Evaluation of Different Classification Algorithms for Land Use Land Cover Mapping

Kaifi Chomani; Shaki Pshdari

doi:10.24017/

Authors

Kaifi Chomani Civil Engineering Department, University of Raparin, Ranya, Sulaymaniyah, Iraq. https://orcid.org/0000-0001-7323-2281
Shaki Pshdari Civil Engineering Department, University of Raparin, Ranya, Sulaymaniyah, Iraq https://orcid.org/0009-0003-6963-4925

Abstract

For efficient sustainable management and monitoring landscape changes over times, reliable land use land cover (LULC) mapping using the most accurate classification algorithms is required. Increasing innovative classification algorithms and satellite data demands finding the most suitable classifier to create accurate maps of different features efficiently. The challenge addressed in this study is to identify the most accurate algorithm for classifying and generating reliable LULC. The objective of this research was to identify the best classification among several algorithms both overall and in each individual class by using ArcGIS Pro and Google Earth Engine with Landsat 8 and Sentinel-2 datasets for Ranya city as the study area. Support vector machine (SVM), maximum likelihood, random tree, classification and regression tree, K-Nearest Neighbor and iterative self organizing cluster algorithms were used to classify the satellite image of the study area. The kappa coefficient matrix was used to assess the performance of each classifier and method. The study showed that the random tree algorithm achieved highest overall accuracy using Sentinel-2 with 83%. Meanwhile, when the specific class accuracy is priority, the result suggests the use of SVM algorithm using Sentinel-2 for building footprint extraction with 92% accuracy. The result also showed that the outcomes of most algorithms were better using Sentinel-2 rather than Landsat 8, making Sentinel-2 more suitable for accurate LULC mapping. The outcomes of the research assessed different classification algorisms to find the best algorithms and methods that can be used to generate accurate and efficient LULC maps.

Keywords:

Satellite imagery, LULC, GIS, Google earth engine, Image classification, Machine learning

References

S. Basheer et al., “Comparison of Land Use Land Cover Classifiers Using Different Satellite Imagery and Machine Learning Techniques,” Remote Sensing, vol. 14, no. 19, p. 4978, 2022, doi: 10.3390/rs14194978.

J. Mäyrä et al., “Utilizing historical maps in identification of long-term land use and land cover changes,” Ambio, vol. 52, no. 11, p. 1777-1792, 2023, doi: 10.1007/s13280-023-01838-z.

F. Ahmad, L. Goparaju, and A. Qayum, “LULC analysis of urban spaces using Markov chain predictive model at Ranchi in India,” Spatial Information Research, vol. 25, no. 3, p. 351-359, 2017, doi: 10.1007/s41324-017-0102-x.

R. Pacheco Quevedo et al., “Land use and land cover as a conditioning factor in landslide susceptibility: a literature review,” Landslides, vol. 20, no. 5, p. 967-982, 2023, doi: 10.1007/s10346-022-02020-4.

K. Thiagarajan et al., “Satellite Image Classification Using a Hierarchical Ensemble Learning and Correlation Coeffi-cient-Based Gravitational Search Algorithm,” Remote Sensing, vol. 13, no. 21, p. 4351, 2021, doi: 10.3390/rs13214351.

H. Ferdous et al., “Machine Learning Approach Towards Satellite Image Classification,” in Proceedings of Interna-tional Conference on Trends in Computational and Cognitive Engineering, Singapore, 2021, doi: 0.1007/978-981-33-4673-4_51.

I. Atef, W. Ahmed, and R.H. Abdel-Maguid, “Modelling of land use land cover changes using machine learning and GIS techniques: a case study in El-Fayoum Governorate, Egypt,” Environmental Monitoring and Assessment, vol. 195, no. 6, p. 637, 2023, doi: 10.1007/s10661-023-11224-7.

G. Abebe, D. Getachew, and A. Ewunetu, “Analysing land use/land cover changes and its dynamics using remote sensing and GIS in Gubalafito district, Northeastern Ethiopia,” SN Applied Sciences, vol. 4, no. 1, p. 30, 2021, doi: 10.1007/s42452-021-04915-8.

A. Tassi and M. Vizzari, “Object-Oriented LULC Classification in Google Earth Engine Combining SNIC, GLCM, and Machine Learning Algorithms,” Remote Sensing, vol. 12, no. 22, p. 3776, 2020, doi: 10.3390/rs12223776.

S. Talukdar et al., “Land-Use Land-Cover Classification by Machine Learning Classifiers for Satellite Observations—A Review,” Remote Sensing, vol. 12, no. 7, p. 1135, 2020, doi: 10.3390/rs12071135.

