Shale wastewater treatment policies recommended by integrated knowledge graph and probability-based algorithms

Shale wastewater (SWW) has received much attention recently due to its non-ignorable threat to the environment and human health. Selection of an appropriate SWW treatment technology or a set of technology combinations could be a challenge particularly when no substantial professional-knowledge (or prior experience) is available. This paper develops a modeling framework integrating knowledge graph (KG) and probability-based recommendation algorithms to produce SWW treatment policies without depending on conventional physically based mathematical models and their associated quantitative data. The model is applied to the shale regions in China, including Chongqing city, the provinces of Sichuan, Yunnan, Guizhou, Shaanxi, and Inner Mongolia Autonomous Region, and utilizes the Monte-Carlo (MC) technique to assess the stability of the output policies. Results show that chemical precipitation, ultrafiltration, membrane bioreactor, and electrodialysis in Knowledge Graph Convolutional Networks (KGCN), as well as ultrafiltration, electrocoagulation, reverse osmosis, and electrocatalytic oxidation in RippleNet, are all preferentially recommended in one scenario, with the MC-based probabilities all higher than 0.86, indicating the stability of recommendation results and robustness of the model. Future studies would focus on improving the current KG and algorithms and offering explanatory mechanisms behind policy recommendations.