Abstract
This study looks into the development of multi-level classification approach for land use change mapping in Indian cities using Landsat imageries. In this study, we mapped 47 Indian cities at different time frames 1990, 2000, 2010, and 2017. We started with traditional classification methods, but results provided unsatisfactory accuracy levels. Thus, we employed multiple classification techniques to achieve results with higher accuracy. The paper captures the evaluation of different classification techniques—hybrid, unsupervised, decision tree classification (DTC), and object-based image analysis (OBIA). The results suggest improvement in accuracy levels by using multi-level classification for different cities at different stages of the classification process. The most prominent is the hybrid classification technique; 14 cities out of 47 reached to accuracy above 72% through hybrid classification. For problematic classes, we used DTC, OBIA, and unsupervised classification techniques after masking the datasets. DTC was used in cities with a greater number of problems in datasets. For example, in the case of Kochi City, the accuracy at the initial level was reported 51% through unsupervised classification which improved to 77% (supervised classification), and finally, it reached 90% by DTC technique. The overall accuracy achieved through the multi-level classification approach described in this paper for the 47 Indian cities ranges from 81 to 93%.
Similar content being viewed by others
Notes
Stripping effect is observed in the images when data is loss by sensor while viewing the geometry. Band stripping is caused by miscalibration of sensor either at the detector level or at scan level.
A mixed pixel issue occurs when image element signifies properties of more than one surface land cover type. Mixed pixels are found at two concerns, firstly at “edges of large objects” and objects with smaller dimensions for instance agricultural fields, rivers or highways, farms or ponds, or even bushes and trees in sparsely vegetated cover. Secondly appear when imaged objects are smaller in proportion as compared to spatial resolution of the satellite. Landsat TM images reported mixed pixels issues in water 29.6% and 68.3% in vegetation cover (Klein-Gebbinck 1998).
The Landsat calibration refers to procedures that convert from pixel value to radiance value of biophysical cover of the earth surface (Chavez 1989).
Image registration is the process of transforming datasets into geographic coordinate system acquired from different satellite, sensors, and timeframe.
The signature value of the area is altered by suspension of fine solid or liquid particles in the air. Aerosols can be natural or anthropogenic. Naturally formed aerosols are fog, soil dust, sea salt, volcanoes, botanical debris, forest fires. Direct emission is particulate air pollution and smoke, haze (Lioy and Kneip 1980).
“Shadow occurs when an object totally or partially occludes light directly from the light source. Shadows can be divided into two classes: cast and self” (Arevalo et al. 2005). In remote sensing, shadowing occurs in the images by different objects such as “cloud (cloud shadow), mountain (topographic shadow), and urban material (urban shadow)” (Shahtahmassebi et al. 2013).
References
Adejoke, A. O., & Badaru, Y. U. (2014). Accuracy assessment of pixel-based image classification of Kwali council area, Abuja, Nigeria. Journal of Natural Science Research, 4(22), 133–140.
Aguilar, C., Zinnert, J., Polo, M., & Young, D. (2012). NDVI as an indicator for changes in water availability to woody vegetation. Ecological Indicators,23, 290–300.
Alrababah, M. A., & Alhamad, M. N. (2006). Land use/cover classification of arid and semi-arid Mediterranean landscapes using Landsat ETM. International Journal of Remote Sensing, 27(13), 2703–2718. https://doi.org/10.1080/01431160500522700.
Amalisana, B., Rokhmatullah, & Hernina, R. (2017). Land cover analysis by using pixel-based and object-based image classification method in Bogor. In The 5th geoinformation science symposium 2017 (GSS 2017): IOP conference series: Earth and environmental science (p. 98).
Arevalo, V., González, J., Valdes, J., & Ambrosio, G. (2005). Detecting shadows in QuickBird satellite images. In ISPRS Commission VII Mid-term symposium ′remote sensing: from pixels to processes′. En-schede, The Netherland.
Arulbalaji, P., & Gurugnanam, B. (2014). Evaluating the normalized difference vegetation index using landsat data by ENVI in Salem district, Tamilnadu, India. International Journal of Development Research,4(9), 1845–1846.
Atkinson, P., & Aplin, P. (2004). Spatial variation in land cover and choice of spatial resolution for remote sensing. International Journal of Remote Sensing,25(18), 3687–3702. https://doi.org/10.1080/01431160310001654383.
Bartolucci, L., Robinson, B., & Silva, L. (1977). Field measurements of the spectral response of natural waters. Photogrammetric Engineering and Remote Sensing,43, 595–598.
Bryant, N., Zobrist, A., Walker, R., & Gokhman, B. (1995). An analysis of Landsat thematic mapper P-product internal geometry and conformity to earth surface geometry. Photogrammetric Engineering and Remote Sensing,51, 1435–1447.
Caetano, M. (Ed.). (2007). Image classification. Retrieved from ESA Advances Training Course on Land Remote Sensing.
Campbell, J., & Wynne, R. (2011). Introduction to remote sensing. New York: Guilford Press.
Chang, C.w., Shi, C., Liew, S. C., & Kwoh, L. (2014). Object-oriented land use cover classification of Landsat 8 OLI images in Sumatra. International Geoscience and Remote Sensing Symposium (IGARSS). https://doi.org/10.1109/IGARSS.2014.6947422.
Chavez, P. (1989). Radiometric calibration of Landsat thematic mapper multispectral images. Photogrammetric Engineering and Remote Sensing,55, 1285–1294.
Chavez, P. (1996). Image-based atmospheric corrections- revisited and improved. Photogrammetric Engineering and Remote Sensing,62(9), 1025–1036.
