Modeling prevention behaviors during the COVID-19 pandemic using Bayesian belief networks and protection motivation theory.

Prevention behaviors are important in mitigating the transmission of COVID-19. The protection motivation theory (PMT) links perceptions of risk and coping ability with the act of adopting prevention behaviors. The goal of this research is to test the application of the PMT in predicting adoption of prevention behaviors during the COVID-19 pandemic. Two research objectives are achieved to explore motivating factors for adopting prevention behaviors. (1) The first objective is to identify variables that are strong predictors of prevention behavior adoption. A data-driven approach is used to train Bayesian belief network (BBN) models using results of a survey of N = 7797 $N=7797$ participants reporting risk perceptions and prevention behaviors during the COVID-19 pandemic. A large set of models are generated and analyzed to identify significant variables. (2) The second objective is to develop models based on the PMT to predict prevention behaviors. BBN models that predict prevention behaviors were developed using two approaches. In the first approach, a data-driven methodology trains models using survey data alone. In the second approach, expert knowledge is used to develop the structure of the BBN using PMT constructs. Results demonstrate that trust and experience with COVID-19 were important predictors for prevention measure adoption. Models that were developed using the PMT confirm relationships between coping appraisal, threat appraisal, and protective behaviors. Data-driven and PMT-based models perform similarly well, confirming the use of PMT in this context. Predicting adoption of social distancing behaviors provides insight for developing policies during pandemics.

Operationalizing a fisheries social-ecological system through a Bayesian belief network reveals hotspots for its adaptive capacity in the southern North sea.

Fisheries social-ecological systems (SES) in the North Sea region confront multifaceted challenges stemming from environmental changes, offshore wind farm expansion, and marine protected area establishment. In this paper, we demonstrate the utility of a Bayesian Belief Network (BN) approach in comprehensively capturing and assessing the intricate spatial dynamics within the German plaice-related fisheries SES. The BN integrates ecological, economic, and socio-cultural factors to generate high-resolution maps of profitability and adaptive capacity potential (ACP) as prospective management targets. Our analysis of future scenarios, delineating changes in spatial constraints, economics, and socio-cultural aspects, identifies factors that will exert significant influence on this fisheries SES in the near future. These include the loss of fishing grounds due to the installation of offshore wind farms and marine protected areas, as well as reduced plaice landings due to climate change. The identified ACP hotspots hold the potential to guide the development of localized management strategies and sustainable planning efforts by highlighting the consequences of management decisions. Our findings emphasize the need to consider detailed spatial dynamics of fisheries SES within marine spatial planning (MSP) and illustrate how this information may assist decision-makers and practitioners in area prioritization. We, therefore, propose adopting the concept of fisheries SES within broader integrated management approaches to foster sustainable development of inherently dynamic SES in a rapidly evolving marine environment.

Climate risk analysis of low-altitude tea gardens in central Taiwan using a Bayesian network.

Tea is a vital agricultural product in Taiwan. Due to global warming, the increasing extreme weather events have disrupted tea garden conditions and caused economic losses in agriculture. To address these challenges, a comprehensive tea garden risk assessment model, a Bayesian network (BN), was developed by considering various factors, including meteorological data, disaster events, tea garden environment (location, altitude, tea tree age, and soil characteristics), farming practices, and farmer interviews, and constructed risk assessment indicators for tea gardens based on the climate change risk analysis concept from the Intergovernmental Panel on Climate Change Fifth Assessment Report (IPCC AR5). The results demonstrated an accuracy of over 92% in both validating and testing the model for tea tree damage and yield reduction. Sensitivity analysis revealed that tea tree damage and yield reduction were mutually influential, with weather, fertilization, and irrigation also impacting tea garden risk. Risk analysis under climate change scenarios from various global climate models (GCMs) indicated that droughts may pose the highest risk with up to 41% and 40% of serious tea tree growth damage and tea yield reduction, respectively, followed by cold events that most tea gardens may have less than 20% chances of serious impacts on tea tree growth and tea yield reduction. The impacts of heavy rains get the least concern because all five tea gardens may not be affected in terms of tea tree growth and tea yield with large chances of 67 to 85%. Comparing farming methods, natural farming showed lower disaster risk than conventional and organic approaches. The tea plantation risk assessment model can serve as a valuable resource for analyzing and offering recommendations for tea garden disaster management and is used to assess the impact of meteorological disasters on tea plantations in the future.

