What have we learnt about CO2 leakage from CO2 release field experiments, and what are the gaps for the future?

Legislation and guidelines developed for Carbon Capture and Storage (CCS) have set performance requirements to minimize leakage risk, and to quantify and remediate any leaks that arise. For compliance it is necessary to have a comprehensive understanding of the possible spread, fate and impacts of any leaked CO2, and the ability to detect and quantify any CO2 seepage into marine or terrestrial environments. Over the past decade, a number of field scale CO2 release experiments have been conducted around the world to address many of the uncertainties regarding the characteristics of near-surface expression of CO2 in terms of the impact and quantitation of CO2 leaks. In these experiments, either free phase or dissolved CO2 was injected and released into the shallow subsurface so as to artificially simulate a CO2 leak into the near-surface environment. The experiments differ in a number of ways, from the geological conditions, surface environments, injection rates and experimental set-up - including the injection and monitoring strategy. These experiments have provided abundant information to aid in the development of our scientific understanding of environmental impacts of CO2 while assessing state of the art monitoring techniques. We collated a global dataset of field-scale shallow (depths < similar to 25 m) controlled CO2 release experiments. The dataset includes 14 different field experiment locations, of which nine intended to release CO2 to the surface, and the remaining sites intended for CO2 to remain in the shallow subsurface. Several release experiments have been conducted at half of these sites, and so in total, 41 different CO2 release tests have taken place at the 14 sites in our dataset. We scrutinized our dataset to establish: (i) the range of experimental approaches and settings explored to date (such as the environment, subsurface conditions, injection strategy and whether gaseous or dissolved CO2 were injected and in what quantities); (ii) the range of CO2 injection and surface release rates at these experiments; (iii) the collective learnings about the surface and subsurface manifestation of the CO2 release, the spread and fate of the CO2, rates of CO2 flux to surface, and methods of measuring these; (iv) the strengths and limitations of current approaches for detecting and quantifying CO2. This allowed us to highlight where uncertainties remain and identify knowledge gaps that future experiments should seek to address. Further, drawing on the collective experiences, we have identified common issues or complications which future CO2 release experiments can learn from.