MétaCan
Menu
← Back to cohort
Record W3170966223 · doi:10.5194/egusphere-egu21-8609

Integration of Hidden Markov States in a hydrological model calibration/validation protocol

2021· article· en· W3170966223 on OpenAlexaff
Étienne Guilpart, Vahid Espanmanesh, Amaury Tilmant, François Anctil

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldEnvironmental Science
TopicHydrology and Watershed Management Studies
Canadian institutionsUniversité Laval
Fundersnot available
KeywordsClimate changeCalibrationComputer scienceClimate modelMarkov chainSeries (stratigraphy)Environmental scienceSample (material)Hidden Markov modelClimatologyHydrology (agriculture)StatisticsArtificial intelligenceMathematicsMachine learningGeology

Abstract

fetched live from OpenAlex

Due to climate changes, the stationary assumption in hydrology has become obsolete. Moreover, the uncertainty regarding the future evolution of the Earth's climate and its impact on flow regimes is still large. Over the last decade, new risk management approaches have been proposed to support water resources planning under deep uncertainty. Those approaches rely at some point on a hydrological model to derive time series of streamflows for various hydro-climatic scenarios. One of the key issue is to make sure that the hydrological model is robust, i.e. that it performs well over contrasted hydro-climatic conditions. The differential split-sample test principle proposed by Klemes in 1986 recommends partitioning the time series into numerous and independent subperiods with different stationary climate features. Then, the hydrological model calibration is achieved on a specific climate period, and the validation on other(s). Classical detection methods commonly used to partition the times series, such as Mann-Kendall test or Pettitt test, can only detect a single change point, and thus are unable to handle complex climate sequences with multiple change points. We propose a calibration/validation protocol of hydrological models which rely on both the differential split-sample test and on an Hidden Markov Model to identify a succession of subsequences in a time series based on the state of the underlying process. We applied the proposed protocol on the Senegal River (West Africa). The hydrological model used is the conceptual GR2M model. Results show that (i) when the river discharges time series does not display a clear climate trend, and have multiple change points, classical rupture tests are not suitable. Hidden Markov Models are a good alternative as long as the climate sub-sequences are long enough (typically around 30 years or more); (ii) including a Hidden Markov Models in such protocol open up the range of possibilities for calibrate/validate, which can lead to an enhancement of the criterion function (but not necessarily). Klemes, V.: Operational testing of hydrological simulation models, Hydrological Sciences Journal, 31, 13-24, 415 https://doi.org/10.1080/02626668609491024, 1986.

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 machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.033
metaresearch head score (Gemma)0.064
Version: metacan-v3-hybrid-931329e0061cValidation 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: Methods · Consensus signal: Methods
Teacher disagreement score0.033
Threshold uncertainty score0.177

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0330.064
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0020.001
Science and technology studies0.0010.002
Scholarly communication0.0020.005
Open science0.0030.005
Research integrity0.0020.004
Insufficient payload (model declined to judge)0.0060.002

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 head0.019
GPT teacher head0.263
Teacher spread0.244 · 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

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreMethods

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".

Quick stats

Citations0
Published2021
Admission routes1
Has abstractyes

Explore more

Same topicHydrology and Watershed Management Studies→French-language works237,207→