Nima Kamali - Academia.edu (original) (raw)

Papers by Nima Kamali

Research paper thumbnail of Encoder–Decoder Convolutional Neural Networks for Flow Modeling in Unsaturated Porous Media: Forward and Inverse Approaches

Water, Aug 10, 2023

This article is an open access article distributed under the terms and conditions of the Creative... more This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY

Research paper thumbnail of Erratum to: Synthesis of vinasse-dolomite nanocomposite biochar via a novel developed functionalization method to recover phosphate as a potential fertilizer substitute

Frontiers of Environmental Science & Engineering, Jan 12, 2021

Research paper thumbnail of Phosphorus removal and recovery: state of the science and challenges

Environmental Science and Pollution Research, Jul 3, 2022

Research paper thumbnail of Encoder–Decoder Convolutional Neural Networks for Flow Modeling in Unsaturated Porous Media: Forward and Inverse Approaches

Water

The computational cost of approximating the Richards equation for water flow in unsaturated porou... more The computational cost of approximating the Richards equation for water flow in unsaturated porous media is a major challenge, especially for tasks that require repetitive simulations. Data-driven modeling offers a faster and more efficient way to estimate soil moisture dynamics, significantly reducing computational costs. Typically, data-driven models use one-dimensional vectors to represent soil moisture at specific points or as a time series. However, an alternative approach is to use images that capture the distribution of porous media characteristics as input, allowing for the estimation of the two-dimensional soil moisture distribution using a single model. This approach, known as image-to-image regression, provides a more explicit consideration of heterogeneity in the porous domain but faces challenges due to increased input–output dimensionality. Deep neural networks (DNNs) provide a solution to tackle the challenge of high dimensionality. Particularly, encoder–decoder convo...

Research paper thumbnail of Implementing Spectral Decomposition of Time Series Data in Artificial Neural Networks to Predict Air Pollutant Concentrations

Environmental Engineering Science, 2015

A model to predict air pollutants' concentrations was developed by implementing spectral decompos... more A model to predict air pollutants' concentrations was developed by implementing spectral decomposition of time series data, obtained by Kolmogorov-Zurbenko filter, in Artificial Neural Networks (ANN). This model was utilized to separate and individually predict three spectral components of air pollutants' time series of short, seasonal, and long-term. The best set of input variable was selected by evaluating the significance of different input variables while modeling different time series components. Moreover, different possible approaches for constructing such models were examined. Performance of the constructed model to predict air pollutants' level at a central location in Tehran, Iran, which is one of the most polluted cities in the world, was assessed. The constructed model showed firm and reliable performance in modeling and predicting the two selected air pollutants of NO x and PM 10. The R 2 between predicted and observed values were *0.90 for most cases. It was shown that the developed model could perform better in modeling air pollutants compared with ordinary ANN models, especially in episodes of highly elevated pollution levels. Furthermore, this model provided the opportunity to separately predict pollutants' spectral components, such as baseline concentrations, which represent urban background levels. Predictions of baseline concentrations were also in fine agreement with the observed data. Such modeling and prediction could help policymakers to oversee different trends of pollutants' fluctuations, and make proper decisions to control the pollutants.

Research paper thumbnail of Predicting hourly air pollutant levels using artificial neural networks coupled with uncertainty analysis by Monte Carlo simulations

Environmental Science and Pollution Research, 2013

Keywords Urban air pollution. Predicting pollutants. Artificial neural networks. Meteorological v... more Keywords Urban air pollution. Predicting pollutants. Artificial neural networks. Meteorological variables. Monte Carlo simulations. Prediction intervals Background, aim, and scope Many large cities in developing countries are increasingly facing episodes of critically high levels of atmospheric pollution, affecting their quality of life and public health (McMichael 2000; Molina and Molina 2004). Reliable forecasting of air pollution would allow taking more efficient countermeasures to prevent air pollution crisis and protect

Research paper thumbnail of Phosphorus removal and recovery: state of the science and challenges

Environmental Science and Pollution Research

Research paper thumbnail of Erratum to: Synthesis of vinasse-dolomite nanocomposite biochar via a novel developed functionalization method to recover phosphate as a potential fertilizer substitute

Frontiers of Environmental Science & Engineering, 2021

Due to the typesetting error, there are some errors in the Equation (4) in the manuscript, the co... more Due to the typesetting error, there are some errors in the Equation (4) in the manuscript, the correction is as follows, and we apologize to the reader.

Research paper thumbnail of Comparison of micro and nano MgO-functionalized vinasse biochar in phosphate removal: Micro-nano particle development, RSM optimization, and potential fertilizer

The present study is conducted to synthesize vinasse-derived biochar, followed by modification wi... more The present study is conducted to synthesize vinasse-derived biochar, followed by modification with Micro and Nano MgO in an attempt to assess their effects on the phosphate (P) removal from aqueous medium. Based on the characterization results of modified biochars and adsorption capacities, Nano-MgO Functionalized ones have proven to be more capable in P removal, with the specific surface areas of 119.98–125.41 m2/g and maximum P adsorption capacity of 188.67 mg/g. The dependencies of adsorption on initial P concentration (50–350 mg/L), contact time (5–90 min), and solution pH level (3–11) were investigated by 20 experiments designed via CCD-based RSM. The regression analysis showed a good fit of the experimental data to the second-order polynomial model with coefficient of determination (R2) value of 0.9916 and model F-value of 131.82. The optimum conditions of pH (7.00), contact time (75 min), and initial P concentration (250 mg/L) were recorded from desirability function. Based ...

