The water environment restoration project portfolio (WERP) selection is discussed in this paper. By complying with the analysis of the project’s multidimensional property and operation mode, this paper develops the chance constraint and the management constraint of the WERP from the perspectives of public service and enterprise operation. In addition, the multi-objective mixed integer linear programming model is constructed by combining the expectation method and the fuzzy chance constraint programming method. The results demonstrate that: (1) Our proposed method successfully circumvents the occurrence of local objective optimization within a specific confidence interval, thereby achieving a balance between economic and water environment restoration objectives; (2) including fuzzy chance constraints in our proposed method significantly diminishes the risk of exceeding the WERP capacity, thereby ensuring the effectiveness of water environment restoration by adopting a market-based approach. However, further examination of the impact of various sub-projects in WERP is necessary, along with the integration of novel evolutionary algorithms to enhance the efficiency of our model.

The Chinese government’s substantial investment in water restoration has created numerous lucrative opportunities for commercial environmental restoration enterprises. Accordingly, this research study seeks to address the primary challenge faced by enterprise managers: selecting projects that fulfill both strategic imperatives and maximize economic returns. To tackle this issue, we segmented the overarching strategic period into multiple phases and studied the project portfolio from a holistic strategic period perspective. We introduced a decision model for the dynamic, sequential updating of the portfolio throughout the strategic period, emphasizing the combined benefits at each phase. This model guides the strategic selection of projects at any decision-making stage to optimize the benefits across the entire strategic duration. The multi-agent Nash Q-learning algorithm was employed for portfolio construction and updating strategies. This approach yields an optimal project portfolio for each phase of the strategy. Unlike traditional methods that predominantly focus on cumulative returns and find it challenging to accommodate strategic shifts, our proposed technique prioritizes intertwined strategic returns. It promotes project choices in tune with strategic contexts and supports ongoing adjustments to project strategies, providing invaluable guidance for decision makers. A comparison of our proposed method with other optimization strategies validated its superior performance. Furthermore, the case study described in this study confirms that our method promotes project choices in tune with strategic contexts and supports ongoing adjustments to project strategies, providing invaluable guidance for decision makers.