Date of Award


Publication Type

Master Thesis

Degree Name



Civil and Environmental Engineering

First Advisor

Carriveau, Rupp

Second Advisor

Ting, David


Commercial Greenhouse, Forecasting, Neural Network, Pepper, Tomato, Water Demand



Creative Commons License

Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.


With rising electricity prices, forecasting water demand has become an essential part of the success of any water utility. Numerous forecasting methods have been suggested, but none have been able to characterize the unique consumer mixes that exist for every utility. This work focuses on a water utility located in Essex County, Ontario, Canada. Examination of the utilities consumer breakdown showed that almost 80% of their capacity was being consumed by commercial greenhouse operations. Current forecasting practices in this region for this sector are almost non-existent, assuming fixed demand for all greenhouse operations. This study presents three papers that focus on evaluation and simplification of forecasting techniques for commercial greenhouse operations. The first paper examines influential factors which drive greenhouse water consumption, with an emphasis on practicality. The second paper evaluates several forecasting model architectures ranging from elementary to complex in order to determine the most suitable method(s). The third paper compares water usage between two crops (tomatoes and bell peppers) in an effort to evaluate a crop to crop forecast technique that relies on one crops watering data in order to produce forecasts for another crop.