Abstract
Timely and accurate assessment of rice productivity, encompassing grain yield, aboveground biomass (AGB), and harvest index (HI), is essential for harvest planning, supply chain coordination, and food security. This study evaluates the feasibility of predicting all three productivity components using satellite and weather time series data while examining trade-offs between forecast accuracy and operational lead time. Five machine learning models (CatBoost, Gaussian Process Regression (GPR), Random Forest, Ridge regression, and TabPFN) were compared across six in-season prediction windows (December to May) using Sentinel-2 vegetation indices (Normalized Difference Vegetation Index (NDVI), Chlorophyll Index Red Edge 2 (CIRE2), Land Surface Water Index (LSWI)), weather variables (minimum and maximum temperature and radiation), and agronomic records from 256 commercial and experimental rice fields in southern New South Wales, Australia, over four growing seasons (2022–2025) using leave-one-year-out cross-validation. Rolling in-season forecasts were evaluated across December–May; March was selected for further analysis as a practical window that balances accuracy and timeliness for decision-making, with minimal additional error reduction in later months closer to harvest. TabPFN had the lowest RMSE for yield prediction (RMSE = 1.85 t ha−1, r=0.72), Ridge had the lowest RMSE for AGB (RMSE = 3.05 t ha−1, r=0.77), while tree-based models yielded the lowest RMSE for derived HI (RMSE ≈ 0.07). HI prediction showed weak regional relationships, with direct prediction yielding |r|≈0.24 and derived HI (predicted yield divided by predicted AGB) showing r≈0. Although strong correlations (r>0.9) between HI and vegetation indices were observed within individual site-seasons, consistent with other studies, these relationships were highly variable across site-seasons, reflecting the difficulty of inferring HI from canopy reflectance when biotic and/or abiotic stresses decouple AGB accumulation from grain filling. Both direct and derived HI approaches yielded comparable errors, indicating that satellite and weather data lack information content for regional-scale HI prediction. These findings support satellite-based yield and AGB forecasting for operational use.
Abstract from the paper’s OpenAlex record; open copy licensed cc-by. Read at the source ↗
The text the model read, with the source record’s inline markup (italics, sub- and superscripts) rendered and its character entities decoded; quote offsets refer to the raw text.
Claims 10
Claim · model-written summary
March balanced forecast accuracy and lead time, with little later error reduction.
- Taxon
- Rice
Oryza sativat0 - Outcome
- accuracy and timelinesse0
- Comparator
- later monthse0
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“March was selected for further analysis as a practical window that balances accuracy and timeliness for decision-making, with minimal additional error reduction in later months closer to harvest”
t0“Rice”
Claim · model-written summary
TabPFN had the lowest yield prediction RMSE of 1.85 t ha−1.
- Taxon
- RiceOryza sativat0
- Outcome
- RMSE for yield predictione0
- Direction
- loweste0
- Value
- 1.85 t ha−1e0
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“TabPFN had the lowest RMSE for yield prediction (RMSE = 1.85 t ha−1, r=0.72)”
t0“Rice”
Claim · model-written summary
Ridge had the lowest biomass prediction RMSE of 3.05 t ha−1.
- Taxon
- RiceOryza sativat0
- Outcome
- RMSE for AGBe0
- Direction
- loweste0
- Value
- 3.05 t ha−1e0
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“Ridge had the lowest RMSE for AGB (RMSE = 3.05 t ha−1, r=0.77)”
t0“Rice”
Claim · model-written summary
Tree-based models had the lowest derived harvest index RMSE, about 0.07.
- Taxon
- RiceOryza sativat0
- Outcome
- RMSE for derived HIe0
- Direction
- loweste0
- Value
- 0.07e0
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“tree-based models yielded the lowest RMSE for derived HI (RMSE ≈ 0.07)”
t0“Rice”
Claim · model-written summary
Direct harvest index prediction had weak regional correlation of about 0.24.
- Taxon
- RiceOryza sativat0
- Outcome
- regional relationshipse0
- Value
- 0.24e0
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“HI prediction showed weak regional relationships, with direct prediction yielding |r|≈0.24”
t0“Rice”
Claim · model-written summary
Derived harvest index prediction had regional correlation near zero.
- Taxon
- RiceOryza sativat0
- Outcome
- derived HIe0
- Value
- 0e0
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“derived HI (predicted yield divided by predicted AGB) showing r≈0”
t0“Rice”
Claim · model-written summary
Within site-seasons, harvest index correlated strongly with vegetation indices.
- Taxon
- RiceOryza sativat0
- Outcome
- correlationse0
- Value
- r>0.9e0
- Setting
- individual site-seasonse0
Not reportedDirection
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“strong correlations (r>0.9) between HI and vegetation indices were observed within individual site-seasons”
t0“Rice”
Claim · model-written summary
The harvest index and vegetation index relationships varied greatly across site-seasons.
- Taxon
- RiceOryza sativat0
- Outcome
- relationships were highly variable across site-seasonse0
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“these relationships were highly variable across site-seasons”
t0“Rice”
Claim · model-written summary
Direct and derived harvest index approaches had comparable errors.
- Taxon
- RiceOryza sativat0
- Outcome
- errorse0
- Comparator
- direct and derived HI approachese0
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“Both direct and derived HI approaches yielded comparable errors”
t0“Rice”
Claim · model-written summary
The authors support satellite yield and biomass forecasting for operational use.
- Taxon
- RiceOryza sativat0
- Outcome
- satellite-based yield and AGB forecasting for operational usee0
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“These findings support satellite-based yield and AGB forecasting for operational use”
t0“Rice”