Bayesian belief network modelling approach for predicting and ranking risk factors for malaria infections among children under 5 years in refugee settlements in Uganda.

BACKGROUND: Malaria risk factors at household level are known to be complex, uncertain, stochastic, nonlinear, and multidimensional. The interplay among these factors, makes targeted interventions, and resource allocation for malaria control challenging. However, few studies have demonstrated malaria's transmission complexity, control, and integrated modelling, with no available evidence on Uganda's refugee settlements. Using the 2018-2019 Uganda's Malaria Indicator Survey (UMIS) data, an alternative Bayesian belief network (BBN) modelling approach was used to analyse, predict, rank and illustrate the conceptual reasoning, and complex causal relationships among the risk factors for malaria infections among children under-five in refugee settlements of Uganda. METHODS: In the UMIS, household level information was obtained using standardized questionnaires, and a total of 675 children under 5 years were tested for malaria. From the dataset, a casefile containing malaria test results, demographic, social-economic and environmental information was created. The casefile was divided into a training (80%, n = 540) and testing (20%, n = 135) datasets. The training dataset was used to develop the BBN model following well established guidelines. The testing dataset was used to evaluate model performance. RESULTS: Model accuracy was 91.11% with an area under the receiver-operating characteristic curve of 0.95. The model's spherical payoff was 0.91, with the logarithmic, and quadratic losses of 0.36, and 0.16 respectively, indicating a strong predictive, and classification ability of the model. The probability of refugee children testing positive, and negative for malaria was 48.1% and 51.9% respectively. The top ranked malaria risk factors based on the sensitivity analysis included: (1) age of child; (2) roof materials (i.e., thatch roofs); (3) wall materials (i.e., poles with mud and thatch walls); (4) whether children sleep under insecticide-treated nets; 5) type of toilet facility used (i.e., no toilet facility, and pit latrines with slabs); (6) walk time distance to water sources (between 0 and 10 min); (7) drinking water sources (i.e., open water sources, and piped water on premises). CONCLUSION: Ranking, rather than the statistical significance of the malaria risk factors, is crucial as an approach to applied research, as it helps stakeholders determine how to allocate resources for targeted malaria interventions within the constraints of limited funding in the refugee settlements.

Nexus between drivers of COVID-19 and country risks.

COVID-19 has disrupted all spheres of life, including country risk regarding the exposure of economies to multi-dimensional risk drivers. However, it remains unexplored how COVID-19 has impacted different drivers of country risk in a probabilistic network setting. This paper uses two datasets on country-level COVID-19 and country risks to explore dependencies among associated drivers using a Bayesian Belief Network model. The drivers of COVID-19 risk, considered in this paper, are hazard and exposure, vulnerability and lack of coping capacity, whereas country risk drivers are economic, financing, political, business environment and commercial risks. The results show that business environment risk is significantly influenced by COVID-19 risk, whereas commercial risk (demand disruptions) is the least important factor driving COVID-19 and country risks. Further, country risk is mainly influenced by financing, political and economic risks. The contribution of this study is to explore the impact of various drivers associated with the country-level COVID-19 and country risks in a unified probabilistic network setting, which can help policy-makers prioritize drivers for managing the two risks.

Prioritizing Multidimensional Interdependent Factors Influencing COVID-19 Risk.

COVID-19 has significantly affected various industries and domains worldwide. Since such pandemics are considered as rare events, risks associated with pandemics are generally managed through reactive approaches, which involve seeking more information about the severity of the pandemic over time and adopting suitable strategies accordingly. However, policy-makers at a national level must devise proactive strategies to minimize the harmful impacts of such pandemics. In this article, we use a country-level data-set related to humanitarian crises and disasters to explore critical factors influencing COVID-19 related hazard and exposure, vulnerability, lack of coping capacity, and the overall risk for individual countries. The main contribution is to establish the relative importance of multidimensional factors associated with COVID-19 risk in a probabilistic network setting. This study provides unique insights to policy-makers regarding the identification of critical factors influencing COVID-19 risk and their relative importance in a network setting.

