Using Bayesian networks for environmental health risk assessment

Capturing and quantifying the aggregate effects of multi-source factors affecting miners' health and well-being: Construction of Bayesian belief networks

Factors originating at the organizational, work, and individual levels are closely interrelated and intricately intertwined, affecting health rates. There was limited research on the interdependence and aggregate effects between multi-source factors and occupational health and well-being (OHW). It is challenging to achieve management goals. Therefore, considering cross-level factors and across the "work environment-stress-exposure-OHW" chain, individual vulnerability was considered. A Fuzzy Bayesian Belief Network (FBBN) driven by both domain knowledge and data was constructed to carve out the logic between multi-source factors and OHW. Workers from four coal mines were surveyed twice in 6 months. 714 valid samples were included in the analysis. The interdependencies among multi-source factors were identified by the Interpretive Structure Modeling method and the visual probability estimation was achieved based on FBBN. It revealed that the work and the organizational level were the root factors. Eight factors involved in work stress were mainly mediating, and actual exposure and individual vulnerability were direct factors. Pathway interventions and joint interventions were proposed. The prediction ability and scheme feasibility of FBBN were verified. The approach developed allows robust assessments of aggregate effects and obtains multi-source factor importance. This study provides vital insights and evaluation tools for understanding workplace stress and OHW management.

Mapping health vulnerability to short-term summer heat exposure based on a directional interaction network: Hotspots and coping strategies

Health risk resulting from non-optimal temperature exposure, referred to as "systematic risk", has been a sustainable-development challenge in the context of global warming. Previous studies have recognized interactions between and among system components while assessing the vulnerability to climate change, but have left open the question of indicator directional interactions. The question is important, not least because indicator directional association analysis provides guidance to address climate risks by revealing the key nodes and pathways. The purpose of this work was to assess health vulnerability to short-term summer heat exposure based on a directional interaction network. Bayesian network model and network analysis were used to conduct a directional interaction network. Using indicator directional associations as weights, a weighted technique for the order of preference by similarity to ideal solution method was then proposed to assess heat-related health vulnerability. Finally, hotspots and coping strategies were explored based on the directional interaction network and health vulnerability assessments. The results showed that (1) indicator directional interactions were revealed in the health vulnerability framework, and the interactions differed between northern and southern China; (2) there was a dramatic spatial imbalance of health vulnerability in China, with the Beijing-Tianjin-Hebei Region and the Yangtze River Basin identified as hotspots; (3) particulate matter and ozone were recognized as priority indicators in the most vulnerable cities of northern China, while summer heat exposure level and variation were priority indicators in southern China; and (4) adaptive capacity could alter the extent of risk; thus, mitigation and adaptation should be implemented in an integrated way. Our study has important implications for strengthening the theoretical basis for the vulnerability assessment framework by providing indicator directional associations and for guiding policy design in dealing with heat-related health vulnerability in China.

Contribution of Bayesian networks as a robust tool in risk assessment under sustainability considerations, a case study of Bandarabbas refinery

Background and purpose

Refineries are among the industrial centers that supply the energy and raw materials to downstream industries. To achieve sustainable development goals, creating appropriate balance between economical and environmental goals has always been the focus of managers and policy makers in the societies. Bayesian Network model has become a robust tool in the field of risk assessment and uncertainty management in refineries. The focus of this research is to prioritizing different units from the point of view of social and ecological aspects for facilitating the decision making process in the context of waste material treatment in Bandarabbas refinery in line with the sustainable development goals.

Materials and methods

The methodology of this research is based on risk assessment with the aid of Bayesian Networks. To this end, first material flow analysis of the processes procured risk identification, subsequently influence diagram and Bayesian Network structure were designed. After completing conditional probability tables, finally risk factors were prioritized. What is more, sensitivity analysis of the model performed by applying three approaches namely predictive, diagnostic, and considering only one risk.

Conclusion

According to the risk assessment results, Amine treatment and Fuel units were classified as the most significant risk factors, whereas Pipelines and Plant air & instrument air system were identified as the most environmental friendly units. In addition, sensitivity analysis of the model provided appropriate framework to shed some light on the circumstances of determining dominant risk factors whether only one or concurrently all of the endpoints are evaluated.

A New Wearable System for Sensing Outdoor Environmental Conditions for Monitoring Hyper-Microclimate

The rapid urbanization process brings consequences to urban environments, such poor air quality and the urban heat island issues. Due to these effects, environmental monitoring is gaining attention with the aim of identifying local risks and improving cities’ liveability and resilience. However, these environments are very heterogeneous, and high-spatial-resolution data are needed to identify the intra-urban variations of physical parameters. Recently, wearable sensing techniques have been used to perform microscale monitoring, but they usually focus on one environmental physics domain. This paper presents a new wearable system developed to monitor key multidomain parameters related to the air quality, thermal, and visual domains, on a hyperlocal scale from a pedestrian’s perspective. The system consisted of a set of sensors connected to a control unit settled on a backpack and could be connected via Wi-Fi to any portable equipment. The device was prototyped to guarantee the easy sensors maintenance, and a user-friendly dashboard facilitated a real-time monitoring overview. Several tests were conducted to confirm the reliability of the sensors. The new device will allow comprehensive environmental monitoring and multidomain comfort investigations to be carried out, which can support urban planners to face the negative effects of urbanization and to crowd data sourcing in smart cities.