Research paper thumbnail of Synthesis of vinasse-dolomite nanocomposite biochar via a novel developed functionalization method to recover phosphate as a potential fertilizer substitute

Frontiers of Environmental Science & Engineering

Research paper thumbnail of Encoder–Decoder Convolutional Neural Networks for Flow Modeling in Unsaturated Porous Media: Forward and Inverse Approaches

Water, Aug 10, 2023

This article is an open access article distributed under the terms and conditions of the Creative... more This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY

Research paper thumbnail of Erratum to: Synthesis of vinasse-dolomite nanocomposite biochar via a novel developed functionalization method to recover phosphate as a potential fertilizer substitute

Frontiers of Environmental Science & Engineering, Jan 12, 2021

Research paper thumbnail of Phosphorus removal and recovery: state of the science and challenges

Environmental Science and Pollution Research, Jul 3, 2022

Research paper thumbnail of Encoder–Decoder Convolutional Neural Networks for Flow Modeling in Unsaturated Porous Media: Forward and Inverse Approaches

Water

The computational cost of approximating the Richards equation for water flow in unsaturated porou... more The computational cost of approximating the Richards equation for water flow in unsaturated porous media is a major challenge, especially for tasks that require repetitive simulations. Data-driven modeling offers a faster and more efficient way to estimate soil moisture dynamics, significantly reducing computational costs. Typically, data-driven models use one-dimensional vectors to represent soil moisture at specific points or as a time series. However, an alternative approach is to use images that capture the distribution of porous media characteristics as input, allowing for the estimation of the two-dimensional soil moisture distribution using a single model. This approach, known as image-to-image regression, provides a more explicit consideration of heterogeneity in the porous domain but faces challenges due to increased input–output dimensionality. Deep neural networks (DNNs) provide a solution to tackle the challenge of high dimensionality. Particularly, encoder–decoder convo...

Research paper thumbnail of Implementing Spectral Decomposition of Time Series Data in Artificial Neural Networks to Predict Air Pollutant Concentrations

Environmental Engineering Science, 2015

A model to predict air pollutants' concentrations was developed by implementing spectral decompos... more A model to predict air pollutants' concentrations was developed by implementing spectral decomposition of time series data, obtained by Kolmogorov-Zurbenko filter, in Artificial Neural Networks (ANN). This model was utilized to separate and individually predict three spectral components of air pollutants' time series of short, seasonal, and long-term. The best set of input variable was selected by evaluating the significance of different input variables while modeling different time series components. Moreover, different possible approaches for constructing such models were examined. Performance of the constructed model to predict air pollutants' level at a central location in Tehran, Iran, which is one of the most polluted cities in the world, was assessed. The constructed model showed firm and reliable performance in modeling and predicting the two selected air pollutants of NO x and PM 10. The R 2 between predicted and observed values were *0.90 for most cases. It was shown that the developed model could perform better in modeling air pollutants compared with ordinary ANN models, especially in episodes of highly elevated pollution levels. Furthermore, this model provided the opportunity to separately predict pollutants' spectral components, such as baseline concentrations, which represent urban background levels. Predictions of baseline concentrations were also in fine agreement with the observed data. Such modeling and prediction could help policymakers to oversee different trends of pollutants' fluctuations, and make proper decisions to control the pollutants.

Research paper thumbnail of Predicting hourly air pollutant levels using artificial neural networks coupled with uncertainty analysis by Monte Carlo simulations

Environmental Science and Pollution Research, 2013

Keywords Urban air pollution. Predicting pollutants. Artificial neural networks. Meteorological v... more Keywords Urban air pollution. Predicting pollutants. Artificial neural networks. Meteorological variables. Monte Carlo simulations. Prediction intervals Background, aim, and scope Many large cities in developing countries are increasingly facing episodes of critically high levels of atmospheric pollution, affecting their quality of life and public health (McMichael 2000; Molina and Molina 2004). Reliable forecasting of air pollution would allow taking more efficient countermeasures to prevent air pollution crisis and protect

Research paper thumbnail of Phosphorus removal and recovery: state of the science and challenges

Environmental Science and Pollution Research

Research paper thumbnail of Erratum to: Synthesis of vinasse-dolomite nanocomposite biochar via a novel developed functionalization method to recover phosphate as a potential fertilizer substitute

Frontiers of Environmental Science & Engineering, 2021

Due to the typesetting error, there are some errors in the Equation (4) in the manuscript, the co... more Due to the typesetting error, there are some errors in the Equation (4) in the manuscript, the correction is as follows, and we apologize to the reader.

Research paper thumbnail of Comparison of micro and nano MgO-functionalized vinasse biochar in phosphate removal: Micro-nano particle development, RSM optimization, and potential fertilizer

The present study is conducted to synthesize vinasse-derived biochar, followed by modification wi... more The present study is conducted to synthesize vinasse-derived biochar, followed by modification with Micro and Nano MgO in an attempt to assess their effects on the phosphate (P) removal from aqueous medium. Based on the characterization results of modified biochars and adsorption capacities, Nano-MgO Functionalized ones have proven to be more capable in P removal, with the specific surface areas of 119.98–125.41 m2/g and maximum P adsorption capacity of 188.67 mg/g. The dependencies of adsorption on initial P concentration (50–350 mg/L), contact time (5–90 min), and solution pH level (3–11) were investigated by 20 experiments designed via CCD-based RSM. The regression analysis showed a good fit of the experimental data to the second-order polynomial model with coefficient of determination (R2) value of 0.9916 and model F-value of 131.82. The optimum conditions of pH (7.00), contact time (75 min), and initial P concentration (250 mg/L) were recorded from desirability function. Based ...

Research paper thumbnail of Synthesis of vinasse-dolomite nanocomposite biochar via a novel developed functionalization method to recover phosphate as a potential fertilizer substitute

Frontiers of Environmental Science & Engineering