In recent years, the rapid increase in the number of vehicles has led to widespread traffic problems. Accurate prediction of traffic flow can help reduce congestion, optimize transportation infrastructure, enhance travel safety, and mitigate environmental impacts. This study aimed to predict the traffic volume for the next hour on the Karaj-Chalus axis, one of Iran’s busiest roads with complex weather and topographic conditions. To this end, traffic data from two traffic counters and synoptic weather data (with three-hour intervals) were collected. Given the capability of Convolutional Neural Networks (CNN) in extracting hidden features and spatial-temporal patterns, as well as the efficiency of Long Short-Term Memory (LSTM) networks in modeling time series, a hybrid Conv-LSTM model was proposed. This model, leveraging the strengths of both approaches, was designed for accurate traffic volume prediction. The proposed model was implemented in the Python programming language and compared with an Attention-based Long Short-Term Memory (A-LSTM) model. Evaluation results showed that the Conv-LSTM model achieved a coefficient of determination (R²) of 82.45% on the test dataset, outperforming the A-LSTM model with an R² of 81.93%. Additionally, the Mean Squared Error (MSE) and Root Mean Squared Error (RMSE), which indicate the discrepancy between predicted and actual values, were reported as 14.311 and 120 for Conv-LSTM, and 14.740 and 122 for A-LSTM, respectively. These values indicate lower dispersion and higher prediction accuracy for Conv-LSTM compared to A-LSTM. The application of the proposed model in predicting traffic volume on the Karaj-Chalus axis provides valuable insights for identifying congested routes, redistributing traffic, preventing accidents, dynamic route planning, and optimizing travel time management. Furthermore, this approach contributes to improved environmental sustainability and transportation efficiency by reducing fuel consumption and air pollution.