Cong Ma, Ran Tong, Nianfu Zhu, Wenwen Yuan, Yanji Li, G. Geoff Wang, Tonggui Wu
{"title":"Deciphering nitrogen concentrations in Metasequoia glyptostroboides: a novel approach using RGB images and machine learning","authors":"Cong Ma, Ran Tong, Nianfu Zhu, Wenwen Yuan, Yanji Li, G. Geoff Wang, Tonggui Wu","doi":"10.1007/s11676-024-01769-9","DOIUrl":null,"url":null,"abstract":"<p>Recent advances in spectral sensing techniques and machine learning (ML) methods have enabled the estimation of plant physiochemical traits. Nitrogen (N) is a primary limiting factor for terrestrial forest growth, but traditional methods for N determination are labor-intensive, time-consuming, and destructive. In this study, we present a rapid, non-destructive method to predict leaf N concentration (LNC) in <i>Metasequoia glyptostroboides</i> plantations under N and phosphorus (P) fertilization using ML techniques and unmanned aerial vehicle (UAV)- based RGB (red, green, blue) images. Nine spectral vegetation indices (VIs) were extracted from the RGB images. The spectral reflectance and VIs were used as input features to construct models for estimating LNC based on support vector machine, random forest (RF), and multiple linear regression, gradient boosting regression and classification and regression trees (CART). The results show that RF is the best fitting model for estimating LNC with a coefficient of determination (<i>R</i><sup>2</sup>) of 0.73. Using this model, we evaluated the effects of N and P treatments on LNC and found a significant increase with N and a decrease with P. Height, diameter at breast height (DBH), and crown width of all <i>M. glyptostroboides</i> were analyzed by Pearson correlation with the predicted LNC. DBH was significantly correlated with LNC under N treatment. Our results highlight the potential of combining UAV RGB images with an ML algorithm as an efficient, scalable, and cost-effective method for LNC quantification. Future research can extend this approach to different tree species and different plant traits, paving the way for large-scale, time-efficient plant growth monitoring.</p>","PeriodicalId":15830,"journal":{"name":"Journal of Forestry Research","volume":null,"pages":null},"PeriodicalIF":3.4000,"publicationDate":"2024-08-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Forestry Research","FirstCategoryId":"97","ListUrlMain":"https://doi.org/10.1007/s11676-024-01769-9","RegionNum":2,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"FORESTRY","Score":null,"Total":0}
引用次数: 0
Abstract
Recent advances in spectral sensing techniques and machine learning (ML) methods have enabled the estimation of plant physiochemical traits. Nitrogen (N) is a primary limiting factor for terrestrial forest growth, but traditional methods for N determination are labor-intensive, time-consuming, and destructive. In this study, we present a rapid, non-destructive method to predict leaf N concentration (LNC) in Metasequoia glyptostroboides plantations under N and phosphorus (P) fertilization using ML techniques and unmanned aerial vehicle (UAV)- based RGB (red, green, blue) images. Nine spectral vegetation indices (VIs) were extracted from the RGB images. The spectral reflectance and VIs were used as input features to construct models for estimating LNC based on support vector machine, random forest (RF), and multiple linear regression, gradient boosting regression and classification and regression trees (CART). The results show that RF is the best fitting model for estimating LNC with a coefficient of determination (R2) of 0.73. Using this model, we evaluated the effects of N and P treatments on LNC and found a significant increase with N and a decrease with P. Height, diameter at breast height (DBH), and crown width of all M. glyptostroboides were analyzed by Pearson correlation with the predicted LNC. DBH was significantly correlated with LNC under N treatment. Our results highlight the potential of combining UAV RGB images with an ML algorithm as an efficient, scalable, and cost-effective method for LNC quantification. Future research can extend this approach to different tree species and different plant traits, paving the way for large-scale, time-efficient plant growth monitoring.
期刊介绍:
The Journal of Forestry Research (JFR), founded in 1990, is a peer-reviewed quarterly journal in English. JFR has rapidly emerged as an international journal published by Northeast Forestry University and Ecological Society of China in collaboration with Springer Verlag. The journal publishes scientific articles related to forestry for a broad range of international scientists, forest managers and practitioners.The scope of the journal covers the following five thematic categories and 20 subjects:
Basic Science of Forestry,
Forest biometrics,
Forest soils,
Forest hydrology,
Tree physiology,
Forest biomass, carbon, and bioenergy,
Forest biotechnology and molecular biology,
Forest Ecology,
Forest ecology,
Forest ecological services,
Restoration ecology,
Forest adaptation to climate change,
Wildlife ecology and management,
Silviculture and Forest Management,
Forest genetics and tree breeding,
Silviculture,
Forest RS, GIS, and modeling,
Forest management,
Forest Protection,
Forest entomology and pathology,
Forest fire,
Forest resources conservation,
Forest health monitoring and assessment,
Wood Science and Technology,
Wood Science and Technology.