Chen, Y., Dou, P., & Yang, X. (2017). Improving land use/cover classification with a multiple classifier system using AdaBoost integration technique. Remote Sensing,9(10), 1055.
Choodarathnakara, A., Kumar, A., Koliwad, S., & Patil, G. (2012). Mixed pixels: A challenge in remote sensing data classification for improving performance. International Journal of Advanced Research in Computer Engineering & Technology (IJARCET),1(9), 261.
Congalton, R., & Green, K. (2019). Assessing the accuracy of remotely sensed data: Principles and practices (3rd ed.). Boca Raton: CRC Press.
Coppin, P., Jonckheere, I., Nackaerts, K., Muys, B., & Lambin, E. (2004). Digital change detection methods in ecosystem monitoring: A review. International Journal of Remote Sensing,25(9), 1565–1596.
DeFries, R., & Chan, J.-W. (2000). Multiple criteria for evaluating machine learning algorithms for land cover classification from satellite data. Remote Sensing of Environment,74(3), 503–515. https://doi.org/10.1016/S0034-4257(00)00142-5.
Demir, B., Minello, L., & Bruzzone, L. (2014). Definition of effective training sets for supervised classification of remote sensing images by a novel cost-sensitive active learning method. IEEE Transactions on Geoscience and Remote Sensing,52(2), 1272–1284.
Di Gregorio, A., & Jansen, L. (1998). A new concept for a land-cover classification system. Land,2(1), 55–65.
Dorren, L., Maier, B., & Seijmonsbergen, A. (2003). Improved Landsat-based forest mapping in steep mountainous terrain using object-based classification. Forest Ecology and Management,183(1–3), 31–46.
Dronova, I. (2015). Object-based image analysis in wetland research: A review. Remote Sensing,7(5), 6380–6413.
Duong, N. (2012). Waterbody extraction from multispectral image by spectral pattern analysis. In International archives of the photogrammetry, remote sensing and spatial information sciences (pp. 181–186). Melbourne: XXII ISPRS Congress.
Fichera, C., Modica, G., & Pollino, M. (2012). Land Cover classification and change-detection analysis using multi-temporal remote sensed imagery and landscape metrics. European Journal of Remote Sensing,45(1), 1–18.
Friedl, M., & Brodley, C. (1997). Decision tree classification of land cover from remotely sensed data. Remote Sensing of Environment,61(3), 399–409.
Garg, A., Avashia, V., & Parihar, S. (2018). Land use change trends of Indian cities: A bird’s-eye view-vulnerabilities of unplanned urban growth. New Delhi: Sage India.
Green, E., Mumby, P., Edwards, A., & Clark, C. (1996). A review of remote sensing for the assessment and management of tropical coastal resources. Coastal Management,24(1), 1–40.
Guha, S. (2016). Capability of NDVI technique in detecting mangrove vegetation. International Journal of Advanced Biological Research,6(2), 253–258.
Hecher, J., Filippi, A., Guneralp, I., & Paulus, G. (2012). Extracting River features from remotely sensed data: An evaluation of thematic correctness (Doctoral dissertation, Department of Geography, Texas A&M University), pp. 187–196.
Holben, B. (1986). Characteristics of maximum-value composite images from temporal AVHRR data. International Journal of Remote Sensing,7(11), 1417–1434.
Hua, L., Man, W., Wang, Q., & Zhao, X. (2012). A new decision tree classification approach for extracting urban land from Landsat TM in a coastal city, China. In Fourth international symposium on information science and engineering, (pp. 282–286).
Hussain, M., Chen, D., Cheng, A., Wei, H., & Stanley, D. (2013). Change detection from remotely sensed images: From pixel-based to object-based approaches. ISPRS Journal of Photogrammetry and Remote Sensing,80, 91–106.
Islam, K., Jashimuddin, M., Nath, B., & Nath, T. K. (2018). Land use classification and change detection by using multi-temporal remotely sensed imagery: the case of Chunati wildlife sanctuary, Bangladesh. The Egyptian Journal of Remote Sensing and Space Science, 21(1), 37–47. https://doi.org/10.1016/j.ejrs.2016.12.005.
Kantakumar, L., & Neelamsetti, P. (2015). Multi-temporal land use classification using hybrid approach. The Egyptian Journal of Remote Sensing and Space Science,18(2), 289–295.
Keuchel, J., Naumann, S., Heiler, M., & Siegmund, A. (2003). Automatic land cover analysis for Tenerife by supervised classification using remotely sensed data. Remote Sensing of Environment,86(4), 530–541. https://doi.org/10.1016/S0034-4257(03)00130-5.
Kindu, M., Schneider, T., Teketay, D., & Knoke, T. (2013). Land use/land cover change analysis using object-based classification approach in Munessa-Shashemene landscape of the Ethiopian highlands. Remote Sensing,5(5), 2411–2435.
Klein-Gebbinck, M. S. (1998). Decomposition of mixed pixels in remote sensing images to improve the area estimation of agricultural fields. Veenendaal: University of Nijmegen, University Press.
Lee, L., Chen, L., Wang, X., & Zhao, J. (2011). Use of Landsat TM/ETM+ data to analyze urban heat island and its relationship with land use/cover change. In International conference on remote sensing, environment and transportation engineering (pp. 922–927).
Li, M., Zang, S., Zhang, B., Li, S., & Wu, C. (2014). A review of remote sensing image classification techniques: The role of spatio-contextual information. European Journal of Remote Sensing,47(1), 389–411.
