PhenoAI: A deep learning Python framework to process close-range time-lapse PhenoCam data
Bibliographic record
Abstract
Close-range digital repeat photography is a powerful technique for studying phenology and the seasonal dynamics of plants. However, the processing of PhenoCam images is time-consuming and requires substantial human expertise. This paper describes PhenoAI , a Python framework that automates the processing of time-series PhenoCam images. The package consists of four modules: (i) image quality control, (ii) vegetation segmentation using deep learning, (iii) greenness index calculation, and (iv) parameter extraction. These modules are consistent with the standard and established methodologies used in the literature. We demonstrate the application of the PhenoAI package in a case study by analyzing black spruce [ Picea mariana (Mill.) B.S.P.] phenology in Quebec, Canada, over five years (2017–2021). The result revealed that the Start of Season (SOS) of Green Chromatic Coordinate (GCC) occurred in the third week of May (DOY 144 ± 5), End of Season (EOS) occurred in the end of September (DOY 269 ± 20) and day of maximum greenness occurred in the first week of July (DOY 183 ± 5). The findings correlate with the previous studies in the same region and species, confirming the ability of the PhenoAI to replicate field observations accurately. PhenoAI is an open-source software package that can be customized to suit specific research needs, reduces significantly the processing time, and simplifies the workflow, making it accessible for use by new users for close range observations taken by PhenoCam. PhenoAI will enhance efficiency and accuracy of data extraction for scientists using phenological data for ecological and forestry research. • PhenoAI automates the data processing chain for close-range PhenoCam imagery. • The image quality control module filters out low-quality images for analysis. • Deep learning effectively segments and identifies different types of vegetation. • Demonstrated the framework in a 5-year case study of black spruce phenology. • PhenoAI reduces processing time and simplifies image analysis workflow.
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 | 0.003 |
| 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 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.003 | 0.002 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.012 | 0.006 |
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".