Training-Informed Differentiable Bayesian Inference with PROSPECT for Leaf Trait Retrieval and Uncertainty Analysis

Leaf radiative transfer models provide a physical basis for leaf trait retrieval, but compensating parameter effects and measurement discrepancies constrain estimation accuracy and uncertainty characterization. This study proposes Training-Informed Differentiable Bayesian Inference (TI-DBI). This method integrates training-derived joint lognormal priors, wavelength-specific spectral biases, and residual scales into a differentiable PROSPECT-D model, enabling joint parameter inference via the No-U-Turn Sampler (NUTS). Evaluated on multi-source datasets, TI-DBI yields relative root mean square errors (rRMSEs) of 27.31%, 33.72%, 16.22%, and 37.66% for chlorophyll (Cab), carotenoids (Car), equivalent water thickness (Cw), and leaf dry mass per area (Cm). Outperforming an uncalibrated Markov chain Monte Carlo (MCMC) baseline for all traits and partial least squares regression (PLSR) for Cab, Car, and Cw, these results confirm the specific value of the data-informed probabilistic framework. Beyond point-estimation, TI-DBI substantially improves uncertainty characterization. It yields narrower interval widths and lower interval scores than the uncalibrated baseline, with prediction interval coverage probability (PICP) of the 95% highest density intervals (HDIs) reaching 93.14%, 96.46%, 89.62%, and 86.22% for Cab, Car, Cw, and Cm, respectively. Ablation and sensitivity studies confirm that both the learned priors and spectral error calibration drive these performance gains across varying training fractions and spectral configurations. TI-DBI strictly preserves the forward model’s physical structure while providing a robust, practical framework for jointly evaluating trait estimation accuracy and posterior uncertainty.

Authors

Institutions

Publication Details

Journal
Remote Sensing
Published
2026-11-12
DOI
https://doi.org/10.3390/rs18223892
Primary Topic
Remote Sensing in Agriculture
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Training-Informed Differentiable Bayesian Inference with PROSPECT for Leaf Trait Retrieval and Uncertainty Analysis

Zhuqiang Li, Lisai Cao, Binxiang Qian, Jean‐Philippe Gastellu‐Etchegorry et al.
Remote Sensing
Remote Sensing in Agriculture
article

Training-Informed Differentiable Bayesian Inference with PROSPECT for Leaf Trait Retrieval and Uncertainty Analysis

Zhuqiang Li, Lisai Cao, Binxiang Qian, Jean‐Philippe Gastellu‐Etchegorry, Yin TianGang, Zhijun Zhen, Yunna Wu, Huaan Jin, Shengbo Chen
article en

Abstract

Leaf radiative transfer models provide a physical basis for leaf trait retrieval, but compensating parameter effects and measurement discrepancies constrain estimation accuracy and uncertainty characterization. This study proposes Training-Informed Differentiable Bayesian Inference (TI-DBI). This method integrates training-derived joint lognormal priors, wavelength-specific spectral biases, and residual scales into a differentiable PROSPECT-D model, enabling joint parameter inference via the No-U-Turn Sampler (NUTS). Evaluated on multi-source datasets, TI-DBI yields relative root mean square errors (rRMSEs) of 27.31%, 33.72%, 16.22%, and 37.66% for chlorophyll (Cab), carotenoids (Car), equivalent water thickness (Cw), and leaf dry mass per area (Cm). Outperforming an uncalibrated Markov chain Monte Carlo (MCMC) baseline for all traits and partial least squares regression (PLSR) for Cab, Car, and Cw, these results confirm the specific value of the data-informed probabilistic framework. Beyond point-estimation, TI-DBI substantially improves uncertainty characterization. It yields narrower interval widths and lower interval scores than the uncalibrated baseline, with prediction interval coverage probability (PICP) of the 95% highest density intervals (HDIs) reaching 93.14%, 96.46%, 89.62%, and 86.22% for Cab, Car, Cw, and Cm, respectively. Ablation and sensitivity studies confirm that both the learned priors and spectral error calibration drive these performance gains across varying training fractions and spectral configurations. TI-DBI strictly preserves the forward model’s physical structure while providing a robust, practical framework for jointly evaluating trait estimation accuracy and posterior uncertainty.

Remote SensingVol. 18(22)
Hong Kong Polytechnic University (HK), Jilin University (CN), Chinese Academy of Sciences (CN), Peking University (CN), Centre d'Études Spatiales de la Biosphère (FR), Institute of Mountain Hazards and Environment (CN), Université de Toulouse (FR)
National Natural Science Foundation of China
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