MétaCan
Menu
Back to cohort
Record W4408948502 · doi:10.3389/fenvs.2025.1543852

Regression-based machine learning models for nitrate and chloride prediction in surface water in a small agricultural sand plain sub-watershed in southwestern Ontario, Canada

2025· article· en· W4408948502 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

VenueFrontiers in Environmental Science · 2025
Typearticle
Languageen
FieldEnvironmental Science
TopicHydrological Forecasting Using AI
Canadian institutionsMinistry of the Environment, Conservation and ParksUniversité du Québec à MontréalUniversity of Guelph
Fundersnot available
KeywordsWatershedNitrateAgricultureHydrology (agriculture)Environmental scienceSurface waterGeologyMachine learningGeographyArchaeologyEnvironmental engineeringEcologyGeotechnical engineeringComputer science

Abstract

fetched live from OpenAlex

Machine learning (ML) models have proven to be an efficient technique for better understanding and quantification of surface water quality, especially in agricultural watersheds where considerable anthropogenic activities occur. However, there is a lack of systematic investigations that can examine the application of different ML regression models in agricultural settings to predict the surface water quality using a group of input variables, including hydrological (e.g., surface flow), meteorological (e.g., precipitation), and field (e.g., crop cover) conditions. In this study, multiple ML regression models, including support vector machine (SVM) and regression trees (RT), were employed on a 2-year dataset collected from a sand plain agricultural sub-watershed in southwestern Ontario, Canada (i.e., Lower Whitemans Creek) to predict the nitrate and chloride concentrations in surface water at nine sampling sites within the sub-watershed. The prediction capabilities of these ML models were determined using a group of evaluation metrics including the coefficient of determination (R 2 ) and root-mean squared error (RMSE). In general, the Gaussian Process Regression (GPR) model was the optimal algorithm to predict the nitrate and chloride concentrations in surface water (R 2 was 0.99 and 0.98 respectively for training and testing). According to the results of a feature importance analysis, it was found that the field conditions (specifically the location of sampling site (main channel or tributary site) and crop cover) were the most crucial model input variables for accurate predictions of the output variables. This study underscores that ML regression models can be implemented to effectively quantify the water quality properties of surface water in agricultural watersheds using easily measurable parameters. These models can assist decision makers in advancing successful actions and steps towards protecting the available surface water resources.

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: Observational · Consensus signal: Observational
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.323
Threshold uncertainty score0.769

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 studies0.0000.000
Scholarly communication0.0000.000
Open science0.0000.000
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 head0.009
GPT teacher head0.174
Teacher spread0.166 · 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