How we gather data and how much of it we gather is important in environmental research. Therefore, improving and optimising sampling efforts is important. Sensors offer plenty of opportunity for data gathering and statistical approaches can be used compare what data are likely to be valuable in different situations.

Value of information (VOI) is simply how much someone would pay for information related to a decision before the decision is made. From an environmental perspective, how should we monitor pollutants to make decisions about industrial operations?

In terms of data gathering and VOI we want to consider the following:

· Is the VOI larger than the price of data gathering/experiment?

· Is the VOI larger for gathering method A or B?

· Is the VOI larger for data type A or B?

The VOI often has a clear economic interpretation. This approach can also be used to compare experimental design based on some statistical criterion or a reward function.

Statistical data gathering schemes can be based on different criteria:

· Maximize average distance between location

· Maximum variance reduction

· Maximum entropy reduction

· Minimize expected prediction error

An application that was discussed looked at using marine robotics and spatial statistic to suggests methods that minimize the expected uncertainty reduction in the multivariate spatial fields. This work showed that exploration can be made more effective by prioritizing sampling efforts at ambiguous locations.

Header image credit: Eidsvik, J., Mukerji, T., & Bhattacharjya, D. (2015). Value of Information in the Earth Sciences: Integrating Spatial Modeling and Decision Analysis. Cambridge: Cambridge University Press. doi:10.1017/CBO9781139628785

Related Blogs

• 

  Annual meeting of the Society for Decision Making under Deep Uncertainty, 2022

• 

  The Cryosphere 2022 Conference

• 

  DSNE Reseachers receive best poster award at CDE Conference 2022

Disclaimer

The opinions expressed by our bloggers and those providing comments are personal, and may not necessarily reflect the opinions of Lancaster University. Responsibility for the accuracy of any of the information contained within blog posts belongs to the blogger.