Journal article
Prediction of formation of polycyclic aromatic hydrocarbon (PAHs) on sediment of Caspian Sea using artificial neural networks
Petroleum Science and Technology, Vol.37(18), pp.1987-2000
17/09/2019
Metrics
14 Record Views
UN Sustainable Development Goals (SDGs)
This output has contributed to the advancement of the following goals:
Source: InCites
Abstract
In this article the amount of polycyclic aromatic hydrocarbon (PAHs) on the sediment of Caspian Sea predicted by artificial neural networks multi-layer perceptron (MLP) and generalized regression (GRNN) models. PAH is a most important pollutant in a marine environment derived from an anthropogenic and natural source. This component is mutagenic and Carcinogenic extremely. In this investigation, a multi-layer perceptron and Generalized regression neural network models have been developed by experimental data (organic matter, latitude, longitude, depth and effective matter (particle size)) reported in the literature. As a result, experimental data compared to the output of models by calculation of mean squared error (MSE), root mean squared error (RMSE), mean absolute error percent (MEAE), maximum absolute error percent (MAAE) and R2. Results have shown an appropriate fitting for experimental data with predicted values .Also, MLP neural network has the best performance to predicating of PAHs.
Details
- Title
- Prediction of formation of polycyclic aromatic hydrocarbon (PAHs) on sediment of Caspian Sea using artificial neural networks
- Creators
- Javad Sayyad Amin - University of GuilanHossein Rajabi Kuyakhi - University of GuilanAlireza Bahadori - Southern Cross University
- Publication Details
- Petroleum Science and Technology, Vol.37(18), pp.1987-2000
- Publisher
- Taylor & Francis Inc.
- Identifiers
- 991012927074702368
- Copyright
- © 2018 Taylor & Francis Group, LLC
- Academic Unit
- Faculty of Science and Engineering; School of Environment, Science and Engineering
- Language
- English
- Resource Type
- Journal article