您好，欢迎访问贵州省农业科学院 机构知识库！
贵州省农业科学院机构知识库

全部

  • 全部
  • 标题
  • 学者
  • 机构
  • 关键词

Improved estimation of forage nitrogen in alpine grassland by integrating Sentinel-2 and SIF data

文献类型： 外文期刊

作者： Zhang, Yongkang 1 ; Gao, Jinlong 1 ; Zhang, Dongmei 2 ; Liang, Tiangang 1 ; Wang, Zhiwei 3 ; Zhang, Xuanfan 1 ; Ma, Zhanping 1 ; Yang, Jinhuan 4 ;

作者机构： 1.Lanzhou Univ, Coll Pastoral Agr Sci & Technol, State Key Lab Herbage Improvement & Grassland Agro, Key Lab Grassland Livestock Ind Innovat, Lanzhou 730000, Peoples R China

2.Chinese Acad Sci, Northwest Inst Ecoenvironm & Resources, Key Lab Cryospher Sci & Frozen Soil Engn, Lanzhou 730000, Peoples R China

3.Guizhou Acad Agr Sci, Guizhou Inst Prataculture, Guiyang 550006, Peoples R China

4.Forestry & Grassland Bur Haiyuan Cty, Zhongwei 755200, Peoples R China

关键词： Alpine grasslands; Forage quality; Multispectral data; Remote sensing; Machine learning

期刊名称：PLANT METHODS （ 影响因子：4.4； 五年影响因子：5.7 ）

ISSN：

年卷期： 2025 年 21 卷 1 期

页码：

收录情况： SCI

摘要： Nitrogen is an essential element for the growth and reproduction of vegetation in alpine grasslands and plays a vital role in determining the nutrient-carrying capacity of plants and maintaining the balance of forage nutrition supply and demand. In recent years, the widespread application of high-resolution multispectral satellites (i.e., Sentinel-2) equipped with multiple red-edge bands has proven an effective approach for estimating forage nitrogen content in alpine grassland habitats. In addition, solar-induced chlorophyll fluorescence (SIF), as a direct probe of vegetation photosynthesis, has become an effective indicator for estimating key growth parameters of green vegetation in recent years. However, it currently unknown whether integrating SIF and Sentinel-2 satellite data can further enhance the mapping accuracy of forage nitrogen content in alpine grassland. In this study, we integrates SIF products from TanSat and Orbiting Carbon Observatory-2 (OCO-2) satellites, Sentinel-2 Multi-Spectral Instrument (MSI) data with derived vegetation indices, and field observations across phenological stages (green-up stage, vigorous growth stage, and senescence stage) in northeastern Tibetan Plateau alpine grasslands to develop support vector machine (SVM), gaussian process regression (GPR), and artificial neural network (ANN) models for regional-scale forage nitrogen estimation. The results indicated that both the Sentinel-2 (V-R2 of 0.68-0.71, CVRMSE of 17.73-18.65%) and SIF data (V-R2 of 0.59-0.73, CVRMSE of 17.05-21.40%) individually yielded relatively accurate estimates of the forage nitrogen. The integrated model constructed using both spectral data types explained 69-74% of the variation in forage nitrogen content, with a CVRMSE ranging from 16.89 to 17.85%, which indicates that the synergy between Sentinel-2 and SIF data can slightly enhance the model's estimation capability of forage nitrogen content. Thus, integrating Sentinel-2 and SIF data presents a potential solution for precisely measuring spatial distribution of forage nitrogen in alpine grassland at the regional scale. The proposed method provides a feasible framework for the spatiotemporal prediction of the key forage growth parameters of forage and offers a theoretical basis for determining the rational utilization of grassland resources and studying the nutritional balance between grassland and livestock.

  • 相关文献
作者其他论文 更多>>
置顶
购物车
反馈

© 京ICP备09089781号-29 主办单位：贵州省农业科学院

学术资源： 中国农业科学院 农业专业知识服务系统 农科联盟资源共建共享平台 中国农业科技文献与信息服务平台 中国农业期刊集成服务平台