Transportation activities such as fuel consumption, vehicle wear and road deicing can detrimentally affect the groundwater quality of fragile roadside wetland environments including. Nineteen parameters (Cu, Pb, Zn, Cd, Cr, Ni, Hg, As, pH, TDS, Ca²⁺, Mg²⁺, Na⁺, K⁺, SO₄²⁻, Cl⁻, HCO₃⁻, NO₃⁻ and F⁻) were determined in groundwater samples from turfy swamps impacted by highway traffic from Jiangyuan (JY), Longquan (LQ), and Huangsongdian (HSD). Our results indicate that the metals Cu, Pb, Zn, Cr, Cd, the ions Na⁺, K⁺ and Cl⁻ in groundwater were negatively affected by highway transportation, and the maximum affected distance of these pollutants varied from 15 to 100 m. The content of most of these pollutants in roadside groundwater decreased exponentially with the distance from the highway, as did the heavy metal pollution index HPI and C_d. The values of HPI and C_d in these three sites ranged from 46.8 to 78.4 and −4.9 to −2.9, respectively. The low pollution levels of heavy metals are related to the strong adsorption capacity of turfy soil towards metals. In any case, road transport activities increased the Cu, Pb, Zn, Cr, Cd, Na⁺, K⁺ and Cl⁻ content in roadside groundwater in turfy swamp. With the increase of highway operation time, it will inevitably have a great influence on the groundwater quality of these wetlands. Therefore, the long-term monitoring is necessary to protect the sustainable development of turfy swamp.

Rockburst intensity prediction is one of the basic works of underground engineering disaster prevention and mitigation. Considering the dynamic variability and fuzziness in rockburst intensity prediction, variable fuzzy sets (VFS) are selected for evaluation and prediction. Here, there are two problems in the application of traditional VFS: (i) the relative membership degree (RMD) calculation process is complex and time-consuming, and the RMD matrix of all indexes can be only obtained by using the RMD function repeatedly; (ii) unreasonable weights of indicators have great impact on the synthetic relative membership degree (SRMD), so it is difficult to guarantee the correctness of the final prediction result. In view of the above problem, this paper established three simplified feature relationship expressions of RMD based on VFS principle and used the SRMD function to establish a BP neural network model to optimize SRMD. The improved VFS method is more efficient and the prediction results are more stable and reliable than the traditional VFS method. The main advantages are as follows: (1) the improved VFS method has higher computational efficiency; (2) the improved VFS method can verify the correctness of RMD at all times; (3) the improved VFS method has higher prediction accuracy; and (4) the improved VFS method has higher fault tolerance and practicability.