Forecasting Construction Equipment Productivity Based on Weather Conditions: A Data-Driven Time-Series Machine Learning Approach
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.
Bibliographic record
Abstract
Accurate forecasting of construction equipment productivity is crucial for effectively planning and controlling construction resources. Traditional approaches often rely on data from previous projects and the subjective experience of project managers, which can result in inaccurate estimates. Moreover, previous studies in forecasting construction equipment productivity often tend to overlook the time dependencies in the data which is inherent to the nature of construction productivity. This study presents a generic data-driven framework for forecasting productivity data from ongoing construction field activities and weather conditions, utilizing daily report logs. The framework combines machine learning (ML) models with time-series analysis to forecast, over time, the productivity of construction equipment while considering weather conditions as exogenous factors. Modeling construction productivity as a time series enables the reflection of temporal dependencies in the data. The framework was evaluated through a case study involving excavation activities for an infrastructure project over eight months. The ML-based time-series model yielded a model fit (R2) of 0.89, outperforming the classical Seasonal Autoregressive Integrated Moving Average (SARIMAX) time-series model, which achieved an R2 of 0.71. Moreover, the ML-based time-series model showed a 63% reduction in the estimation error compared to the project manager’s approach. Once the construction field productivity is accurately estimated, project managers can leverage the estimates to make data-driven resource allocation decisions.
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 imitationNot 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.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 it