Pouya Rezazadeh Kalehbasti
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Pouya Rezazadeh Kalehbasti has a total of 27 co-authors. Here are the top co-authors by number of shared publications:
Liubov Nikolenko
Stanford University
2 shared publicationsMichael D. Lepech
Department of Civil and Environmental Engineering, Stanford University, Stanford, CA, United States
2 shared publicationsAvradip Mandal
Fujitsu Laboratories of America, Inc
1 shared publication- Avradip Mandal
Fujitsu Research of America, Inc., Sunnyvale, USA
1 shared publication Craig S. Criddle
Department of Civil and Environmental Engineering, Stanford University, Stanford, CA, United States
1 shared publication- Ebrahim Asadi Oskouei
Atmospheric Science and Meteorology Research Center (ASMERC), Tehran, Iran
1 shared publication
Latest Publications
- 10 December 2022
- Published by Elsevier in Journal of Cleaner Production
- Vol. 384
Benchmarking sidestream shortcut nitrogen removal processes against nitrous oxide recovery from a life cycle perspective
- 10 December 2022
- Published by Elsevier in Journal of Cleaner Production
- Vol. 384
Benchmarking sidestream shortcut nitrogen removal processes against nitrous oxide recovery from a life cycle perspective
- Open Access
- 31 March 2022
- Published by Frontiers Media SA in Frontiers in Sustainable Cities
- Vol. 4
Integrated Design and Optimization of Water-Energy Nexus: Combining Wastewater Treatment and Energy System
Designing more sustainable urban infrastructure is an essential topic in practice and research. While many have tried to address this challenge by focusing on sustainability of either supply or demand in a single infrastructure system, few studies have integrated the decisions for both supply and demand across several infrastructure. This paper proposes a novel method to design and optimize the hourly demand and supply of integrated energy and water system in an urban district for environmental and economic sustainability. This modular framework concurrently designs the optimal building mix of an urban district and the systems supplying the district with wastewater treatment, cooling, heating, and electricity. The model is tested on a sample neighborhood from San Francisco, California, with 21 building prototypes, 32 combined heating and power engines, 16 chillers, and 3 wastewater treatment systems (a central treatment plant and two decentralized membrane-based systems). The results of this study show that the median values of normalized life-cycle cost, social cost of carbon, annual energy demand, and annual wastewater production of the integrated designs of water-energy system are, respectively, 20, 75, 8, and 20% lower than those of the traditional segregated designs. The results also demonstrate the economic and environmental viability of using decentralized advanced treatment in urban areas when energy system, wastewater treatment, and building mix are designed together.
- 31 March 2022
- Published by Frontiers Media SA in Frontiers in Sustainable Cities
- Vol. 4
Open AccessIntegrated Design and Optimization of Water-Energy Nexus: Combining Wastewater Treatment and Energy System
Designing more sustainable urban infrastructure is an essential topic in practice and research. While many have tried to address this challenge by focusing on sustainability of either supply or demand in a single infrastructure system, few studies have integrated the decisions for both supply and demand across several infrastructure. This paper proposes a novel method to design and optimize the hourly demand and supply of integrated energy and water system in an urban district for environmental and economic sustainability. This modular framework concurrently designs the optimal building mix of an urban district and the systems supplying the district with wastewater treatment, cooling, heating, and electricity. The model is tested on a sample neighborhood from San Francisco, California, with 21 building prototypes, 32 combined heating and power engines, 16 chillers, and 3 wastewater treatment systems (a central treatment plant and two decentralized membrane-based systems). The results of this study show that the median values of normalized life-cycle cost, social cost of carbon, annual energy demand, and annual wastewater production of the integrated designs of water-energy system are, respectively, 20, 75, 8, and 20% lower than those of the traditional segregated designs. The results also demonstrate the economic and environmental viability of using decentralized advanced treatment in urban areas when energy system, wastewater treatment, and building mix are designed together.
- Open Access
- 9 November 2021
- Published by Springer Nature in Theoretical and Applied Climatology
- Vol. 147 (1-2) , 63
Correction to: New climatic zones in Iran: a comparative study of different empirical methods and clustering technique
- 9 November 2021
- Published by Springer Nature in Theoretical and Applied Climatology
- Vol. 147 (1-2) , 63
Open AccessCorrection to: New climatic zones in Iran: a comparative study of different empirical methods and clustering technique
- 10 August 2021
- Published by Springer Nature
- p. 173-184
Airbnb Price Prediction Using Machine Learning and Sentiment Analysis
- 10 August 2021
- Published by Springer Nature
- p. 173-184
Airbnb Price Prediction Using Machine Learning and Sentiment Analysis
- 10 August 2021
- Published by Springer Nature
- p. 21-33
When in Doubt, Ask: Generating Answerable and Unanswerable Questions, Unsupervised
- 10 August 2021
- Published by Springer Nature
- p. 21-33
When in Doubt, Ask: Generating Answerable and Unanswerable Questions, Unsupervised
- Open Access
Augmenting High-dimensional Nonlinear Optimization with Conditional GANs
Many mathematical optimization algorithms fail to sufficiently explore the solution space of high-dimensional nonlinear optimization problems due to the curse of dimensionality. This paper proposes generative models as a complement to optimization algorithms to improve performance in problems with high dimensionality. To demonstrate this method, a conditional generative adversarial network (C-GAN) is used to augment the solutions produced by a genetic algorithm (GA) for a 311-dimensional nonconvex multi-objective mixed-integer nonlinear optimization. The C-GAN, composed of two networks with three fully connected hidden layers, is trained on solutions generated by GA, and then given sets of desired labels (i.e., objective function values), generates complementary solutions corresponding to those labels. Six experiments are conducted to evaluate the capabilities of the proposed method. The generated complementary solutions are compared to the original solutions in terms of optimality and diversity. The generative model generates solutions with objective functions up to 100% better, and with hypervolumes up to 100% higher, than the original solutions. These findings show that a C-GAN with even a simple training approach and architecture can, with a much shorter runtime, highly improve the diversity and optimality of solutions found by an optimization algorithm for a high-dimensional nonlinear optimization problem. [Link to GitHub repository: https://github.com/PouyaREZ/GAN_GA]
Open AccessAugmenting High-dimensional Nonlinear Optimization with Conditional GANs
Many mathematical optimization algorithms fail to sufficiently explore the solution space of high-dimensional nonlinear optimization problems due to the curse of dimensionality. This paper proposes generative models as a complement to optimization algorithms to improve performance in problems with high dimensionality. To demonstrate this method, a conditional generative adversarial network (C-GAN) is used to augment the solutions produced by a genetic algorithm (GA) for a 311-dimensional nonconvex multi-objective mixed-integer nonlinear optimization. The C-GAN, composed of two networks with three fully connected hidden layers, is trained on solutions generated by GA, and then given sets of desired labels (i.e., objective function values), generates complementary solutions corresponding to those labels. Six experiments are conducted to evaluate the capabilities of the proposed method. The generated complementary solutions are compared to the original solutions in terms of optimality and diversity. The generative model generates solutions with objective functions up to 100% better, and with hypervolumes up to 100% higher, than the original solutions. These findings show that a C-GAN with even a simple training approach and architecture can, with a much shorter runtime, highly improve the diversity and optimality of solutions found by an optimization algorithm for a high-dimensional nonlinear optimization problem. [Link to GitHub repository: https://github.com/PouyaREZ/GAN_GA]
- 13 April 2021
- Published by Springer Nature
- p. 350-361
Ising-Based Louvain Method: Clustering Large Graphs with Specialized Hardware
- 13 April 2021
- Published by Springer Nature
- p. 350-361
Ising-Based Louvain Method: Clustering Large Graphs with Specialized Hardware
- Open Access
- 5 January 2021
- Published by Open Engineering Inc in engrXiv
MASTERPLANNER: A CENTRAL UTILITY PLANT DESIGN AND OPTIMIZATION TOOL
This paper presents a web-based software for designing optimal central utility plants. This tool can receive user-defined load profiles or generate typical load profiles based on user-specified combination and areas of 16 reference building types. The software then solves a linear-programming optimization comprising 8760 sets of equations and constraints to design central plant configurations with minimal first cost, operating cost, life-cycle cost, energy use, or marginal carbon emissions. The tool also calculates simultaneous heating and cooling loads to evaluate using heat-recovery chillers, and it can design both hot and cold thermal energy storage as well as water-side economizers.
