A hybrid SVR-BO model for predicting the soil thermal conductivity with uncertainty
Bibliographic record
Abstract
This study proposes a generalised framework for developing a hybrid machine learning (ML) model that combines support vector regression (SVR) with hyperparameter optimisation to predict thermal conductivity ( k) with uncertainty. The framework contains four phases: data pre-processing, determining the best-performing hybrid model, selecting the optimal input combination, and uncertainty implementation. A database containing 2197 data points is first compiled to train the ML model. Three hyperparameter optimisation algorithms are adopted to tune hyperparameters, and their performance is evaluated by model evaluation metrics. Results show that SVR with Bayesian optimisation (SVR-BO) is the best-performing model since it produces more accurate predictions for k than models that employ grid and random searches. Given the sample insufficiency issue encountered in practice, the SVR-BO models with 144 input combinations are analysed. The compassion among models under various input combinations indicates that incorporating temperature as an additional input can provide moderate improvement in the accuracy and generalisability of the hybrid model. Based on the comparison, a five-input model is selected as the best candidate to implement the uncertainty evaluation for k. Results demonstrate that the predicted k possesses higher reliability for denser datasets and shows promising potential for applications in k with uncertainty assessments.
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 | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| 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".