An application of Bayesian Belief Networks to assess management scenarios for aquaculture in a complex tropical lake system in Indonesia.
Ontology highlight
ABSTRACT:
SUBMITTER: Yuniarti I
PROVIDER: S-EPMC8051808 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Aquaculture activities are embedded in complex social-ecological systems. However, aquaculture development decisions have tended to be driven by revenue generation, failing to account for interactions with the environment and the full value of the benefits derived from services provided by local ecosystems. Trade-offs resulting from changes in ecosystem services provision and associated impacts on livelihoods are also often overlooked. This paper proposes an innovative application of Bayesian belief networks - influence diagrams - as a decision support system for mediating trade-offs arising from the development of shrimp aquaculture in Thailand. Senior experts were consulted (n?=?12) and primary farm data on the economics of shrimp farming (n?=?20) were collected alongside secondary information on ecosystem services, in order to construct and populate the network. Trade-offs were quantitatively assessed through the generation of a probabilistic impact matrix. This matrix captures nonlinearity and uncertainty and describes the relative performance and impacts of shrimp farming management scenarios on local livelihoods. It also incorporates export revenues and provision and value of ecosystem services such as coastal protection and biodiversity. This research shows that Bayesian belief modeling can support complex decision-making on pathways for sustainable coastal aquaculture development and thus contributes to the debate on the role of aquaculture in social-ecological resilience and economic development.
| S-EPMC3796531 | biostudies-literature
Project description:Grasslands are crucial components of ecosystems. In recent years, owing to certain natural and socio-economic factors, alpine grassland ecosystems have experienced significant degradation. This study integrated the frequency ratio model (FR) and Bayesian belief networks (BBN) for grassland degradation risk assessment to mitigate several issues found in previous studies. Firstly, the identification of non-encroached degraded grasslands and shrub-encroached grasslands could help stakeholders more accurately understand the status of different types of alpine grassland degradation. In addition, the index discretization method based on the FR model can more accurately ascertain the relationship between grassland degradation and driving factors to improve the accuracy of results. On this basis, the application of BBN not only effectively expresses the complex causal relationships among various variables in the process of grassland degradation, but also solves the problem of identifying key factors and assessing grassland degradation risks under uncertain conditions caused by a lack of information. The obtained result showed that the accuracies based on the confusion matrix of the slope of NDVI change (NDVIs), shrub-encroached grasslands, and grassland degradation indicators in the BBN model were 85.27, 88.99, and 74.37%, respectively. The areas under the curve based on the ROC curve of NDVIs, shrub-encroached grasslands, and grassland degradation were 75.39% (P < 0.05), 66.57% (P < 0.05), and 66.11% (P < 0.05), respectively. Therefore, this model could be used to infer the probability of grassland degradation risk. The results obtained using the model showed that the area with a higher probability of degradation (P > 30%) was 2.22 million ha (15.94%), with 1.742 million ha (78.46%) based on NDVIs and 0.478 million ha (21.54%) based on shrub-encroached grasslands. Moreover, the higher probability of grassland degradation risk was mainly distributed in regions with lower vegetation coverage, lower temperatures, less potential evapotranspiration, and higher soil sand content. Our research can provide guidance for decision-makers when formulating scientific measures for alpine grassland restoration.
| S-EPMC8600186 | biostudies-literature
Project description:[This corrects the article DOI: 10.1371/journal.pone.0198678.].
| S-EPMC6042792 | biostudies-literature
Project description:Background Aquaculture systems for giant gourami, Osphronemus goramy Lacepède (1801), have significantly improved fish production yields and food security in Indonesia. However, these systems also cause serious problems in terms of eutrophication in waterbodies. This study analysed the nutrient loading and farm characteristics of giant gourami in floating cages in Lake Maninjau. Method A total of 20 floating cages were used to record these nutrients in feed supply, female and male juvenile fish, dead fish and harvested fish to estimate nutrient loading. Data on the harvested fish, production cycle, stock number and cage capacity were used to estimate the stocking density, feeding rate, feed efficiency, and net fish yield, and the relationship between feed supply and nutrient loading and farm characteristics was analysed by least squares regression methods. Results A total of 20 floating cages released nutrients into waterbodies at an average rate of 236.27±60.44 kg/cycle for C, 84.52±20.86 kg/cycle for N and 8.70±3.63 kg/cycle for P. On average, fish production for each floating cage (±SD) was 1226±282 kg wet weight/cycle, and the net fish yield was 12.63±2.82 kg/m 3/cycle. Survival rates ranged from 86.33 to 95.27%/cycle. The production cycles varied from 160 to 175 days with feed conversion ratios between 1.60 and 1.75, feed conversion efficiencies were between 0.58 and 0.63. The production parameters that had strong relationships with the net fish yield were feed supply ( r 2=0.960), stocking rates ( r 2=0.924) and feeding rates ( r 2=0.961). In contrast, the length of the production cycle was not strongly related to the net fish yield ( r 2=0.187). Conclusion Nutrient loading from the supplied feed was greater than that from the harvested fish, juvenile fish and dead fish. Increasing the net fish yield in floating cages was better predicted by the stocking densities and feeding levels than by the other factors.
