Main content



Loading wiki pages...

Wiki Version:
# Publication This work is published in the Journal of Water Resources Planning and Management. Link [here][6]. # Presentation This work was presented at the 2020 International Environmental Modelling and Software Society Conference which was held virtually due to the COVID-19 pandemic. [Here][1] is a link to the presentation. # Blog Post [This]( blog post walks through a very simple example of a multi-objective approach to tuning hyperparameters with a well-known dataset. # Project Components Hosted on This Page This page contains code and datasets to reproduce several aspects of this paper. All components include a [dockerfile][2] to allow for reproducibility across all computing platforms. ## [Spatial Features Model][3] This component contains an example run of our novel "spatial features model" which produces features that explicitly capture *where* a dam is located relative to vulnerable populations ## [Phase 1 Optimization][4] This component contains an example run of a multi-objective optimization of both the machine learning hyperparameters as well as the parameters for the spatial features model. It should be noted that the provided code is a serialized optimization of a single seed, whereas the published analysis conducted a parallelized search across five different seeds. ## [Phase 2 Assessment][5] This component contains an example of how the optimal parameters from the Phase 1 Optimization perform when predicting new observations. [1]: [2]: [3]: [4]: [5]: [6]:
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, see our Privacy Policy and information on cookie use.

Start managing your projects on the OSF today.

Free and easy to use, the Open Science Framework supports the entire research lifecycle: planning, execution, reporting, archiving, and discovery.