Forecasting water quality variable using deep learning and weighted averaging ensemble models

• Published in: Environmental science and pollution research international Vol. 30; no. 59; pp. 124316 - 124340
• Main Authors: Zamani, Mohammad G., Nikoo, Mohammad Reza, Jahanshahi, Sina, Barzegar, Rahim, Meydani, Amirreza
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.12.2023; Springer Nature B.V
• Subjects: Algae; Algorithms; Aquatic ecosystems; Aquatic organisms; Aquatic Pollution; Atmospheric Protection/Air Quality Control/Air Pollution; Chlorophyll; Cyanobacteria; data collection; Deep learning; Earth and Environmental Science; Ecotoxicology; Environment; Environmental Chemistry; Environmental Health; Forecasting; Genetic algorithms; Greece; lakes; Long short-term memory; Machine learning; Mathematical models; Multiple objective analysis; Neural networks; Recurrent neural networks; Research Article; Sorting algorithms; Waste Water Technology; Water Management; Water Pollution Control; Water quality; Greece; Water quality forecasting; Non-dominated genetic algorithm (NSGA-II); Single- and multi-objective optimization algorithms; Ensemble model; Deep learning (DL)
• ISSN: 1614-7499; 0944-1344; 1614-7499
• DOI: 10.1007/s11356-023-30774-4

Water quality variables, including chlorophyll-a (Chl-a), play a pivotal role in comprehending and evaluating the condition of aquatic ecosystems. Chl-a, a pigment present in diverse aquatic organisms, notably algae and cyanobacteria, serves as a valuable indicator of water quality. Thus, the objectives of this study encompass: (1) the assessment of the predictive capabilities of four deep learning (DL) models — namely, recurrent neural network (RNN), long short-term memory (LSTM), gated recurrence unit (GRU), and temporal convolutional network (TCN) — in forecasting Chl-a concentrations; (2) the incorporation of these DL models into ensemble models (EMs) employing genetic algorithm (GA) and non-dominated sorting genetic algorithm (NSGA-II) to harness the strengths of each standalone model; and (3) the evaluation of the efficacy of the developed EMs. Utilizing data collected at 15-min intervals from Small Prespa Lake (SPL) in Greece, the models employed hourly Chl-a concentration lag times, extending up to 6 h, as models’ inputs to forecast Chla (t+1). The proposed models underwent training on 70% of the dataset and were subsequently validated on the remaining 30%. Among the standalone DL models, the GRU model exhibited superior performance in Chl-a forecasting, surpassing the RNN, LSTM, and TCN models by 8%, 2%, and 2%, respectively. Furthermore, the integration of DL models through single-objective GA and multi-objective NSGA-II optimization algorithms yielded hybrid models adept at effectively forecasting both low and high Chl-a concentrations. The ensemble model based on NSGA-II outperformed standalone DL models as well as the GA-based model across a range of evaluation indices. For instance, considering the R -squared metric, the study’s findings demonstrated that the EM-NSGA-II stands out with exceptional effectiveness compared to DL and EM-GA models, showcasing improvements of 14% (RNN), 8% (LSTM), 6% (GRU), 8% (TCN), and 3% (EM-GA) during the testing phase.