Abstract
This was the first study to assess improvements in accuracy related to ancillary data integration in Landsat 8 image classification since its launch in February 2013. Hoa Binh (northern Vietnam) is a mountainous province with natural forests at high elevations and planted forests on lower slopes. This study integrated a normalized difference vegetation index (NDVI) and digital elevation model (DEM) with the spectral bands of a Landsat 8 image to minimize the influence of shadows on image classification, distinguish between natural and planted forests, and produce a land cover map of Hoa Binh Province for forest inventory support. The image was geo-referenced to the projection of Vietnam (VN-2000) and digital numbers of bands 4 and 5 were converted to reflectance for the NDVI calculation. A DEM was generated from 1:50,000 topographic maps with 40-m contour intervals. A classification of accuracy was performed on a multisource dataset (bands 1–7, and 9, NDVI, and DEM) in comparison with results from a spectral image. The results indicated that user and producer accuracies increased by 14.36 and 11.29 % (natural forest), 7.27 and 10.33 % (regenerated forest), and 8.43 and 11.28 % (planted forest), respectively. Accuracies of identification of barren and agricultural lands, settlements, water bodies, and other classes increased insignificantly. Generally, overall accuracy improved by 5.23 % (from 84.51 to 89.74 %), and the kappa coefficient of the spectral classification was 0.72 compared with 0.86 for the ancillary classification. This study concluded that integration of DEM and NDVI data improved the accuracy of Landsat 8 image classification.
Similar content being viewed by others
References
Alsaaideh B, Al-Hanbali A, Tateishi R, Kobayashi T, Nguyen TH (2013) Mangrove forests mapping in the southern part of Japan using Landsat ETM+ with DEM. J Geogr Inf Syst 5:369–377. doi:10.4236/jgis.2013.54035
Anderson JR, Hardy EE, Roach JT, Witmer RE (1976) A land use and land cover classification system for use with remote sensor data. Department of interior, United States Government Printing Office, Washington
Cibula WG, Nyquist MO (1987) Use of topographic and climatological models in a geographical data base to improve Landsat MSS classification for Olympic national park. Photogramm Eng Remote Sens 53:67–75
Davidson A, Wang S (2004) The effects of sampling resolution on the surface albedos of dominant land cover types in the North American boreal region. Remote Sens Environ 93:211–224
De Jong W, Sam DD, Hung TV (2006) Forest rehabilitation in Vietnam: histories, realities and future. Center for International Forestry Research (CIFOR), Bogor
De Koninck R (1999) Deforestation in Vietnam. International Development Research Center (IDRC), Ottawa
Eiumnoh A, Shrestha P (2000) Application of DEM data to Landsat image classification: evaluation in a tropical wet-dry Landscape of Thailand. Photogramm Eng Remote Sens 66:297–304
Foody GM, Campbell NA, Trodd NM, Wood TF (1992) Derivation and applications of probabilistic measures of class membership from maximum likelihood classification. Photogramm Eng Remote Sens 58:1335–1341
Franklin SE (1987) Terrain analysis from digital patterns in geomorphometry and landsat MSS spectral response. Photogramm Eng Remote Sens 53:59–65
Gonzalez RC, Woods RE (2012) Digital image processing, 3rd edn. Dorling Kindersley, India
Guneriussen T, Johnsen H (1996) DEM corrected ERS-1 SAR data for snow monitoring. Int J Remote Sens 17:181–195
Jamieson NL, Lê TC, Rambo TA (1998) The development crisis in Vietnam’s mountains. East West Center Special Reports 6:1–32
Jensen JR (2012) Remote sensing of the Environment: an earth resource perspective. Dorling Kindersley, India
Kanungo DP, Sarkar S (2011) Use of multi-source data sets for land use/land cover classification in a hilly terrain for landslide study. J Disaster Dev 5:35–51
Kerkvliet BJ, Porter DJ (1995) Vietnam’s rural transformation. Westview Press, Boulder Co
Li H, Zhang S, Sun Y, Gao J (2011) Land cover classification with multi-source data using evidential reasoning approach. J Chin Geogr Sci 21:312–321. doi:10.1007/s11769-011-0465-1
Mather PM (1999) Computer processing of remotely sensed images: an introduction. Wiley, Chichester
Meyfroidt P, Lambin EF (2008) The causes of the reforestation in Vietnam. Land Use Policy 25:182–197. doi:10.1016/j.landusepol.2007.06.001
Parente C (2013) TOA reflectance and NDVI calculation for Landsat 7 ETM+ images of Sicily. In: Electronic international interdisciplinary conference, p 351
Peoples Council and Peoples Commission of Hoa Binh Province (2005) Chorography of HoaBinh. Publishing house of National Politics, Hanoi (In Vietnamese)
Saha AK (2005) Land cover classification using IRS LISS III image and DEM in a rugged terrain: a case study in Himalayas. Geocarto International 20:33–40
Sikor T (1998) Forest policy reform: from state to household forestry. In: Poffenberger M (ed) Stewards of Vietnam’s upland forests asian forestry network
USGS_a, Global Visualization Viewer. Available: http://glovis.usgs.gov/. Accessed 23 Jun 2015
USGS_b, Landsat 8 instruments. Available: http://landsat.usgs.gov/landsat8.php. Accessed 21 Jun 2015
USGS_c, Landsat mission. Available: http://landsat.usgs.gov/band_designations_landsat_satellites.php. Accessed 1 Dec 2015
Vietnam Ministry of Agriculture and Rural Development (2001) Stakeholders in program of five million ha forests. Technical report
Vũ TL (2005) Vietnam physical geography. Publishing house of Education University, Hanoi (In Vietnamese)
Watanachaturaporn P, Arora MK, Varshney PK (2008) Multisource classification using support vector machines: an empirical comparison with decision tree and neural network classifiers. Photogramm Eng Remote Sens 74:239–246. doi:10.14358/PERS.74.2.239
Xie Y, Sha Z, Yu M (2008) Remote sensing imagery in vegetation mapping: a review. J Plant Ecol UK 1:9–23
Yuan D, Elvidge CD, Lunetta RS (1998) Survey of multispectral methods for land cover change analysis. In: Remote change detection environmental monitoring methods and applications. Ann Arbor Press, Chelsea
Acknowledgments
We offer sincere thanks to Assoc. Prof. Dr. Nguyen Ngoc Thach and the staff at Hanoi University of Science (HUS), of the Vietnam National University (VNU), for supporting this paper. We are also grateful to the reviewers who made considerable contributions to the improvement of this article.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Nguyen, T.T.H., Pham, T.T.T. Incorporating ancillary data into Landsat 8 image classification process: a case study in Hoa Binh, Vietnam. Environ Earth Sci 75, 430 (2016). https://doi.org/10.1007/s12665-016-5278-1
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s12665-016-5278-1