Evaluation of the classification accuracy of NDVI index in the preparation of land cover map

Document Type : Research Paper

Authors

1 Center for Remote Sensing and GIS studies, Shahid Beheshti University, Tehran, Iran

2 Department of Geography, Yazd University, Yazd, Iran

Abstract

The preparation of land cover maps provides the possibility of studying the impact of land surface changes on sustainable development and is significant for a wide range of important issues at the global level. The current research aims to facilitate the preparation of land cover maps using the classification of Normalized Difference Vegetation Index (NDVI) values ​​and prepare land cover maps from it. For this purpose, first, two complete consecutive Landsat-8 scenes of parts of Iran and Turkmenistan were selected for August 30, 2021. Then the images were classified using supervised classification algorithms including Neural Network Classification (NNC), maximum Likelihood Classification (MLC), Support Vector Machine (SVM), Minimum Distance (MinD) and Mahalanobis Distance (MahD). In the next step, to perform an evaluation, by using a thousand ROI for a test, the overall accuracy, kappa coefficient, user accuracy and producer accuracy of the map produced by each of the algorithms were calculated. Then, using the most optimal algorithm, the threshold of NDVI image values ​​was extracted in order to classify it and the obtained map was re-evaluated for accuracy. Among the evaluated algorithms, the MLC algorithm had the most optimal performance with a kappa coefficient of 0.75 and overall accuracy of 80.86%. The results of evaluating the accuracy of the NDVI Based land cover Classification (NBC) index also indicated that this map has extracted the land cover map with an overall accuracy of 83% and a Kappa coefficient of 0.77. This index showed good performance in the classification of Bare Land Class (BLC), Water Area Class (WAC) and Salt Marsh Class (SMC) with user accuracy and producer accuracy above 94%. This is while the Agricultural Land Class (ALC) and Vegetation Class (VC) were classified by this index with producer accuracy of above 73% and user accuracy of 69% and 97%, respectively. The results of this research indicate the acceptable accuracy of NDVI index values ​​for the production of natural land cover maps and can be used in order to prepare these maps for geographic monitoring and achieving sustainable environmental development.

Keywords


References 
 
Aburas M. M., S. H. Abdullah, M. F. Ramli, & Z. H. Ash’aari, 2015. Measuring land cover change in Seremban, Malaysia using NDVI index. Procedia Environmental Sciences, 30; 238-243. Ahmad, A., & S. Quegan, 2012. Analysis of maximum likelihood classification on multispectral data. Applied Mathematical Sciences, 6(129); 6425-6436.  Ahmadi, H., & A. Nusrath, 2010. Vegetation change detection of Neka River in Iran by using remotesensing and GIS. Journal of geography and geology, 2(1); 58.  Alavipanah, S. K., M. Karimi Firozjaei, M., Sedighi, A., Fathololoumi, S., Zare Naghadehi, S., Saleh, S., & P. M.Atkinson, 2022. The Shadow Effect on Surface Biophysical Variables Derived from Remote Sensing: A Review. Land, 11(11); 1-30. Asadi M, Oshnooei-Nooshabadi A, Saleh Sa, Habibnezhad F, Sarafraz-Asbagh S, Van Genderen JL, 2022. Simulation of Urban Sprawl by Comparison Cellular Automata-Markov and ANN. ?????? Avdan, U., & G. Jovanovska, 2016. Algorithm for automated mapping of land surface temperature using LANDSAT 8 satellite data. Journal of Sensors, 2016; 1-8.  Bhandari, A., A. Kumar, & G. Singh, 2012. Feature extraction using Normalized Difference Vegetation Index (NDVI): A case study of Jabalpur city. Procedia technology, 6; 612-621.  Bischof, H., W. Schneider, & A. J. Pinz, 1992. Multispectral classification of Landsat-images using neural networks. IEEE Transactions on Geoscience and Remote Sensing, 30(3); 482-490.  Bishop, C. M., 1995. Neural networks for pattern recognition. Oxford University Press.  Chang, Y., K. Hou, X. Li, Y. Zhang, & P. Chen. (2018). Review of land use and land cover change research progress. IOP Conference Series: Earth and Environmental Science. pp. 12-87 Collobert, R., & J. Weston. (2008). A unified architecture for natural language processing: Deep neural networks with multitask learning. Proceedings of the 25th international conference on Machine learning. pp, 160-167. Dean, A., & G. Smith, 2003. An evaluation of per-parcel land cover mapping using maximum likelihood class probabilities. International Journal of Remote Sensing, 24(14); 2905-2920.  DeFries, R. S., & J. Townshend, 1994. NDVI-derived land cover classifications at a global scale. International Journal of Remote Sensing, 15(17); 3567-3586.  Exelis Visual Information Solutions Inc, 2015. ENVI 5.3 help. Fan, H., X. Fu, Z. Zhang, & Q. Wu, 2015. Phenology-based vegetation index differencing for mapping of rubber plantations using Landsat OLI data. Remote Sensing, 7(5); 6041-6058.  Ghayebi, A., A. Ahmadi, & B. Bigdeli, 2022. Investigating the surface changes of Urmia Lake using the integration of Landsat-8 and Sentinel-2 satellite data. Journal of RS and GIS for Natural Resources. Hacihaliloglu, I., & M. Karta. (2004). DCT and DWT based image compression in remote sensing images. IEEE Antennas and Propagation Society Symposium, 2004; 3856-3858. Hamimi, Z., W. Hagag, S. Kamh, & A. El-Araby, 2020. Application of remote-sensing techniques in geological and structural mapping of Atalla Shear Zone and Environs, Central Eastern Desert, Egypt. Arabian Journal of Geosciences, 13(11); 1-27.  Huang, C., L. Davis, & J. Townshend, 2002. An assessment of support vector machines for land cover classification. International Journal of remote sensing, 23(4); 725-749.  Ishtiaque, A., M. Shrestha, & N. Chhetri, 2017. Rapid urban growth in the Kathmandu Valley, Nepal: Monitoring land use land cover dynamics of a himalayan city with landsat imageries. Environments, 4(4); 1-16.  Jeevalakshmi, D., S. N. Reddy, & B. Manikiam. (2016). Land cover classification based on NDVI using LANDSAT8 time series: A case study Tirupati region. 2016 International Conference on Communication and Signal Processing (ICCSP). pp. 1332-1335.  Jensen, J. R., 1996. Introductory digital image processing: a remote sensing perspective. Prentice-Hall Inc.  Kadavi, P. R., & C.-W. Lee, 2018. Land cover classification analysis of volcanic island in Aleutian Arc using an artificial neural network (ANN) and a support vector machine (SVM) from Landsat imagery. Geosciences Journal, 22(4); 653-665.  
 340                                                                                                                        DESERT, 27-2, 2022 
 
