Prediction of Geosmin at Different Depths of Lake Using Machine Learning Techniques

Abstract

Geosmin is a major concern in the management of water sources worldwide. Thus, we predicted concentration categories of geosmin at three different depths of lakes (i.e., surface, middle, and bottom), and analyzed relationships between geosmin concentration and factors such as phytoplankton abundance and environmental variables. Data were collected monthly from three major lakes (Uiam, Cheongpyeong, and Paldang lakes) in Korea from May 2014 to December 2015. Before predicting geosmin concentration, we categorized it into four groups based on the boxplot method, and multivariate adaptive regression splines, classification and regression trees, and random forest (RF) were applied to identify the most appropriate modelling to predict geosmin concentration. Overall, using environmental variables was more accurate than using phytoplankton abundance to predict the four categories of geosmin concentration based on AUC and accuracy in all three models as well as each layer. The RF model had the highest predictive power among the three SDMs. When predicting geosmin in the three water layers, the relative importance of environmental variables and phytoplankton abundance in the sensitivity analysis was different for each layer. Water temperature and abundance of Cyanophyceae were the most important factors for predicting geosmin concentration categories in the surface layer, whereas total abundance of phytoplankton exhibited relatively higher importance in the bottom layer.

Secondary Organic Aerosol Formation from Cyanobacterial-Derived Volatile Organic Compounds

“…Ultimately, the precise ecological triggers of 2-MIB and GSM production are unknown . However, 2-MIB and GSM are elevated during late spring through early fall when CHABs occur and are linked to periods with heightened nutrient concentrations. ,,, Concentrations of both compounds in eutrophic waterbodies range from <10 to >1000 ng L –1 , with averages ∼10 ng L –1 . , To date, only one study has reported ambient concentrations of airborne 2-MIB and GSM, which ranged from 0.16 to 0.31 μg L –1 and 0.01 to 0.25 μg L –1 in the airspace above soils, respectively . These VOCs share many structural characteristics with terpenoids such as α-pinene and camphor, two well documented precursors to vapor pressure-driven SOA. − To investigate aerosol formation as one transformation pathway for GSM and 2-MIB emissions, we oxidized GSM and 2-MIB in the gas phase with • OH in a series of experimental aerosol formation experiments.…”

“…2,5,60,61 Concentrations of both compounds in eutrophic waterbodies range from <10 to >1000 ng L −1 , with averages ∼10 ng L −1 . 62,63 To date, only one study has reported ambient concentrations of airborne 2-MIB and GSM, which ranged from 0.16 to 0.31 μg L −1 and 0.01 to 0.25 μg L −1 in the airspace above soils, respectively. 64 These VOCs share many structural characteristics with terpenoids such as α-pinene and camphor, two well documented precursors to vapor pressuredriven SOA.…”