S. Dhingra and D. Kumar, “A review of remotely sensed satellite image classification,” International Journal of Elec-trical and Computer Engineering, vol. 9, no. 3, p. 1720, 2019, doi: 10.11591/ijece.v9i3.pp.1720-1731.

Z. Abbas and H.S. Jaber, “Accuracy assessment of supervised classification methods for extraction land use maps using remote sensing and GIS techniques,” in IOP Conference Series: Materials Science and Engineering, 2020, doi: 10.1088/1757-899X/745/1/012166.

E.A. Alshari and B.W. Gawali, “Development of classification system for LULC using remote sensing and GIS,” Global Transitions Proceedings, vol. 2, no. 1, p. 8-17, 2021, doi: 10.1016/j.gltp.2021.01.002.

K. Nivedita Priyadarshini et al., “A COMPARATIVE STUDY OF ADVANCED LAND USE/LAND COVER CLASSI-FICATION ALGORITHMS USING SENTINEL-2 DATA,” Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., vol. XLII-5, p. 665-670, 2018, doi: 10.5194/isprs-archives-XLII-5-665-2018.

Lubis, A. R., & Lubis, M. ‘Optimization of distance formula in K-Nearest Neighbor method’, Bulletin of Electrical Engineering and Informatics, 9(1), 326-338, 2020, doi: 10.11591/eei.v9i1.1464.

A. Tassi and M. Vizzari, "Object-Oriented LULC Classification in Google Earth Engine Combining SNIC, GLCM, and Machine Learning Algorithms," Remote Sensing, vol. 12, no. 22, p. 3776, 2020. doi: 10.3390/rs12223776.

B. Norovsuren et al., “Land cover classification using maximum likelihood method (2000 and 2019) at Khandgait valley in Mongolia,” IOP Conference Series: Earth and Environmental Science, vol. 381, no. 1, p. 012054, 2019, doi: 10.1088/1755-1315/381/1/012054.

Y. Hu et al., “Land Use/Land Cover Change Detection and NDVI Estimation in Pakistan’s Southern Punjab Prov-ince,” Sustainability, vol. 15, no. 4, p. 3572, 2023, doi: 10.3390/su15043572.

C.C. Fonte et al., “Assessing The Accuracy Of Land Use Land Cover (Lulc) Maps Using Class Proportions In The Reference Data,” ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., vol. V-3-2020, p. 669-674, 2020, doi: 10.5194/isprs-annals-V-3-2020-669-2020.

K.-S. Cheng et al., “Quantifying Uncertainty in Land-Use/Land-Cover Classification Accuracy: A Stochastic Simula-tion Approach,” Frontiers in Environmental Science, vol. 9, 2021, doi: 10.3389/fenvs.2021.628214.

M. Jamil, H.U. Rehman, SaleemUllah, I. Ashraf, and S. Ubaid "Smart Techniques for LULC Micro Class Classification Using Landsat8 Imagery," Comput. Mater. Contin., vol. 74, no. 3, pp. 5545-5557. 2023,doi: 10.32604/cmc.2023.033449.

Landis, J. R., & Koch, G. G “The measurement of observer agreement for categorical data,” Biometrics, vol. 33(1), pp. 159-174, 1977, doi: 10.2307/2529310.

S. G. Setegn, R. Srinivasan, B. Dargahi, and A. M. Melesse, "Spatial delineation of soil erosion vulnerability in the Lake Tana Basin, Ethiopia," Hydrological Processes: An International Journal, vol. 23, no. 26, pp. 3738-3750, Dec. 2009, doi: 10.1002/hyp.7476.

Nicolau, A. P., Dyson, K., Saah, D., & Clinton, N. “Accuracy Assessment: Quantifying Classification Quality. In Cloud-Based Remote Sensing with Google Earth Engine: Fundamentals and Applications” Springer International Publishing, pp. 135-145, 2024, doi: 10.1007/978-3-031-26588-4_7.

R. C. Chen, C. Dewi, S. W. Huang, and others, "Selecting critical features for data classification based on machine learning methods," Journal of Big Data, vol. 7, p. 52, 2020. doi: 10.1186/s40537-020-00327-4.

R. G. McClarren, "Decision Trees and Random Forests for Regression and Classification," in Machine Learning for Engineers. Cham, Switzerland: Springer, 2021. doi: 10.1007/978-3-030-70388-2_3.

M. Awad and R. Khanna, "Support Vector Machines for Classification," in Efficient Learning Machines. Berkeley, CA: Apress, 2015. doi: 10.1007/978-1-4302-5990-9_3.