Utilization of Band Combination for Feature Selection in Machine Learning-Based Roof Material Types Identification

Ayom Widipaminto, Yohanes Fridolin Hestrio, Donna Monica, Yuvita Dian Safitri, Dedi Irawadi, - Rokhmatuloh, Djoko Triyono, Erna Sri Adiningsih


Land monitoring requires remote sensing data, which varies in its spectral and spatial resolution. Remote sensing data with the high spatial resolution is especially needed for urban monitoring. However, high spatial resolution data is usually expensive with limited coverage and complex analysis. This paper aims to find the most efficient way to do urban monitoring, specifically surface material identification. In material identification, the distinctive feature that can be used to differentiate one material surface from one another is its reflectance responses. This leads to a question of which absorption features are significant to different surface materials, especially roofing materials, and which absorption features are not discriminant enough to be used at classification. This paper proposed a machine learning-based identification of roof material types using band combinations as classification features. The experiment was done on Pleiades data, multispectral satellite imagery with very high spatial resolution. We first calculated the image’s reflectance values for each band and then grouped them based on their spectral range, yielding 11 possible combinations as the classification features. The experiment found that reflectance responses for band Red and NIR are the most distinctive trait of a material type and thus sufficient for material identification. We minimized the number of spectral responses used in material identification down to two bands, which can help the data collection and processing of material identification easier, cheaper, and less time-cost. Our experiment yields overall accuracy of 0.9959, with a computational time of 19.72 seconds.


Material identification; band combination; reflectance responses.

Full Text:



Y. Jamei, P. Rajagopalan, and Q. C. Sun, “Time-series dataset on land surface temperature, vegetation, built up areas and other climatic factors in top 20 global cities (2000–2018),” Data Br., vol. 23, p. 103803, 2019, doi: https://doi.org/10.1016/j.dib.2019.103803.

X. Zhang, J. Yao, J. Wang, and K. Sila-Nowicka, “Changes of forestland in China’s coastal areas (1996-2015): Regional variations and driving forces,” Land use policy, vol. 99, p. 105018, 2020, doi: https://doi.org/10.1016/j.landusepol.2020.105018.

M. Matsa, O. Mupepi, T. Musasa, and R. Defe, “A GIS and remote sensing aided assessment of land use/cover changes in resettlement areas; a case of ward 32 of Mazowe district, Zimbabwe,” J. Environ. Manage., vol. 276, p. 111312, 2020, doi: https://doi.org/10.1016/j.jenvman.2020.111312.

J. Yan, W. Zhou, L. Han, and Y. Qian, “Mapping vegetation functional types in urban areas with WorldView-2 imagery: Integrating object-based classification with phenology,” Urban For. Urban Green., vol. 31, pp. 230–240, 2018, doi: https://doi.org/10.1016/j.ufug.2018.01.021.

S. Ahmed, “Assessment of urban heat islands and impact of climate change on socioeconomic over Suez Governorate using remote sensing and GIS techniques,” Egypt. J. Remote Sens. Sp. Sci., vol. 21, no. 1, pp. 15–25, 2018, doi: https://doi.org/10.1016/j.ejrs.2017.08.001.

J. Magidi and F. Ahmed, “Assessing urban sprawl using remote sensing and landscape metrics: A case study of City of Tshwane, South Africa (1984–2015),” Egypt. J. Remote Sens. Sp. Sci., vol. 22, no. 3, pp. 335–346, 2019, doi: 10.1016/j.ejrs.2018.07.003.

M. Eghtesadifard, P. Afkhami, and A. Bazyar, “An integrated approach to the selection of municipal solid waste landfills through GIS, K-Means and multi-criteria decision analysis,” Environ. Res., vol. 185, p. 109348, 2020, doi: https://doi.org/10.1016/j.envres.2020.109348.

S. N. Shorabeh, A. Varnaseri, M. K. Firozjaei, F. Nickravesh, and N. N. Samany, “Spatial modeling of areas suitable for public libraries construction by integration of GIS and multi-attribute decision making: Case study Tehran, Iran,” Libr. Inf. Sci. Res., vol. 42, no. 2, p. 101017, 2020, doi: https://doi.org/10.1016/j.lisr.2020.101017.

