Use of Machine Learning Combined With UV-VIS-NIR Spectroscopy to Monitor Okra Plant Growth and Development in Controlled Light Environment
Bibliographic record
Abstract
Climate change has led growers with uncertainty on crop growth, development, quality and yield. Thus there is a critical need to set up proper tools to help growers follow up their crop during the growth period and ensure better production at the end. In this context we used predictive machine learning models for predictions of Okra development in a controlled lighting environment based on UV-VIS-NIR spectroscopy. Fluorescence and reflectance spectroscopy data was collected from several leaves of Okra grown under different artificial lighting condition, then vegetation spectral indices were computed and used as features for the prediction of four growth and development parameters namely Plant Height (PH), Leaf Number (LN), stem diameter (SD) and Leaf Area Index (LAI). The different trained machine learning models explicitly Linear regression, K-nearest Neighbor, Support Vector Machine, Single Tree, Random Forest, Gradient Boosting, extreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine (LightGBM) and Categorical Boosting (CatBoost) give good performance in the prediction of PH (R2 ranged from 0.93 to 0.97), LN (R2 ranged from 0.88 to 0.94), SD (R2 ranged from 0.95 to 0.98) with the tree-based algorithm outperformed the others. However, these trained models give poor performance on the prediction of LAI (R2 ranged from 0.25 to 0.37). Furthermore, the most responsive features and vegetation spectral indices were also identified using Shapley Additive Explanations. This work aims to help growers to follow up their crops development and moreover intend to be used as a decision tool in an overall horticultural management process to engineer their crop development.
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 | 0.001 | 0.001 |
| 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".