North Dakota State University
Prediction of Freshwater Harmful Algal Blooms in Western Lake Erie Using Artificial Neural Network Modeling Techniques
Abstract
dc:description.abstractBlue-green algae are a major environmental concern in freshwater produce toxins and cause a wide range of problems including oxygen depletion, fish kills, harm or death to other aquatic organisms, and subsequent habitat loss. Cyanobacteria are a type of blue-green algae that form harmful algal blooms (HABs) in water ecosystems. In this study, artificial intelligence techniques, in particular artificial neural networks, were developed to estimate blue-green algae fluorescence for the year-round data collected in 2016-17 from western Lake Erie, USA. Based on the lake’s environmental conditions and available data, eight input parameters including phosphorous, nitrogen, chlorophyll-a, air temperature, water temperature, turbidity, wind speed, and pH were used to run the model. Five different learning algorithms were TESTED, and the Levenberg-Marquardt algorithm resulted in the highest R2 values of 0.98 and 0.72 for eight, and three (phosphorous, nitrogen, and chlorophyll-a) input parameters, respectively. Eight input parameters produced the best estimation approach.
Degree
thesis:*- Grantor dc:publisher
- North Dakota State University
- Year dc:date.issued
- 2019
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Guzel, Haci Osman
Subjects
dc:subject × 3Rights
dc:rights- Statement dc:rights
-
- NDSU Policy 190.6.2
Identifiers
dc:identifier.*- Handle dc:identifier.uri
- https://hdl.handle.net/10365/29605