Multistep Ahead Groundwater Level Time-Series Forecasting Using Gaussian Process Regression and ANFIS

What is it about?

Univariate time-series Gaussian Process Regression and Adaptive Neuro Fuzzy Inference System (ANFIS) models are simulated and applied for multistep lead time forecasting of groundwater levels.

Featured Image

Why is it important?

Over the last decade, groundwater depletion is one of the major issue worldwide, which is posing direct or indirect impacts on human livelihoods, flora and fauna, natural habitat and ecosystems. Depletion of groundwater storage, land subsidence, reductions in stream flow and lake water levels, saltwater intrusion, loss of wetland and riparian ecosystems and variations in groundwater quality are some of the vital factors influencing the sustainability of groundwater resources. The benefits of groundwater level forecasting include assessment of annual and long-term changes in groundwater storage, estimation of recharge rates, manage drinking water demand and to ensure the sustainable use of groundwater resources.