Water quality is intimately related to the livelihood of the numerous people, and affects the development and operating benefits of various industries in society. This study clarifies the effects of human-driven economic activities on inland water quality in Hainan Island, and reveals relationships between water quality and tourism on the island. Based on previously monitored data, this study uses a static Bayesian network and radial basis function neural network (RBFNN) to model and predict the future water quality. From 2012 to 2015, water quality in the Nandu, Wanquan and Changhua Rivers was good (at level II, GB3838-2002). The static Bayesian network demonstrated that Gross Output Value (GOV) of agriculture, GOV of fishery, GOV of animal husbandy and chemical oxygen demand (COD) discharge will significantly affect water quality in the Nandu and Changhua Rivers. The effect of tourism on water quality in Wanquan River was significantly higher than that on the Nandu and Changhua Rivers. In the Wanquan River, the DO content fluctuated greatly in comparison to the other two rivers, and unexpectedly, increased tourism led to higher DO values. However, it remains necessary to closely monitor negative changes in water quality due to tourism, especially in Wanquan River and eastern Hainan province. The developed RBFNN showed that the changes in water quality were predicted accurately in comparison with experimental values in the present study and the water quality also is continuously improving. Overall, results suggest that current anthropogenic socioeconomic activities had a modest effect on water quality in Hainan Island. Agriculture, fishery, animal husbandy and COD discharge were relatively important factors affecting water quality, while tourism had a perceptible effect in eastern Hainan. Our findings provide a reference for the balance of water quality, people’s livelihood and economic development (tourism and port construction) in Hainan province.
Abstract:the model was established, it was the dynamic knowledge model of suiting soybean varieties, variety selection and variety sowing time determinationExperimental data. the knowledge model was verified through six different ecological points of Inner Mongolia and different varieties data. The results show that the model has a better decision-making and universal application.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.