An Integrative Approach for Mineral Nutrient Quantification in Dioscorea Leaves: Uniting Image Processing and Machine Learning
Bibliographic record
Abstract
Dioscorea, lauded for its environmental sustainability and versatility, is pivotal in various industries, ranging from food to medicine.The significant yields it offers, coupled with low cultivation inputs and substantial nutritional benefits -including high protein content and minimal sugar levels, necessitate precision in yield predictions and growth management.This, in turn, fosters the evolution of mechanized agriculture and automation.To address this need, a novel methodology amalgamating digital image processing and machine learning algorithms has been established to accurately determine the mineral nutrient content in Dioscorea leaves.This methodology initiates with the separation of the foreground and background in leaf images, achieved through the implementation of the H-component OTSU algorithm.Subsequently, the computation of 54 color features is carried out, and machine learning techniques are harnessed to form models that delineate image features in correlation with a SPAD value exceeding 0.9.The aspiration of this model development lies in the prediction of chlorophyll, nitrogen, phosphorus, and potassium content in Dioscorea leaves.It has been determined that the Multilayer Perceptron (MLP), post 100 iterations, constructs the most accurate model for predicting SPAD content in Dioscorea nipponica.In terms of nitrogen content prediction, a regression model exploiting the SL characteristic has been discovered to be optimal, demonstrating an R2 of 0.850.For phosphorus, a model incorporating the NRI characteristic has yielded an R2 of 0.819, affirming its efficacy.Meanwhile, potassium content prediction has been found to be most precise with a model centered on the Sb characteristic, as evidenced by an achieved R2 of 0.865.This cuttingedge methodology can significantly advance the agricultural sector, particularly in the realm of mechanized agriculture and automation.
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 | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 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".