SavedAdd your journal

Journals / International Journal of Engineering and Geosciences / 2026 / Volume: 11 Issue: 3

An Integrated Data Driven Approach of Multi-Index and K-Means Clustering for Spatiotemporal Monitoring and Forecasting of Desertification Risk in Iraq

Ayat Khaleel Dhiab(University of Tabriz)0000-0001-5561-8025
Khalil Valizadeh Kamran(University of Tabriz. Iran)0000-0003-4648-842X
Iraj Teymuri(University of Tabriz)0000-0002-3167-5580
Bakhtiar Feizizadeh(University of Tabriz. Iran)0000-0002-3367-2925
Pages
—
Publication Date
2026-06-28
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

The K-means clustering results for 2030 and 2035 revealed both degradation and recovery trajectories, with some regions improving from Class 3 to Class 5 and others deteriorating into Class 1

📌 3 Key Takeaways

🎯
Objective & Hypothesis:Desertification is one of the major environmental challenges threatening the ecological integrity and socio-economic stability of arid and semiarid climates worldwide.
📊
Key Findings & Data:For this goal, six key spectral-based indicators, including Land Surface Temperature (LST), Normalized Difference Vegetation Index (NDVI), Soil Adjusted Vegetation Index (SAVI), Albedo, Modified Normalized Difference Water Index (MNDWI), and Normalized Difference Built-up Index (NDBI), were applied through the integrated data-driven approach on the MODIS and Sentinel-2 datasets for the period 2015–2022.
💡
Conclusion & Impact:The K-means clustering results for 2030 and 2035 revealed both degradation and recovery trajectories, with some regions improving from Class 3 to Class 5 and others deteriorating into Class 1
🔬Design:Research Article
📍Scope:2015–2022 Verileri
⚙️Variables:Desertification risk index · Google Earth Engine · K-Means Clustering

Abstract

Desertification is one of the major environmental challenges threatening the ecological integrity and socio-economic stability of arid and semiarid climates worldwide. This study presents a multi-index remote sensing approach to assess and predict desertification risk across Iraq using the Google Earth Engine (GEE). For this goal, six key spectral-based indicators, including Land Surface Temperature (LST), Normalized Difference Vegetation Index (NDVI), Soil Adjusted Vegetation Index (SAVI), Albedo, Modified Normalized Difference Water Index (MNDWI), and Normalized Difference Built-up Index (NDBI), were applied through the integrated data-driven approach on the MODIS and Sentinel-2 datasets for the period 2015–2022. Annual composites were generated, and pixel-wise linear trends were calculated using least-squares regression. All trend resulting data were normalized to a common scale, and a composite Desertification Risk Index (DRI) was constructed. Future projections for 2030 and 2035 were computed based on linear extrapolation of DRI trends. Additionally, K-means clustering was applied to classify desertification risk into five categories, enabling spatial segmentation and comparative analysis. The results revealed a clear intensification of desertification in southern and central Iraq, particularly in Al-Muthanna, Dhi Qar, and Basrah, where high DRI values and class 1 clustering indicate severe ecological stress. Central governorates such as Najaf, Wasit, and Karbala are transitioning from moderate to high risk, whereas the northern regions such as Erbil and Dohuk remain relatively stable. However, early signs of vulnerability emerge in the peripheral zones between 2022 and 2035, approximately 52.7% of Iraq’s land area is projected to fall within the moderate to high desertification risk categories. The K-means clustering results for 2030 and 2035 revealed both degradation and recovery trajectories, with some regions improving from Class 3 to Class 5 and others deteriorating into Class 1

🔖

Cite This Article

Dhiab, A. K., Kamran, K. V., Teymuri, I., Feizizadeh, B. (2026). An Integrated Data Driven Approach of Multi-Index and K-Means Clustering for Spatiotemporal Monitoring and Forecasting of Desertification Risk in Iraq. International Journal of Engineering and Geosciences, Volume: 11 Issue: 3. https://doi.org/10.26833/ijeg.1830799

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (53)