Lioy, P., & Kneip, T. (1980). Aerosols: Anthropogenic and natural sources and transport. Journal of Air Pollution Control Association,30(4), 358–361.
Liu, W., Gopal, S., & Woodcock, C. (2004). Uncertainty and confidence in land cover classification using a hybrid classifier approach. Photogrammetric Engineering and Remote Sensing,70(8), 963–971.
Liu, J., & Mason, P. (2009). Essential image processing and GIS for remote sensing. Hoboken: Wiley.
Lu, D., & Weng, Q. (2007). A survey of image classification methods and techniques for improving classification performance. International Journal of Remote Sensing,28(5), 823–870.
Luus, F., Salmon, B., van den Bergh, F., & Maharaj, B. (2015). Multiview deep learning for land-use classification. IEEE Geoscience and Remote Sensing Letters,12(12), 2448–2452.
Ma, L., Li, M., Ma, X., Cheng, L., Du, P., & Liu, Y. (2017). A review of supervised object-based land-cover image classification. ISPRS Journal of Photogrammetry and Remote Sensing,130, 277–293. https://doi.org/10.1016/j.isprsjprs.2017.06.001.
Mandal, J., Ghosh, N., & Mukhopadhyay, A. (2019). Urban growth dynamics and changing land-use land-cover of megacity Kolkata and its environs. Journal of the Indian Society of Remote Sensing,47, 1707–1725. https://doi.org/10.1007/s12524-019-01020-7.
Manandhar, R., Odeh, I., & Ancev, T. (2009). Improving the accuracy of land use and land cover classification of landsat data using post-classification enhancement. Remote Sensing., 1(3), 330–344. https://doi.org/10.3390/rs1030330.
Masocha, M., & Skidmore, A. (2011). Integrating conventional classifiers with a GIS expert system to increase the accuracy of invasive species mapping. International Journal of Applied Earth Observation and Geoinformation (JAG),13(3), 487–494.
Mather, P., & Koch, M. (2011). Computer processing of remotely-sensed images: An introduction (4th ed.). Hoboken: Wiley.
Mather, P., & Tso, B. (2009). Classification methods for remotely sensed data (2nd ed.). Boca Raton: CRC Press.
McCallum, I., Obersteiner, M., Nilsson, S., & Shvidenko, A. (2006). A spatial comparison of four satellite derived 1 km global land cover datasets. International Journal of Applied Earth Observation and Geoinformation,8(4), 246–255.
Meer, M., & Mishra, A. (2020). Remote sensing application for exploring changes in land-use and land-cover over a district in Northern India. Journal of the Indian Society of Remote Sensing. https://doi.org/10.1007/s12524-019-01095-2.
Meyer, W., & Turner, B., II. (1992). Human population growth and global land-use/cover change. Annual Review of Ecology and Systematics,23, 39–61.
Mohammady, M., Moradi, H., Zeinivand, H., & Temme, A. (2015). A comparison of supervised, unsupervised and synthetic land use classification methods in the north of Iran. International Journal of Environmental Science and Technology,12, 1515–1526.
Morfitt, R., Storey, J., Choate, M., Rengarajan, R., & Lubke, M. (2017). Landsat 8 geometry status. Sioux Falls: USGS Earth Resources Observation and Science (EROS) Center.
Moskal, L. M., Styers, D. M., & Halabisky, M. (2011). Monitoring urban tree cover using object-based image analysis and public domain remotely sensed data. Remote Sensing,3(10), 2243–2262.
Nazmfar, H., & Jafarzadeh, J. (2018). Classification of satellite images in assessing urban land use change using scale optimization in object-oriented processes (A case study: Ardabil city, Iran). Journal of the Indian Society of Remote Sensing,46, 1983–1990. https://doi.org/10.1007/s12524-018-0850-7.
Nicholas, C. T. (2012). Land use/land cover classification: Methods to overcome pixel confusion and the effects of tree shadows in very high resolution multispectral imagery. Maryville: Northwest Missouri State University.
Pal, M., & Mather, P. (2003). An assessment of the effectiveness of decision tree methods for land cover classification. Remote Sensing of Environment,86(4), 554–565. https://doi.org/10.1016/S0034-4257(03)00132-9.
Parthasarathy, R., Baranwal, A., Gupta, M., & Parihar, S. (2014). P5 shoreline changes in south Gujarat coast: Understanding linkages, threats and impacts.
Peña, J., Gutiérrez, P., Hervás-Martínez, C., Six, J., Plant, R., & López-Granados, F. (2014). Object-based image classification of summer crops with machine learning methods. Remote Sensing,6(6), 5019–5041.
Phiri, D., & Morgenroth, J. (2017). Developments in landsat land cover classification methods: A review. Remote Sensing,9(9), 967.
Rahman, M.d., Ullah, R., & Lan, M., Sri Sumantyo, J., Kuze, H., & Tateishi, R. (2013). Comparison of Landsat image classification methods for detecting mangrove forests in Sundarbans. International Journal of Remote Sensing, 34, 1041–1056. https://doi.org/10.1080/01431161.2012.717181.
Ramachandran, R., & Reddy, C. (2017). Monitoring of deforestation and land use changes (1925–2012) in Idukki district, Kerala, India using remote sensing and GIS. Journal of the Indian Society of Remote Sensing,45, 163–170. https://doi.org/10.1007/s12524-015-0521-x.
Rozenstein, O., & Karnieli, A. (2011). Comparison of methods for land-use classification incorporating remote sensing and GIS inputs. Applied Geography,31(2), 533–544.
