Optimization of the Low-Impact Development Facility Area Based on a Surrogate Model

Low-impact development (LID) facilities constitute an important element of sponge cities. In this paper, a system of siting suitability indicators was established for green roofs, permeable pavement and rain gardens. Based on the ArcGIS superposition analysis tool, the suitable area and area upper limit of LID facilities in each subcatchment were determined. Nonlinear functions of the LID deployment area and various rainfall characteristics were constructed using a multilayer perceptron (MLP) as a surrogate model. The results showed that (1) the upper limit of the suitable area for green roof deployment in each subcatchment ranged from 5.46% to 22.87%. The upper limit of the suitable area for permeable pavement application varied between 8.31% and 23.65%. The upper limit of the suitable area for rain garden deployment varied between 18.12% and 36.95%; (2) a final LID facility layout scheme was selected at a total outflow of 10,700 m3, peak discharge of 3.49 m3/s and total investment of 0.76 billion yuan during the construction and management period; (3) the total outflow reduction rate under the LID model ranged from 32.15% to 40.29%, and the peak discharge reduction rate ranged from 17.93% to 36.20%; (4) the computation time of the surrogate optimization model could be reduced to 0.37% of that of Storm Water Management Model (SWMM) conventional numerical optimisation. Herein, the surrogate model can be used to determine the optimal solution for the LID facility placement area assuming fixed reduction amounts of the outflow and peak discharge.