In tunnel construction, the prediction of the surrounding rock deformation is related to the construction safety and stability of the tunnel structure. In order to achieve an accurate prediction of the surrounding rock deformation in soft rock tunnel construction, a Long Short-Term Memory (LSTM) neural network is used to construct a prediction model of the vault settlement and the horizontal convergence of the upper conductor in soft rock tunnels. The crested porcupine optimisation (CPO) algorithm is used to realise the hyper-parameter optimisation of the LSTM model and to construct the framework of the calculation process of the CPO-LSTM model. Taking the soft rock section of the Baoshishan Tunnel as an example, the large deformation of the surrounding rock is measured and analysed in situ, and the monitoring data of arch settlement and superconducting level convergence are obtained, which are substituted into the CPO-LSTM model for calculation, and compared and analysed with traditional machine learning and optimisation algorithms. The results show that the CPO-LSTM model has an R² of 0.9982, a MAPE of 0.8595% and an RMSE of 0.1922, which are the best among all the models. In order to further improve the optimisation capability of the CPO, some improvements were made to the CPO and an Improved Crested Porcupine Optimiser (ICPO) was proposed. The ICPO-LSTM prediction model was established, and the ZK6 + 834 section was selected as a research object for comparison and analysis with the CPO-LSTM model. The results of the error analysis show that the prediction accuracy of the improved ICPO-LSTM model has been further improved, and the prediction accuracy of the model meets the requirements of guiding construction.

The disposal of peat soil poses an increasingly difficult problem for actual engineering projects of Dianchi Lake area. This study obtains peat soil from seven areas around Dianchi Lake, and the content of humic acid (HA) in peat soil is between 2.36% and 28.13%. Then, this study simulates the peat soil by adding HA into the cohesive soil and uses cement to solidify it. The effect of cement and HA on the strength development of samples is examined by the unconfined compressive strength (UCS) test. Additionally, the microstructures of typical mixes are analyzed by scanning electron microscopy (SEM), X-ray diffraction (XRD), and mercury intrusion porosimetry (MIP). The results showed that HA will significantly reduce the UCS of cement soil. The SEM, XRD, and MIP confirmed that cement hydration reaction increases with cement ratio. In addition to the cementitious soil particles, hydration products gradually fill the pores of the soil and effectively reduce the number of large-size (6000∼40,000 nm) pores in cement soil, which makes the soil particle framework stronger. When the cement ratio increases from 15% to 25%, the diffraction peak of CAH and CSH increases faster. Combined with the results of the UCS test, it could be proved that cement ratio greater than 20% weakens the influence of HA on the strength development of cement soil sample.

The influence of peat soil environment (PSE) on the mechanical properties of cement-soil in the area around Dianchi Lake and Erhai Lake in Yunnan Province has attracted much attention. This study explores the change law of cement-soil UCS in the PSE, and provides guidance for the development and sustained usage of peat soil foundation. The paper discusses the preparation of cement-soil samples by adding humic acid (HA) and cement to cohesive soil with low organic matter content (blending method) and soaking it in fulvic acid (FA) solution and deionized water (steeping method) to simulate the actual working environment of cement-soil. Unconfined compressive strength (UCS), acid consumption, ion leaching, scanning electron microscope (SEM), and X-ray diffraction (XRD) tests are carried out on cement-soil samples soaked for 90 days. The results show that HA can significantly reduce the UCS of cement-soil. FA can reduce the UCS of cement-soil when the content of HA is less than 18%. However, when the amount of HA is more than 18%, the UCS of cement-soil increases slightly. FA makes the deformation and failure type of cement-soil gradually change from brittle shear failure to plastic shear failure. FA reacts with the cement hydration products in the sample so that the cumulative acid consumption of the cement-soil sample continues to increase, and the dissolution of Ca²⁺, Mg²⁺, Al³⁺, and Fe³⁺ in the sample increases the ion concentration of the soaking solution. In addition, SEM and XRD show that HA can increase the macropores and connectivity of cement-soil, while FA fills part of the pores of the wetting layer. In the PSE, FA can strengthen the inner structure of HA particles and fill and cement the layers of cohesive particles, enhancing the construction of cement-soil with HA content greater than 18%, so that its UCS is relatively improved. However, when the amount of HA is less than 18%, there are more small pores in the cement-soil. The interaction between FA and HA in the cement-soil is weak. The influence of FA on cement-soil is mainly a weakening effect, and its UCS is relatively reduced.

The disposal of soil containing humic acid (HA) poses an increasingly difficult problem for geotechnical environmental engineering. In this study, the unconfined compressive strength (UCS) test of cement‐soil with different HA contents is conducted to analyze the effect of HA on the strength of cement‐soil. Mercury intrusion porosimetry (MIP), scanning electron microscopy (SEM), and X‐ray diffraction (XRD) experiments reveal the effective mechanism of HA on the strength of cement‐soil from the microscopic level. The results show that the strength of cement‐soil decreases gradually with the increase of HA content. The failure mode of cement‐soil slightly changed from brittle failure to plastic failure. The microscopic test shows that the incorporation of HA will lead to the apparent enlargement of the pores in the cement‐soil. The large pores in the sample increase, the small micropores decrease, and the structure tends to be loose and overhead. The increased HA content added will significantly reduce the cement hydration products and destroy the cementation of the hydration products.

Treating peat soil foundations around Dianchi Lake and Erhai Lake in Yunnan is a complex problem in practical engineering projects. Peat soil solely reinforced with ordinary cement (OPC) does not satisfy demand. This study aims to solidify soil to achieve better mechanical properties. The preparation of peat soil incorporates a humic acid (HA) reagent into cohesive soil, and cement and ultra-fine cement (UFC) are mixed by stirring to prepare cement soil samples. They are then immersed in fulvic acid (FA) solution to simulate cement soil in the actual environment. X-ray diffraction (XRD), mercury intrusion porosimetry (MIP), scanning electron microscopy (SEM), and pores and cracks analysis system (PCAS) tests are used to study the impact of the UFC on the microscopic pore structure of cement soil in a peat soil environment. The unconfined compressive strength (UCS) test is used for verification. The microscopic test results indicate that incorporating UFC enhances the specimen’s micropore structure. The XRD test results show the presence of C–S–H, C–A–S–H, and C–A–H. SEM and PCAS tests show that the UFC proportion increases by between 0% and 10%, and the percentage reduction in the macropore volume is the largest, at 38.84%. When the UFC admixture is 30%, the cumulative reduction in the percentage of macropore volume reaches 71.55%. The MIP test results show that the cumulative volume greater than 10 µm in pore size decreases from 7.68% to 0.17% with an increase in the UFC proportion. The UCS test results show that the maximum strength growth of cement soil is 12.99% when the UFC admixture is 0–10%. Incorporating UFC to form a compound curing agent solves the problem of the traditional reinforcement treatment of peat soil foundation being undesirable and decreases the amount of cement. This study provides practical guidance for reducing carbon emissions in actual projects.