With the emphasis on preventing urban flooding and the enhancement of rational urban development, data related to urban flooding are also collected with unbalanced sample size that is a widespread phenomenon in other world fields. The performance of the classification model is compromised by unbalanced datasets, therefore, minority-class samples, floods with higher risk, are often missing alerted or incorrectly warned. To solve this problem, a novel hybrid resampling proposal is proposed in this research proved to be effective for balancing data. First, it optimizes an imbalanced dataset by the Borderline-SMOTE algorithm. Next, alternative datasets are synthesized through under-sampling techniques, whose qualities are evaluated by using information entropy and calculated rely on the k-nearest neighbor entropy estimator. The suggested method not only makes full use of the original data information, but also avoids under-fitting due to the single under-sampling utilization. A practical application in the central area of Zhengzhou, China, combining the resampling proposal and the Random Forest classification model optimized by Genetic Algorithm, the results show that significantly better results are yielded compared without any treatment in terms of all assessment indicators (Accuracy, Recall, G-mean and F1-score) have been improved.

Eco-compensation is an important means to implement the rights and responsibilities of ecological protection and alleviate the water conflicts inside and outside the river. Previous studies focused on water conflicts among users, overlooking the government's regulatory role in the eco-compensation mechanism and the coordinating function of water transfer compensation fees among users. This study constructed a tripartite evolutionary game model involving government regulatory agencies (GRA), in-channel ecological environment water demanders (EEWD), and off-channel socio-economic water users (SEWU). The evolutionary stability strategies (ESS) of the GRA, EEWD, and SEWU and the evolutionary trend of the tripartite system were analyzed using the finite rationality evolutionary game model, and the sensitivity analysis of the influencing factors was conducted using the eigenvalues of the Jacobi matrix and numerical simulation. Taking the Bai River Basin in Nanyang, China, as the case study, the results showed that the GRA's rewards and penalties were controlled within a reasonable range can promote the enthusiasm of the participating subjects in the water quantity compensation mechanism; water quantity compensation standard for the SEWU was an important indicator for the smooth implementation of the compensation mechanism, the loss coefficient and the overall ecological benefit allocation coefficient of the EEWD will influence the formulation of water quantity compensation standards. This suggested that the GRA should enhance the management of the eco-compensation-related policies and laws and regulations, limit the SEWU's eco-compensation standard, and improve the net benefit of EEWD, to achieve the optimal eco-compensation strategy of ''supervision, protection, compensation''. The research results provide a reference value for the formulation of the water quantity eco-compensation mechanism for water use coordination inside and outside the river.

The risk assessment of urban flood disasters (UFRA) is an effective way to prevent urban disasters, which plays an important role in risk management. Urban floods have occurred frequently in recent years, it is necessary to carry out research on UFRA. Considering four main factors: disaster-pregnant, disaster-causing, disaster-forming, and disaster-curing, this paper established a risk assessment model for urban flood disasters. Firstly, constructing a city flood risk assessment index system, and calculating the optimal combination weight (CW) by determining the subjective weight (SW) and objective weight (OW). Secondly, by using the cloud model to reveal the uncertainty relationship between evaluation indexes and level, the comprehensive UFRA was obtained. Rainfall and water information of all kinds of building types could be collected through cloud model and SWMM, the index system of the disaster-causing information by GIS was improved. Taking the 100-year return period rainfall in the central urban area of Zhengzhou City as an example, the comprehensive flood risk level was obtained, and the factors contributing to the risk in each region were analyzed. The results indicated that Jinshui District (JD) was at a high risk level and all other districts in Zhengzhou were at a sub-high risk. This model provides new insights for flood risk management.

High accuracy prediction of urban flood risk is conducive to avoid potential losses, however, it's negatively affected by unbalanced data. Furthermore, ensemble model has been demonstrated to have the ability to improve to prediction accuracy. Nevertheless, the performance of ensemble model is influenced by basic model and ensemble rules, and determining the best ensemble model remains an open issue. To improve the accuracy of flood risk prediction, an approach covering data optimization and ensemble modeling was presented to optimize unbalanced flood data and the selection of various ensemble models based on efficiency and performance. A practical application in Zhengzhou City shows that Borderline-SMOTE2 is the most applicable for optimizing the flood risk data among the state-of-the-art oversampling algorithm utilized, because of the excellent entropy value. The effect of unbalanced data on the performance of the basic models was pervasive according to changes of the common indicators. The optimal ensemble model for flood risk prediction is composed of K-Nearest Neighbor, Decision Tree, Gaussian Naive Bayes and Extreme Gradient Boosting under Stacking rule in the current study. The results of this study supply the valuable reference for the flood prediction and mitigation.