  1. Montanarella, L., Scholes, R., & Brainich, A. (2018). The Assessment Report on Land Degradation and Restoration. IPBES.
  2. Nedd, R., & Anandhi, A. (2024). A synthesis on land degradation in the context of sustainable development goals. Land Degradation & Development, 35, 3937–3964. https://doi.org/10.1002/ldr.5678
  3. Prăvălie, R. (2021). Exploring the multiple land degradation pathways across the planet. Earth Science Reviews, 220, 103689.
  4. Stringer, L. C., & Harris, A. (2014). Land degradation in Dolj County, Southern Romania. Land Degradation & Development, 25, 17–28. https://doi.org/10.1002/ldr.2150
  5. Wang, B., He, W. J., An, M., Fang, X., & Ramsey, T. S. (2024). Natural capital accounting of land resources. Science of the Total Environment, 914, 170051. https://doi.org/10.1016/j.scitotenv.2023.170051
  6. Prăvălie, R. (2016). Drylands extent and environmental issues. Earth Science Reviews, 161, 259–278. https://doi.org/10.1016/j.earscirev.2016.08.003
  7. Al-Obaidi, H. J., Al-Azzawi, A. M., & Al-Mashhadani, S. A. (2022). Desertification in Iraq. Environmental Challenges, 7, 100456. https://doi.org/10.1016/j.envc.2022.100456
  8. Mohammed Abdulwahid, W., Feizizadeh, B., Blaschke, T., Karimzadeh, S., 2025. A Geoinformation Approach for Spatiotemporal Mapping of Climate Change Environmental Impacts on Sustainable Food Production in Iraq, International Journal of Environmental Research, 9, 175 (2025). https://doi.org/10.1007/s41742-025-00821-8.
  9. Prăvălie, R., Patriche, C., Săvulescu, I., et al. (2020a). Spatial assessment of land sensitivity to degradation in Romania. Catena, 187, 104407. https://doi.org/10.1016/j.catena.2019.104407
  10. Niacsu, L., Ionita, I., Samoila, C., et al. (2021). Land degradation and soil conservation measures in the Moldavian Plateau. Water, 13(20), 2877. https://doi.org/10.3390/w13202877
  11. Stan, C. O., Pîrnău, R. G., Roșca, B., & Sirbu-Radasanu, D. S. (2022). Risk of salinization in agricultural soils of semi-arid regions. Sustainability, 14(24), 17056. https://doi.org/10.3390/su142417056
  12. Feizizadeh, B., Lakes, T., Omarzadeh, D., Pourmoradian, D., 2023. Health effects of shrinking hyper-saline lakes: spatiotemporal modeling of the Lake Urmia drought on the local population, case study of the Shabestar County, Nature of Scientific Report. https://doi.org/10.1038/s41598-023-28332-6
  13. Feizizadeh, B., Abdollahi, Z., Shokati, B., Lakes, T., 2022b.A GIS-based spatiotemporal impact assessment of droughts in the hyper-saline Urmia Lake Basin on the hydro-geochemical quality of nearby aquifers, Remote Sesning, 14(11), 2516; https://doi.org/10.3390/rs14112516
  14. Feizizadeh, B., Mohmmadzadeh Alajujeh, K., Lakes,T., Blaschke, T., Omarzadeh, D.,2021a. A comparative approach of integrated fuzzy object-based deep learning and machine learning techniques for monitoring land use/cover changes and environmental impacts assessment, GIScience and remote sesning, https://doi.org/10.1080/15481603.2021.2000350
  15. Feizizadeh, B., Omarzadeh, D., Kazemi Garajeh, M., Lakes, T., Blaschke, T., 2021b. Machine learning data-driven approaches for land use/cover mapping and trend analysis using google Earth engine. J. Environ. Plann. Manag. https://doi.org/10.1080/15481603.2021.2000350
  16. Ontel, I., Cheval, S., Irimescu, A., et al. (2023). Assessing recent trends of land degradation and desertification in Romania. Remote Sensing, 15(19), 4842. https://doi.org/10.3390/rs15194842
  17. Rivera-Marin, D., Dash, J., & Ogutu, B. (2022). The use of remote sensing for desertification studies: A review. Journal of Arid Environments, 206, 104829. https://doi.org/10.1016/j.jaridenv.2022.104829
  18. Fan, Z., Li, S., & Fang, H. (2020). Identifying desertification change in CMREC area using multisource remote data. Remote Sensing, 12(19), 3170. https://doi.org/10.3390/rs12193170
  19. Feng, K., Wang, T., Liu, S., et al. (2022). Monitoring desertification using machine learning techniques with MODIS indicators. Remote Sensing, 14(11), 2663. https://doi.org/10.3390/rs14112663