Towards sustainable forestry: Using a spatial Bayesian belief network to quantify trade-offs among forest-related ecosystem services.

Assessing trade-offs among ecosystem services (ESs) that are provided by forests is necessary to support decision-making and to minimize negative effects of timber harvesting. In this study, we examined how spatial data, forest operational rules, ESs, and probabilistic statistics can be combined into a practical tool for trade-off analysis that could guide decision-making towards sustainable forestry. Our main goal was to analyze trade-offs among the wood provisioning ES and other forest ESs at the landscape level using a Bayesian belief network (BBN). We used LiDAR data to derive four ES layers as inputs to a spatial BBN: (i) wood provisioning; (ii) erosion regulating; (iii) climate regulating; and (iv) habitat supporting. We quantified operational constraints with four forest operational rules (FOR) that were defined in terms of: (i) potential harvest block size; (ii) distance between a small potential harvest block and a larger harvest block; (iii) gross merchantable volume (GMV); and (iv) distance to an existing resource road. Maps of the most probable trade-off classes between the wood provisioning ES and other ESs enabled us to identify areas where timber harvesting should be avoided or where timber harvesting should have a very low negative effect on other ESs. Even with our most restrictive management scenario, the total GMV that could be harvested met the annual allowable cut (AAC) volume required to meet sustainable forestry objectives. Through our study, we demonstrated that high-resolution spatial data could be used to quantify trade-offs among wood provisioning ES and other forest-related ESs and to simulate small changes in ES indicators within the BBN. We also demonstrated the potential to evaluate management scenarios to reduce trade-offs by considering FOR as inputs to the BBN. Maps of the most probable trade-off classes among two or three ESs under operational constraints provide key information to guide forest management decision-making towards sustainable forestry.

A Bayesian Modelling Framework for Integration of Ecosystem Services into Freshwater Resources Management.

Models of ecological response to multiple stressors and of the consequences for ecosystem services (ES) delivery are scarce. This paper describes a methodology for constructing a BBN combining catchment and water quality model output, data, and expert knowledge that can support the integration of ES into water resources management. It proposes "small group" workshop methods for elucidating expert knowledge and analyses the areas of agreement and disagreement between experts. The model was developed for four selected ES and for assessing the consequences of management options relating to no-change, riparian management, and decreasing or increasing livestock numbers. Compared with no-change, riparian management and a decrease in livestock numbers improved the ES investigated to varying degrees. Sensitivity analysis of the expert information in the BBN showed the greatest disagreements between experts were mainly for low probability situations and thus had little impact on the results. Conversely, in our applications, the best agreement between experts tended to occur for the higher probability, more likely, situations. This has implications for the practical use of this type of model to support catchment management decisions. The complexity of the relationship between management measures, the water quality and ecological responses and resulting changes in ES must not be a barrier to making decisions in the present time. The interactions of multiple stressors further complicate the situation. However, management decisions typically relate to the overall character of solutions and not their detailed design, which can follow once the nature of the solution has been chosen, for example livestock management or riparian measures or both.

The Role of Different Types of Actors In The Future of Sustainable Agriculture In a Dutch Peri-urban Area.

Peri-urban areas support a broad range of multifunctional demands for public goods. In northwest Europe, peri-urban areas tend to overlap with intensive agricultural land, resulting in conflicts between agricultural use and the public good demands of residents. Sustainable intensification (SI) of agriculture might help reconcile agricultural and well-being goals, but it is unclear how the mix of actors in a peri-urban setting can trigger or restrain SI. In a Dutch case study, we explored how SI of agriculture can contribute to making peri-urban areas more sustainable, and which actors are key enabling factors for implementing SI. We used interviews, surveys, workshops, and empirical analysis to obtain insight into the stakeholder's vision of a sustainable future for the case study area, the farming system and actor network. We integrated these insights in a Bayesian Belief Network, where we linked the actor network to implementation of three SI measures (farm-level efficiency measures, small landscape elements, and direct sales), and used sensitivity analysis to model effects of support for implementation by different groups of actors. The case study has a dense stakeholder network, where, dependent on the SI measure, farmers are triggered by all actors to implement SI, or have a stronger role in uptake themselves. The sensitivity analysis suggested that the future preferred by the stakeholders requires broad support of all actors involved, with local actors without a formal role being essential for uptake. Overall, trade-offs among public goods are almost inevitable when taking up SI measures.