E. Taherzadeh and H. Z. M. Shafri, “Development of a Generic Model for the Detection of Roof Materials Based on an Object-Based Approach Using WorldView-2 Satellite Imagery,” Adv. Remote Sens., vol. 2, pp. 312–321, 2013, doi: 10.4236/ars.2013.24034.

A. G. Copado-Rivera, J. Bello-Pineda, J. A. Aké-Castillo, and P. Arceo, “Spatial modeling to detect potential incidence zones of harmful algae blooms in Veracruz, Mexico,” Estuar. Coast. Shelf Sci., vol. 243, p. 106908, 2020, doi: https://doi.org/10.1016/j.ecss.2020.106908.

H. MacDonald and D. McKenney, “Envisioning a global forest transition: Status, role, and implications,” Land use policy, vol. 99, p. 104808, 2020, doi: https://doi.org/10.1016/j.landusepol.2020.104808.

D. H. Lang, A. Kumar, S. Sulaymanov, and A. Meslem, “Building typology classification and earthquake vulnerability scale of Central and South Asian building stock,” J. Build. Eng., vol. 15, pp. 261–277, 2018, doi: https://doi.org/10.1016/j.jobe.2017.11.022.

C. Arunplod, “Detecting the potential roof for green rooftop development using geospatial techniques: A case study in North of Bangkok,” Springer Geogr., pp. 12–20, 2020, doi: 10.1007/978-3-030-33900-5_2.

Y. Liu, J. Li, L. Duan, M. Dai, and W. Chen, “Material dependence of cities and implications for regional sustainability,” Reg. Sustain., vol. 1, no. 1, pp. 31–36, 2020, doi: https://doi.org/10.1016/j.regsus.2020.07.001.

M. Hendel, S. Parison, A. Grados, and L. Royon, “Which pavement structures are best suited to limiting the UHI effect? A laboratory-scale study of Parisian pavement structures,” Build. Environ., vol. 144, pp. 216–229, 2018, doi: https://doi.org/10.1016/j.buildenv.2018.08.027.

X. Guo and P. Li, “Mapping plastic materials in an urban area: Development of the normalized difference plastic index using WorldView-3 superspectral data,” ISPRS J. Photogramm. Remote Sens., vol. 169, pp. 214–226, 2020, doi: https://doi.org/10.1016/j.isprsjprs.2020.09.009.

D. Pandey and K. C. Tiwari, “Extraction of urban built-up surfaces and its subclasses using existing built-up indices with separability analysis of spectrally mixed classes in AVIRIS-NG imagery,” Adv. Sp. Res., vol. 66, no. 8, pp. 1829–1845, 2020, doi: https://doi.org/10.1016/j.asr.2020.06.038.

W. Xia, Z. Chen, Y. Zhang, and J. Liu, “An Approach for Road Material Identification by Dual-Stage Convolutional Networks 1 China Transport Telecommunications & Information Center , Beijing 100011 , China , 2 School of Computer Science and Technology , Donghua University , Shanghai 201620 , China,” pp. 7153–7156, 2018.

H. Baluyan, B. Joshi, A. Al Hinai, and W. L. Woon, “Novel Approach for Rooftop Detection Using Support Vector Machine,” ISRN Mach. Vis., vol. 2013, pp. 1–11, 2013, doi: 10.1155/2013/819768.

M. Jilge, U. Heiden, C. Neumann, and H. Feilhauer, “Gradients in urban material composition: A new concept to map cities with spaceborne imaging spectroscopy data,” Remote Sens. Environ., vol. 223, pp. 179–193, 2019, doi: https://doi.org/10.1016/j.rse.2019.01.007.

O. Okwuashi and C. E. Ndehedehe, “Deep support vector machine for hyperspectral image classification,” Pattern Recognit., vol. 103, p. 107298, 2020, doi: https://doi.org/10.1016/j.patcog.2020.107298.

L. M. Francis and N. Sreenath, “TEDLESS – Text detection using least-square SVM from natural scene,” J. King Saud Univ. - Comput. Inf. Sci., vol. 32, no. 3, pp. 287–299, 2020, doi: https://doi.org/10.1016/j.jksuci.2017.09.001.

