Predicting discharge using a low complexity machine learning model

H. Zia, N. Harris, G. Merrett, Mark Rivers

Research output: Contribution to journalArticlepeer-review

16 Citations (Scopus)


© 2015 Elsevier B.V. This paper reports on the validation of a simplified discharge prediction model that is suitable for implementation on a resourced constrained system such as a wireless sensor network, which will allow their operation to become more proactive rather than reactive. The data-driven model, utilising an M5 decision tree modelling technique, is validated using a 12-month training data set derived from published measured data. Daily runoff and drainage is predicted, and the results are compared with existing data-driven models developed in this domain. Results for the model give an R2 of 0.82 and Root Relative Mean Square Error (RRMSE) of 35.9%. 80% of the residuals for the predicted test values fall within a ±2mm discharge depth/day error range. The main significance is that the proposed model gives comparable results with fewer samples and simpler parameters when compared to previous published research, which offers the potential for implementation in resource constrained monitoring and control systems.
Original languageEnglish
Pages (from-to)350-360
JournalComputers and Electronics in Agriculture
Publication statusPublished - 2015


Dive into the research topics of 'Predicting discharge using a low complexity machine learning model'. Together they form a unique fingerprint.

Cite this