Rwanga, S., & Ndambuki, J. (2017). Accuracy assessment of land use/land cover classification using remote sensing and GIS. International Journal of Geosciences., 8, 611–622. https://doi.org/10.4236/ijg.2017.84033.
Sader, S. A., Ahl, D., & Liou, W. S. (1995). Accuracy of Landsat-TM and GIS rule-based methods for forest wetland classification in Maine. RemoteSensing of Environment, 53, 133–144.
Schowengerdt, R. (2006). Remote sensing: Models and methods for image processing. Cambrigde: Academic Press.
Schweitzer, C., Rücker, G., Conrad, C., Strunz, G., & Bendix, J. (2005). ‘Knowledge-based land use classification combining expert knowledge, GIS, multi-temporal Landsat 7 ETM+ and MODIS time series data in Khorezm. Uzbekistan: Göttingen GIS & Remote Sensing Days.
Shahtahmassebi, A., Yang, N., Wang, K., Moore, N., & Shen, Z. (2013). Review of shadow detection and de-shadowing methods in remote sensing. Chinese Geographical Science,23, 403–420.
Sharma, R., Ghosh, A., & Joshi, P. (2013). Decision tree approach for classification of remotely sensed satellite data using open source support. Journal of Earth System Science,122, 1237–1247.
Sharma, K., Jain, S., & Garg, P. (1984). Monitoring landuse and landcover changes using landsat images. Journal of the Indian Society of Photo-Interpretation and Remote Sensing,12, 65–70.
Son, N., Chen, C., Chang, N., Chen, C., Chang, L., & Thanh, B. (2015). Mangrove mapping and change detection in Ca Mau Peninsula, Vietnam, using landsat data and object-based image analysis. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 8(2), 503–510. https://doi.org/10.1109/JSTARS.2014.2360691.
Song, X.-P., Huang, C., Feng, M., Sexton, J., Channan, S., & Townshend, J. (2014). Integrating global land cover products for improved forest cover characterization: An application in North America. International Journal of Digital Earth,7(9), 709–724.
Steele, B. (2000). Combining multiple classifiers: An application using spatial and remotely sensed information for land cover type mapping. Remote Sensing of Environment,74(3), 545–556. https://doi.org/10.1016/S0034-4257(00)00145-0.
Storey, J., & Choate, M. (2000). Landsat 7 on-orbit geometric calibration and performance. In Proceedings of SPIE-The international society for optical engineering.
Tampubolon, T., Abdullah, K., & Hwee, L. (2013). Comparison of pixel and object based approaches using landsat data for land use and land cover classification in coastal zone of Medan, Sumatera. International Journal of Tomography & Simulation, 24(3).
Tarantino, E., Novelli, A., Aquilino, M., Figorito, B., & Fratino, U. (2015). Comparing the MLC and JavaNNS approaches in classifying multi-temporal LANDSAT satellite imagery over an ephemeral river area. International Journal of Agricultural and Environmental Information Systems (IJAEIS),6(4), 20.
Tewolde, M., & Cabral, P. (2011). Urban sprawl analysis and modeling in Asmara, Eritrea. Remote Sensing,3, 2148–2165.
Tilahun, A., & Teferie, B. (2015). Accuracy assessment of land use land cover classification using google earth. American Journal of Environmental Protection, 4, 193–198. https://doi.org/10.11648/j.ajep.20150404.14.
Tucker, C., Grant, D., & Dykstra, J. (2004). NASA’s global orthorectified Landsat data set. American Society for Photogrammetry and Remote Sensing,10(3), 313–322.
Vaz, E., Taubenböck, H., Kotha, M., & Arsanjani, J. (2017). Urban change in Goa, India. Habitat International,68, 24–29.
Wang, X., & Chen, X. (2012). Classification of ASTER image using SVM and local spatial statistics Gi. In International conference on computer vision in remote sensing, (pp. 366–370). Xiamen.
Warrender, C., & Augusteijn, M. (1999). Fusion of image classifications using Bayesian techniques with Markov random fields. International Journal of Remote Sensing,20(10), 1987–2002.
Wulder, M., Masek, J., Cohen, W., Loveland, T., & Woodcock, C. (2012). Opening the archive: How free data has enabled the science and monitoring promise of Landsat. Remote Sensing of Environment,122, 2–10.
Yang, C.-C., Prasher, S., Enright, P., Madramootoo, C., Burgess, M., Goel, P., et al. (2003). Application of decision tree technology for image classification using remote sensing data. Agricultural Systems,76, 1101–1117.
Zhan, Q. (2003). A hierarchical object- based approach for urban land-use classification from remote sensing data. Enschede: International Institute for Geo-Information Science and Earth Observation.
Zhang, Q., Wang, J., Peng, X., Gong, P., & Shi, P. (2002). Urban built-up land change detection with road density and spectral information from multi-temporal Landsat TM data. International Journal of Remote Sensing,23(15), 3057–3078. https://doi.org/10.1080/01431160110104728.
Zhao, P., Zhao, J., Wu, J., Yang, Y., Xue, W., & Hou, Y. (2016). Integration of multi-classifiers in object-based methods for forest classification in the Loess plateau, China. ScienceAsia,42, 283–289.
Acknowledgements
This research study was partly funded by the Indo-Norwegian Cooperation Project (INCP-2014/10093), as well as DDP Initiative (ddpinitiative.org) and the International Climate Initiative (IKI) (18_I_326_Global_A_Climate Action After Paris). INCP was jointly undertaken by the Governments of India and Norway through University Grants Commission (UGC) India and The Norwegian Centre for International Cooperation in Education (SIU). The Federal Ministry for the Environment, Nature Conservation and Nuclear Safety (BMU) supports the DDP initiative on the basis of a decision adopted by the German Bundestag under the project titled “From NDCs to Pathways and Policies: Transformative Climate Action After Paris.”
