Through quantitatively analyzing the implementation of the sponge city concept in urban green space systems, this research explored the role of urban green spaces in collecting and using rainwater in a urban landscaping. By combining the ecological and recreational functions of the urban green spaces, as well as appropriate quantitative indexes, reasonable approaches for applying rainwater collection, infiltration and retention technologies in urban green space design and construction are suggested. Thus, the implementation of the sponge city concept in the initial planning stage of green spaces was considered. The Taihu New City in Wuxi was chosen as study case. Thus, this paper combined current planning status between green space and rainwater collection systems and analyzed them. As result, usable green spaces for the sponge city construction were obtained. Also, details on the construction characteristics of various usable green spaces were acquired. The role of these green spaces in the sponge city construction were classified and quantitatively assessed and compared with relevant standards. On the basis of guaranteeing green space intended purposes, this paper analyzed the results of coordinating the green space areas with rainwater collection systems and specified the role of various green spaces in the rainwater collection.

The term “Artificial Intelligence” (AI) refers to the simulation of human intelligence on a computer. Higher education can benefit from AI because it is a computationally efficient paradigm. Learning adapted to the changing demands of students is one of the key educational advantages of AI. Students can modify the pace of a course to better competency. Poor faculty and teaching quality and a general lack of motivation and interest among students are among the difficulties facing higher education. An artificial intelligence-assisted integrated teaching–learning framework (AL-ITLF) for higher education is proposed in this research. Multiple tutoring services are also involved in the curriculum, which is skill-based. The extreme learning machine (ELM) technique evaluates designs integrated into the suitable student monitoring model weighted score (WS) and exam results. An educational model that is more efficient, adaptable, and effective than current traditional education has been developed due to AI research in higher education. Higher education’s use of AI has resulted in a more efficient, adaptive, and effective educational model than traditional schooling. High accuracy, higher performance, lower processing costs, and a high prediction and low error rate are advantages of the suggested AI-ITLF approach. The WS and exam results were evaluated using an ELM algorithm as part of a proper student monitoring model.

No abstract