Machine learning and physical model derived Sentinel-2 vegetation indices for estimation of leaf area index: an approach to address optical data gaps

Accurate estimation of leaf area index (LAI) plays a crucial role in assessing crop growth and agricultural productivity. Sentinel-2 optical imagery enables accurate LAI estimation through vegetation indices (VIs), but its temporal availability is often limited by cloud cover and adverse weather, causing gaps in data availability. To overcome this limitation, this study proposes estimating Sentinel-2 VIs from Sentinel-1 synthetic aperture radar (SAR) data using machine learning methods. Our results indicate that while VIs obtained from Sentinel-2 data offer the highest accuracy in LAI prediction (R2 up to 0.88), VIs estimated from Sentinel-1 SAR parameters also perform well (R2 of up to 0.85), demonstrating their reliability when optical data are unavailable. In addition, LAI can be estimated without Sentinel-2 data by employing physically based approaches such as radiative transfer models. By integrating physically based model (PROSAIL) with machine learning algorithms, a hybrid framework is developed that improved prediction accuracy compared with the physical model alone, achieving R2 values up to 0.82, highlighting the effectiveness of this approach. The key contribution of this study is the synergistic use of Sentinel-1 SAR data for machine learning-based estimation of Sentinel-2 VIs and hybrid modeling to enable consistent and reliable LAI monitoring under limited optical data availability.

Authors

Institutions

Publication Details

Journal
Journal of Applied Remote Sensing
Published
2026-11-17
DOI
https://doi.org/10.1117/1.jrs.20.048501
Primary Topic
Remote Sensing in Agriculture
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Machine learning and physical model derived Sentinel-2 vegetation indices for estimation of leaf area index: an approach to address optical data gaps

Abishek Murugesan, Koushik Saha, R. H. Dave, Saptarshi Dey
4 links
Journal of Applied Remote Sensing
Remote Sensing in Agriculture
article

Machine learning and physical model derived Sentinel-2 vegetation indices for estimation of leaf area index: an approach to address optical data gaps

Abishek Murugesan, Koushik Saha, R. H. Dave, Saptarshi Dey
article en

Abstract

Accurate estimation of leaf area index (LAI) plays a crucial role in assessing crop growth and agricultural productivity. Sentinel-2 optical imagery enables accurate LAI estimation through vegetation indices (VIs), but its temporal availability is often limited by cloud cover and adverse weather, causing gaps in data availability. To overcome this limitation, this study proposes estimating Sentinel-2 VIs from Sentinel-1 synthetic aperture radar (SAR) data using machine learning methods. Our results indicate that while VIs obtained from Sentinel-2 data offer the highest accuracy in LAI prediction (R2 up to 0.88), VIs estimated from Sentinel-1 SAR parameters also perform well (R2 of up to 0.85), demonstrating their reliability when optical data are unavailable. In addition, LAI can be estimated without Sentinel-2 data by employing physically based approaches such as radiative transfer models. By integrating physically based model (PROSAIL) with machine learning algorithms, a hybrid framework is developed that improved prediction accuracy compared with the physical model alone, achieving R2 values up to 0.82, highlighting the effectiveness of this approach. The key contribution of this study is the synergistic use of Sentinel-1 SAR data for machine learning-based estimation of Sentinel-2 VIs and hybrid modeling to enable consistent and reliable LAI monitoring under limited optical data availability.

Journal of Applied Remote SensingVol. 20(04)
Anand Agricultural University (IN), Indian Institute of Technology Dharwad (IN)
Remote Sensing in Agriculture
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon