Smarter irrigation for Cairns parks aims to save water and protect reef

Published:09 October 2019

Varun Chandrappa, Dr Biplob Ray, Associate Professor Nanjappa Ashwath, Dan Mosbauer and Dr Pramod Shrestha; and Associate Professor Nanjappa Ashwath, Matthew Ritchie, Dr Biplob Ray, Dr Pramod Shrestha and Varun Chandrappa

TOP: Varun Chandrappa (Research Higher Degree student, CQUni), Dr Biplob Ray (IoT and data scientist, CQUni), Associate Professor Nanjappa Ashwath (Soil and Plant scientist, CQUni), Dan Mosbauer (Cairns Regional Council, Supervisor Parks Infrastructure), Dr Pramod Shrestha ( Research officer, CQUni). BELOW: Associate Professor Nanjappa Ashwath (Soil and Plant scientist, CQUni), Matthew Ritchie (, IoT engineer), Dr Biplob Ray (IoT and data scientist, CQUni), Dr Pramod Shrestha (Research officer, CQU) and Varun Chandrappa (Research Higher Degree student, CQUni).

We all love our parks to be lush and green but over-irrigation has the potential to waste water while boosting seepage and leaking of nutrients into nearby streams, or even the Great Barrier Reef itself.

That's why Cairns Regional Council and CQUniversity have sourced funding from the Smart Cities and Suburbs Program, to investigate smarter ways of irrigating the parks in Cairns.

Park managers are working with CQUni plant, soil and computing scientists and a local irrigation consultant to design and test an intelligent irrigation system. This will not only gather data but also help forecast and regulate water use in the parks.

The system will combine plant, soil and climate data with the Internet of Things (IoT) and machine learning.

Key collaborators include Associate Professor Nanjappa Ashwath and Dr Biplob Ray from CQUni, Dan Mosbauer of Cairns Regional Council, and Matthew Ritchie of (a not-for-profit Maker Space that strives to give the community access to cutting-edge technology, resources and know-how).

Associate Professor Ashwath says water management in the parks is fraught with difficulties, as the aesthetic requirements by the community does not match with the environmental needs of the parks system.

"The parks system is constantly exposed to various pressures, such as rainfall events, temperature variations, gusty winds, changes in relative humidity, public traffic and variations in the capacity of the plants to use water (such as winter versus summer).

"Furthermore, parks are established on a variety of soil systems. Since the composition and depth of soils differ significantly from one park to the other, and the type of plants established in the parks also differ from grasses to trees and shrubs, predicting the water requirements of the parks system could become extremely complicated.

"This project is using advanced technologies such as electromagnetic sensor (Duel EM) surveys of the soil to measure changes in soil moisture content, as well as the salinity and bulk density of the soils, to produce soil moisture maps.

"These maps will allow us to identify locations of interest within the park so these locations can be used to install moisture sensors. These moisture sensors and the micro-weather station will be connected to the Internet of Things (IoT) system for continuous and real-time monitoring.

"The signals received from the soil monitoring systems (both Duel EM and IoT-based moisture sensors) will be calibrated to actual soil moisture content by taking soil samples from representative locations.

"The soil profile, localised weather data and calibrated dataset from both Duel EM and IoT-based moisture sensors can be used to build a computer model based on machine learning to manage the watering system of the Cairns parks."

This new model will send instructions to the parks irrigation system which regulates the quantities and the duration of irrigation provided to each zone of the park.

Dr Ray says the new approach will be more novel, as the existing watering system only uses threshold-based watering for the entire park.

"As a result, it misses the opportunity to take advantage of learning over time like a human’s brain," Dr Ray says.

"In our machine learning-based approach, our model not only learns for making better decisions in the future, but it can also predict total water usages for a specific time.

"At the end of the day, this holistic smart watering approach will save water resources and minimise seepage and nutrient leaching, while ensuring the parks meet the expectations of the public."