This paper takes a new look at dam hazard potential classification via machine learning algorithms by proposing a novel geospatial model to estimate new predictors. We take a multi-objective approach to the process of machine learning hyperparameter tuning. We show that such an approach gives analysts more insights into the classification problem as well as justification for hyperparameter selection. We demonstrate this framework on dams in Massachusetts, United States.
OSF does not support the use of Internet Explorer. For optimal performance, please switch to another browser.
This website relies on cookies to help provide a better user experience. By clicking Accept or continuing to use the site, you agree. For more information,
and information on cookie use.