| S-EPMC8459621 | biostudies-literature
Project description:Increasing farmers' adoption of sustainable nitrogen management practices is crucial for improving water quality. Yet, research to date provides ambiguous results about the most important farmer-level drivers of adoption, leaving high levels of uncertainty as to how to design policy interventions that are effective in motivating adoption. Among others, farmers' engagement in outreach or educational events is considered a promising leverage point for policy measures. This paper applies a Bayesian belief network (BBN) approach to explore the importance of drivers thought to influence adoption, run policy experiments to test the efficacy of different engagement-related interventions on increasing adoption rates, and evaluate heterogeneity of the effect of the interventions across different practices and different types of farms. The underlying data comes from a survey carried out in 2018 among farmers in the Central Valley in California. The analyses identify farm characteristics and income consistently as the most important drivers of adoption across management practices. The effect of policy measures strongly differs according to the nitrogen management practice. Innovative farmers respond better to engagement-related policy measures than more traditional farmers. Farmers with small farms show more potential for increasing engagement through policy measures than farmers with larger farms. Bayesian belief networks, in contrast to linear analysis methods, always account for the complex structure of the farm system with interdependencies among the drivers and allow for explicit predictions in new situations and various kinds of heterogeneity analyses. A methodological development is made by introducing a new validation measure for BBNs used for prediction.
| S-EPMC9079016 | biostudies-literature
Project description:While some other countries had started their 5G deployment with excellent business use cases, Indonesia is restrained for a moment due to the unreadiness of 5G actors. Several factors which still need attention from 5G actors in Indonesia are telecommunication infrastructures such as spectrum frequency and transport, policy and regulation, innovation ecosystem and social impact. Despite those concerning factors, there are also key drivers that stimulate the 5G deployment in Indonesia. They are demand and needs from end customers, cost reduction and additional revenue stream from mobile network operator, industry automation and country competitive advantage. Two scenarios are built using those key drivers following the scenario-based planning methodology. The scenarios are called The Optimistic Champion and The Wait and Respond.
| S-EPMC7417945 | biostudies-literature
Project description:ObjectiveThis study seeks to develop a fully automated method of generating synthetic data from a real dataset that could be employed by medical organizations to distribute health data to researchers, reducing the need for access to real data. We hypothesize the application of Bayesian networks will improve upon the predominant existing method, medBGAN, in handling the complexity and dimensionality of healthcare data.Materials and methodsWe employed Bayesian networks to learn probabilistic graphical structures and simulated synthetic patient records from the learned structure. We used the University of California Irvine (UCI) heart disease and diabetes datasets as well as the MIMIC-III diagnoses database. We evaluated our method through statistical tests, machine learning tasks, preservation of rare events, disclosure risk, and the ability of a machine learning classifier to discriminate between the real and synthetic data.ResultsOur Bayesian network model outperformed or equaled medBGAN in all key metrics. Notable improvement was achieved in capturing rare variables and preserving association rules.DiscussionBayesian networks generated data sufficiently similar to the original data with minimal risk of disclosure, while offering additional transparency, computational efficiency, and capacity to handle more data types in comparison to existing methods. We hope this method will allow healthcare organizations to efficiently disseminate synthetic health data to researchers, enabling them to generate hypotheses and develop analytical tools.ConclusionWe conclude the application of Bayesian networks is a promising option for generating realistic synthetic health data that preserves the features of the original data without compromising data privacy.
