Garden Monitor is a mobile application developed in the context of the MK:Smart project (http://www.mksmart.org/). This project is developing innovative solutions to tackle key sustainability issues and support economic growth in Milton Keynes.
An important issue for the project concerns the sustainable management of water resources (http://www.mksmart.org/water/). Milton Keynes, being located in one of the driest parts of the country, is under pressure. With a rapidly increasing population and in the context of climate change, new solutions are needed to reduce water consumption, if this growth is to be sustainable.
Every year, a large amount of water is wasted through inefficient watering of domestic gardens. To help reduce water wastage related to gardening activities, we have developed Garden Monitor, a mobile application which supports efficient water management in gardens. Garden Monitor forecasts the conditions of a garden over the following ten days and generates a customized calendar advising users on whether and when they may need to water their garden. It also produces a historical record of a garden in terms of soil moisture, temperature, rainfall and so on, allowing users to monitor the status of their garden and to understand how it reacts to variations in weather conditions.
From July to October 2016, we have conducted an evaluation of Garden Monitor with eight users in Milton Keynes. This evaluation was designed to assess the performance of the machine learning of Garden Monitor, as well as its value to users and its usability. At the end of the evaluation, we asked our users to answer a questionnaire focusing on the last two aspects.
The results of this evaluation are promising.
About the performance of the machine learning engine, the computation of Root Mean Square Error (RMSE) values show models becoming more accurate with time. Moreover, users reported positive feedback regarding the correctness of the predicted soil moisture values.
About the value of Garden Monitor to users, their gardens were in healthy shapes at the end of the evaluation even though users were watering less frequently. This observation suggests Garden Monitor effectively helped users in reducing water wastage related to gardening activities.
About the usability of Garden Monitor, answers to a System Usability Scale questionnaire yielded a mean score of 72.5. This score is above the standard threshold of 68, which means that the application can be considered easy-to-use, even though this is still an initial prototype.
How it works
- The Koubachi Plant Pro 2 sensors are used to measure soil moisture and meteorological data, which are then stored in the Data Hub.
- The Dark Sky API provides weather forecast data.
The Garden Monitor API is at the heart of the system. It is this API that carries out the machine learning processes in order to forecast future soil moisture values. The algorithm performs a multiple linear regression on seven parameters: soil moisture, max temperature, min temperature, pressure, humidity, rainfall, and wind speed. With the resulting models of gardens, the predictions for future soil moisture values are then computed using the current day’s soil moisture value and weather forecast data. Finally, the Garden Monitor Android application reads the data computed by the Garden Monitor API and displays it to the user.
Angelo Antonio Salatino
Please enter your contact details and a short message below and I will try to answer your query as soon as possible.