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Appendices
Appendix 1: Land Use Shares for 47 Cities for 1990, 2000, 2010, and 2017
Agartala
Agra
Ahmedabad
Allahabad
Amritsar
Asansol
Aurangabad
Bengaluru
Bhopal
Chandigarh
Chennai
Dehradun
Delhi
Dhanbad
Durg-Bhilainagar
Faridabad
Gangtok
Ghaziabad
Guwahati
Hyderabad
Indore
Jabalpur
Jaipur
Jodhpur
Kanpur
Kochi
Kolkata
Kota
Lucknow
Ludhiana
Madurai
Mumbai
Mysuru
Nagpur
Nashik
Panaji
Patna
Pune
Rajkot
Shimla
Srinagar
Surat
Tiruchirapalli
Vadodara
Varanasi
Vasai-Virar
Vishakhapatnam
Appendix 2: Accuracy Assessment for all 47 Cities
S. No. | Cities | Accuracy (in percentage) | ||
---|---|---|---|---|
Classes | User | Producer | ||
1 | Agartala | Agriculture | 96.39 | 67.80 |
Built-up | 98.90 | 98.90 | ||
River | 95.59 | 96.30 | ||
Urban open | 96.77 | 95.24 | ||
Urban green | 66.12 | 97.56 | ||
Waterbody | 98.16 | 96.39 | ||
Overall accuracy | 91.92 | |||
Kappa coefficient | 90.24 | |||
2 | Agra | Agriculture | 91.60 | 82.76 |
Built-up | 100.00 | 98.23 | ||
River | 100.00 | 99.40 | ||
Urban open | 87.88 | 98.31 | ||
Urban green | 77.39 | 76.07 | ||
Waterbody | 100.00 | 98.75 | ||
Forest | 81.48 | 92.63 | ||
Overall accuracy | 91.63 | |||
Kappa coefficient | 90.10 | |||
3 | Ahmedabad | Agriculture | 84.75 | 90.91 |
Built-up | 93.75 | 91.84 | ||
River | 100.00 | 86.27 | ||
Urban open | 93.02 | 88.64 | ||
Urban green | 5.88 | 87.91 | ||
Waterbody | 71.01 | 100.00 | ||
Overall accuracy | 90.06 | |||
Kappa coefficient | 0.88 | |||
4 | Allahabad | Agriculture | 93.10 | 98.18 |
Built-up | 89.74 | 89.74 | ||
River | 79.17 | 79.17 | ||
Urban open | 97.50 | 97.50 | ||
Urban green | 94.44 | 89.47 | ||
Waterbody | 84.78 | 85.71 | ||
Overall accuracy | 107.09 | |||
Kappa coefficient | 0.88 | |||
5 | Amritsar | Agriculture | 72.31 | 85.45 |
Built-up | 98.13 | 98.13 | ||
Urban open | 97.40 | 87.21 | ||
urban green | 91.67 | 91.67 | ||
Waterbody | 100.00 | 97.30 | ||
Overall accuracy | 92.10 | |||
Kappa coefficient | 0.90 | |||
6 | Asansol | Agriculture | 88.96 | 78.38 |
Built-up | 100.00 | 97.94 | ||
River | 66.92 | 86.14 | ||
Urban open | 95.24 | 100.00 | ||
Urban green | 78.22 | 87.29 | ||
Waterbody | 100.00 | 84.24 | ||
Overall accuracy | 91.15 | |||
Kappa coefficient | 0.89 | |||
7 | Aurangabad | Agriculture | 91.73 | 89.05 |
Built-up | 89.38 | 100.00 | ||
River | 93.48 | 87.76 | ||
Urban open | 91.93 | 98.67 | ||
Urban green | 82.39 | 77.06 | ||
Waterbody | 95.29 | 98.78 | ||
Forest | 98.10 | 97.64 | ||
Overall accuracy | 91.81 | |||
Kappa coefficient | 90.18 | |||
8 | Bangalore | Agriculture | 85.42 | 82.00 |
Built-up | 83.33 | 62.50 | ||
River | 100.00 | 100.00 | ||
Urban open | 82.66 | 93.46 | ||
urban green | 81.63 | 83.33 | ||
Waterbody | 100.00 | 100.00 | ||
Forest | 93.88 | 95.83 | ||
Overall accuracy | 88.89 | |||
Kappa coefficient | 86.81 | |||
9 | Bhopal | Agriculture | 91.11 | 91.11 |
Built-up | 83.33 | 61.22 | ||
River | 100.00 | 100.00 | ||
Urban open | 88.27 | 95.33 | ||
Urban green | 87.69 | 87.69 | ||
Waterbody | 100.00 | 100.00 | ||
Forest | 94.85 | 95.83 | ||
Overall accuracy | 92.66 | |||
Kappa coefficient | 91.19 | |||
10 | Chandigarh | Agriculture | 82.20 | 84.35 |
Built-up | 98.36 | 98.36 | ||
River | 100.00 | 91.57 | ||
Urban open | 94.35 | 99.40 | ||
Urban green | 72.88 | 66.15 | ||
Waterbody | 81.58 | 100.00 | ||
Forest | 91.49 | 86.00 | ||
Overall accuracy | 91.62 | |||
Kappa coefficient | 89.99 | |||
11 | Chennai | Agriculture | 82.95 | 84.88 |
Built-up | 92.00 | 94.52 | ||
River | 100.00 | 95.10 | ||