R. Bhuvaneswari and R. Subban, “Novel object detection and recognition system based on points of interest selection and SVM classification,” Cogn. Syst. Res., vol. 52, pp. 985–994, 2018, doi: https://doi.org/10.1016/j.cogsys.2018.09.022.

A. Chitlangia and G. Malathi, “Handwriting Analysis based on Histogram of Oriented Gradient for Predicting Personality traits using SVM,” Procedia Comput. Sci., vol. 165, pp. 384–390, 2019, doi: https://doi.org/10.1016/j.procs.2020.01.034.

L. Blanchet et al., “Constructing bi-plots for random forest: Tutorial,” Anal. Chim. Acta, vol. 1131, pp. 146–155, 2020, doi: https://doi.org/10.1016/j.aca.2020.06.043.

S. Wangchuk and T. Bolch, “Mapping of glacial lakes using Sentinel-1 and Sentinel-2 data and a random forest classifier: Strengths and challenges,” Sci. Remote Sens., vol. 2, p. 100008, 2020, doi: https://doi.org/10.1016/j.srs.2020.100008.

M. Wainberg, B. Alipanahi, and B. J. Frey, “Are random forests truly the best classifiers?,” vol. 17, pp. 1–5, 2016.

S. Ghosh and A. Das, “Wetland conversion risk assessment of East Kolkata Wetland: A Ramsar site using random forest and support vector machine model,” J. Clean. Prod., vol. 275, p. 123475, 2020, doi: https://doi.org/10.1016/j.jclepro.2020.123475.

Z. Fu and A. Robles-Kelly, “Discriminant Absorption-Feature Learning for Material Classification,” Geosci. Remote Sensing, IEEE Trans., vol. 49, pp. 1536–1556, 2011, doi: 10.1109/TGRS.2010.2086462.

R. M. Parish, “The Application of Visible / Near-Infrared Reflectance ( VNIR ) Spectroscopy to Chert : A Case Study from the Dover Quarry Sites , Tennessee,” vol. 26, no. 3, pp. 420–439, 2011, doi: 10.1002/gea.20354.

S. Li, H. Wu, D. Wan, and J. Zhu, “Knowledge-Based Systems An effective feature selection method for hyperspectral image classification based on genetic algorithm and support vector machine,” Knowledge-Based Syst., vol. 24, no. 1, pp. 40–48, 2011, doi: 10.1016/j.knosys.2010.07.003.

W. Heldens, T. Esch, U. Heiden, and S. Dech, “Potential of hyperspectral remote sensing for characterisation of urban structure in Munich,” 2008, pp. 94–103.

Astrium, Pléiades Imagery User Guide, no. October. 2012.

X. Meng, H. Shen, H. Li, L. Zhang, and R. Fu, “Review of the pansharpening methods for remote sensing images based on the idea of meta-analysis: Practical discussion and challenges,” Inf. Fusion, vol. 46, pp. 102–113, 2019, doi: https://doi.org/10.1016/j.inffus.2018.05.006.

M. Ehlers, “Multisensor image fusion techniques in remote sensing,” ISPRS J. Photogramm. Remote Sens., vol. 46, no. 1, pp. 19–30, 1991, doi: https://doi.org/10.1016/0924-2716(91)90003-E.

A. E. Bayá and M. G. Larese, “Pixel sampling by clustering,” Expert Syst. Appl., vol. 159, p. 113576, 2020, doi: https://doi.org/10.1016/j.eswa.2020.113576.

Astrium, “SPOT 6 & SPOT 7 Imagery User Guide,” no. July, 2013.

C. Lei et al., “A comparison of random forest and support vector machine approaches to predict coal spontaneous combustion in gob,” Fuel, vol. 239, pp. 297–311, 2019, doi: https://doi.org/10.1016/j.fuel.2018.11.006.

DOI: http://dx.doi.org/10.18517/ijaseit.11.5.13102


  • There are currently no refbacks.

Published by INSIGHT - Indonesian Society for Knowledge and Human Development