{"title":"Digital hemispherical photographs and Sentinel-2 multi-spectral imagery for mapping leaf area index at regional scale over a tropical deciduous forest","authors":"","doi":"10.1007/s42965-024-00327-y","DOIUrl":null,"url":null,"abstract":"<h3>Abstract</h3> <p>The leaf area index (LAI) provides valuable input for modeling climate and ecosystem processes. However, ground-based observations are necessitated across various phenophases from dense tropical forests for a better understanding in terms of their contribution to carbon fixation. In this study, Digital Hemispherical Photography (DHP) was used for LAI observation from Similipal Biosphere Reserve, and to predict high-resolution LAI using Random Forest Machine Learning approach. Observations were taken from ninety-three Elementary sampling units (ESUs) corresponding to the beginning and end of leaf fall seasons across moist deciduous, dry deciduous, and semi-evergreen forests. LAI demonstrated high values for dry deciduous, followed by semi-evergreen and moist deciduous forests for the start of the leaf fall season, whereas moist deciduous forests demonstrated high values during the end of the leaf fall season. Satellite-based spectral reflectance bands of Sentinel-2 and vegetation indices (VIs) were used as predictor variables, wherein the band-7, band-8, band-12, enhanced vegetation index (EVI), and Red-edge based EVI were evaluated as the most dominant responsive variables for LAI estimation. Random Forest (RF) model provided good accuracy (R<sup>2</sup> = 0.64, RMSE = 0.62) with observed DHP-based LAI. However, a comparison of RF model-based predicted LAI with global LAI products (MOD15A2H and VNP15A2H) provided a moderate correlation. Such studies demonstrate the potential of site or region-specific case studies to evaluate coarser-resolution global LAI products for possible improvement.</p>","PeriodicalId":54410,"journal":{"name":"Tropical Ecology","volume":"47 1","pages":""},"PeriodicalIF":1.1000,"publicationDate":"2024-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Tropical Ecology","FirstCategoryId":"93","ListUrlMain":"https://doi.org/10.1007/s42965-024-00327-y","RegionNum":4,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"ECOLOGY","Score":null,"Total":0}
引用次数: 0
Abstract
The leaf area index (LAI) provides valuable input for modeling climate and ecosystem processes. However, ground-based observations are necessitated across various phenophases from dense tropical forests for a better understanding in terms of their contribution to carbon fixation. In this study, Digital Hemispherical Photography (DHP) was used for LAI observation from Similipal Biosphere Reserve, and to predict high-resolution LAI using Random Forest Machine Learning approach. Observations were taken from ninety-three Elementary sampling units (ESUs) corresponding to the beginning and end of leaf fall seasons across moist deciduous, dry deciduous, and semi-evergreen forests. LAI demonstrated high values for dry deciduous, followed by semi-evergreen and moist deciduous forests for the start of the leaf fall season, whereas moist deciduous forests demonstrated high values during the end of the leaf fall season. Satellite-based spectral reflectance bands of Sentinel-2 and vegetation indices (VIs) were used as predictor variables, wherein the band-7, band-8, band-12, enhanced vegetation index (EVI), and Red-edge based EVI were evaluated as the most dominant responsive variables for LAI estimation. Random Forest (RF) model provided good accuracy (R2 = 0.64, RMSE = 0.62) with observed DHP-based LAI. However, a comparison of RF model-based predicted LAI with global LAI products (MOD15A2H and VNP15A2H) provided a moderate correlation. Such studies demonstrate the potential of site or region-specific case studies to evaluate coarser-resolution global LAI products for possible improvement.
摘要 叶面积指数（LAI）为气候和生态系统过程建模提供了宝贵的信息。然而，为了更好地了解热带密林对碳固定的贡献，有必要对热带密林的各个物候期进行地面观测。本研究使用数字半球摄影（DHP）观测西米里帕尔生物圈保护区的 LAI，并使用随机森林机器学习方法预测高分辨率 LAI。观测数据来自 93 个基本取样单元（ESU），这些单元分别对应于潮湿落叶林、干燥落叶林和半常绿林的落叶季节的开始和结束。在落叶季节开始时，干燥落叶林的 LAI 值较高，其次是半常绿林和湿润落叶林，而在落叶季节结束时，湿润落叶林的 LAI 值较高。将哨兵-2 的卫星光谱反射波段和植被指数（VIs）作为预测变量，其中波段-7、波段-8、波段-12、增强植被指数（EVI）和基于红边的 EVI 被评估为 LAI 估算的最主要响应变量。随机森林（RF）模型与基于 DHP 的 LAI 观测结果具有良好的准确性（R2 = 0.64，RMSE = 0.62）。然而，基于 RF 模型预测的 LAI 与全球 LAI 产品（MOD15A2H 和 VNP15A2H）的比较结果显示两者之间的相关性一般。这些研究表明，针对特定地点或区域的案例研究有潜力评估更粗分辨率的全球 LAI 产品，以寻求可能的改进。
期刊介绍：
Tropical Ecology is devoted to all aspects of fundamental and applied ecological research in tropical and sub-tropical ecosystems. Nevertheless, the cutting-edge research in new ecological concepts, methodology and reviews on contemporary themes, not necessarily confined to tropics and sub-tropics, may also be considered for publication at the discretion of the Editor-in-Chief. Areas of current interest include: Biological diversity and its management; Conservation and restoration ecology; Human ecology; Ecological economics; Ecosystem structure and functioning; Ecosystem services; Ecosystem sustainability; Stress and disturbance ecology; Ecology of global change; Ecological modeling; Evolutionary ecology; Quantitative ecology; and Social ecology.
The Journal Tropical Ecology features a distinguished editorial board, working on various ecological aspects of tropical and sub-tropical systems from diverse continents.
Tropical Ecology publishes:
· Original research papers
· Short communications
· Reviews and Mini-reviews on topical themes
· Scientific correspondence
· Book Reviews
京公网安备 11010802042870号
京ICP备2023020795号-1
分享
求助内容：
应助结果提醒方式：
扫码关注我们