Urban open | 95.83 | 81.18 | ||
Urban green | 84.78 | 84.78 | ||
Waterbody | 89.25 | 91.21 | ||
Bay | 65.38 | 85.00 | ||
Overall accuracy | 88.40 | |||
Kappa coefficient | 86.59 | |||
12 | Dehradun | Agriculture | 90.45 | 90.96 |
Built-up | 98.06 | 96.19 | ||
River | 87.10 | 96.43 | ||
Urban open | 98.77 | 81.63 | ||
Urban green | 67.35 | 75.86 | ||
Waterbody | 100.00 | 100.00 | ||
Forest | 87.84 | 89.04 | ||
Overall accuracy | 89.01 | |||
Kappa coefficient | 86.70 | |||
13 | Delhi (New Delhi) | Agriculture | 76.36 | 87.50 |
Built-up | 95.00 | 93.44 | ||
River | 89.41 | 96.20 | ||
Urban open | 85.29 | 90.63 | ||
Urban green | 96.67 | 69.88 | ||
Waterbody | 74.07 | 95.24 | ||
Forest | 97.06 | 95.65 | ||
Overall accuracy | 88.84 | |||
Kappa coefficient | 86.74 | |||
14 | Dhanbad | Agriculture | 86.67 | 96.30 |
Built-up | 96.30 | 88.64 | ||
River | 100.00 | 98.46 | ||
Urban open | 96.59 | 77.98 | ||
Urban green | 89.36 | 84.85 | ||
Waterbody | 100.00 | 100.00 | ||
Forest | 98.11 | 92.86 | ||
Mines | 78.71 | 98.39 | ||
Overall accuracy | 91.09 | |||
Kappa coefficient | 89.65 | |||
15 | Durg | Agriculture | 90.97 | 78.77 |
Built-up | 97.67 | 98.82 | ||
River | 87.23 | 93.18 | ||
Urban open | 97.17 | 92.79 | ||
Urban green | 87.26 | 95.80 | ||
Waterbody | 97.84 | 95.77 | ||
Overall accuracy | 91.97 | |||
Kappa coefficient | 89.70 | |||
16 | Faridabad | Agriculture | 92.59 | 76.92 |
Built-up | 96.55 | 91.80 | ||
River | 96.00 | 98.36 | ||
Urban open | 90.91 | 85.71 | ||
Urban green | 73.33 | 86.84 | ||
Waterbody | 91.67 | 100.00 | ||
Forest | 81.16 | 98.25 | ||
Overall accuracy | 90.25 | |||
Kappa coefficient | 88.61 | |||
17 | Gangtok | Agriculture | 81.63 | 95.24 |
Built-up | 94.92 | 73.68 | ||
River | 94.12 | 98.46 | ||
Urban open | 98.88 | 90.72 | ||
Urban green | 88.89 | 77.42 | ||
Waterbody | 96.67 | 93.55 | ||
Forest | 92.50 | 90.24 | ||
snow | 73.33 | 91.67 | ||
Overall accuracy | 88.55 | |||
Kappa coefficient | 86.86 | |||
18 | Ghaziabad | Agriculture | 88.64 | 83.57 |
Built-up | 97.73 | 97.73 | ||
River | 79.31 | 88.46 | ||
Urban open | 97.56 | 93.75 | ||
Urban green | 84.80 | 91.77 | ||
Waterbody | 95.71 | 91.78 | ||
Overall accuracy | 91.03 | |||
Kappa coefficient | 88.80 | |||
19 | Guwahati | Agriculture | 97.14 | 87.18 |
Built-up | 95.74 | 97.83 | ||
River | 93.48 | 96.63 | ||
Urban open | 97.56 | 93.75 | ||
Urban green | 85.56 | 96.86 | ||
Waterbody | 79.31 | 83.13 | ||
Overall accuracy | 91.75 | |||
Kappa coefficient | 89.64 | |||
20 | Hyderabad | Agriculture | 91.67 | 77.88 |
Built-up | 93.22 | 94.83 | ||
River | 94.52 | 80.23 | ||
Urban open | 90.74 | 97.03 | ||
Urban green | 70.73 | 84.06 | ||
Waterbody | 85.22 | 90.74 | ||
Forest | 85.96 | 89.09 | ||
Overall accuracy | 87.29 | |||
Kappa coefficient | 85.02 | |||
21 | Indore | Agriculture | 94.71 | 90.45 |
Built-up | 91.30 | 93.33 | ||
River | 86.54 | 93.75 | ||
Urban open | 96.00 | 92.31 | ||
Urban green | 84.16 | 88.54 | ||
Waterbody | 85.19 | 88.46 | ||
Overall accuracy | 91.54 | |||
Kappa coefficient | 88.88 | |||
22 | Jabalpur | Agriculture | 78.57 | 80.73 |
Built-up | 90.32 | 93.33 | ||
River | 100.00 | 88.89 | ||
Urban open | 92.47 | 99.26 | ||
Urban green | 92.73 | 89.08 | ||
Waterbody | 82.67 | 100.00 | ||
Forest | 94.37 | 90.54 | ||
Overall accuracy | 90.94 | |||
Kappa coefficient | 89.12 | |||
23 | Jaipur | Agriculture | 86.36 | 78.08 |
Built-up | 96.08 | 96.08 | ||
River | 91.67 | 81.48 | ||
Urban open | 88.06 | 92.19 | ||
Urban green | 84.11 | 84.91 | ||
Waterbody | 78.00 | 90.70 | ||
Forest | 89.74 | 92.11 | ||