Integrated methods and scenarios for assessment of sand dunes ecosystem services.

Anthropogenic and natural ecosystems in coastal dunes provide considerable benefits to human well-being. However, to date, we still lack a good understanding of how ecosystem services (ES) supply varies from young dunes (e.g., embryo and fore dunes) to mature dunes (e.g., brown and red dunes). This study proposed a novel modelling methodology by integrating an expert-based matrix, a Bayesian Belief Network (BBN), a structural equation model, and a scenario development method. It aims at evaluating dune ecosystem services for the sustainable development of coastal areas. The model was tested using data collected from dunes in Vietnam. An expert-based matrix to assess the supply capacity of 18 ES in different types of dunes was generated with the participation of 21 interdisciplinary scientists. It was found that red dune ecosystems could supply the most regulation and cultural ecosystem services, while gray dunes provided the least amount. Results from a scenario analysis recommended that decision-making is able to optimize multiple ES by: (i) keeping embryo/fore dunes in their natural state instead of using them for mineral mining and urbanization; (ii) enlarging certified and protected forests areas in gray and yellow dunes; and (iii) optimizing cultural ES supply in red dunes.

Uncertainty analysis of the performance of a management system for achieving phosphorus load reduction to surface waters.

The recent re-eutrophication of Lake Erie suggests an inadequate phosphorus management system that results in excessive loads to the lake. In response, governments in Canada and the U.S. have issued a new policy objective: 40% reductions in total phosphorus (TP) and dissolved reactive phosphorus (DRP) loads relative to 2008. The International Organization for Standardization (ISO) 31000 is a risk management standard. One of its analytical tools is the ISO 31010:2009 Bowtie Risk Analysis Tool, a tool that structures the cause-effect-impact pathway of risk but lacks the ability to capture the probability of reducing risk associated with different management systems. Here, we combined the Bowtie Risk Analysis Tool with a Bayesian belief network model to analyze the probability of different agricultural management systems of best management practices (BMPs) to achieve the 40% reductions in TP and DRP loads using different adoption rates. The commonly used soil conservation BMPs (e.g., reduced tillage) have a low probability of reducing TP and DRP to achieve the policy objective; while it can achieve the TP load reduction objective at increased adoptions rates >40%, it does not achieve the DRP load reduction objective, and in fact has the unintended consequence of increasing DRP loads. If decision makers continue to rely on soil conservation BMPs, the trade-offs between meeting objectives of different forms of phosphorus will require deciding whether the management priority is to achieve 40% load reduction objectives or to prevent further increases in DRP loads, the identified culprit causing the repeated algal blooms. In contrast, TP- and DRP-effective BMPS had higher probabilities of achieving the policy objective, especially at increased adoption rates >20%. The integration of Bayesian belief networks with the ISO risk management standard allows decision makers to determine the most probable outcomes of their management decisions, and to track and prepare for less probable outcomes, thereby decreasing the risk of failing to achieve policy objectives.

Exploring sustainable land use in forested tropical social-ecological systems: A case-study in the Wet Tropics.

Tropical countries lie at the nexus of three pressing issues for global sustainability: agricultural production, climate change mitigation and biodiversity conservation. The forces that drive forest protection do not necessarily oppose those that drive forest clearance for development. This decoupling, enhanced by the stronger economic forces compared to conservation, is detrimental for the social-ecological sustainability of forested tropical landscapes. This paper presents an integrated, and spatially-explicit, Agent-Based Model that examines the future impacts of land-use change scenarios on the sustainability of the Wet Tropics region of tropical Queensland, Australia. In particular, the model integrates Bayesian Belief Networks, Geographical Information Systems, empirical data and expert knowledge, under a land-sharing/land-sparing analysis, to study the impact of different landscape configurations on trade-offs and synergies among biodiversity and two ecosystem services (sugarcane production and carbon sequestration). Contrary to most tropical regions, model simulations show that Business As Usual is helping to reconcile these contrasting goals in the forested landscape of the Wet Tropics. The paper analyses which combination of governance and socio-economic factors is causing these positive results. This is an outstanding achievement for a tropical region, considering that most tropical areas are characterized for having stronger economic-land clearing forces compared to conservation forces, which reduce important ecosystem services for human wellbeing and the health of ecosystems.

