Separating leaf area index from plant area index using semi-supervised classification of digital hemispheric canopy photographs: A case study of dryland vegetation
Bibliographic record
Abstract
Leaf area index ( LAI ) describes the main plant surface area for gas exchange. Accurate LAI measurements are integral to effective hydrological, ecological, and climate modelling. LAI is commonly modelled using canopy gap fraction measurements from optical sensors. In woody vegetation, however, the wood to total plant area ratio ( α ) must also be estimated to convert plant area index ( PAI ) to LAI . Historically, estimating α required destructive harvests and is a potential source of LAI error. In this study, we present a theoretical framework for estimating LAI from digital hemispheric canopy photography by correcting for α within each image using semi-supervised pixel classification. We apply this framework to 201 images collected in semi-arid Australian vegetation (overstorey LAI range 0–5) to explore potential sources of error from: image classification, LAI model implementation, and differences in α among vegetation types. Leaf, wood, and canopy gap (sky) pixels were classified using a random forest (RF) algorithm with 87.7 ± 0.01 % accuracy (mean ± standard error) under overcast skies but 81.3 ± 0.01 % under clear sky conditions where leaf and wood pixel classification was inconsistent. LAI estimates using the proposed approach had a strong linear relationship to PAI ( r 2 ≥ 0.97). However, the proportional contribution of woody material to canopy gap fraction was zenith angle dependent. Allowing α to vary by zenith and azimuth angle when calculating LAI resulted in estimates 10–17 % higher than widely used PAI conversion methods. The zenith angle distribution of α also differed among co-occurring vegetation types. Allowing the PAI to LAI regression slope to vary based on the dominant genus reduced PAI conversion error by ∼2 % ( p < 0.001). Quantifying α variability within canopies and between vegetation types using the method outlined here can reduce on-ground LAI measurement uncertainty.
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) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| 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 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".