Measuring Photosynthetic Photon Flux Density in the Blue and Red Spectrum for Horticultural Lighting Using Machine Learning Methods
Bibliographic record
Abstract
This article presents development of a low-cost sensor to measure the light intensity for plant growth, referred to as photosynthetic photon flux density (PPFD), which is a quantum light measurement unit for horticultural LED lighting. The total PPFD is comprised of daylight and supplemental LED lights in the red and blue photosynthesis wavebands with peak wavelengths at 660 and 457 nm, respectively. To this end, a multiwaveband spectral light sensor is utilized along with an accurate spectroradiometer reference sensor for calibration. A comparative study of machine learning-based methods is presented to obtain the sensor coefficients for measuring the PPFD, indicating that the decision tree and random forest models exhibit low mean absolute percentage errors (MAPEs) of 0.01%–0.88% for red and blue channels, respectively; but may lead to data over-fitting in real-time applications because of their complexity. However, the simple multilinear regression method yields MAPEs of 0.98% and 0.84% for red and blue channels, respectively, which may be better suited for real-time applications. As a use-case scenario, the calibrated PPFD sensor was experimentally tested on a hydroponic testbed located inside a greenhouse facility. The system was exposed to natural and supplemental light emitting diode (LED) lighting, in the blue and red light spectra, under a daylighting feedback control scheme. Experiments demonstrate that daily light integral (DLI) values with less than 20% tracking errors can be achieved on the blue and red channels using the calibrated sensors.
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 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 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 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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".