MétaCan
Menu
Back to cohort
Record W4395676539 · doi:10.2166/ws.2024.092

Hybrid modeling of karstic springs: Error correction of conceptual reservoir models with machine learning

2024· article· en· W4395676539 on OpenAlex
Najim Bouhafa, Charlotte Sakarovitch, Laura Lalague, F. Goulard, Alexandre Pryet

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.

Bibliographic record

VenueWater Science & Technology Water Supply · 2024
Typearticle
Languageen
FieldEarth and Planetary Sciences
TopicKarst Systems and Hydrogeology
Canadian institutionsUniversité Laval
FundersAgence Nationale de la Recherche
KeywordsKarstConceptual modelHydrology (agriculture)Computer scienceGeologyArtificial intelligenceEnvironmental scienceMachine learningGeotechnical engineering

Abstract

fetched live from OpenAlex

ABSTRACT Accurate spring discharge modeling and prediction is crucial for water management, helping authorities optimize use, manage variability, and prepare for droughts. Developing reliable simulation and forecasting tools is essential for effective management of groundwater resources from karstic springs. Although hybrid modeling approaches have been explored in hydrology, their application to spring discharge modeling is underexplored. Previous studies have focused on conceptual/distributed or data-driven models separately, missing the potential advantages of combining them. This creates a research gap in exploring the benefits of hybrid models for spring discharge. This study developed a hybrid model combining a conceptual GR5J model with Random Forests to simulate spring discharge from Bordeaux's largest karst aquifer. Model performance was assessed through comparison with the individual GR5J, RF, and benchmark models (weekly average of observed values). The hybrid model outperformed all models. Evaluation using actual meteorological data found the hybrid model achieved the highest accuracy by reducing GR5J simulation errors by 22%. When considering meteorological uncertainty, the hybrid model outperformed the individual GR5J, RF and benchmark models by 11, 30 and 47% respectively. The study findings suggest combining conceptual and machine learning approaches can improve spring discharge simulations, opening promising opportunities for enhanced forecasting in karst aquifers.

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 categoriesnone
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 score0.138
Threshold uncertainty score0.802

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0010.001
Science and technology studies0.0000.002
Scholarly communication0.0000.001
Open science0.0010.000
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 head0.014
GPT teacher head0.204
Teacher spread0.190 · 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