Quantifying error in fine-scale crop yield forecasts to guide data and algorithm improvements: case study of mango in Tamil Nadu, India
Bibliographic record
Abstract
Accurate and timely prediction of mango yield is essential for optimizing resource management, market planning, and climate adaptation strategies. However, dealing with spatial variation of uncertainty and error in fine-scale (e.g., district) yield forecasts has yet to be fully explored. This study investigates a modelling approach that combines statistical methods including bootstrap robust least-angle regression, leave-one-out cross-validation, Bayesian-based spatial correlation analysis, and Markov chain Monte Carlo scheme, and machine learning (ML) (random forest technique) to enhance predictor selection, capture spatial trends, and generate probabilistic mango yield forecasts at the district scale in Tamil Nadu, India. Results showed that pre-flowering drought stress, temperature fluctuation and rainfall distribution, during flowering, fruit set, and fruit development, along with drought conditions in March and July, were dominant drivers of yield variability. Model evaluation revealed acceptable levels of errors in estimating mango yield, with root mean square error ≤ 2.0 t ha −1 , and mean absolute percentage error ≤ 30 % in 18 out of 31 districts. However, forecasting errors at three different lead times (two and one months prior to, and at start of harvest) varied spatially across districts, with lower errors in southern and north-western regions but higher errors in northern and central districts, reflecting the complexity of district-level forecasting under diverse environmental conditions. Agroclimatic variables alone might not be sufficient for accurate mango yield forecasts across Tamil Nadu. By integrating diverse data for model training and refining the ML-based forecast algorithm between fine-scale regions, this study can serve as a foundation for developing climate-resilient mango production strategies tailored to regional variability.
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 | 0.000 | 0.001 |
| 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".