| S-EPMC7973486 | biostudies-literature
Project description:Understanding the determinants of household water treatment (HWT) behavior in developing countries is important to increase the rate of its regular use so that households can have safe water at home. This is especially so when the quality of the water source is not reliable. We present a hierarchical Bayesian Belief Network (BBN) model supported by statistical analysis to explore the influence of household's socio-economic characteristics (SECs) on the HWT behavior via household's psychological factors. The model uses eight SECs, such as mother's and father's education, wealth, and religion, and five RANAS psychological factors, i.e., risk, attitude, norms, ability, and self-regulation to analyse HWT behavior in a suburban area in Palu, Indonesia. Structured household interviews were conducted among 202 households. We found that mother's education is the most important SEC that influences the regular use of HWT. An educated mother has more positive attitude towards HWT and is more confident in her ability to perform HWT. Moreover, self-regulation, especially the attempt to deal with any barrier that hinders HWT practice, is the most important psychological factor that can change irregular HWT users to regular HWT users. Hence, this paper recommends to HWT-program implementers to identify potential barriers and discuss potential solutions with the target group in order to increase the probability of the target group being a regular HWT user.
| S-EPMC7647107 | biostudies-literature
Project description:A recent advancement in modeling was the development of quantum Bayesian networks (QBNs). QBNs generally differ from BNs by substituting traditional Bayes calculus in probability tables with the quantum amplification wave functions. QBNs can solve a variety of problems which are unsolvable by, or are too complex for, traditional BNs. These include problems with feedback loops and temporal expansions; problems with non-commutative dependencies in which the order of the specification of priors affects the posterior outcomes; problems with intransitive dependencies constituting the circular dominance of the outcomes; problems in which the input variables can affect each other, even if they are not causally linked (entanglement); problems in which there may be >1 dominant probability outcome dependent on small variations in inputs (superpositioning); and problems in which the outcomes are nonintuitive and defy traditional probability calculus (Parrondo's paradox and the violation of the Sure Thing Principle). I present simple examples of these situations illustrating problems in prediction and diagnosis, and I demonstrate how BN solutions are infeasible, or at best require overly-complex latent variable structures. I then argue that many problems in ecology and evolution can be better depicted with ecological QBN (EcoQBN) modeling. The situations that fit these kinds of problems include noncommutative and intransitive ecosystems responding to suites of disturbance regimes with no specific or single climax condition, or that respond differently depending on the specific sequence of the disturbances (priors). Case examples are presented on the evaluation of habitat conditions for a bat species, representing state-transition models of a boreal forest under disturbance, and the entrainment of auditory signals among organisms. I argue that many current ecological analysis structures-such as state-and-transition models, predator-prey dynamics, the evolution of symbiotic relationships, ecological disturbance models, and much more-could greatly benefit from a QBN approach. I conclude by presenting EcoQBNs as a nascent field needing the further development of the quantum mathematical structures and, eventually, adjuncts to existing BN modeling shells or entirely new software programs to facilitate model development and application.
| S-EPMC8069849 | biostudies-literature
Project description:BackgroundBayesian networks have been proposed as a way to identify possible causal relationships between measured variables based on their conditional dependencies and independencies. We explored the use of Bayesian network analyses applied to the GAW20 data to identify possible causal relationships between differential methylation of cytosine-phosphate-guanine dinucleotides (CpGs), single-nucleotide polymorphisms (SNPs), and blood lipid trait (triglycerides [TGs]).MethodsAfter initial exploratory linear regression analyses, 2 Bayesian networks analyses were performed. First, we used the real data and modeled the effects of 4 CpGs previously found to be associated with TGs in the Genetics of Lipid Lowering Drugs and Diet Network Study (GOLDN). Second, we used the simulated data and modeled the effect of a fictional lipid modifying drug with 5 known causal SNPs and 5 corresponding CpGs.ResultsIn the real data we show that relationships are present between the CpGs, TGs, and other variables-age, sex, and center. In the simulated data, we show, using linear regression, that no CpGs and only 1 SNP were associated with a change in TG levels, and, using Bayesian network analysis, that relationships are present between the change in TG levels and most SNPs, but not with CpGs.ConclusionsEven when the causal relationships between variables are known, as with the simulated data, if the relationships are not strong then it is challenging to reproduce them in a Bayesian network.
| S-EPMC6157285 | biostudies-literature