#20220114 WaterLess: Predicting Water Footprint using Machine Learning

The study focuses on assessing individual water consumptions by considering the direct and indirect water use through the water footprint indicator. This research evaluates the different aspects of individual water consumption from different perspectives such as gender, education level, age, and income level. The dataset will be collected through the prepared survey. The dataset that will be used in the study will contain 500 different people's responses. The survey has 31 questions about water consumption for various contexts. The survey has four sections; demographic information, food consumption, indoor and outdoor consumption. Given answers will be collected and stored. Water footprint calculations will be used in machine learning models. The dataset will contain numerical data. The trained machine learning model will be used in a cross-platform mobile application. The application will show the water footprint results of the individual’s consumption data. Recommendations for decreasing water footprint will be displayed.

WaterLess is a cross-platform mobile application using machine learning for raising awareness of individual water consumption. The app predicts the water footprint of the user and recommends solutions to them about how to save water according to their water consumption. Individuals will be able to compare their water footprint results with general water consumption data.

In this study, the water footprint of individuals will be calculated, used in machine learning models. Different machine learning models will be used and trained in a cross-platform mobile application. Recommendations for users will be available in the application.

Project is a mobile application. The application can be used with a internet connected mobile phone.