The science-policy interface of risk-based freshwater and marine management systems: From concepts to practical tools.

Maintaining the current state of ecosystem services from freshwater and marine ecosystems around the world is at risk. Cumulative effects of multiple human pressures on ecosystem components and functions are indicative of residual pressures that "fall through" the cracks of current industry sector management practices. Without an understanding of the level of residual pressures generated by these measures, we are unlikely to reconcile the root causes of ecosystem effects to improve these management practices to reduce their residual pressures. In this paper, we present a new modelling framework that combines a qualitative and quantitative assessments of the effectiveness of the measures used in the daily operations of industry sectors to predict their residual pressure that is delivered to the ecosystem. The predicted residual pressure can subsequently be used as an input variable for ecosystem models. We combine the Bow-tie analysis of the measures with a Bayesian belief network to quantify the effectiveness of the measures and predict the residual pressures.

Predicting arboviral disease emergence using Bayesian networks: a case study of dengue virus in Western Australia.

A Bayesian Belief Network (BBN) for assessing the potential risk of dengue virus emergence and distribution in Western Australia (WA) is presented and used to identify possible hotspots of dengue outbreaks in summer and winter. The model assesses the probabilities of two kinds of events which must take place before an outbreak can occur: (1) introduction of the virus and mosquito vectors to places where human population densities are high; and (2) vector population growth rates as influenced by climatic factors. The results showed that if either Aedes aegypti or Ae. albopictus were to become established in WA, three centres in the northern part of the State (Kununurra, Fitzroy Crossing, Broome) would be at particular risk of experiencing an outbreak. The model can also be readily extended to predict the risk of introduction of other viruses carried by Aedes mosquitoes, such as yellow fever, chikungunya and Zika viruses.

Context Relevant Prediction Model for COPD Domain Using Bayesian Belief Network.

In the last three decades, researchers have examined extensively how context-aware systems can assist people, specifically those suffering from incurable diseases, to help them cope with their medical illness. Over the years, a huge number of studies on Chronic Obstructive Pulmonary Disease (COPD) have been published. However, how to derive relevant attributes and early detection of COPD exacerbations remains a challenge. In this research work, we will use an efficient algorithm to select relevant attributes where there is no proper approach in this domain. Such algorithm predicts exacerbations with high accuracy by adding discretization process, and organizes the pertinent attributes in priority order based on their impact to facilitate the emergency medical treatment. In this paper, we propose an extension of our existing Helper Context-Aware Engine System (HCES) for COPD. This project uses Bayesian network algorithm to depict the dependency between the COPD symptoms (attributes) in order to overcome the insufficiency and the independency hypothesis of naïve Bayesian. In addition, the dependency in Bayesian network is realized using TAN algorithm rather than consulting pneumologists. All these combined algorithms (discretization, selection, dependency, and the ordering of the relevant attributes) constitute an effective prediction model, comparing to effective ones. Moreover, an investigation and comparison of different scenarios of these algorithms are also done to verify which sequence of steps of prediction model gives more accurate results. Finally, we designed and validated a computer-aided support application to integrate different steps of this model. The findings of our system HCES has shown promising results using Area Under Receiver Operating Characteristic (AUC = 81.5%).

Distinct respiratory responses of soils to complex organic substrate are governed predominantly by soil architecture and its microbial community.

Factors governing the turnover of organic matter (OM) added to soils, including substrate quality, climate, environment and biology, are well known, but their relative importance has been difficult to ascertain due to the interconnected nature of the soil system. This has made their inclusion in mechanistic models of OM turnover or nutrient cycling difficult despite the potential power of these models to unravel complex interactions. Using high temporal-resolution respirometery (6 min measurement intervals), we monitored the respiratory response of 67 soils sampled from across England and Wales over a 5 day period following the addition of a complex organic substrate (green barley powder). Four respiratory response archetypes were observed, characterised by different rates of respiration as well as different time-dependent patterns. We also found that it was possible to predict, with 95% accuracy, which type of respiratory behaviour a soil would exhibit based on certain physical and chemical soil properties combined with the size and phenotypic structure of the microbial community. Bulk density, microbial biomass carbon, water holding capacity and microbial community phenotype were identified as the four most important factors in predicting the soils' respiratory responses using a Bayesian belief network. These results show that the size and constitution of the microbial community are as important as physico-chemical properties of a soil in governing the respiratory response to OM addition. Such a combination suggests that the 'architecture' of the soil, i.e. the integration of the spatial organisation of the environment and the interactions between the communities living and functioning within the pore networks, is fundamentally important in regulating such processes.

