# 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](https://kravitsjacob.github.io/multiobjective-hyperparameter/) 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]: https://www.youtube.com/watch?v=JNjcqWhYYWc [2]: https://docs.docker.com/engine/reference/builder/ [3]: https://osf.io/vmd3j/ [4]: https://osf.io/ta6ec/ [5]: https://osf.io/baunh/ [6]: https://ascelibrary.org/doi/abs/10.1061/%28ASCE%29WR.1943-5452.0001414