Data-driven Oil and Gas engineer specializing in CO₂ emissions analysis and subsurface modeling.
Focused on accelerating carbon capture and storage through machine learning and simulation.
Developing a data-driven surrogate model for CO₂ injection and storage efficiency using the SPE Comparative Solution Project (CSP) 11C—a full 3D field-scale benchmark for multiphase CO₂ flow prediction—by leveraging engineered spatial–temporal features and neural-network modeling to replace costly numerical simulations, enabling rapid scenario evaluation with future extensions toward full-field plume prediction and multi-scenario optimization. Code and data workflow can be found here.
Evaluating Air Quality Index (AQI) from five AQI monitoring stations in Jakarta (2010–2025). Using Python and libraries such as Matplotlib, the study applies a data visualization and exploratory analysis approach to examine long-term trends, seasonal variations, and inter-pollutant relationships. The aim is to generate insights that can support evidence-based environmental policies, public awareness, and sustainable urban development.
Forecasts future AQI (2025–2030) across Jakarta’s five main monitoring stations, based on environmental and policy improvement scenarios is available here, and the full source code and data workflow are provided here.
Analyzing CO₂ emissions per capita in ASEAN to understand how emissions have evolved over time (1900s–2024). The analysis uses Python for data cleaning and exploratory data analysis, highlighting regional progress in energy transition. Forecasting future CO₂ emissions in ASEAN using a Polynomial Regression model combined with Prophet forecasting. The results provide insights that may support policy makers in planning effective mitigation strategies.
The complete source code and data pipeline are available here, and the interactive Streamlit dashboard can be accessed here.
