25 Applied Geology, Environmental, Engineering, Hydrogeology, and Applied Geophysics (Posters)

Sunday, 19 March 2017
1:30 PM - 5:30 PM
Grand Ballroom, 17th Floor

APPLICATION OF ARIMA AND ARTIFICIAL NEURAL NETWORKS TO FORECASTING NITRATE CONCENTRATION IN THE AQUIDNECK ISLAND IN RHODE ISLAND, USA

Paper number: 25-18
Program: Theme Sessions
Time: 1:30 PM – 5:30 PM

Authors

Abstract

Public drinking water systems of Rhode Island face a wide array of challenges to meet the public health protection standards to ensure safe drinking water. The situation is quite vulnerable in both community and private sources of drinking water. Nitrate (NO3-), often from fertilizer application and septic systems, is a threat to local water supplies, increasing the cost of drinking water treatment as the source water becomes more polluted. Nitrate levels in both groundwater and surface water have been increasing over a long period of time, and it is unlikely that these trends can be reversed quickly. Under such situation, future conditions could be understood through seasonal forecasting of nitrate concentration. Autoregressive integrated moving average (ARIMA) is one of the popular linear models in time series forecasting. Recent research activities in forecasting with artificial neural networks (ANNs) suggest that ANNs can be a promising alternative to the traditional linear methods. ARIMA models and ANNs are often compared with mixed conclusions in terms of the superiority in forecasting performance. Nitrate data was collected every 30 minutes from S::CAN spectro::lysers installed in Cork Brook, Bailey’s Brook and Maidford River, in watersheds dominated by forest, urban and agricultural land uses, respectively. Data duration was 22nd June, 2014 to 15th November, 2016. Nitrate concentration data are used for ARIMA (Linear) model and the other quality parameter like pH, temperature, conductivity (from YSI EXO sondes) were used for ANN (Nonlinear). The main objective of the study was to forecast the nitrate concentration applying ARIMA and validate the forecast using ANN model that will help the policy planner to take initiatives to address nutrient problems.

Key words: Drinking water system, Safe drinking water, Autoregressive integrated moving average, Artificial neural networks, Forecast.

Geological Society of America Abstracts with Programs. Vol. 49, No. 2

doi: 10.1130/abs/2017NE-291436

© Copyright 2017 The Geological Society of America (GSA), all rights reserved. Permission is hereby granted to the author(s) of this abstract to reproduce and distribute it freely, for noncommercial purposes. Permission is hereby granted to any individual scientist to download a single copy of this electronic file and reproduce up to 20 paper copies for noncommercial purposes advancing science and education, including classroom use, providing all reproductions include the complete content shown here, including the author information. All other forms of reproduction and/or transmittal are prohibited without written permission from GSA Copyright Permissions.