Deep Learning Application to Time-Series Prediction of Daily Chlorophyll-a Concentration

Abstract

Algal bloom in rivers is a major environmental concern which threatens the stable water supply and river ecosystem. Due to its complexity and nonlinearity, previous studies have tried various machine learning techniques to predict algal bloom. However, conventional approaches have limitations on predicting unobserved near future, and thus it is hard to apply to actual preparation policy. In this study, long short-term memory (LSTM), as a deep learning approach, is applied to predict the concentration of chlorophyll-a. Daily measured water quality information is used as input data and chlorophyll-a is used to output value for representing algal bloom. In addition to 1-day prediction, 4days prediction task is attempted as sequence data prediction. As a result, LSTM network shows better performance, compared to the previous approaches, in predicting chlorophyll-a in 4-days prediction as well as 1-day prediction. In addition, the regularization methods are applied to model and batch normalization is proved to be a suitable way to improve accuracy. This result can lead to improvement in preventing algal bloom and also suggest various applications of deep learning methods in chlorophyll-a prediction task.

Advances in forecasting harmful algal blooms using machine learning models: A case study with Planktothrix rubescens in Lake Geneva

“…In contrast to these hydro-ecological models, one of the major advantages of machine learning models is that they do not require a priori assumptions (Breiman, 2001;Tsanas and Xifara, 2012;Zhao and Zhang, 2008). In the following non-exhaustive list, it is evident that many studies use this advantage of machine learning to bypass the prediction difficulties concerning the phytoplankton: (Cho et al, 2018;Cho and Park, 2019;Du et al, 2018;Kehoe et al, 2015;Lee et al, 2016;Lee and Lee, 2018;Rivero-Calle et al, 2015;Shamshirband et al, 2019;Shin et al, 2017;Thomas et al, 2018;Yajima and Derot, 2018;Zhang et al, 2016).…”

A Review of Recent Machine Learning Advances for Forecasting Harmful Algal Blooms and Shellfish Contamination

“…Has a high complexity and computational cost. [46][47][48][49] The vector autoregressive (VAR) model, which extends the AR model to the multivariate setting, emerged as a solution to address this latter issue. A VAR model is an n-variable, n-equation linear model in which each variable is explained by its own lagged values, plus current and past values of the remaining n − 1 variables [23].…”

“…Additionally, when large variations in chl-a occurred, the LSTM model predictions were closer to the actual data than those of the MLP model. Cho et al (2018) [47] used a deep recurrent network composed of LSTM units to predict algal blooms in Geum River, South Korea. The authors used daily water quality parameters measured from 2013 to 2017 to predict chl-a concentration one-and four-days in advance.…”

“…Similarly, Cho and Park (2019) [48] also predicted algal blooms in the Geum River. Besides the daily water quality parameters used by Cho et al (2018) [47], other auxiliary variables from different sources were used. The authors introduced a merged-LSTM model, composed of three parallel LSTM layers, one for each data source, and a merge layer to yield the output.…”

Evaluation of Machine Learning predictions of a highly resolved time series of Chlorophyll-a concentration

“…CC-BY 4.0 International license made available under a (which was not certified by peer review) is the author/funder, who has granted bioRxiv a license to display the preprint in perpetuity. It is The copyright holder for this preprint this version posted May 12, 2021. ; https://doi.org/10.1101/2021.05.12.443749 doi: bioRxiv preprint chlorophyll concentrations, mainly in fresh water systems, with a few in marine regions [8], [9], [10], [11].…”