Dynamic Bayesian Networks to Assess Anthropogenic and Climatic Drivers of Saltwater Intrusion: A Decision Support Tool Toward Improved Management
Bibliographic record
Abstract
Abstract Saltwater intrusion (SWI) is a global coastal problem caused by aquifer overpumping, land-use change, and climate change impacts. Given the complex pathways that lead to SWI, coastal urban areas with poorly monitored aquifers are in need of probabilistic-based decision support tools that can assist in better understanding and predicting SWI, while exploring effective means for sustainable aquifer management. In this study, we develop a Bayesian Belief Network (BBN) to account for the complex interactions of climatic and anthropogenic processes leading to SWI, while relating the severity of SWI to associated socioeconomic impacts and possible adaptation strategies. The BBN is further expanded into a Dynamic Bayesian Network (DBN) to assess the temporal progression of SWI and account for the compounding uncertainties over time. The proposed DBN is then tested at a pilot coastal aquifer underlying a highly urbanized water-stressed metropolitan area along the Eastern Mediterranean coastline (Beirut, Lebanon). The results show that the future impacts of climate change are largely secondary when compared to the persistent water deficits. While both supply and demand management could halt the progression of salinity, the potential for reducing or reversing SWI is not evident. The indirect socioeconomic burden associated with aquifer salinity was observed to improve, albeit heterogeneously, with the application of various adaptation strategies; however, this was at a cost associated with the implementation and operation of these strategies. The proposed DBN acts as an effective decision support tool that can promote sustainable aquifer management in coastal regions through its robust representation of the main drivers of SWI and linking them to expected socioeconomic burdens and management options. Integr Environ Assess Manag 2021;17:202–220. © 2020 SETAC KEY POINTS A Dynamic Bayesian Network (DBN) was developed to assess the temporal progression of saltwater intrusion in a coastal aquifer through time-slicing and the inclusion of temporal clones. The DBN consisted of multiple variables categorized into 4 components, namely a climate component, a hydrogeological component, a demographic component, and a socioeconomic component. The DBN results showed that the impacts of climate change were secondary when compared to persistent water deficits in the study area. Both supply and demand management were able to halt the progression of salinity but not reverse it. The developed DBN proved to be an effective decision support tool for promoting sustainable aquifer management in coastal regions through its robust representation of the main drivers of saltwater instrusion (SWI) and linking them to expected socioeconomic burdens and management options.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.002 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".