Spectral index to improve the extraction of built-up area from WorldView-2 imagery Adeniyi Adeyemi , a, * Abel Ramoelo , b,c Moses Cho, d,e and Cecilia Masemola f a University of South Africa, College of Agriculture and Environmental Science, Department of Environmental Science, Pretoria, South Africa b Scientific Services, South African National Parks, Pretoria, South Africa c University of Pretoria, Department of Geography, Geoinformatics and Meteorology, Pretoria, South Africa d Precision Agriculture, Council for Scientific and Industrial Research, Pretoria, South Africa e University of Pretoria, Department of Plant and Soil Sciences, Pretoria, South Africa f University of KwaZulu-Natal, Department of Agriculture, Engineering & Environmental Science, Pietermaritzburg, South Africa Abstract. Globally, the unprecedented increase in population in many cities has led to rapid changes in urban landscape, which requires timely assessments and monitoring. Accurate deter- mination of built-up information is vital for urban planning and environmental management. Often, the determination of the built-up area information has been dependent on field surveys, which is laborious and time-consuming. Remote sensing data are the only option for deriving spatially explicit and timely built-up area information. There are few spectral indices for built-up areas and often not accurate as they are specific to impervious material, age, colour, and thick- ness, especially using higher resolution images. The objective of this study is to test the utility of a new built-up extraction index (NBEI) using WorldView-2 (WV-2) to improve built-up material mapping irrespective of material type, age, and color. The new index was derived from spectral bands such as green, red edge, NIR1, and NIR2 bands that profoundly explain the variation in built-up areas on WV-2 image. The result showed that NBEI improves the extraction of built-up areas with high accuracy [area under the receiver operating characteristic curve, ðAUROCÞ¼ ∼0.82] compared to the existing indices such as built-up area index (AUROC ¼ ∼0.73), built-up spectral index (AUROC ¼ ∼0.78), red edge/green index (AUROC ¼ ∼0.71) and WorldView- Built-up Index (WV-BI) (AUROC ¼ ∼0.67). The study demonstrated that the new built-up index could extract built-up areas using high-resolution images. The performance of NBEI could be attributed to the fact that it is not material-specific, and would be necessary for urban area mapping. © 2021 Society of Photo-Optical Instrumentation Engineers (SPIE) [DOI: 10.1117/1.JRS.15 .024510] Keyword: WorldView-2; spectral indices; built-up; very high resolution. Paper 210046 received Jan. 24, 2021; accepted for publication Apr. 8, 2021; published online Apr. 26, 2021. 1 Introduction The global urban population proliferated from 220 million to 2.8 billion over the twentieth century. 1 This unprecedented increase in population concentration in cities led to rapid urban landscape changes. 2,3 The highest rate of urbanization and associated land use or cover changes have been observed in developing countries. 4 Over the last decades, Southern Africa has been facing significant land use and land cover changes, such as loss of natural land, i.e., forest or plantations, agricultural lands, and grasslands coupled with growing built-up impervious sur- faces, which are developed and constructed artificial surfaces that water cannot infiltrate to *Address all correspondence to Adeniyi Adeyemi, adedayoadeyemi01@gmail.com 1931-3195/2021/$28.00 © 2021 SPIE Journal of Applied Remote Sensing 024510-1 Apr–Jun 2021 • Vol. 15(2)