Robust Optimization for Tree-Structured Stochastic Network Design
This work addresses the problem of optimizing river connectivity for fish movement in computational sustainability, but it is incremental as it extends existing stochastic network design by incorporating robustness to parameter uncertainty.
The paper tackles the robust river network design problem for optimizing fish movement by removing barriers, assuming imprecise passability probabilities within interval bounds. The approach scales well to large networks and achieves a significantly higher robust ratio than baseline solutions using mean parameter estimates.
Stochastic network design is a general framework for optimizing network connectivity. It has several applications in computational sustainability including spatial conservation planning, pre-disaster network preparation, and river network optimization. A common assumption in previous work has been made that network parameters (e.g., probability of species colonization) are precisely known, which is unrealistic in real- world settings. We therefore address the robust river network design problem where the goal is to optimize river connectivity for fish movement by removing barriers. We assume that fish passability probabilities are known only imprecisely, but are within some interval bounds. We then develop a planning approach that computes the policies with either high robust ratio or low regret. Empirically, our approach scales well to large river networks. We also provide insights into the solutions generated by our robust approach, which has significantly higher robust ratio than the baseline solution with mean parameter estimates.