Prediction of Groundwater Level in The Shallow Aquifer Using Artificial Neural Network Approach

Ardana, Putu Doddy Heka and Redana, I Wayan and Yekti, Mawiti Infantri and Simpen, I Nengah (2021) Prediction of Groundwater Level in The Shallow Aquifer Using Artificial Neural Network Approach. IOP Conference Series: Earth and Environmental Science.

	Text Korespondensi IOP.pdf Download (296kB)
	Text Pak Doddy CEK TURN_3 okkk.pdf Download (2MB)
	Text ICRES J0007 certificate.pdf Download (139kB)

Abstract

In these regions, groundwater is often the most significant source of water. Groundwater level estimation accuracy is a vital component of efficient water supply management. In this paper, an artificial neural network (ANN) with gradient descent with momentum and adaptive learning rate backpropagation algorithm for groundwater level forecasting applications is proposed. The ANN model used an 8-5-3-1 and 8-10-5-1 network architecture with the input parameter of the form such as precipitation, evaporation, atmospheric pressure, wind, humidity, long exposure to the sun and temperature simultaneously and a relatively short length of groundwater level data recorded from January 2017 to December 2019 at two observation wells in the North Denpasar, Bali, Indonesia. The study's findings show that ANN models can predict groundwater levels. It is suggested that more research be conducted on this proposed process, which can then be used to help establish and incorporate more efficient and long-term groundwater management strategies.

Actions (login required)

View Item