Assessing regulatory violations of disinfection by-products in water distribution networks using a non-compliance potential index.

Inactivating pathogens is essential to eradicate waterborne diseases. However, disinfection forms undesirable disinfection by-products (DBPs) in the presence of natural organic matter. Many regulations and guidelines exist to limit DBP exposure for eliminating possible health impacts such as bladder cancer, reproductive effects, and child development effects. In this paper, an index named non-compliance potential (NCP) index is proposed to evaluate regulatory violations by DBPs. The index can serve to evaluate water quality in distribution networks using the Bayesian Belief Network (BBN). BBN is a graphical model to represent contributing variables and their probabilistic relationships. Total trihalomethanes (TTHM), haloacetic acids (HAA5), and free residual chlorine (FRC) are selected as the variables to predict the NCP index. A methodology has been proposed to implement the index using either monitored data, empirical model results (e.g., multiple linear regression), and disinfectant kinetics through EPANET simulations. The index's usefulness is demonstrated through two case studies on municipal distribution systems using both full-scale monitoring and modeled data. The proposed approach can be implemented for data-sparse conditions, making it especially useful for smaller municipal drinking water systems.

Risk of fire occurrence in arid and semi-arid ecosystems of Iran: an investigation using Bayesian belief networks.

Identifying areas that have a high risk of burning is a main component of fire management planning. Although the available tools can predict the fire risks, these are poor in accommodating uncertainties in their predictions. In this study, we accommodated uncertainty in wildfire prediction using Bayesian belief networks (BBNs). An influence diagram was developed to identify the factors influencing wildfire in arid and semi-arid areas of Iran, and it was populated with probabilities to produce a BBNs model. The behavior of the model was tested using scenario and sensitivity analysis. Land cover/use, mean annual rainfall, mean annual temperature, elevation, and livestock density were recognized as the main variables determining wildfire occurrence. The produced model had good accuracy as its ROC area under the curve was 0.986. The model could be applied in both predictive and diagnostic analysis for answering "what if" and "how" questions. The probabilistic relationships within the model can be updated over time using observation and monitoring data. The wildfire BBN model may be updated as new knowledge emerges; hence, it can be used to support the process of adaptive management.

Analysis of regional scale risk of whirling disease in populations of Colorado and Rio Grande cutthroat trout using a Bayesian belief network model.

Introduction and spread of the parasite Myxobolus cerebralis, the causative agent of whirling disease, has contributed to the collapse of wild trout populations throughout the intermountain west. Of concern is the risk the disease may have on conservation and recovery of native cutthroat trout. We employed a Bayesian belief network to assess probability of whirling disease in Colorado River and Rio Grande cutthroat trout (Oncorhynchus clarkii pleuriticus and Oncorhynchus clarkii virginalis, respectively) within their current ranges in the southwest United States. Available habitat (as defined by gradient and elevation) for intermediate oligochaete worm host, Tubifex tubifex, exerted the greatest influence on the likelihood of infection, yet prevalence of stream barriers also affected the risk outcome. Management areas that had the highest likelihood of infected Colorado River cutthroat trout were in the eastern portion of their range, although the probability of infection was highest for populations in the southern, San Juan subbasin. Rio Grande cutthroat trout had a relatively low likelihood of infection, with populations in the southernmost Pecos management area predicted to be at greatest risk. The Bayesian risk assessment model predicted the likelihood of whirling disease infection from its principal transmission vector, fish movement, and suggested that barriers may be effective in reducing risk of exposure to native trout populations. Data gaps, especially with regard to location of spawning, highlighted the importance in developing monitoring plans that support future risk assessments and adaptive management for subspecies of cutthroat trout.