Intelligent Inversion Analysis of Hydraulic Engineering Geological Permeability Coefficient Based on an RF–HHO Model

The permeability of the natural geology plays a crucial role in accurately analyzing seepage behavior project area. This study presents novel approach for inverse analysis coefficient. finite element model (FEM) combined with orthogonal experimental design is used to construct sample set coefficient inversion. established random forest (RF) algorithm surrogate applied determine optimal values parameters area using Harris hawk optimization (HHO) algorithm. method was explore and verify distribution fields P hydropower station. results showed that RF outperformed classical CART BP models at each borehole regarding performance evaluation indices. Furthermore, water head prediction were more accurate, performed admirably terms prediction, anti-interference, generalization. HHO effectively searched geology. maximum value relative error inverted 1.11%, accuracy met engineering standards. initial field pattern calculated followed basic mountain field.