Using incentives to allocate scarce goods is a core tenet of environmental economics but may result in unpalatable distributional outcomes. We analyze surcharges enacted during a severe drought in Southern California within nonlinear rate structures. Using machine learning to generate counterfactual predictions, we find surcharges lead to limited water conservation despite steep price increases. “Budget-based” rates counteract conservation goals by shielding large users from high prices and surcharges do little to reduce the regressivity of water expenditures. Simpler rate structures can dominate along equity dimensions and their progressivity can be enhanced via lump-sum transfers within the rate structure.