Energy Audits Based on Risk Prediction and AI
Bibliographic record
Abstract
Energy auditing is a critical process for assessing energy consumption and identifying opportunities for improving efficiency in buildings, industries, and systems. With increasing global emphasis on sustainability and reducing carbon footprints, effective energy management has become a priority for organizations and governments alike. In this context, artificial intelligence (AI) offers transformative potential in revolutionizing energy auditing practices. AI can enhance the accuracy, speed, and scalability of audits, providing predictive insights, and automated recommendations. This study presents how AI has been applied to automate several aspects of energy audits following an innovative approach based on risk prediction. Predictive models based on supervised learning enhance both the risk prediction indicator and consumption modelling to prioritize energy efficient measures while clustering techniques support the auditor in analyzing the behaviour of different facilities to better assess the impact of recommended measures. Input data used to train the models include information on energy consumption measurements, temperature, occupancy, production, facility characteristics, and energy self-assessment questionnaires. The AI modules have been integrated on a web-based application that includes different views for data provision and analysis. The results demonstrate satisfactory accuracies, indicating their ability to enhance the assessment of energy risks and generate more precise, robust, and quicker energy audits
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 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 0.001 |
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".