Overall accuracy | 87.37 | |||
Kappa coefficient | 86.91 | |||
24 | Jodhpur | Agriculture | 86.67 | 85.53 |
Built-up | 100.00 | 97.37 | ||
River | 92.31 | 96.00 | ||
Urban open | 95.31 | 92.42 | ||
Urban green | 76.00 | 82.61 | ||
Waterbody | 94.83 | 90.16 | ||
Overall accuracy | 90.61 | |||
Kappa coefficient | 80.15 | |||
25 | Kanpur | Agriculture | 75.44 | 97.73 |
Built-up | 84.21 | 91.43 | ||
River | 79.31 | 76.67 | ||
Urban open | 95.45 | 84.00 | ||
Urban green | 87.76 | 78.18 | ||
Waterbody | 95.83 | 92.00 | ||
Overall accuracy | 87.20 | |||
Kappa coefficient | 84.39 | |||
26 | Kochi | Agriculture | 75.76 | 72.46 |
Built-up | 94.74 | 98.36 | ||
River | 93.75 | 82.19 | ||
Urban open | 85.94 | 91.67 | ||
Urban green | 73.42 | 71.60 | ||
Waterbody | 81.94 | 93.65 | ||
Bay | 80.65 | 55.56 | ||
Mangrove | 89.61 | 94.52 | ||
Overall accuracy | 86.47 | |||
Kappa coefficient | 83.91 | |||
27 | Kolkata | Agriculture | 71.43 | 71.43 |
Built-up | 96.23 | 96.23 | ||
Urban open | 90.00 | 83.08 | ||
Urban green | 78.72 | 90.24 | ||
Waterbody | 100.00 | 97.96 | ||
Overall accuracy | 88.98 | |||
Kappa coefficient | 0.86 | |||
28 | Kota | Agriculture | 88.89 | 83.81 |
Built-up | 91.80 | 94.92 | ||
River | 97.78 | 91.67 | ||
Urban open | 89.61 | 94.52 | ||
Urban green | 82.76 | 88.89 | ||
Waterbody | 90.59 | 97.47 | ||
Forest | 87.50 | 80.00 | ||
Overall accuracy | 89.88 | |||
Kappa coefficient | 88.14 | |||
29 | Lucknow | Agriculture | 89.09 | 92.45 |
Built-up | 91.30 | 91.30 | ||
Urban open | 96.43 | 83.08 | ||
Urban green | 88.64 | 95.12 | ||
Waterbody | 100.00 | 95.24 | ||
Overall accuracy | 91.25 | |||
Kappa coefficient | 0.88 | |||
30 | Ludhiana | Agriculture | 83.61 | 86.44 |
Built-up | 96.15 | 96.15 | ||
Urban open | 95.83 | 80.70 | ||
Urban green | 87.95 | 96.05 | ||
Waterbody | 99.08 | 99.08 | ||
Overall accuracy | 92.92 | |||
Kappa coefficient | 0.91 | |||
31 | Madurai | Agriculture | 77.78 | 94.23 |
Built-up | 97.06 | 97.06 | ||
River | 85.37 | 92.11 | ||
Urban open | 98.82 | 92.31 | ||
Urban green | 92.55 | 87.88 | ||
Waterbody | 96.39 | 93.02 | ||
Overall accuracy | 92.00 | |||
Kappa coefficient | 90.14 | |||
32 | Mumbai | Agriculture | 94.94 | 75.00 |
Built-up | 94.92 | 56.00 | ||
River | 100.00 | 100.00 | ||
Urban open | 98.78 | 82.00 | ||
Urban green | 96.80 | 133.00 | ||
Waterbody | 100.00 | 175.00 | ||
Bay | 73.56 | 64.00 | ||
Mangrove | 92.31 | 64.00 | ||
Saltpan | 71.52 | 136.00 | ||
Overall accuracy | 90.40 | |||
Kappa coefficient | 0.89 | |||
33 | Mysore | Agriculture | 86.15 | 82.35 |
Built-up | 94.87 | 98.67 | ||
River | 91.55 | 98.48 | ||
Urban open | 96.83 | 83.56 | ||
Urban green | 73.85 | 87.27 | ||
Waterbody | 98.21 | 90.16 | ||
Overall accuracy | 90.20 | |||
Kappa coefficient | 88.23 | |||
34 | Nagpur | Agriculture | 86.15 | 90.32 |
Built-up | 91.36 | 98.67 | ||
River | 91.55 | 98.48 | ||
Urban open | 96.00 | 77.42 | ||
Urban green | 80.00 | 84.21 | ||
Waterbody | 98.21 | 90.16 | ||
Overall accuracy | 90.34 | |||
Kappa coefficient | 88.38 | |||
35 | Nashik | Agriculture | 89.34 | 91.60 |
Built-up | 93.33 | 100.00 | ||
River | 93.62 | 96.70 | ||
Urban open | 97.03 | 85.22 | ||
Urban green | 77.59 | 84.91 | ||
Waterbody | 95.89 | 92.11 | ||
Overall accuracy | 91.82 | |||
Kappa coefficient | 90.08 | |||
36 | Panaji | Agriculture | 93.85 | 98.39 |
Built-up | 94.55 | 96.30 | ||
River | 100.00 | 71.54 | ||
Urban open | 95.70 | 98.89 | ||
Urban green | 97.76 | 95.62 | ||
Waterbody | 100.00 | 100.00 | ||
Bay | 70.27 | 97.50 | ||
Mangrove | 96.74 | 94.68 | ||
