Optimizing neural network architectures for ground temperature prediction in ground source heat pump systems
Bibliographic record
Abstract
Ground source heat pump (GSHP) systems typically use vertical borehole heat exchangers (BHEs) as heat sources or sinks. The performance of GSHP systems is highly dependent on the ground temperature surrounding the BHEs, which varies with several parameters during operation. Accurate prediction of this temperature is crucial for optimizing the design and sizing of the BHEs.This study proposes an approach using artificial neural networks (ANNs) to model temperature variations around the borehole based on six operational parameters: time, ground thermal diffusivity, porosity, groundwater speed, heat extraction rate, and distance from the borehole. Various ANN configurations were explored to derive an explicit mathematical equation from the relationships stored within the trained ANN model. The Levenberg–Marquardt algorithm was identified as the most suitable for training, achieving a maximum accuracy of R2 = 0.9997 with ten neurons and the Tansig transfer function in both layers. Simpler configurations, such as an ANN with two neurons (R2 = 0.9783) and one neuron (R2 = 0.9437), were also evaluated to provide more practical equations with reduced complexity.The results demonstrate that careful selection of ANN structure is essential for balancing accuracy and usability. The derived mathematical equations can assist system designers in predicting ground temperature changes for different operational conditions, thus optimizing GSHP system performance. Future work will validate the model with real-world GSHP data to further enhance its practical applicability.
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 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.000 |
| 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".