Empirical modeling and simulation for discharge dynamics enabling catchment-scale water quality management
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
Zia, Huma
74118b4c-35ab-44e8-a44f-daa4cc6f83e8
Harris, Nick
237cfdbd-86e4-4025-869c-c85136f14dfd
Merrett, Geoff V.
89b3a696-41de-44c3-89aa-b0aa29f54020
Zia, Huma
74118b4c-35ab-44e8-a44f-daa4cc6f83e8
Harris, Nick
237cfdbd-86e4-4025-869c-c85136f14dfd
Merrett, Geoff V.
89b3a696-41de-44c3-89aa-b0aa29f54020
Zia, Huma, Harris, Nick and Merrett, Geoff V.
(2014)
Empirical modeling and simulation for discharge dynamics enabling catchment-scale water quality management.
The 26th European Modeling & Simulation Symposium.
10 - 12 Sep 2014.
(Submitted)
Record type:
Conference or Workshop Item
(Paper)
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 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
Text
I3M 2014-Final Paper.pdf
- Other
Restricted to Registered users only
Request a copy
More information
Submitted date: 2014
Venue - Dates:
The 26th European Modeling & Simulation Symposium, 2014-09-10 - 2014-09-12
Organisations:
EEE
Identifiers
Local EPrints ID: 365853
URI: http://eprints.soton.ac.uk/id/eprint/365853
PURE UUID: bab26bc9-df7b-4b89-b003-f95e0c0db16f
Catalogue record
Date deposited: 19 Jun 2014 11:28
Last modified: 15 Mar 2024 03:23
Export record
Contributors
Author:
Huma Zia
Author:
Nick Harris
Author:
Geoff V. Merrett
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics