Smart Systems Engineering
Xiaonan Wang Research Group | Learning Hub
Department of Chemical and Biomolecular Engineering, National University of Singapore
4 Engineering Drive 4, E5 03-04, Singapore 117585
Check our latest papers at https://www.smartsystemsengineering.com/publications
Environmental science & technology 52, 5 (2018): 3257–3266.
Energy, water, and waste systems analyzed at a nexus level are important to move toward
more sustainable cities. Waste-to-energy pathways, along with the water and energy sectors are studied, aiming to develop waste treatment capacity and energy recovery with the lowest economic and environmental cost. Read more
Computers & Chemical Engineering 115 (2018): 213-225.
Get fascinated by the rapid development of energy storage technologies but have no clue what their true impacts are? Check out our recently published work on a decision-making framework for energy storage systems selection on our flagship PSE journal Computers & Chemical Engineering. Thanks for the great collaboration with Tsinghua Energy and Power Engineering and AquaBattery.
Matter 3 (2020): 393–432
How is AI accelerating all stages of Material Discovery? Our review published on #Matter provides a holistic look of what #AI and #machinelearning brings to the table for discovery & design by considering ultimate application & end-use of the material.
Almost two years' team efforts to put this holistic review together! Congrats to my PhD students and more exciting outcome to expect!
Fuel properties of hydrochar and pyrochar: Prediction and exploration with machine learning
Applied Energy 269 (2020): 115166.
Conversion of wet organic wastes into renewable energy is a promising way to substitute fossil fuels and avoid environmental deterioration. Machine learning models for multi-task prediction of fuel properties of the chars were developed and optimized based on two datasets for hydrochar and pyrochar. Feature importance and correlation were explored based on optimized ML model, and feature re-examination was conducted for model improvement.