Kavzoglu, T., & I. Colkesen, 2009. A kernel functions analysis for support vector machines for land cover classification. International Journal of Applied Earth Observation and Geoinformation, 11(5); 352-359.  Li, C., J. Wang, L. Wang, L. Hu, & P. Gong, 2014. Comparison of classification algorithms and training sample sizes in urban land classification with Landsat thematic mapper imagery. Remote Sensing, 6(2); 964-983.  Li, X., Y. Zhou, G. R. Asrar, M. Imhoff, & X. Li, 2017. The surface urban heat island response to urban expansion: A panel analysis for the conterminous United States. Science of the Total Environment, 605; 426-435.  Maleki M., J.L. Van Genderen, S.M. Tavakkoli-Sabour, S.S. Saleh, E. Babaee, 2020. Land use/cover change in Dinevar rural area of West Iran during 2000–2018 and its prediction for 2024 and 2030. Geogr.Tech., 15; 93-105. Mansourmoghaddam, M., H. R. Ghafarian Malamiri, I. Rousta, H. Olafsson, & H. Zhang, 2022a. Assessment of Palm Jumeirah Island’s Construction Effects on the Surrounding Water Quality and Surface Temperatures during 2001–2020. Water, 14(4); 1-16. Mansourmoghaddam, M., H. R. Ghafarian Malamiri, F. Arabi Aliabad, M. Fallah Tafti, M. Haghani, & S. Shojaei, 2022b. The Separation of the Unpaved Roads and Prioritization of Paving These Roads Using UAV Images. Air, Soil and Water Research, 15; 1-10. Mansourmoghaddam M., I. Rousta, M. S. Zamani, M. H. Mokhtari, M. Karimi Firozjaei, S. K. Alavipanah. 2022c. Investigating And Modeling the Effect of The Composition and Arrangement of The Landscapes of Yazd City on The Land Surface Temperature Using Machine Learning and Landsat-8 and Sentinel-2 Data. Iranian Journal of Remote Sensing & GIS, 15(3). Mansourmoghaddam, M., I. Rousta, M. Zamani, M. H. Mokhtari, M. Karimi Firozjaei, & S. K. Alavipanah, 2021. Study and prediction of land surface temperature changes of Yazd city: assessing the proximity and changes of land cover. Journal of RS and GIS for Natural Resources, 12(4); 1-27.  Mohammadnazhad, P., M. Moameri, A. Ghorbani, F. Dadjou, & V. Mohammadi, 2022. Modeling aboveground net primary production using Landsat-8 indices in Siahpoosh and Ganjgah rangelands of Ardabil province, Iran. Journal of RS and GIS for Natural Resources, 14(3); 13-16.  Paola JD., R. A. Schowengerdt, 1995. A detailed comparison of backpropagation neural network and maximum-likelihood classifiers for urban land use classification. IEEE Transactions on Geoscience, 33(4); 981-996. Richards, J.A., 1999. Remote Sensing Digital Image Analysis Berlin: Springer-Verlag; p. 240. Rouse Jr, J. W., R. H. Haas, J. Schell, & D. Deering. (1973). Monitoring the vernal advancement and retrogradation (green wave effect) of natural vegetation (No. E75-10354). Sabins Jr, F. F. (1986). Remote sensing: principles and interpretation; p. 280-289. Sexton, J. O., D. L. Urban, M. J. Donohue, & C. Song, 2013. Long-term land cover dynamics by multitemporal classification across the Landsat-5 record. Remote sensing of environment, 128; 246-258.  Shang, S., K.-N. He, Z.-B. Wang, T. Yang, M. Liu, & X. Li, 2020. Sea clutter suppression method of HFSWR based on RBF neural network model optimized by improved GWO algorithm. Computational Intelligence and Neuroscience, 2020; 1-10.  Silakhori, E., & M. Ownegh, 2018. Identification and differentiating of geomorphology facies of Sabzevar region using Remote sensing and GIS. Journal of RS and GIS for Natural Resources, 9(1); 113-130. Stathopoulou, M., C. Cartalis, & M. Petrakis, 2007. Integrating Corine Land Cover data and Landsat TM for surface emissivity definition: application to the urban area of Athens, Greece. International Journal of Remote Sensing, 28(15); 3291-3304.  Story, M., & R. G. Congalton, 1986. Accuracy assessment: a user’s perspective. Photogrammetric Engineering and remote sensing, 52(3); 397-399.  Strahler, A. H., 1980. The use of prior probabilities in maximum likelihood classification of remotely sensed data. Remote sensing of Environment, 10(2); 135-163.  Taufik, A., S. S. S. Ahmad, & A. Ahmad, 2016. Classification of landsat 8 satellite data using NDVI tresholds. Journal of Telecommunication, Electronic and Computer Engineering (JTEC), 8(4); 3740.  Thompson, W. D., & S. D. Walter, 1988. A reappraisal of the kappa coefficient. Journal of clinical epidemiology, 41(10); 949-958.  
  Evaluation of the classification accuracy of NDVI index in the preparation …                                                                     341  
 
