تقييم دقة التصنيف والمقارنات الإحصائية في التحديد النوعي لاستخدام الأرض في واحة الأحساء بتقنية نظم المعلومات الجغرافية

Nashmiah Saud Awad ‎ Al Hujuri

doi:10.35516/Hum.2025.8052

Authors

Nashmiah Saud Awad ‎ Al Hujuri Department of Geography, College of Arts, King Faisal University, Al-Ahsa, Kingdom of Saudi Arabia https://orcid.org/0000-0002-0790-1309

DOI:

https://doi.org/10.35516/Hum.2025.8052

Keywords:

Land cover, urban changes, development planning, learning, GIS, Al-Ahsa Oasis

Abstract

Objectives: The study aimed to examine performing cell-based classification (PBC), and objective-based classification (OBC) of space visuals within digital environments of geographic technologies, as well as a statistical comparison between the machine learning algorithms used, and to evaluate their accuracy in classifying categories/qualifying the use of Land (LU) for the purpose of producing qualitative maps with high accuracy that can be relied upon in applied studies and development planning projects.

Methods: The study relied on a quantitative analytical approach in collecting and analyzing its data, using Geographic Information Systems (GIS) technology. And applying machine learning algorithms. This is done on a random sample in the category-based classification and the application of evaluating the validity of the classification.

Results: Applying objective-based classification (OBC) is very effective in urban and similar environments, with the overall accuracy reaching 92.72%, and the Kappa coefficient value reaching 89.86%. The results of the statistical comparison between machine learning algorithms (partial accuracy assessment) for mapping cover/land use also showed that the water category was 100%, followed by the agricultural land category at 98.2%, then the vacant land category at 95.6%, while urbanization recorded a rate of 90.8%.

Conclusions: The guidance in choosing the appropriate algorithm to improve classification accuracy is due to some controls that must be taken into account, the most important of which is determining the category to be classified, and the study may represent a model applicable to similar urban environments.

Downloads

Download data is not yet available.

References

Abdi, A. M. (2020). Land cover and land use classification performance of machine learning algorithms in a boreal landscape using Sentinel-2 data. GIScience & Remote Sensing, 57(1), 1–20. https://doi.org/10.1080/15481603.2019.1650447

Abduh, W. al-D. M. (2013). Muqaddimah ilá al-Istishʻār ʻan baʻda wa-taṭbīqātuhu (1st ed.) [In Arabic]. Maktabat al-Mutanabbī.

Adam, H. E., Csaplovics, E., & Elhaja, M. E. (2016). A comparison of pixel-based and object-based approaches for land use land cover classification in semi-arid areas, Sudan. 8th IGRSM International Conference and Exhibition on Remote Sensing & GIS (IGRSM 2016), IOP Conference Series: Earth and Environmental Science, 37, 012061. https://doi.org/10.1088/1755-1315/37/1/012061

Adugna, T., Xu, W., & Fan, J. (2022). Comparison of Random Forest and Support Vector Machine classifiers for regional land cover mapping using coarse resolution FY-3C images. Remote Sensing, 14(3), 574. https://doi.org/10.3390/rs14030574

al-Ḥajūrī, N. S., & wāldghyry, M. I. (2023). Al-Muḥākāh al-makānīyah lil-Takhṭīṭ wa-al-tanmiyah al-ḥaḍarīyah fī wāḥat al-Aḥsāʼ bi-istikhdām namūdhaj al-sulūk al-dhātī alkhlwy-Mārkwf CA-Markov [In Arabic]. Majallat al-Jāmiʻah al-Islāmīyah lil-ʻUlūm al-Tarbawīyah wa-al-Ijtimāʻīyah, 329, 13-358. https://journals.iu.edu.sa/ESS/Main/Article/9638

al-Ḥasan, ʻI. M. (2007). Muʻālajat al-ṣuwar al-raqmīyah fī al-Istishʻār ʻan baʻda [In Arabic]. Markaz Buḥūth Kullīyat al-Handasah, Jāmiʻat al-Malik Saʻūd.

