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
Bibliographic record
Abstract
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 (R2) 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 (R2 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.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot 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.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 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 source (direct Gemma or distilled Codex), 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".