Reduction of greenhouse gas emissions into the environment is a key requisite for ensuring a healthy and sustainable planet.
Reduction of greenhouse gas emissions into the environment is a key requisite for ensuring a healthy and sustainable planet. The initiative has gained rapid momentum and almost all major businesses are focused on minimizing their carbon footprint and greenhouse emissions to counter climate change.
Over the years, scientists, researchers, and technologists have been actively exploring several methods to cut down the release of CO2 and other greenhouse gases into the atmosphere.
For effective CO2 sequestration that can have an optimum positive impact on the environment, we need to get two things right - ideal subsurface warehousing for CO2 and accurate mapping and delineation of carbon.
Due to sparse seismic datasets, the traditional technique for mapping and estimating the quantity of carbon storage ability is neither adequate nor accurate. Moreover, it’s also time consuming. So, to explore the possibility of creating value for your operations, Halliburton Landmark has developed a data-driven Machine Learning (ML) solution that has passed our test cases with an accuracy of up to 85 percent.
Artificial Intelligence (AI) has become a game changer when it comes to estimating carbon storage capacity volume using sparse 2D/3D seismic data.
To achieve realistic estimates of carbon capacity, various sources of relevant data is integrated and ingested. This data is then subjected to analysis, pre-processing and data engineering using numerous derived seismic attributes to augment additional features. This enables us to compute a Relative Storage Index (RSI) through deep learning-based ML algorithm.
RSI is a ML predicted value which can be customized to define suitable ranges for different geological setups. This helps provide a better understanding of the strength and weaknesses of the subsurface storage.
Artificial Intelligence also helps develop data-driven geological models to predict the subsurface storage capacity volume for carbon dioxide. Recent case studies have indicated that carbon capture supported by data-driven ML solutions can be up to ten times faster than applying conventional modelling techniques, by providing a seamless workflow. It aggregates the current and historical data of the given location and simplifies the decision-making process. This helps reduce environmental hazards, without compromising on efficiency during the sequestration process.
To learn more about how AI and ML can provide efficient carbon capture storage estimation, watch the webinar today.
Expert: Samiran Roy | Principal Consultant, Big Data Center Of Excellence
Bhaskar Mandapaka | Senior Data Scientist, Big Data Center Of Excellence