al-Ghāmidī, S. A. R. (2007). Taṣnīf Istikhdāmāt al-arāḍī fī Madīnat Makkah al-Mukarramah ʻan ṭarīq Muʻālajat bayānāt Aqmār ṣināʻīyah mdmjh [In Arabic]. al-Majallah al-jughrāfīyah al-Miṣrīyah, 11(47), 33-55. https://search.mandumah.com/Record/1348818

al-Majlisī, F. S., & al-Ghāmidī, ʻA. M. (2017). Al-taṣnīf alhdfy lāstkhlāṣ al-arāḍī al-faḍāʼ min ṣuwar al-Aqmār al-Ṣināʻīyah ʻĀliyah al-wuḍūḥ: Dirāsah taṭbīqīyah ʻalá Madīnat al-Riyāḍ [In Arabic]. Majallat al-ʻImārah wa-al-takhṭīṭ, 29(2), 211-240. https://cap.ksu.edu.sa/sites/cap.ksu.edu.sa/files/attach/jap_ksu_jul2017_ar4.pdf

Almthyby, A. M., & wāljʻydy, F. Ḥ. (2021). Taqyīm uslūb al-taṣnīf alhdfy (OBC) li-istikhrāj al-mabānī min almrʼyāt al-faḍāʼīyah [In Arabic]. Majallat al-ʻImārah wa-al-takhṭīṭ, 33(1), 1-27. https://doi.org/10.33948/JAP-KSU-33-1-1

al-Mubārak, Ḥ. ʻA., & wālḥājy, Z. R. (2019). Taḥlīl athar artfāʻ darajāt al-ḥarārah ʻalá al-tawassuʻāt al-ʻumrānīyah alʼfqyh: Muḥāfaẓat al-Aḥsāʼ dirāsah taṭbīqīyah bi-istikhdām taqnīyat al-Istishʻār ʻan buʻd wGIS [In Arabic]. al-Majallah al-ʻArabīyah lil-Dirāsāt al-jughrāfīyah, 2(2), 73-110. https://doi.org/10.21608/jasg.2019.43524

al-Najm, ʻA. Ḥ., & wālmwswy, I. I. (2020). Al-taṣnīf al-raqmī ltghyr istiʻmālāt al-arḍ al-zirāʻīyah fī Qaḍāʼ al-Kūfah bi-istiʻmāl GIS-RS [In Arabic]. Jāmiʻat al-Qādisīyah, al-ʻIrāq. https://repository.qu.edu.iq/wpcontent/uploads/sites/31/2020/12/

Baroud, F. K. (2019). Remote sensing in ArcGIS (1st ed.).

Chen, Y., Zhou, Y., Ge, Y., An, R., & Chen, Y. (2018). Enhancing land cover mapping through integration of pixel-based and object-based classifications from remotely sensed imagery. Remote Sensing, 10(1), 10-33. https://doi.org/10.3390/rs10010077

Copernicus Open Access Hub. (n.d.). Retrieved from https://scihub.copernicus.eu/

Dabija, A., Kluczek, M., Zagajewski, B., Raczko, E., Kycko, M., Al-Sulttani, A. H., Tardà, A., Pineda, L., & Corbera, J. (2021). Comparison of support vector machines and random forests for Corine land cover mapping. Remote Sensing, 13(4), 777. https://doi.org/10.3390/rs13040777

De Paul, O. V. (2007). Remote sensing: New applications for urban areas. Proceedings of the IEEE, 12(95). https://doi.org/10.1109/JPROC.2007.908065

Ghāzī al-Bannā, R. (2005). Muqāranah natāʼij ṭarāʼiq al-taṣnīf al-raqmī wdqthā fī taṣnīf al-Ghiṭāʼ al-arḍī ljzʼ min Madīnat al-Mawṣil [In Arabic]. al-Majallah al-ʻIrāqīyah al-Waṭanīyah li-ʻUlūm al-arḍ, 5(2), 64-77. https://doi.org/10.33899/earth.2005.41153

Anderson, J. R., et al. (n.d.). A land use and land cover classification system for use with remote sensor data. U.S. Geological Survey Paper, 6-22.

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. https://doi.org/10.1080/01431160600746456

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. https://doi.org/10.5721/EuJRS20144723

Maxwell, A. E., Warner, T. A., & Fang, F. (2018). Implementation of machine-learning classification in remote sensing: An applied review. International Journal of Remote Sensing, 39(9), 2784–2817. https://doi.org/10.1080/01431161.2018.1433343

Naz, F., Nuthammachot, N., & Shabbir, R. (2024). Comparative analysis of support vector machine, random forest, K-nearest neighbors, and maximum likelihood algorithms for land use and land cover change detection: Mardan District, Pakistan. SSRN. https://ssrn.com/abstract=4806019 or http://dx.doi.org/10.2139/ssrn.4806019

Tilahun, A., & Teferie, B. (2015). Accuracy assessment of land use land cover classification using Google Earth. American Journal of Environmental Protection, 4(4), 193.