Replication Data for: A Machine learning approach for filling long gaps in Eddy Covariance time series data in a Tropical Dry Forest
Bibliographic record
Abstract
These datasets are part of the input and output of the ML approach used to fill longer gaps in EC time series, concerning the manuscript “A Machine learning approach for filling long gaps in Eddy 2 Covariance time series data in a Tropical Dry Forest.” These files represent the Eddy-Covariance flux time series from the Principe flux site at the Santa Rosa National Park-Environmental Monitoring Superior Site (SRNP-EMSS). ‘SRNP_Principe 2013-2022-_timeseries - CO2.csv’ is the carbon flux (µmol/m2/sec) at 30-minute intervals, including gaps filled in first stage (using MissForest ML for shorter gaps), and second stage (using Prophet model for longer gaps). ‘SRNP_Principe 2013-2022-_timeseries – H.csv’ is the sensible heat flux (W/m2) at 30-minute intervals, including the outputs from the first and second stage ML time series gap-filling. ‘SRNP_Principe 2013-2022-_timeseries – LE.csv’ is the latent heat flux (W/m2) at 30-minute intervals, including the first and second-stage ML time series gap-filling outputs. ‘SRNP_Principe 2013-2022-_timeseries – RH.csv’ is the relative humidity (%) at 30-minute intervals, including the outputs from the first and second stage ML time series gap-filling. ‘SRNP_Principe 2013-2022-_timeseries – Tair.csv’ is the air temperature (℃) at 30-minute intervals, including the outputs from the first and second stage ML time series gap-filling. Finally, ‘SRNP_Principe 2013-2022-_timeseries – VPD.csv’ is the Vapor pressure deficit (kPa) at 30-minute intervals, including the first and second-stage ML time series gap-filling outputs.
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 | 0.002 | 0.013 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.002 |
| Science and technology studies | 0.001 | 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) | 0.026 | 0.011 |
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".