MétaCan
Menu
Back to cohort
Record W6948035955 · doi:10.48336/azar-yx75

Coupling of multi-agent based simulation and particle swarm optimization for environmental planning and decision making

2022· article· en· W6948035955 on OpenAlex

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.
aboutThe title or abstract carries a Canadian signal from the geographic lexicon.

Bibliographic record

VenueMemorial University Research Repository (Memorial University) · 2022
Typearticle
Languageen
FieldChemistry
TopicWood and Agarwood Research
Canadian institutionsMemorial University of Newfoundland
Fundersnot available
KeywordsParticle swarm optimizationConvergence (economics)Multi-swarm optimizationProcess (computing)ComputationCoupling (piping)Swarm behaviour

Abstract

fetched live from OpenAlex

Environmental design making modeling is a vital part in environmental decision making process to help to conclude which decisions should be made and how to find alternatives for each decision. However, the complicated circumstances, massive data, uncertainties and multiple criteria standards make the decision-making process sophisticated and hard to realize. This research focused on developing new environmental modelling methods by dynamic coupling of agent based modelling (ABM) and a multi-agent system (MAS) with PSO optimization algorithm and other kinds of traditional environmental simulation models for supporting environmental engineering decision making. Firstly, a novel multi-agent hybrid particle swarm optimization (MAHPSO) approach was developed for a wastewater treatment plant network design. A hybrid particle swarm optimization module was proposed to account for both continuous and binary variables, and then integrated with the concept of multi-agent to enhance solution convergence and stability. The feasibility and effectiveness of method was tested and demonstrated by a case based on the wastewater treatment plants network of the city of St. John’s, Canada. The results were compared with those of the traditional GA approach and the HPSO method. The proposed MAHPSO approach was approved to be capable of significantly enhancing solution convergence without sacraficing the computation time/efficiency, and of providing optimal results with high accuracy and repeatability. The approach could be used as an effective evolutionary algorithm for complex system optimization and planning problems in environmental and other fields. Secondly, a simulation-based multi-agent particle swarm optimization (SA-PSO) approach was developed for supporting dynamic decision making in offshore oil spill responses. The ABM as an emerging simulation method was introduced into oil spill responses in the first time to simulate the response actions with consideration of dynamic interactions among individual devices and/or response centre. A PSO method was further adopted to optimize the allocation of response devices/vessels among spill sites and warehouses with minimal total cost and time. Through a hypothetical oil spill case, the proposed SA-PSO approach showed strong capability and efficiency in reducing response time and optimizing responses. The results indicated that the proposed SA-PSO approach could efficently decrease the total response time, and dynamically optimize the allocation of response equipment. It had the strong potential to be applied to decision making problems in environmental and other fields. This research developed two new modeling methods for supporting WWTP network designs and oil spill responses, respectively. The results of two case studies demonstrated the value of the integration of emerging artificial intelligence approaches with traditional environmental simulation models for facilitating environmental engineering and management.

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.

Full frame distilled prediction

Teacher imitation

Not 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.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesScience and technology studies
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.055
Threshold uncertainty score0.999

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0020.000
Scholarly communication0.0000.000
Open science0.0000.001
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

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.

Opus teacher head0.047
GPT teacher head0.294
Teacher spread0.247 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it