The development of reliable predictive models for soil behavior represents a crucial advancement in geotechnical engineering, particularly for optimizing material compositions and reducing experimental uncertainties. Traditional experimental approaches for determining the optimal rubber particle size and content are often resource-intensive, time-consuming, and subject to significant variability. In this study, the shear strength of clay mixed with rubber particles solidified by the Enzyme-Induced Calcium Carbonate Precipitation (EICP) technique was investigated and predictively modeled using a machine learning algorithm. The effects of different rubber contents and particle sizes on the shear strength of the clay were analyzed experimentally, and a hybrid model of a convolutional neural network (CNN) and long short-term memory (LSTM) network optimized based on the crown porcupine optimization (CPO) algorithm was proposed to predict the shear strength of the EICP-treated clay mixed with rubber particles. The superiority of the CPO-CNN-LSTM model in predicting shear strength was verified by comparing multiple machine learning algorithms. The results show that the addition of rubber particles significantly improves the shear strength of the clay, especially at a 5% rubber content. The coefficient of determination (R²) of the CPO-CNN-LSTM model on the training and test datasets reaches 0.98 and 0.97, respectively, which exhibit high prediction accuracy and generalization ability.

The bridge tower beams of long-span bridges freeze during winter. The accumulated ice on the beam flakes off and falls into the bridge deck from a high altitude with temperature rise, threatening traffic safety. To solve this problem, an electric heating method is used to melt the snow and ice on bridge tower beams. A design scheme based on embedding carbon fiber heating wires in a bridge tower beam is proposed in which electrical energy is converted into heat energy to melt the snow and ice on the beam. In this paper, a beam icing test and beam de-icing test are carried out through a laboratory model test. The model test results show that under the conditions of a wind speed of 4.5 m/s and an ambient temperature of −15 °C, the average internal temperature of the beam after heating stabilization is 1.37 °C; this is higher than the average critical temperature of 1.31 °C. This temperature is sufficient to melt the ice and proves the practicability of this method. The de-icing method of embedded carbon fiber heating is simple, efficient, and environmentally friendly. This can provide a reliable reference for the practical application of de-icing a bridge beam.