  20. Secu, C. V., Stoleriu, C. C., Lesenciuc, C. D., & Ursu, A. (2022). Normalized Sand Index for identification of bare sand areas. Remote Sensing, 14(15), 3802. https://doi.org/10.3390/rs14153802
  21. Chen, Y., Ma, L., Wang, X., et al. (2025). Spatiotemporal patterns of desertification sensitivity in Inner Mongolia. Ecological Informatics, 89, 103190. https://doi.org/10.1016/j.ecoinf.2025.103190
  22. Huang, B., Duan, H., & Cao, W. (2025). Multidimensional analysis of desertification sensitivity in Horqin Sandy Land. Ecological Indicators, 178, 113847. https://doi.org/10.1016/j.ecolind.2025.113847
  23. Prăvălie, R., Patriche, C., Tişcovschi, A., et al. (2020b). Spatio-temporal changes of land sensitivity due to climate and human activity. Ecological Indicators, 118, 106755. https://doi.org/10.1016/j.ecolind.2020.106755
  24. Cai, D., Wang, X., Geng, X., et al. (2022). Baseline and status of desertification in Central Asia. Land Degradation & Development, 33(3), 458–472. https://doi.org/10.1002/ldr.4214
  25. Vieira, R. M., Tomasella, J., Santana, M., et al. (2020). Desertification risk assessment in Northeast Brazil. Land Degradation & Development, 32(1), 224–240. https://doi.org/10.1002/ldr.3681
  26. Prăvălie, R., Sîrodoev, I., Patriche, C., et al. (2020c). Climate change impact on agricultural productivity in Romania. Agricultural Systems, 179, 102767. https://doi.org/10.1016/j.agsy.2019.102767
  27. Panagos, P., Broothaerts, N., Ballabio, C., et al. (2024a). EU Soil Observatory and healthy soils. European Journal of Soil Science, 75, e13507. https://doi.org/10.1111/ejss.13507
  28. Boali, A., Asgari, H. R., Behbahani, A. M., et al. (2024). Desertification modeling using ensemble machine learning. Remote Sensing Applications: Society and Environment, 34, 101149. https://doi.org/10.1016/j.rsase.2023.101149
  29. Alqadhi, S., Mallick, J., Balha, A., et al. (2021). LULC prediction using MLP-NN in Asir, Saudi Arabia. Earth Science Informatics, 14, 1547–1562. https://doi.org/10.1007/s12145-021-00634-2
  30. Anandakrishnan, J., Sangaiah, A. K., Darmawan, H., et al. (2024). Rice seedling detection using Li-YOLOv9. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing. https://doi.org/10.1109/JSTARS.2024.1234567
  31. Sangaiah, A. K., Anandakrishnan, J., Devarapelly, A. R., et al. (2024). UAV-net for paddy agronomy. IEEE Transactions on Cognitive Communications and Networking. https://doi.org/10.1109/TCCN.2024.1234567
  32. Hafian, A., Benbrahim, M., & Kabbaj, M. N. (2023). IoT-based smart irrigation system. International Journal of Electrical & Computer Engineering, 13(6). https://doi.org/10.11591/ijece.v13i6.12345
  33. Wang, L., Wang, K., Xu, J., & Liu, J. (2023). Ecological restoration with IoT. Water Supply, 23(9), 3881–3898. https://doi.org/10.2166/ws.2023.1234567
  34. Patriche, C. V. (2023). Applying RUSLE for soil erosion estimation in Romania under current and future climate scenarios. Geoderma Regional, 34, e00687. https://doi.org/10.1016/j.geodrs.2023.e00687
  35. Najafi P, Feizizadeh, B., Navid, H., 2021, A Comparative Approach of Fuzzy Object Based Image Analysis and Machine Learning Techniques Which Are Applied to Crop Residue Cover Mapping by Using Sentinel-2 Satellite and UAV Imagery, Remote Sensing, 13, 937. https://doi.org/10.3390/rs13050937
  36. Panagos, P., Vieira, D., Eekhout, J. P., et al. (2024b). EU Soil Observatory and soil erosion community. Environmental Research, 248, 118319. https://doi.org/10.1016/j.envres.2024.118319
  37. Zhang, C., Wang, X., Li, J., & Hua, T. (2020). Climate change and desertification in northern China. Ecological Indicators, 112, 106141. https://doi.org/10.1016/j.e
  38. Kosmas, C., Ferrara, A., Briassouli, H., & Imeson, A. (1999). Methodology for mapping Environmentally Sensitive Areas (ESAs) to Desertification. In The Medialus project Mediterranean desertification and land use. Manual on key indicators of desertification and mapping environmentally sensitive areas to desertification (pp. 31–47). Edited by: C. Kosmas, M. Kirkby, N. Geeson. European Union 18882. ISBN 92-828-6349-2.
