An empirical study on sea water quality prediction

Abstract

This paper studies the problem of predicting future values for a number of water quality variables, based on measurements from under-water sensors. It performs both exploratory and automatic analysis of the collected data with a variety of linear and nonlinear modeling methods. The paper investigates issues, such as the ability to predict future values for a varying number of days ahead and the effect of including values from a varying number of past days. Experimental results provide interesting insights on the predictability of the target variables and the performance of the different learning algorithms.

Greedy regression ensemble selection: Theory and an application to water quality prediction

“…Lead is the number of the intermediate days between the last day used for generating the attributes and the day we are going to predict the target variable. Based on the findings of a previous study [19] we set the window to 9 and the lead to 2.…”

Short-Term Prediction of Marine Sensor Data with Fuzzy Clustering

“…7,17,18 In applied¯sheries, prediction of water quality is necessary for the assessment of¯sh stocks. 20 For water sustainability, it is important to monitor and predict di®erent water quality variables.…”

“…18 Prediction of water quality is also used in decision-making purposes for water resource management. 7 In predicting water quality variables, di®erent statistical methods (e.g. ARIMA, Linear transfer function) are used.…”

Computational Intelligence Techniques for Predicting Earthquakes

“…Thus, an empirical study on sea water quality prediction can be found in [7]. Hatzikos et al faced the problem of forecasting water quality based on underwater sensors measurements, by means of a large variety of both linear and nonlinear methods.…”