Multispectral Approach for Identifying Invasive Plant Species Based on Flowering Phenology Characteristics

Abstract

Invasive plant species (IPS) are the second biggest threat to biodiversity after habitat loss. Since the spatial extent of IPS is essential for managing the invaded ecosystem, the current study aims at identifying and mapping the aggressive IPS of Acacia salicina and Acacia saligna, to understand better the key factors influencing their distribution in the coastal plain of Israel. This goal was achieved by integrating airborne-derived hyperspectral imaging and multispectral earth observation for creating species distribution maps. Hyperspectral data, in conjunction with high spatial resolution species distribution maps, were used to train the multispectral images at the species level. We incorporated a series of statistical models to classify the IPS location and to recognize their distribution and density. We took advantage of the phenological flowering stages of Acacia trees, as obtained by the multispectral images, for the support vector machine classification procedure. The classification yielded an overall Kappa coefficient accuracy of 0.89. We studied the effect of various environmental and human factors on IPS density by using a random forest machine learning model, to understand the mechanisms underlying successful invasions, and to assess where IPS have a higher likelihood of occurring. This algorithm revealed that the high density of Acacia most closely related to elevation, temperature pattern, and distances from rivers, settlements, and roads. Our results demonstrate how the integration of remote-sensing data with different data sources can assist in determining IPS proliferation and provide detailed geographic information for conservation and management efforts to prevent their future spread.

Identifying Vegetation in Arid Regions Using Object-Based Image Analysis with RGB-Only Aerial Imagery

“…Much research has focused on time series analyses of desertification or forest decline (Peters et al [66], Joshi et al [67], and more recently Dorman et al [68], Bajocco et al [69], Fensholt et al [70], and Zhang et al [71]). Remote sensing data has aided research in tracking the health and distribution of certain species of vegetation (Escobar-Flores et al [72], Pham et al [4], Paz-Kagan et al [5]). Yet, again, all of the above employed additional spectral bands.…”

“…The NDVI has found extensive use in various applications such as space-time trend analysis of vegetation health (Shoshany and Karnibad [8]), mapping of invasive species (Paz-Kagan et al [5]), and identification of environmental factors that influence vegetation (Karnieli et al [9]). Despite widspread adoption, several notable limitations of this index have been documented.…”

“…They covered spectral-based classifiers as well as object-based image analysis. Both Paz-Kagan et al [5] and Hong et al [6] have shown that hyperspectral images with limited spatial coverage can be used to train multispectral images with a larger spatial extent for vegetation mapping. Hong et al [6] used small-scale hyperspectral images to train three classification models, then applied the models to multispectral images of a much larger area.…”

“…Hong et al [6] used small-scale hyperspectral images to train three classification models, then applied the models to multispectral images of a much larger area. Similarly, Paz-Kagan et al [5] identified the penology stage of an invasive species using hyperspectral data with a random forest classifier, then expanded the analysis to a much larger region using multispectral imagery. Hong et al [7] addressed the issue of mixed pixels by expanding the classic linear mixed model to more accurately derive abundance maps.…”

Integration of remote sensing and bioclimatic data for prediction of invasive species distribution in data-poor regions: a review on challenges and opportunities

“…Invasive species are a serious worldwide threat to biodiversity (Paz-Kagan et al 2019;Somers and Asner 2012;Truong et al 2017). They moreover negatively affect livelihoods (Shackleton et al 2014(Shackleton et al , 2015, density, richness, and diversity of native woody species, and quality and distribution of water (Bekele et al 2018).…”