Predicting algal bloom in riverine systems: A nonparametric approach
Abstract
In order to provide user-friendly application and prompt decision making to water engineers, we developed simplified and generalized nonparametric forecasting model for cyanobacterial occurrence and probabilities of exceedance in riverine systems. This model was able to predict algal bloom using only three dominant environmental factors; water temperature, velocity and phosphorus. These environmental variables were selected due to not only direct or joint contribution to algal bloom but also the ease of their availability either through direct measurements or as modelled responses in the river location of interest. Furthermore, in order to apply bacterial growth dynamic to the model, weight functions which give the load to the three variables depending on cell number of the preceding time was built up and equipped to the model. An extensive dataset spanning from 2013 to 2018 at 16 representative locations across the 4 major rivers in South Korea was used to develop and validate the model. Through cross-validation, this model was established to have more than 75% forecasting accuracy despite the use of a relatively simple algorithm. The selected environmental variables were found to be quite effective in capturing the onset of cyanobacteria and the algal proliferation mechanism over the study region. As the developed model makes use of commonly available environmental variables, we expect that it can easily be extended to locations across the country where very limited or no prior information about cyanobacteria bloom is available.
- Publication:
-
AGU Fall Meeting Abstracts
- Pub Date:
- December 2019
- Bibcode:
- 2019AGUFM.H43Q2323K
- Keywords:
-
- 1848 Monitoring networks;
- HYDROLOGY;
- 1871 Surface water quality;
- HYDROLOGY;
- 1879 Watershed;
- HYDROLOGY;
- 1880 Water management;
- HYDROLOGY