Integrated phenology and climate in rice yields prediction using machine learning methods
Bibliographic record
Abstract
Rice (Oryza sativa L.) is a staple cereal crop and its demand is substantially increasing with the growth of the global population. Precisely predicting rice yields are of vital importance to ensure the food security in countries like China, where rice accounts for one-fifth of the total agricultural production. Previous studies found that the rice yields had been significantly impacted by climate change. In addition, phenological variables were found to be important factors concerning rice yields due to its fundamental role in carbon allocation between plant organs, but its impacts on rice yields were seldom evaluated. In this study, eleven combinations of phenology, climate and geography data were tested to predict the site-based rice yields using a traditional regression-based method (MLR, multiple linear regression), and more advanced three machine learning (ML) methods: backpropagation neural network (BP), support vector machine (SVM) and random forest (RF). The results showed that ML methods were more precise than MLR method. The combination using the integrated phenology, climate during growing season and geographical information was better for yields predictions than other combinations across the ML methods, e.g. the difference RMSE (R2) between prediction and observed rice yields were 800 (0.24), 737 (0.33), and 744 (0.31) kg/ha for BP, SVM and RF, respectively. The SVM had achieved the highest precisions in yield predictions and the phenological variables substantially improved the accuracy of yield predictions, and the relative importance of phenological variables were even similar as climatic variables. We highlight the phenology and climate need to be accurately represented in the crop models to improve the accuracy in rice yield prediction under climate change conditions using integrated ML methods.
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 | 0.002 |
| 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 | 0.000 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| 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".