Predicting Chemical Parameters of River Water Quality from Bioindicator Data

Authors:
Sašo Džeroski;Damjan Demšar;Jasna Grbović
Affiliations:
Jožef Stefan Institute, Jamova 39, SI-1000 Ljubljana, Slovenia;Jožef Stefan Institute, Jamova 39, SI-1000 Ljubljana, Slovenia;Hydrometeorological Institute, Vojkova 1b, SI-1000 Ljubljana, Slovenia
Venue:
Applied Intelligence
Year:
2000

Citing 0
Cited 13

Relational data mining applications: an overview

Relational Data Mining
Guest Editorial: Artificial Intelligence and Environmental Applications

Applied Intelligence
Artificial Intelligence and Environmental Decision Support Systems

Applied Intelligence
Sciences: environmental sciences

Handbook of data mining and knowledge discovery
An empirical study on sea water quality prediction

Knowledge-Based Systems
Greedy regression ensemble selection: Theory and an application to water quality prediction

Information Sciences: an International Journal
Ensembles of Multi-Objective Decision Trees

ECML '07 Proceedings of the 18th European conference on Machine Learning
Applying adaptive prediction to sea-water quality measurements

Expert Systems with Applications: An International Journal
Parallel ILP for distributed-memory architectures

Machine Learning
Constraint based induction of multi-objective regression trees

KDID'05 Proceedings of the 4th international conference on Knowledge Discovery in Inductive Databases
Learning predictive clustering rules

KDID'05 Proceedings of the 4th international conference on Knowledge Discovery in Inductive Databases
Tree ensembles for predicting structured outputs

Pattern Recognition
Multi-target regression with rule ensembles

The Journal of Machine Learning Research

Quantified Score

Hi-index	0.00

Visualization

Abstract

We address the problem of inferring chemical parameters of river water quality from biological ones. This task is important for enabling selective chemical monitoring of river water quality. We apply machine learning, in particular regression tree induction, to biological and chemical data on the water quality of Slovenian rivers. Regression trees are constructed that predict values of chemical parameters from data on the presence of bioindicator taxa at the species and family levels.