Species Distribution Modelling performance and its implication for Sentinel-2-based prediction of invasive Prosopis juliflora in lower Awash River basin, Ethiopia

نویسندگان

چکیده

Abstract Background Species Distribution Modelling (SDM) coupled with freely available multispectral imagery from Sentinel-2 (S2) satellite provides an immense contribution in monitoring invasive species. However, attempts to evaluate the performances of SDMs using S2 spectral bands and Radiometric Indices (S2-RIs) biophysical variables, particular, were limited. Hence, this study aimed at evaluating performance six commonly used one ensemble model for S2-based variables modelling current distribution Prosopis juliflora lower Awash River basin, Ethiopia. Thirty-five computed Sentinel-2B level-2A, out twelve significant selected Variable Inflation Factor (VIF). A total 680 presence absence data collected train validate tenfold bootstrap replication approach R software “sdm” package. The models was evaluated sensitivity, specificity, True Skill Statistics (TSS), kappa coefficient, area under curve (AUC), correlation. Results Our findings demonstrated that except bioclim all machine learning regression provided successful prediction. Among tested models, Random Forest (RF) performed better 93% TSS 99% AUC followed by Boosted Regression Trees (BRT), ensemble, Generalized Additive Model (GAM), Support Vector Machine (SVM), Linear (GLM) decreasing order. relative influence vegetation indices highest soil indices, water According RF prediction, 16.14% (1553.5 km 2 ) invaded alien Conclusions results highlighted S2-RIs combined have a higher capacity species distribution. Besides, use algorithms such as algorithm is highly essential remote sensing-based SDM.

برای دانلود باید عضویت طلایی داشته باشید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Species distribution modelling of invasive alien species; Pterois miles for current distribution and future suitable habitats

The present study aims to predict the potential geographic distribution and future expansion of invasive alien lionfish (Pterois miles) with ecological niche modelling along the Mediterranean Sea. The primary data consisted of occurrence points of P. miles in the Mediterranean and marine climatic data layers were collected from global databases. All the used models run 100% su...

متن کامل

Mapping Current and Potential Distribution of Non-Native Prosopis juliflora in the Afar Region of Ethiopia

We used correlative models with species occurrence points, Moderate Resolution Imaging Spectroradiometer (MODIS) vegetation indices, and topo-climatic predictors to map the current distribution and potential habitat of invasive Prosopis juliflora in Afar, Ethiopia. Time-series of MODIS Enhanced Vegetation Indices (EVI) and Normalized Difference Vegetation Indices (NDVI) with 250 m2 spatial reso...

متن کامل

Biology and Impacts of Pacific Island Invasive Species. 6. Prosopis pallida and Prosopis juliflora (Algarroba, Mesquite, Kiawe) (Fabaceae)

Prosopis pallida and P. juliflora (commonly referred to as algarroba, mesquite, or kiawe) were introduced from South America to areas in Oceania, Asia, and Africa during the early nineteenth century. In many cases, they naturalized and became widespread. In some places, alien Prosopis species are highly valued for the products and services that they can provide such as shade, cattle fodder, woo...

متن کامل

Diets of the Red-billed Quelea (quelea Quelea) in the Awash River Basin of Ethiopia

INTRODUCTION An understanding of the feeding ecology of the red-billed quelea (Quelea quelea) is necessary for a comprehensive assessment of the potential impact of this species on cereals development. Queleas are reported to subsist primarily on wild Gramineae (Ward 1965a; Gaston 1976), but their mobility and tendency to feed in large aggrega-tions readily adapts them to becoming a major cerea...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

ژورنال

عنوان ژورنال: Ecological processes

سال: 2021

ISSN: ['2097-1311', '2192-1709']

DOI: https://doi.org/10.1186/s13717-021-00285-6