Turner, B. L., D. Skole, S. Sanderson, G. Fischer, L. Fresco, & R. Leemans, 1995. Land-use and landcover change: science/research plan. [No source information available].  Wei, W., & J. M. Mendel, 2000. Maximum-likelihood classification for digital amplitude-phase modulations. IEEE transactions on Communications, 48(2); 189-193.  Whiteside, T. G., G. S. Boggs, & S. W. Maier, 2011. Comparing object-based and pixel-based classifications for mapping savannas. International Journal of Applied Earth Observation and Geoinformation, 13(6); 884-893.  Xiu, L.-n., & X.-n. Liu, 2003. Current status and future direction of the study on artificial neural network classification processing in remote sensing. Remote Sensing Technology and Application, 18(5); 339-345.  Yusuf, F. R., K. B. Santoso, M. U. L. Ningam, M. Kamal, & P. Wicaksono. (2018). Evaluation of atmospheric correction models and Landsat surface reflectance product in Daerah Istimewa Yogyakarta, Indonesia. IOP Conference Series: Earth and Environmental Science, 169; 1-10. Zare Naghadehi S., M. Asadi, M. Maleki, S. M. Tavakkoli-Sabour, J.L. Van Genderen, S.S. Saleh, 2021. Prediction of Urban Area Expansion with Implementation of MLC, SAM and SVMs’ Classifiers Incorporating Artificial Neural Network Using Landsat Data. ISPRS International Journal of Geo Information, 10(8); 1-16. Zhang, J., C. Lu, J. Wang, X.-G. Yue, S.-J. Lim, Z. Al-Makhadmeh, & A. Tolba, 2020. Training convolutional neural networks with multi-size images and triplet loss for remote sensing scene classification. Sensors, 20(4); 1-21.  Ziaul, S., Pal S. 2016. Image based surface temperature extraction and trend detection in an urban       area of West Bengal, India. Journal of Environmental Geography, 9(3-4); 13-25.