Saltpan | 75.69 | 76.76 | ||
Overall accuracy | 90.83 | |||
Kappa coefficient | 0.90 | |||
37 | Patna | Agriculture | 81.16 | 83.58 |
Built-up | 97.10 | 97.10 | ||
River | 93.10 | 96.43 | ||
Urban open | 91.53 | 87.10 | ||
Urban green | 82.28 | 83.33 | ||
Waterbody | 95.95 | 92.21 | ||
Overall accuracy | 90.16 | |||
Kappa coefficient | 88.16 | |||
38 | Pune | Agriculture | 87.12 | 93.50 |
Built-up | 93.67 | 100.00 | ||
River | 100.00 | 91.84 | ||
Urban open | 92.68 | 88.37 | ||
Urban green | 86.79 | 100.00 | ||
Waterbody | 98.06 | 84.87 | ||
Forest | 100.00 | 84.87 | ||
Overall accuracy | 93.98 | |||
Kappa coefficient | 0.93 | |||
39 | Rajkot | Agriculture | 76.47 | 85.53 |
Built-up | 98.88 | 88.89 | ||
River | 94.23 | 97.03 | ||
Urban open | 94.55 | 81.25 | ||
Urban green | 80.61 | 89.77 | ||
Waterbody | 96.51 | 93.26 | ||
Overall accuracy | 89.94 | |||
Kappa coefficient | 87.87 | |||
40 | Shimla | Agriculture | 85.42 | 52.56 |
Built-up | 91.84 | 97.83 | ||
River | 93.55 | 100.00 | ||
Urban open | 96.70 | 93.62 | ||
Forest | 66.39 | 88.76 | ||
Waterbody | 100.00 | 94.23 | ||
Overall accuracy | 87.95 | |||
Kappa coefficient | 85.39 | |||
41 | Srinagar | Agriculture | 70.97 | 90.41 |
Built-up | 100.00 | 98.18 | ||
River | 90.63 | 100.00 | ||
Urban open | 96.25 | 92.77 | ||
Forest | 89.90 | 77.39 | ||
Waterbody | 100.00 | 90.32 | ||
Overall accuracy | 89.69 | |||
Kappa coefficient | 87.49 | |||
42 | Surat | Agriculture | 97.78 | 97.78 |
Built-up | 98.89 | 96.74 | ||
River | 100.00 | 84.42 | ||
Urban open | 92.59 | 94.34 | ||
Urban green | 93.33 | 88.29 | ||
Waterbody | 97.09 | 100.00 | ||
Bay | 75.58 | 97.01 | ||
Mangrove | 87.76 | 94.51 | ||
Saltpan | 82.86 | 72.50 | ||
Overall accuracy | 91.85 | |||
Kappa coefficient | 0.91 | |||
43 | Trichy | Agriculture | 85.22 | 83.76 |
Built-up | 100.00 | 98.82 | ||
River | 90.32 | 87.50 | ||
Urban open | 96.08 | 90.74 | ||
Urban green | 87.72 | 92.59 | ||
Waterbody | 95.74 | 96.77 | ||
Overall accuracy | 92.24 | |||
Kappa coefficient | 90.44 | |||
44 | Vadodara | Agriculture | 86.41 | 79.46 |
Built-up | 94.92 | 98.25 | ||
River | 94.23 | 97.03 | ||
Urban open | 96.70 | 90.72 | ||
Urban green | 82.05 | 89.51 | ||
Waterbody | 98.45 | 96.94 | ||
Overall accuracy | 91.93 | |||
Kappa coefficient | 90.04 | |||
45 | Varanasi | Agriculture | 83.19 | 88.39 |
Built-up | 97.53 | 95.18 | ||
River | 92.00 | 95.83 | ||
Urban open | 96.74 | 81.65 | ||
Urban green | 86.21 | 92.59 | ||
Waterbody | 96.74 | 93.68 | ||
Overall accuracy | 90.84 | |||
Kappa coefficient | 0.89 | |||
46 | Vasai-Virar | Agriculture | 98.36 | 97.30 |
Built-up | 98.04 | 97.09 | ||
River | 100.00 | 88.00 | ||
Urban open | 95.12 | 83.87 | ||
Urban green | 97.06 | 79.52 | ||
Waterbody | 100.00 | 99.38 | ||
Bay | 50.86 | 94.68 | ||
Mangrove | 100.00 | 95.15 | ||
Saltpan | 90.91 | 78.43 | ||
Overall accuracy | 90.24 | |||
Kappa coefficient | 0.89 | |||
47 | Vizag | Agriculture | 93.94 | 97.48 |
Built-up | 93.75 | 93.75 | ||
River | 100.00 | 78.76 | ||
Urban open | 97.96 | 84.21 | ||
Urban green | 96.70 | 83.81 | ||
Waterbody | 100.00 | 100.00 | ||
Bay | 67.72 | 91.49 | ||
Mangrove | 100.00 | 96.91 | ||
Saltpan | 82.35 | 91.80 | ||
Overall accuracy | 91.43 | |||
Kappa coefficient | 0.90 |
About this article
Cite this article
Avashia, V., Parihar, S. & Garg, A. Evaluation of Classification Techniques for Land Use Change Mapping of Indian Cities. J Indian Soc Remote Sens 48, 877–908 (2020). https://doi.org/10.1007/s12524-020-01122-7
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12524-020-01122-7