Research Article | Open Access

Volume 2026 |Article ID 100125 | https://doi.org/10.1016/j.plaphe.2025.100125

DeepSpecN: A new hybrid method combining PROSPECT-PRO and Conv-Transformer to estimate leaf nitrogen content from leaf reflectance

Shuai Yang,^1,2,3,4,5 Anirudh Belwalkar,¹ Dong Li,¹ Yufeng Ge,^6,7 Tao Cheng,⁸ Fei Wu,¹ Longkang Peng,⁹ Daoliang Li ,^2,3,4,5 and Kang Yu ¹

¹Precision Agriculture Lab, School of Life Sciences, Technical University of Munich, Freising, 85354, Germany
²National Innovation Center for Digital Fishery, China Agricultural University, China
³Key Laboratory of Smart Farming Technologies for Aquatic Animal and Livestock, Ministry of Agriculture and Rural Affairs, China Agricultural University, Beijing, 100083, China
⁴Beijing Engineering and Technology Research Center for Internet of Things in Agriculture, Beijing, 100083, China
⁵College of Information and Electrical Engineering, China Agricultural University, Beijing, 100083, China
⁶Department of Biological Systems Engineering, University of Nebraska-Lincoln, Lincoln, NE, 68583, United States
⁷Center for Plant Science Innovation, University of Nebraska-Lincoln, Lincoln, NE, 68588, United States
⁸National Engineering and Technology Center for Information Agriculture (NETCIA), Nanjing Agricultural University, Nanjing, China
⁹Department of Land Surveying and Geo-Informatics, The Hong Kong Polytechnic University, Hong Kong, China

Abstract

Accurate, non-destructive quantification of leaf nitrogen content (LNC) is crucial for monitoring crop health and growth. Traditional empirical methods require extensive in-situ data for training, while physically-based methods are limited by ill-posed inversion, and hybrid methods suffer from domain shift between in-situ and simulated data. To overcome these limitations, this study introduces DeepSpecN, a novel hybrid method for maize LNC estimation using leaf-scale hyperspectral bidirectional reflectance. Without requiring in-situ data for training, DeepSpecN combines four key components: continuous wavelet transform (CWT) for reducing specular reflection, PROSPECT-PRO for simulating training data, an improved Transformer model for feature learning, and a spectral similarity-based sample selection method for selecting more valuable training samples. DeepSpecN and other methods, including physically-based methods, non-parametric regression based hybrid methods, and parametric regression methods based on vegetation indices (VIs), were validated using bidirectional reflectance data from 1724 maize leaves. The results showed that, when trained on representative samples, DeepSpecN achieved the highest estimation accuracy among all the methods (RMSE = 0.247 g/m2, R2 = 0.665). The sample selection strategy mitigated the effects of domain shift by identifying representative training samples with high spectral similarity from the simulated database. Furthermore, the results showed that the Chlorophyll (Chl)-based empirical formulas estimated maize LNC more accurately than those based on leaf protein content. Moreover, the validation results on four different crop species confirm the generalizability of DeepSpecN. Our findings demonstrate the potential of hybrid methods that utilize bidirectional reflectance spectra, developed by addressing the domain shift issue, to improve the LNC estimation accuracy.