Dr. Congbo Song holds the position of Senior Research Scientist in Data Science and Analytics in Atmospheric Air Pollution, at The National Centre for Atmospheric Science (NCAS) based in the Department of Earth and Environmental Science, the University of Manchester. He has broad research interests in source emissions, source apportionment, air pollution and machine learning. In particular, he has research interests and extensive expertise on studying air pollution impacted by emissions from on-road vehicles, coal combustion and biomass burning through advanced data analysis on emission measurements and field measurements. He coordinated a number of large field campaigns in the UK and China, including a complex research cruise (RSS Discovery DY151) from Iceland to the Arctic. He has been extensively involved in several UK clean air projects, including SEANA – Shipping Emissions in the Arctic and North Atlantic atmosphere, Air Quality Supersite Triplets (UK-AQST), COP-AQ: UK-China collaboration to optimise net-zero policy options for air quality and health, West Midlands Air Quality Improvement Programme (WM-AIR), Integrated Research Observation System for Clean Air (OSCA). Dr. Song has authored and coauthored over thirty peer-reviewed papers since 2017, with total citations over 2400 and H-index of 21. His publications are mainly in the field of Chain of Air Pollution Accountability, including Emissions, Air Quality, Public health and Air Quality Interventions. A key aspect of his research is to understand the impacts of source-specific air pollution on human health and climate through advanced receptor modelling. He is also interested in understanding environmental policies, environmental drivers and atmospheric processes controlling the air we breath using data-driven models such as machine learning and casual inference techniques. His recent focus is to develope data-driven models to understand causes and changes in air pollution in the real-time towards net-zero emissions. Blogs, data and codes: https://congbo.site

Field Measurement. Research Cruise, tunnel tests, near-road measurements and ambient measurements using a wide range of online and offline instruments. 

Source Emission and Source Apportionment. Detailed characterization of particulate and gas emissions from anthropogenic and natural sources. Interpreting aerosol and gaseous chemical data using multivariate statistical methods (e.g., receptor models) and machine learning techniques; Revealing environmental drivers for source-specific air pollution. His recent focus is to develop real-time source apportionment techniques using single-particle mass spectrometry. 

Machine Learning and Causal Inference. Using machine learning (deweathering) and causal inference techniques to decouple emissions and meteorology to evaluate causality of air quality management.

Instrumentation: Single Particle Aerosol Mass Spectrometer (SPAMS), Aerosol Chemical Speciation Monitor (ACSM), Particle size spectrometers (APS, SMPS, PSM and NAIS), On-line metal elements (Xact), AiRRmonia, Single Particle Soot Photometer – Extended Range (SP2-XR), Aethalometer, Multi Angle Absorption Photometer (MAAP), Cavity Attenuated Phase Shift extinction (CAPS) and Cloud condensation nuclei (CCN). 

Advanced Data Analysis. Multivariate data fusion- Integrating traffic data, meteorological data and pollutant data. Statistical analysis and data mining. Clustering techniques, receptor models (CMB, PMF, ME-2), machine learning techniques, causal inference techniques. Particularly, he is skilled at understanding sources and processes of air pollution (e.g., size-resolved aerosol) using a coupling receptor model and explainable machine learning technique.