Optimised neural network model for river-nitrogen prediction utilizing a new training approach

Abstract

In the past few decades, there has been a rapid growth in the concentration of nitrogenous compounds such as nitrate-nitrogen and ammonia-nitrogen in rivers, primarily due to increasing agricultural and industrial activities. These nitrogenous compounds are mainly responsible for eutrophication when present in river water, and for 'blue baby syndrome' when present in drinking water. High concentrations of these compounds in rivers may eventually lead to the closure of treatment plants. This study presents a training and a selection approach to develop an optimum artificial neural network model for predicting monthly average nitrate-N and monthly average ammonia-N. Several studies have predicted these compounds, but most of the proposed procedures do not involve testing various model architectures in order to achieve the optimum predicting model. Additionally, none of the models have been trained for hydrological conditions such as the case of Malaysia. This study presents models trained on the hydrological data from 1981 to 2017 for the Langat River in Selangor, Malaysia. The model architectures used for training are General Regression Neural Network (GRNN), Multilayer Neural Network and Radial Basis Function Neural Network (RBFNN). These models were trained for various combinations of internal parameters, input variables and model architectures. Post-training, the optimum performing model was selected based on the regression and error values and plot of predicted versus observed values. Optimum models provide promising results with a minimum overall regression value of 0.92.

Water, Soil and Air Pollutants’ Interaction on Mangrove Ecosystem and Corresponding Artificial Intelligence Techniques Used in Decision Support Systems - A Review

“…Meteorological conditions such as monsoon and precipitation rate are persistent factors for environmental change yet little to no studies have incorporated such parameters into the modelling of ecosystem quality for pollution prediction. A relation of meteorological data was identified between the prediction of heavy metals in water bodies or nitrogen and turbidity concentration [116,145,150]. Moreover, meteorological and climatological variables were found to have a profound impact on soil distribution, where air temperature could complement the prediction of soil temperature [193].…”

“…Hydrological and climatological data were used by Kumar, et al [145] and Song and Zhang [150] to predict nitrogen and turbidity values respectively. The model built in both studies were effective and reliable, suggesting the importance of environmental factors to predict water quality.…”

Coastal forecast through coupling of Deep Learning and hydro-morphodynamical modelling

“…Within this module, bottom dissipation, whitecapping, and depth induced breaking are fully accounted for in a dissipation term (Booij, Ris, & Holthuijsen, 1999). ANN, sometime referred to as black-box (Akrami, El-Shafie, & Jaafar, 2013;Pavitra Kumar et al, 2021), mimics the human brain structure (El-Shafie, Noureldin, Taha, Hussain, & Mukhlisin, 2012;P. Kumar et al, 2020) to provide variables predictions through establishment of relationships between them and other pre-define inputs (Akrami et al, 2013).…”

“…Weights and biases are not updated in the validation process. Testing dataset is used for testing the final predictive strength of the model (P Kumar et al, 2020)…”

Machine learning algorithm as a sustainable tool for dissolved oxygen prediction: a case study of Feitsui Reservoir, Taiwan

“…One of these limitations is the complexity and complicated architecture and the difficulties in initializing the input parameters for these hybrid models 37 . Kumar et al 38 found that the artificial neural network's prediction performance can be enhanced by improving the training approach without hybridizing it with optimization algorithms. In addition to that, a recent study highlighted the importance of the input combinations of ML algorithms' output accuracy, where the optimal input combinations can lead to a high level of accuracy without the need to augment ML with optimizers 39 , 40 .…”