Density vs. Cover: Which is the better choice as the proxy for plant community species diversity estimated by spectral indexes?

Tan, Xiaopeng; Shan, Yuanqi; Wang, Lei; Yao, Yunlong; Jing, Zhongwei

doi:10.1016/j.jag.2023.103370

Cited by 2 publications

(2 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Using the MS600 multispectral instrument (Yusense, Inc., Qingdao, China), we obtained multispectral images of the leaves placed within the camera’s field of view. The multispectral instrument (MSI) contained six single-broadband channels with center wavelengths and spectral resolutions of 450@35 nm, 555@27 nm, 660@22 nm, 720@10 nm, 750@10 nm and 840@30 nm [ 32 ]. The corresponding spectral response curve is depicted in Figure 1 .…”

Section: Methodsmentioning

confidence: 99%

Estimation of Biochemical Pigment Content in Poplar Leaves Using Proximal Multispectral Imaging and Regression Modeling Combined with Feature Selection

Zhang,

Xue

2023

Sensors

View full text Add to dashboard Cite

Monitoring the biochemical pigment contents in individual plants is crucial for assessing their health statuses and physiological states. Fast, low-cost measurements of plants’ biochemical traits have become feasible due to advances in multispectral imaging sensors in recent years. This study evaluated the field application of proximal multispectral imaging combined with feature selection and regressive analysis to estimate the biochemical pigment contents of poplar leaves. The combination of 6 spectral bands and 26 vegetation indices (VIs) derived from the multispectral bands was taken as the group of initial variables for regression modeling. Three variable selection algorithms, including the forward selection algorithm with correlation analysis (CORR), recursive feature elimination algorithm (RFE), and sequential forward selection algorithm (SFS), were explored as candidate methods for screening combinations of input variables from the 32 spectral-derived initial variables. Partial least square regression (PLSR) and nonlinear support vector machine regression (SVR) were both applied to estimate total chlorophyll content (Chla+b) and carotenoid content (Car) at the leaf scale. The results show that the nonlinear SVR prediction model based on optimal variable combinations, selected by SFS using multiple scatter correction (MSC) preprocessing data, achieved the best estimation accuracy and stable prediction performance for the leaf pigment content. The Chla+b and Car models developed using the optimal model had R2 and RMSE predictive statistics of 0.849 and 0.825 and 5.116 and 0.869, respectively. This study demonstrates the advantages of using a nonlinear SVR model combined with SFS variable selection to obtain a more reliable estimation model for leaf biochemical pigment content.

show abstract

Section: Methodsmentioning

confidence: 99%

Estimation of Biochemical Pigment Content in Poplar Leaves Using Proximal Multispectral Imaging and Regression Modeling Combined with Feature Selection

Zhang,

Xue

2023

Sensors

View full text Add to dashboard Cite

show abstract

“…Spectral variation hypothesis states that different plant species reflect different intensities of electromagnetic radiation; thus, spectral metrics can be used to assess the composition of and identify plant species (Cavender-Bares et al, 2017;Jetz et al, 2016;Oldeland et al, 2010). Many spectral indices indicate spectral species, but the most widely used is the normalized difference vegetation index (NDVI) (Gholizadeh et al, 2019;Hauser et al, 2021;Peng et al, 2019;Perrone et al, 2023;Pouteau et al, 2018;Somers et al, 2015;Tan et al, 2023). Thus, in the present study, we used this index to simulate the SAC patterns of plant communities.…”

Section: Introductionmentioning

confidence: 99%

Global patterns and drivers of spatial autocorrelation in plant communities in protected areas

Peng,

Xin,

Peng

et al. 2023

Diversity and Distributions

View full text Add to dashboard Cite

AimStochastic and deterministic (biotic factors such as intraspecies competition or abiotic factors) processes affect the spatial patterns of ecological communities. These processes can be quantitatively assessed based on spatial autocorrelation (SAC) parameters. However, the global patterns of SAC and their differences across vegetation types remain unknown. We aimed to (1) quantitatively assess the SAC global pattern in plant communities and their variation from 1990 to 2020 and (2) identify the key drivers of SAC in plant communities in protected areas (PAs).LocationGlobal.Time Period1990–2020.Major Taxa StudiedTerrestrial plants.MethodsUsing normalized difference vegetation index data extracted from remote sensing datasets, we calculated the SAC parameters, including the Nugget, Partial Sill (PSill), and Sill, in 147 samples from 49 PAs in 1990, 2000, 2010, and 2020. The random forest model was employed to identify the drivers among 10 annual and 120 monthly climatic variables.ResultsThe SAC patterns of plant communities in global PAs differed across vegetation types. It reached the highest in grasslands and evergreen needleleaved forests, mainly explained by annual energy metrics, and the lowest in tropical evergreen rain forests around equator and boreal coniferous forests near the Arctic Circle. From 1990 to 2020, the Nugget, PSill, and Sill decreased by 92.36%, 58.36%, and 60.61%, respectively, indicating biological homogeneity. Monthly climatic variables explain SAC variations better than annual ones.Main ConclusionsFrom 1990 to 2020, the SAC parameters decreased sharply across vegetation types, indicating an obvious biologically homogenous trend that was mainly driven by monthly climatic variation, vary across sites and vegetation types. Our results highlight the need to assess the SAC in different vegetation types separately to understand the shifts of global plant communities under climate change.

show abstract

Density vs. Cover: Which is the better choice as the proxy for plant community species diversity estimated by spectral indexes?

Cited by 2 publications

References 47 publications

Estimation of Biochemical Pigment Content in Poplar Leaves Using Proximal Multispectral Imaging and Regression Modeling Combined with Feature Selection

Estimation of Biochemical Pigment Content in Poplar Leaves Using Proximal Multispectral Imaging and Regression Modeling Combined with Feature Selection

Global patterns and drivers of spatial autocorrelation in plant communities in protected areas

Contact Info

Product

Resources

About