Urban waterfront areas, which are essential natural resources and highly perceived public areas in cities, play a crucial role in enhancing urban environment. This study integrates deep learning with human perception data sourced from street view images to study the relationship between visual landscape features and human perception of urban waterfront areas, employing linear regression and random forest models to predict human perception along urban coastal roads. Based on aesthetic and distinctiveness perception, urban coastal roads in Xiamen were classified into four types with different emphasis and priorities for improvement. The results showed that: 1) the degree of coastal openness had the greatest influence on human perception while the coastal landscape with a high green visual index decreases the distinctiveness perception; 2) the random forest model can effectively predict human perception on urban coastal roads with an accuracy rate of 87% and 77%; 3) The proportion of low perception road sections with potential for improvement is 60.6%, among which the proportion of low aesthetic perception and low distinctiveness perception road sections is 10.5%. These findings offer crucial evidence regarding human perception of urban coastal roads, and can provide targeted recommendations for enhancing the visual environment of urban coastal road landscapes.

Constructed wetlands for effluent treatment (CW-ET) play a vital role in the degradation of pollutants, the purification of water, and the improvement of freshwater ecosystems. However, conventional designs often lack a methodical approach for quantifying the efficacy of these wetlands. In this context, numerical simulations aid in optimizing vegetation selection and placement in these systems, thereby enhancing their overall efficiency. In this study, the MIKE21 hydrodynamic (HD) module was coupled with the advection–dispersion (AD) module to simulate the Yingtai CW-ET in Hai’an. Accordingly, key parameters involved in effective water purification were calibrated and the system’s performance in treating effluent from wastewater treatment facilities was evaluated. The findings demonstrated significant removal efficiencies for chemical oxygen demand (COD), total nitrogen (TN), total phosphorus (TP), and ammonia (NH₃-N), with average rates of 51.14%, 43.14%, 63.82%, and 54.38%, respectively. In addition, the simulations exhibited high accuracy, with hydrodynamic predictions deviating by under 5% and water quality approximations by under 15%. The treated water quality met the requirements for Class IV surface water standards. Utilizing numerical simulations offers valuable insights for the design and performance evaluation of future constructed wetlands.

Urban waterfront areas (UWAs), which are essential natural resources and highly perceived public areas in cities, play a crucial role in improving the quality of the urban environment. While numerous studies have delved into the visual perception of urban environments, little attention has been paid to understanding how the visual perception of urban riverfront streets (URSs) differs with various aspects within their unique spatial environment. This study took the Gusu District in Suzhou, China, as a case study, applying deep learning to street-view images to identify urban riverside landscape elements and evaluate their visual attention, aesthetic preference, and distinctiveness through eye-tracking technology and questionnaires. Subsequently, a multidimensional assessment was conducted to analyze how landscape elements influence visual perception in the urban riverfront street. This study concludes that (1) riverfront streets in the Gusu District present balanced visual attention, with high aesthetic preference but limited distinctiveness, and only a few roads in the ancient city score highly for distinctiveness. (2) Greenery, traditional-style buildings, water, and riverfronts positively impact visual perception, while buildings have a negative impact, and backgrounds such as the sky and roads exhibit minimal influence. This study validated the scientific accuracy, appropriateness, and precision of assessments of visual attention, aesthetics, and distinctiveness to quantitatively evaluate the multidimensional human perception of URSs.

Amid rapid urbanization, cities are becoming increasingly compact, leading to intensified land resource constraints and environmental pressures. As a result, urban parks and green spaces have emerged as critical areas for providing cultural ecosystem services (CESs). However, the spatial distribution of CES supply and demand within urban green spaces remains significantly unbalanced, necessitating precise identification and quantification of CES supply–demand patterns to enhance ecosystem service efficiency. This study uses Nanjing, China, as a case study to develop an indicator framework for urban green space CES supply and demand, leveraging multi-source data. By employing spatial autocorrelation analysis (Bivariate Moran’s I) and a coupling coordination model, this research systematically assesses the spatial patterns of CESs in urban parks and green spaces. The results indicate that the overall CES supply–demand coordination in Nanjing exhibits a “high in the city center, low at the edges, and mismatched in the suburbs” pattern. Specifically, while 9.71% of the areas demonstrate well-matched CES supply and demand, 4.14% of the areas experience insufficient CES demand, and 3.66% face CES supply shortages, primarily in the urban outskirts, leading to a mismatch in green space distribution. This study further reveals the spatial heterogeneity of CES supply–demand matching across different urban districts. Based on these findings, this research proposes optimization strategies to improve CES allocation, providing a scientific basis for urban green space ecosystem service management and promoting the sustainable development of cities.

Constructed Wetlands for Effluent treatment (E-CW) play a vital role in the degradation of pollutants, purification of water, and the improvement of freshwater ecosystems. However, conventional designs often lack a methodical approach for quantifying the efficacy of these wetlands, as well as provide feedback on their operational efficiency. In this context, the use of hydrodynamic and water quality simulations facilitates the selection and arrangement of vegetation within these systems, thereby improving their efficiency. The present study utilized the MIKE21 Hydrodynamic (HD) module in conjunction with the ECO-Lab Water Quality (AD) module to perform a numerical simulation of the Yingtai Constructed Wetland for Effluent in Hai'an City. Accordingly, key parameters involved in effective water purification were calibrated and the system's ability to treat effluents from wastewater treatment facilities was assessed. The findings demonstrated significant removal efficiencies for Chemical Oxygen Demand (COD), Total Nitrogen (TN), Total Phosphorus (TP), and ammonia (NH₃-N), with average rates of 51.14%, 43.14%, 63.82%, and 54.38%, respectively. In addition, the simulations exhibited a high degree of accuracy, with hydrodynamic predictions deviating by less than 5% and water quality approximations by less than 15%. The quality of the treated water successfully met the standards set for Class IV surface water, in accordance with the relevant environmental regulations. Additionally, the constructed wetland system satisfactorily met the requirements for effluent purification. As observed, the use of numerical simulations can provide valuable guidelines for the future design and functional assessment of wetlands by offering crucial insights that aid in the optimization of purification processes and vegetation selection.