The risk assessment of urban flood disasters (UFRA) is an effective way to prevent urban disasters, which plays an important role in risk management. Urban floods have occurred frequently in recent years, it is necessary to carry out research on UFRA. Considering four main factors: disaster-pregnant, disaster-causing, disaster-forming, and disaster-curing, this paper established a risk assessment model for urban flood disasters. Firstly, constructing a city flood risk assessment index system, and calculating the optimal combination weight (CW) by determining the subjective weight (SW) and objective weight (OW). Secondly, by using the cloud model to reveal the uncertainty relationship between evaluation indexes and level, the comprehensive UFRA was obtained. Rainfall and water information of all kinds of building types could be collected through cloud model and SWMM, the index system of the disaster-causing information by GIS was improved. Taking the 100-year return period rainfall in the central urban area of Zhengzhou City as an example, the comprehensive flood risk level was obtained, and the factors contributing to the risk in each region were analyzed. The results indicated that Jinshui District (JD) was at a high risk level and all other districts in Zhengzhou were at a sub-high risk. This model provides new insights for flood risk management.

Watershed ecological compensation is an effective economic policy measure for water ecology conservation and water environment management. This study constructed an eco-compensation mechanism under the double control of water quality and quantity, which consisted of the water quality control module, the water quantity control module, and the double control compensation value module. The pollution loss water quantity and the river habitat compensation water quantity were calculated, and the water quality achievement or excess and water quantity surplus or deficit were identified to divide the multi-scenario compensation mode and obtain the double control compensation value. The Bai River Basin in Nanyang, China, was selected as the case study, and the double control compensation value of the three counties in the basin was calculated from 2015 to 2018. The results showed that the water quantity compensation value of all counties was higher than the water quality compensation value, indicating that the water quantity has a greater impact on the water environment compared with water quality, and the ecological water demand of rivers needs to be guaranteed while strengthening water pollution treatment. The compensation mode all belonged to the double control mode. The double-control compensation mechanism had a distinct advantage over the single-control compensation, indicating that water quality and quantity should be considered in the compensation programs to maintain healthy ecological conditions in the water supply. The research results provide ideas for the quantification of eco-compensation and the formulation of long-term ecological protection mechanisms.

针对传统内梅罗指数评价方法中存在的不足,利用层次分析法和熵权法主客观组合赋权的方式改进其忽略各污染指标权重对水质产生的影响,并采用修正最大污染指数计算方法削弱最大污染指标的主导作用.最后以南阳市白河为例,利用改进的内梅罗指数法对白河四个监测断面2015-2018年的水质污染指标进行评价,利用反距离权重法对水质等级进行空间变化分析.结果表明,除南阳市卧龙区丁奉店村断面水质每年均为Ⅳ类水,其余断面水质均在Ⅲ类及以上;在水质等级空间分布上无Ⅰ类及Ⅴ类水质等级区域,水质等级时间分布上Ⅲ类水面积有增加的趋势,Ⅳ类水出现的面积逐渐减小,整体水质趋于好转.研究成果能为流域水质污染的评价及排污监管提供依据和参考.

人类社会的发展导致河道水量不断被压缩,严重影响河流生态健康.对此,提出基于南阳市白河流域河流生态水量保护的生态补偿机制,基于Tennant法核算南阳市白河流域生态流量,进而获取河道内亏缺水量;并采用模糊综合评价法,考虑水环境、水资源、社会经济、用水效率多种因素,核算水资源价值,由此得到补偿价值,南阳市区及南召县均以行政区内各行业向河道内补偿为主.白河上下游地区应增强河流保护意识,合理规划河道外供水量,保障河流基本生态需水.

Watershed ecological compensation has important practical significance for water environment management and ecological protection. This study constructed a Pollution Damage – Protection Bidirectional model for eco-compensation (Bidirectional Model), which consisted of the pollution damage compensation module (PDC Module) and the pollution protection compensation module (PPC Module). The pollution damage compensation index (IPDC) and the pollution protection compensation index (IPPC) were calculated separately to obtain the comprehensive compensation value indicator (CI). The Xiaohong River Basin in Zhumadian, China was selected as the case study area, the bidirectional eco-compensation values (including damage compensation value (DCV) and protection compensation value (PCV)) in the four counties in the river basin from 2012 to 2015 were calculated. The results showed that the DCV in each county was greater than the PCV, which belonged to the "up to down" mode, indicating that the current eco-compensation of the river basin focuses on compensation for pollution damage, and water pollution control needs to be strengthened in the future. This research results have broadened the thinking for the quantification of basin eco-compensation and watershed water environment management.

Due to the complexity of ecological compensation standards and methods, some problems cannot be expected before compensation, but the evaluation of eco-compensation effect can feedback the implementation effect of eco-compensation policies and provide reference for the improvement of eco-compensation policies. This paper constructed a comprehensive evaluation index system of eco-compensation, which covered social and economic development, pollution discharge and monitoring, and pollution treatment aspects. An eco-compensation comprehensive evaluation model was established, which consisted of the projection pursuit model (PP model) and the chaotic particle swarm optimization algorithm (CPSO algorithm). The Xiaohong River Basin in China was selected as a case study. Before and after the implementation of eco-compensation policy, the compensation effects in the four counties in the basin from 2008 to 2015 were evaluated. The results showed that through the implementation of the basin eco-compensation policies, the comprehensive indicators in the four counties showed an upward trend, which indicated that the eco-compensation of the basin had achieved certain effects. Among them, Xincai was the best, and could provide reference for other counties. The research results can provide new ideas and new methods for the evaluation of eco-compensation effects.