With the advent of the modern transportation era, road design needs to emphasize landscape and recreational functions more than traditional safety functions. However, quantifying drivers’ subjective perceptions and the objective visual landscape characteristics that influence them remains challenging due to the subjectivity of landscape perception, and the limitation of data size and the complexity of environmental information capture. This paper aims to overcome these limitations, based on deep learning techniques to achieve high-precision automatic identification and rapid processing of spatial visual elements in the highway landscape. Based on supervised fully connected neural networks, the ELO scoring algorithm, and ArcGIS, it realizes the quantitative evaluation of subjective perception emotions and visual mapping representation. Furthermore, the paper integrates optimization algorithms with deep learning, employing a Whale Optimization Algorithm (WOA) enhanced XGBoost regression model to analyze the interplay between spatial features and subjective experiences. The model’s effectiveness is confirmed through comparative experiments and SHAP analysis, offering insights into the coupling of subjective and objective data. The research results provide theoretical methods and quantitative analysis tools for the digitalization and refinement of highway landscape design, and also help researchers and urban planners to understand the interaction between subjective perception and objective semantics, providing new ways and insights for highway landscape planning and design.

The post-assessment of highway atmospheric environmental impacts was limited by the traditional air pollution prediction model, which cannot adapt to complex terrain and complex obstacle scenes. The traditional model has a single evaluation index, which cannot accurately evaluate and predict the transient and long-term emissions of various pollutants. Based on the computational fluid dynamics model, this work establishes a post-assessment method of the atmospheric environment impact of the Beijing–Chengde Expressway construction project. The main pollution factors NOx and CO of highway traffic for transmission and diffusion simulation analysis were selected. The influence law of traffic function, environmental impact, meteorological conditions, and landform on the diffusion of pollution factors in complex tunnel sections were analyzed. It concludes that the pollution within 200 m along the expressway is severe and mainly concentrated in the tunnel entrance and gully area. The NOx concentration is generally higher than CO. The environmental quality is not up to standard and has a diffusion trend with increased traffic flow, operation time, wind speed, wind temperature, and wind direction frequency. The research results can provide theoretical guidance and technical support for the scientific post-assessment of highway environmental impact under complex conditions.