Groundwater Level Forecasting: USA

Adeniji, Adeola Deborah (2024) Groundwater Level Forecasting: USA. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration Manual) Download (873kB) | Preview

Abstract

Beneath the earth’s surface lies a natural reserve, groundwater, a vital source for drinking water, agriculture, and ecosystem sustainability in arid areas like California, USA. Groundwater management is of utmost importance but faces challenges due to its fluctuation levels and uncertain supplies. With the urgent need to ensure the rational use of this reserve, the Department of Water Resource (DWR), needs to provide a reliable and accurate forecast for groundwater levels, to support California water resource management (CDWR). This research leverages historical data of over 30 years to evaluate the effectiveness of time series models – Simple Time Series, Exponential Smoothing and ARIMA Models, to forecast groundwater levels for the next 8 years. Multiple performance metrics were used to find the best model for long-term water management, including coefficient of determination (R2), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), Akaike's Information Criterion (AIC), and Mean Absolute Percentage Error (MAPE). The results indicated that ARIMA model outperformed the others, achieving the lowest RMSE of 2.31 and the highest R2 of -0.04. However, due to the complex dynamics of groundwater fluctuations, all models including Arima, struggled and were unable to provide satisfactory accuracy for the forecast. These findings underline the need to adopt more advanced methods since current models did not achieve good accuracy that can provide decision-makers useful information, to support sustainable groundwater management. This research contributes to the knowledge base, by identifying the models’ limitations while suggesting alternative ways of improving groundwater level forecasting.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Hamill, David UNSPECIFIED
Uncontrolled Keywords:	Groundwater levels forecasting; time series models; department of water resources (USA); ARIMA prediction; sustainability groundwater use
Subjects:	G Geography. Anthropology. Recreation > GE Environmental Sciences Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Ciara O'Brien
Date Deposited:	01 Sep 2025 13:37
Last Modified:	01 Sep 2025 13:37
URI:	https://norma.ncirl.ie/id/eprint/8668

Actions (login required)

View Item