Development of a Spatiotemporal Estimation Method for Rice Plant Height Using Pattern Matching Based on Time-Series Satellite-Derived Vegetation Indices and In Situ Measurements.
Saved in:
| Title: | Development of a Spatiotemporal Estimation Method for Rice Plant Height Using Pattern Matching Based on Time-Series Satellite-Derived Vegetation Indices and In Situ Measurements. |
|---|---|
| Authors: | Shimda, Shoki1 (AUTHOR) shimada.shohki@jaxa.jp, Segami, Go1 (AUTHOR), Oyoshi, Kei1 (AUTHOR) |
| Source: | Remote Sensing. May2026, Vol. 18 Issue 9, p1388. 19p. |
| Subjects: | Agricultural remote sensing, Pattern matching, Crop development, Precision farming, Uncertainty (Information theory), Spatiotemporal processes, Remote sensing, Crop growth |
| Geographic Terms: | Japan |
| Abstract: | Highlights: What are the main findings? Data-efficient daily height estimation: We developed a Bayesian pattern-matching framework that integrates time-series satellite vegetation indices (GCVI) with sparse in situ measurements to generate continuous daily rice plant height estimates at the field scale (R2 = 0.85, RMSE = 7.08 cm). Pixel-level uncertainty quantification: We produced spatially explicit uncertainty maps that capture ambiguity in growth trajectories, providing a practical reliability measure for remote sensing-based crop monitoring. What are the implications of the main findings? Scalable and interpretable monitoring: The framework enables cost-effective, large-scale crop growth tracking, supporting precision agriculture and carbon accounting in rice production systems. Improved phenological insight: Daily height mapping allows robust identification of key growth stages, including the timing of canopy structural transitions relevant to radar-based inundation analysis. Rice plant height is a key indicator of crop growth and phenology, yet continuous daily estimation remains challenging under limited field observations. This study proposes an interpretable Bayesian LUT-based framework to estimate rice plant height from time-series, satellite-derived GCVI, and sparse in situ measurements. Daily plant height was estimated as a posterior-weighted ensemble of multiple LUT-derived heights, together with uncertainty reflecting ambiguity among plausible growth trajectories. Applied to rice paddies in Ryugasaki City, Japan, using Harmonized Landsat–Sentinel-2 data from the 2025 growing season, the method achieved R 2 = 0.85 and RMSE = 7.08 cm on the validation dataset, outperforming simple baseline approaches. The estimated daily height time series also enabled evaluation of the timing at which plant height reached 70 cm, revealing clear spatial variability among fields and an associated uncertainty of approximately 10 days. Although this threshold was discussed with reference to previous studies on L-band SAR sensitivity, the present study relied solely on optical observations. Overall, the proposed framework provides a data-efficient and explainable approach for daily, spatially explicit rice growth monitoring, while current limitations include the single-region, single-year LUT construction and the simplified statistical assumptions used in the Bayesian weighting framework. [ABSTRACT FROM AUTHOR] |
| Copyright of Remote Sensing is the property of MDPI and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
|
Full text is not displayed to guests.
Login for full access.
|
|
| Abstract: | Highlights: What are the main findings? Data-efficient daily height estimation: We developed a Bayesian pattern-matching framework that integrates time-series satellite vegetation indices (GCVI) with sparse in situ measurements to generate continuous daily rice plant height estimates at the field scale (R2 = 0.85, RMSE = 7.08 cm). Pixel-level uncertainty quantification: We produced spatially explicit uncertainty maps that capture ambiguity in growth trajectories, providing a practical reliability measure for remote sensing-based crop monitoring. What are the implications of the main findings? Scalable and interpretable monitoring: The framework enables cost-effective, large-scale crop growth tracking, supporting precision agriculture and carbon accounting in rice production systems. Improved phenological insight: Daily height mapping allows robust identification of key growth stages, including the timing of canopy structural transitions relevant to radar-based inundation analysis. Rice plant height is a key indicator of crop growth and phenology, yet continuous daily estimation remains challenging under limited field observations. This study proposes an interpretable Bayesian LUT-based framework to estimate rice plant height from time-series, satellite-derived GCVI, and sparse in situ measurements. Daily plant height was estimated as a posterior-weighted ensemble of multiple LUT-derived heights, together with uncertainty reflecting ambiguity among plausible growth trajectories. Applied to rice paddies in Ryugasaki City, Japan, using Harmonized Landsat–Sentinel-2 data from the 2025 growing season, the method achieved R 2 = 0.85 and RMSE = 7.08 cm on the validation dataset, outperforming simple baseline approaches. The estimated daily height time series also enabled evaluation of the timing at which plant height reached 70 cm, revealing clear spatial variability among fields and an associated uncertainty of approximately 10 days. Although this threshold was discussed with reference to previous studies on L-band SAR sensitivity, the present study relied solely on optical observations. Overall, the proposed framework provides a data-efficient and explainable approach for daily, spatially explicit rice growth monitoring, while current limitations include the single-region, single-year LUT construction and the simplified statistical assumptions used in the Bayesian weighting framework. [ABSTRACT FROM AUTHOR] |
|---|---|
| ISSN: | 20724292 |
| DOI: | 10.3390/rs18091388 |
