,et al.  Modular learning models in forecasting natural phenomena , 2006, Neural Networks.

[5]  R. Abrahart,et al.  Detection of conceptual model rainfall—runoff processes inside an artificial neural network , 2003 .

[6]  Andrea Castelletti,et al.  Assessing the predictive capability of randomized tree-based ensembles in streamflow modelling , 2013 .

[7]  Calvin D. Perry,et al.  A real-time wireless smart sensor array for scheduling irrigation , 2008 .

[8]  Alex J. Cannon,et al.  Daily streamflow forecasting by machine learning methods with weather and climate inputs , 2012 .

[9]  J. Arnold,et al.  HYDROLOGICAL MODELING OF THE IROQUOIS RIVER WATERSHED USING HSPF AND SWAT 1 , 2005 .

[10]  Daniela Rus,et al.  Model-based monitoring for early warning flood detection , 2008, SenSys '08.

[11]  Dimitri P. Solomatine,et al.  M5 Model Trees and Neural Networks: Application to Flood Forecasting in the Upper Reach of the Huai River in China , 2004 .

[12]  Ian H. Witten,et al.  The WEKA data mining software: an update , 2009, SKDD.

[13]  D. Solomatine,et al.  Model trees as an alternative to neural networks in rainfall—runoff modelling , 2003 .

[14]  J. R. Quinlan.  Learning With Continuous Classes , 1992 .

[15]  Allen T. Hjelmfelt,et al.  Runoff Probability, Storm Depth, and Curve Numbers , 1985 .