Image dataset of Taro Leaf Blight disease collected from the West African Sub-Region
Bibliographic record
Abstract
This dataset encompasses an extensive collection of 18,248 high-resolution JPEG images, documenting various stages of Taro Leaf Blight (TLB) infection in Taro plants across West Africa. TLB, primarily caused by the pathogen Phytophthora colocasiae, manifests through necrotic leaf spots, white sporangia bands, and orange droplets, severely impacting the agricultural output and economic stability of smallholder farmers in the region. The images represent a range of infection stages-early, mid, late, and healthy conditions-captured during the dry and early rainy seasons in Nigeria and Ghana using smartphones equipped with high-resolution cameras. This dataset was carefully curated to help in the development and training of machine learning models for early and accurate detection of TLB, a crucial step towards effective disease management. By enabling the application of advanced diagnostics through technologies such as smartphone apps and AI-based analysis tools, this dataset not only aims to enhance the technological capabilities within agricultural sectors but also serves as a vital educational resource. Researchers and developers can utilize this dataset to create and refine models that diagnose plant diseases promptly, thereby allowing for timely interventions that can prevent widespread crop damage and subsequent economic losses. Additionally, the dataset supports ongoing efforts to integrate artificial intelligence with traditional farming practices, offering a bridge between advanced technological solutions and accessible applications for resource-limited settings. The potential reuse of this dataset extends beyond disease identification; it encompasses agricultural research, educational purposes, and further development of automated systems for plant health monitoring, making it a cornerstone for future innovations in agricultural technology and management strategies.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| 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 | 0.001 | 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 teacher head, 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".