- 5 January 2021
- Published by Open Engineering Inc in engrXiv
Open AccessMASTERPLANNER: A CENTRAL UTILITY PLANT DESIGN AND OPTIMIZATION TOOL
This paper presents a web-based software for designing optimal central utility plants. This tool can receive user-defined load profiles or generate typical load profiles based on user-specified combination and areas of 16 reference building types. The software then solves a linear-programming optimization comprising 8760 sets of equations and constraints to design central plant configurations with minimal first cost, operating cost, life-cycle cost, energy use, or marginal carbon emissions. The tool also calculates simultaneous heating and cooling loads to evaluate using heat-recovery chillers, and it can design both hot and cold thermal energy storage as well as water-side economizers.
- Open Access
Ising-Based Louvain Method: Clustering Large Graphs with Specialized Hardware
Recent advances in specialized hardware for solving optimization problems such quantum computers, quantum annealers, and CMOS annealers give rise to new ways for solving real-word complex problems. However, given current and near-term hardware limitations, the number of variables required to express a large real-world problem easily exceeds the hardware capabilities, thus hybrid methods are usually developed in order to utilize the hardware. In this work, we advocate for the development of hybrid methods that are built on top of the frameworks of existing state-of-art heuristics, thereby improving these methods. We demonstrate this by building on the so called Louvain method, which is one of the most popular algorithms for the Community detection problem and develop and Ising-based Louvain method. The proposed method outperforms two state-of-the-art community detection algorithms in clustering several small to large-scale graphs. The results show promise in adapting the same optimization approach to other unsupervised learning heuristics to improve their performance.
Open AccessIsing-Based Louvain Method: Clustering Large Graphs with Specialized Hardware
Recent advances in specialized hardware for solving optimization problems such quantum computers, quantum annealers, and CMOS annealers give rise to new ways for solving real-word complex problems. However, given current and near-term hardware limitations, the number of variables required to express a large real-world problem easily exceeds the hardware capabilities, thus hybrid methods are usually developed in order to utilize the hardware. In this work, we advocate for the development of hybrid methods that are built on top of the frameworks of existing state-of-art heuristics, thereby improving these methods. We demonstrate this by building on the so called Louvain method, which is one of the most popular algorithms for the Community detection problem and develop and Ising-based Louvain method. The proposed method outperforms two state-of-the-art community detection algorithms in clustering several small to large-scale graphs. The results show promise in adapting the same optimization approach to other unsupervised learning heuristics to improve their performance.
- Open Access
When in Doubt, Ask: Generating Answerable and Unanswerable Questions, Unsupervised
Question Answering (QA) is key for making possible a robust communication between human and machine. Modern language models used for QA have surpassed the human-performance in several essential tasks; however, these models require large amounts of human-generated training data which are costly and time-consuming to create. This paper studies augmenting human-made datasets with synthetic data as a way of surmounting this problem. A state-of-the-art model based on deep transformers is used to inspect the impact of using synthetic answerable and unanswerable questions to complement a well-known human-made dataset. The results indicate a tangible improvement in the performance of the language model (measured in terms of F1 and EM scores) trained on the mixed dataset. Specifically, unanswerable question-answers prove more effective in boosting the model: the F1 score gain from adding to the original dataset the answerable, unanswerable, and combined question-answers were 1.3%, 5.0%, and 6.7%, respectively. [Link to the Github repository: https://github.com/lnikolenko/EQA]
Open AccessWhen in Doubt, Ask: Generating Answerable and Unanswerable Questions, Unsupervised
Question Answering (QA) is key for making possible a robust communication between human and machine. Modern language models used for QA have surpassed the human-performance in several essential tasks; however, these models require large amounts of human-generated training data which are costly and time-consuming to create. This paper studies augmenting human-made datasets with synthetic data as a way of surmounting this problem. A state-of-the-art model based on deep transformers is used to inspect the impact of using synthetic answerable and unanswerable questions to complement a well-known human-made dataset. The results indicate a tangible improvement in the performance of the language model (measured in terms of F1 and EM scores) trained on the mixed dataset. Specifically, unanswerable question-answers prove more effective in boosting the model: the F1 score gain from adding to the original dataset the answerable, unanswerable, and combined question-answers were 1.3%, 5.0%, and 6.7%, respectively. [Link to the Github repository: https://github.com/lnikolenko/EQA]