Enhancing Nitrogen Nutrition Index estimation in rice using multi-leaf SPAD values and machine learning approaches - Original research

Aug 4, 2026

Accurate nitrogen diagnosis supports maximizing rice yield while reducing environmental impacts from excessive fertilizer. This study evaluates multi-leaf SPAD measurements combined with machine learning to improve nitrogen nutrition diagnostics across five locations using 15 rice cultivars. SPAD values from the first to fifth fully expanded leaves are collected at key growth stages. Random Forest and Extreme Gradient Boosting significantly enhance leaf nitrogen concentration (LNC) and nitrogen nutrition index (NNI) estimation, with 2LFT most critical for LNC and 3LFT pivotal for NNI. Incorporating statistical summaries such as maximum and median SPAD further boosts performance, enabling more precise nitrogen assessment for targeted management.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages16

Reading Time40 min

AccessFree to download

Introduction

Background and importance of nitrogen management in rice

LNC and NNI as nitrogen status indicators

SPAD meter usage and limitations

TYPE Original Research PUBLISHED 10 December 2024 DOI 10.3389/fpls.2024.1492528 OPEN ACCESS EDITED BY Wenyu Zhang, Jiangsu Academy of Agricultural Sciences Wuxi Branch, China REVIEWED BY Zhenwang Li, Yangzhou University, China Qing Gu, Zhejiang Academy of Agricultural Sciences, China *CORRESPONDENCE Haitao Xiang [htxiang@issas.ac.cn](htxiang@issas.ac.cn) RECEIVED 07 September 2024 ACCEPTED 20 November 2024 PUBLISHED 10 December 2024 CITATION Wang Y, Shi P, Qian Y, Chen G, Xie J, Guan X, Shi W and Xiang H (2024) Enhancing Nitrogen Nutrition Index estimation in rice using multi-leaf SPAD values and machine learning approaches. Front. Plant Sci. 15:1492528 . doi: 10.3389/fpls.2024.1492528 COPYRIGHT © 2024 Wang, Shi, Qian, Chen, Xie, Guan, Shi and Xiang. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY) . The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. Enhancing Nitrogen Nutrition Index estimation in rice using multi-leaf SPAD values and machine learning approaches Yuan Wang 1, Peihua Shi 2, Yinfei Qian 3, Gui Chen 4, Jiang Xie 3, Xianjiao Guan 3, Weiming Shi 1 and Haitao Xiang 1* 1State Key Laboratory of Soil and Sustainable Agriculture, Changshu National Agro-Ecosystem Observation and Research Station, Institute of Soil Science, Chinese Academy of Sciences, Nanjing, China, 2 Department of Agronomy and Horticulture, Jiangsu Vocational College of Agriculture and Forestry, Jurong, China, 3Soil and Fertilizer & Resources and Environmental Institute, Jiangxi Academy of Agricultural Sciences, Nanchang, China, 4 Institute of Biotechnology, Jiaxing Academy of Agricultural Science, Jiaxing, China Accurate nitrogen diagnosis is essential for optimizing rice yield and sustainability. This study investigates the potential of using multi-leaf SPAD measurements combined with machine learning models to improve nitrogen nutrition diagnostics in rice. Conducted across ﬁve locations with 15 rice cultivars, SPAD values from the ﬁrst to ﬁfth fully expanded leaves were collected at key growth stages. The study demonstrates that integrating multileaf SPAD data with advanced machine learning models, particularly Random Forest and Extreme Gradient Boosting, signiﬁcantly improves the accuracy of Leaf Nitrogen Concentration (LNC) and Nitrogen Nutrition Index (NNI) estimation. The second fully expanded Leaf From the Top (2LFT) emerged asthe most critical variable for predicting LNC, while the 3LFT was pivotal for NNI estimation. The inclusion of statistical metrics, such as maximum and median SPAD values, further enhanced model performance, underscoring the importance of considering both original SPAD measurements and derived indices. This approach provides a more precise method for nitrogen assessment, facilitating improved nitrogen use efﬁciency and contributing to sustainable agricultural practices through targeted and effective nitrogen management strategies in rice cultivation. KEYWORDS rice nitrogen diagnosis, multi-leaf SPAD values, machine learning, leaf nitrogen concentration, nitrogen nutrition index, statistical metrics Frontiers in Plant Science 01 [frontiersin.org](frontiersin.org) 1 Introduction Nitrogen is one of the most essential nutrients in crop growth, particularly in rice cultivation, where it plays a key role in photosynthesis, biomass accumulation, and overall yield (Zhang et al., 2021) . As a staple food for over half of the world’s population, rice production is vital for global food security (Bandumula, 2018) . Effective nitrogen management is crucial not only for maximizing rice yields but also for reducing environmental impact

FAQs

Why is nitrogen diagnosis important in rice cultivation?

Nitrogen strongly influences photosynthesis, biomass, and yield in rice. Accurate nitrogen management also reduces environmental impacts from over-application, such as water pollution and greenhouse gas emissions.

What indicators does the study focus on for nitrogen status?

The study targets Leaf Nitrogen Concentration (LNC) and Nitrogen Nutrition Index (NNI) as key indicators of rice nitrogen status.

Which machine learning models and leaf measurements improved estimation performance?

Combining multi-leaf SPAD with Random Forest and Extreme Gradient Boosting significantly improved LNC and NNI estimation. The second fully expanded leaf from the top (2LFT) was most critical for predicting LNC, while the third (3LFT) was pivotal for NNI.

Aug 4, 2026

Upload by Theodore