From Seasonality to Causality: Understanding Urban Water Usage Using Statistical and Machine Learning Models

<p>This study examines the relationship between climate conditions and residential water usage, focusing on how seasonal and environmental changes influence water consumption. Utilizing data from over 100,000 households across three micro-climate zones for over a five-year period, we apply statistical analysis and machine learning techniques to assess the impact of temperature, precipitation, evapotranspiration, and location on water usage. By integrating climate and billing data, this research provides a data-driven approach on water usage behaviors in Irvine, CA, in collaboration with Irvine Ranch Water District (IRWD).</p> <p>Our analysis utilizes time series modeling, including a Seasonal Autoregressive Integrated Moving Average (SARIMA) and Long Short-Term Memory (LSTM) model to identify seasonal trends and assess predictive power in water usage. Results indicate a steady decline in overall water usage since 2020. Geographic location also plays a role in determining water usage, ET Zone 2 on average has the highest water usage across the study period. The LSTM significantly outperforms the SARIMA model in capturing seasonal patterns of water usage. Utilizing a causal forest to assess direct causality between individual climate factors and water usage showed that precipitation and evapotranspiration have a strong causal effect on water usage. Confirming that increased rainfall leads to lower water usage, while hotter and drier weather conditions drive up water usage. Other climate factors such as humidity and wind speed show negligible direct effects once evapotranspiration is accounted for.</p> <p>These findings emphasize the importance of addressing seasonal cycles in water usage. By identifying key drivers of water usage and demonstrating the performance of machine learning models and causal inference, this research provides valuable insights for water resource managers to improve upon conservation efforts. Future research can expand on these findings by exploring policy interventions to further optimize water usage in response to climate variability.</p>

Level thesis:degree_level

Thesis

Discipline thesis:degree_discipline

Electrical Engineering and Computer Science

Year

2025

Author dc:creator

• Hawkins, Kelsey

Contributors dc:contributor

• Thomas Piechota
• Chelsea Parlett
• Yuxin Wen

• Water Usage
• Causal Inference
• Machine Learning
• Data Science
• Hydrology

Repository record dc:identifier

https://digitalcommons.chapman.edu/eecs_theses/5

OAI identifier oai:identifier

oai:digitalcommons.chapman.edu:eecs_theses-1005