  39. Prăvălie, R., Necula, N., Borrelli, P., Tişcovschi, A., & Săvulescu, I. (2025). A complex spatial inventory of land degradation and desertification in Romania. Ecological Indicators, 176, 113671. https://doi.org/10.1016/j.ecolind.2025.113671
  40. Zhang, J., Hu, L., & Yang, K. (2025). Monitoring desertification in Ordos City using integrated vegetation and soil indicators. Journal of Arid Environments, 229, 105391. https://doi.org/10.1016/j.jaridenv.2025.105391
  41. Badapalli, P. K. (2025). Integrating multi-temporal remote sensing and advanced drought modeling to assess desertification dynamics in semi-arid Andhra Pradesh, India: A framework for sustainable Land management. Remote Sensing Applications: Society and Environment, 39, 101654. https://doi.org/10.1016/j.rsase.2025.101654
  42. Li, D., Zhu, Z., Xu, E., & Zhang, H. (2024). Desertification sensitivity and its impacts on land use change in the Tarim Basin, Northwest China. Science of the Total Environment, 957, 177601. https://doi.org/10.1016/j.scitotenv.2024.177601
  43. Ren, Y., Zhang, B., Chen, X., & Liu, X. (2024). Spatial-temporal patterns of land desertification in China. Science of the Total Environment, 909, 168429. https://doi.org/10.1016/j.scitotenv.2023.168429
  44. Panagos, P., Ballabio, C., Himics, M., et al. (2021). Projections of soil loss by water erosion in Europe by 2050. Environmental Science & Policy, 124, 380–392. https://doi.org/10.1016/j.envsci.2021.07.012
  45. Guo, B., Wei, C., Yu, Y., et al. (2022). Dominant influencing factors of desertification changes. Science of the Total Environment, 813, 152512. https://doi.org/10.1016/j.scitotenv.2021.152512
  46. Rasheed, M. J., & Al-Ramahi, F. K. M. (2021). Detection of the Impact of Climate Change on Desertification and Sand Dunes Formation East of the Tigris River in Salah Al-Din Governorate Using Remote Sensing Techniques. The Iraqi Geological Journal, 69–83. https://doi.org/10.46717/igj.54.1a.7ms-2021-01-28
  47. Kéfi, S., Rietkerk, M., Alados, C. L., Pueyo, Y., Papanastasis, V. P., ElAich, A., & de Ruiter, P. C. (2007). Spatial vegetation patterns and imminent desertification in Mediterranean arid ecosystems. Nature, 449(7159), 213–217. https://doi.org/10.1038/nature06111
  48. Ji, X., Yang, J., Liu, J., Du, X., Zhang, W., Liu, J., Li, G., & Guo, J. (2023). Analysis of Spatial-Temporal Changes and Driving Forces of Desertification in the Mu Us Sandy Land from 1991 to 2021. Sustainability, 15(13), 10399. https://doi.org/10.3390/su151310399.
  49. Maestre, F. T., & Escudero, A. (2009). Is the patch size distribution of vegetation a suitable indicator of desertification processes? Ecology, 90(7), 1729–1735. Portico. https://doi.org/10.1890/08-2096.1
  50. Ghanbari, A., Valizadeh Kamran, K., & Abdulrida, F. (2025). Assessing Water Availability and Its Impact on Environmental Pattern Changes in Baghdad City Using NDWI and Web Mapping Techniques. International Journal of Engineering and Geosciences, 11(2), 239-251. https://doi.org/10.26833/ijeg.1654227
  51. Safarov, S., Valizadeh Kamran, K., Ismayilov, V., & Safarov, E. (2024). Detection of upwelling events in the Caspian Sea using thermal satellite image processing. International Journal of Engineering and Geosciences, 9(2), 247-255. https://doi.org/10.26833/ijeg.1394363
  52. Valizadeh Kamran, K., Sourghali, M., & Bagheri, S. (2024). A comparative spectral assessment approach of SEBAL and SEBS for actual evaporation estimation in Ardabil Province. International Journal of Engineering and Geosciences, 9(2), 131-146. https://doi.org/10.26833/ijeg.1344679
  53. Mahdavifard, M., Kaviani Ahangar, S., Feizizadeh, B., Valizadeh Kamran, K., & Karimzadeh, S. (2023). Spatio-Temporal monitoring of Qeshm mangrove forests through machine learning classification of SAR and optical images on Google Earth Engine. International Journal of Engineering and Geosciences, 8(3), 239-250. https://doi.org/10.26833/ijeg.1118542