Abstract: Acid mine drainage is one of the major factors causing soil environmental degradation in mining areas, and it is crucial to conduct ecological risk assessment on it. In this evaluation process, indicator weight allocation plays a key role. To address the problems of insufficient consideration of reverse indicators and high subjectivity in manual weighting in existing weighting methods, this study proposes a weighting method based on fuzzy cognitive map (FCM). Eight core risk factors (including reverse indicators) were screened, the hyperbolic tangent function was used to construct the fuzzy cognitive map, weights were calculated through iterative convergence, and sensitivity analysis and Pearson correlation test were integrated for validation, and finally the method is applied to a field evaluation in a mining area of Anhui Province. The results show that the potential ecological risk index of pollutants has the highest weight (0.856), the weights of fracture rate, roadway scale, etc. are all higher than 0.770, and the ecological restoration measure has a negative weight (-0.749). Sensitivity analysis shows that the model has high stability. The Pearson correlation coefficients are all above 0.85. In the field evaluation, after introducing the FCM-based weights, the low-risk area decreased by 5.3%, and the medium-high-risk area increased by 6.5%. A previously overlooked high-risk area at the mixed shaft in the mining area was successfully identified, and the evaluation results are more consistent with the actual situation.

Key words: acid mine drainage, fuzzy cognitive map, weighting allocation method, soil ecological risk