Multi-Source Time-Series Integration for Progressive In-Season Prediction of Rice Yield, Aboveground Biomass, and Harvest Index

Title
Multi-Source Time-Series Integration for Progressive In-Season Prediction of Rice Yield, Aboveground Biomass, and Harvest Index
Publication Date
2026-06-01
Author(s)
Jha, Sunil Kumar
Brinkhoff, James
( author )
OrcID: https://orcid.org/0000-0002-0721-2458
Email: jbrinkho@une.edu.au
UNE Id une-id:jbrinkho
Robson, Andrew J
( author )
OrcID: https://orcid.org/0000-0001-5762-8980
Email: arobson7@une.edu.au
UNE Id une-id:arobson7
Dunn, Brian W
Type of document
Journal Article
Language
en
Entity Type
Publication
Publisher
MDPI AG
Place of publication
Switzerland
DOI
https://doi.org/10.3390/rs18111785
UNE publication id
une:1959.11/73983
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 haβˆ’1, π‘Ÿ=0.72), Ridge had the lowest RMSE for AGB (RMSE = 3.05 t haβˆ’1, π‘Ÿ=0.77), while tree-based models yielded the lowest RMSE for derived HI (RMSE β‰ˆ 0.07). HI prediction showed weak regional relationships, with direct prediction yielding |π‘Ÿ|β‰ˆ0.24 and derived HI (predicted yield divided by predicted AGB) showing |π‘Ÿ|β‰ˆ0. Although strong correlations (π‘Ÿ>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.

Link
Citation
Remote Sensing, 18(11), p. 1-32
ISSN
2072-4292
Start page
1
End page
32
Rights
Attribution 4.0 International

Files:

NameSizeformatDescriptionLink