Application of Artificial Intelligence in Modeling Environmental Degradation Maps in Salah Al-Din Governorate
DOI:
https://doi.org/10.25130/jfa.conf.10.1.9Keywords:
Environmental degradation maps, automated classification, artificial intelligence algorithmsAbstract
The study aims to model and analyze environmental degradation maps in Salah Al-Din Governorate using artificial intelligence techniques by examining the relationship between Land Surface Temperature (LST), the Normalized Difference Vegetation Index (NDVI), and the Standardized Precipitation Index (SPI) derived from satellite data. The research utilized Landsat-8 imagery for the period (2014–2024), with all processing and analysis conducted on the Google Earth Engine (GEE) platform. Artificial intelligence algorithms were applied to predict environmental degradation maps for the year 2025 and to classify environmentally affected areas based on the inverse relationship among the indices. High LST values coupled with low NDVI and SPI values were found to indicate zones of severe vegetation degradation. The results revealed a strong negative correlation between LST, SPI, and NDVI, highlighting the impact of thermal stress on vegetation cover degradation. Moreover, the intelligent models proved highly effective in accurately identifying degradation hotspots, demonstrating their potential as a powerful tool for detecting environmentally degraded areas in the study region
Downloads
References
1 - A Review of Practical AI for Remote Sensing in Earth Sciences. (2023). MDPI.
2 - Wikipedia contributors. (2024). Normalized Difference Vegetation Index. In Wikipedia. Retrieved from https://en.wikipedia.org/wiki/Normalized_difference_vegetation_index
3 - Li, Y., Wang, H., Chen, L., & Xu, J. (2024). WWPASFS-BiGRU: A hybrid attention-based BiGRU model optimized with waterwheel plant algorithm and adaptive fractal search for NDVI prediction. Journal of Big Data Analytics in Agriculture, 10(2), 115–134. https://link.springer.com/article/10.1007/s41060-024-00640-8
4 - Liu, S., Wang, S., & Zhang, L. (2025). Daily Land Surface Temperature Reconstruction in Landsat Cross-Track Areas Using Deep Ensemble Learning With Uncertainty Quantification. arXiv. https://arxiv.org/abs/2502.14433
5 - Bouaziz, S., Hafiane, A., Canals, R., & Nedjai, R. (2025). FuseTen: A Generative Model for Daily 10 m Land Surface Temperature Estimation from Spatio-Temporal Satellite Observations. arXiv. https://arxiv.org/abs/2507.23154
6 - AghaKouchak, A., & Farahmand, A. (2019). A machine learning model for drought tracking and forecasting using satellite precipitation data. Environmental Research Letters, 14(12), 124039.
7 - Rivera, R., & García, J. (2018). Meta-Analysis in Using Satellite Precipitation Products for Drought Monitoring. Remote Sensing, 10(11), 1816.
8 - Liu, S., Wang, S., & Zhang, L. (2025). Daily Land Surface Temperature Reconstruction in Landsat Cross-Track Areas Using Deep Ensemble Learning With Uncertainty Quantification. arXiv. https://arxiv.org/abs/2502.14433
9 - Bouaziz, S., Hafiane, A., Canals, R., & Nedjai, R. (2025). FuseTen: A Generative Model for Daily 10 m Land Surface Temperature Estimation from Spatio-Temporal Satellite Observations. arXiv. https://arxiv.org/abs/2507.23154
10- Das, P., & Singh, S. P. (2025). Shannon Diversity Index (H) as an ecological indicator of environmental pollution: A GIS approach. Environmental Pollution, 300, 118-126. https://doi.org/10.1016/j.envpol.2025.118
11- Kruskal, W. H., & Wallis, W. A. (1952). Use of ranks in one-criterion variance analysis. Journal of the American Statistical Association, 47(260), 583–621. https://doi.org/10.1080/01621459.1952.10483441
12- SciPy Community. (2024). scipy.stats.kruskal — SciPy v1.16.1 Manual. Retrieved September 5, 2025, from https://docs.scipy.org/doc/scipy/reference/generated/scipy.stats.kruskal.html
13- نجيب عبدالرحمن الزيدي، عبير يحيى الساكني، سعد ثامر ابراهيم الحمداني، تطبيقات في الخرائط البيئية، ط1، دار الابداع للطباعة والنشر والتوزيع ، العراق – صلاح الدين – تكريت ، 2025 ، ص 19 .
14- سعد ثامر ابراهيم ، نجيب عبدالرحمن محمود، مشكلات التمثيل الحجمي في الخرائط الموضوعية الكمية، بحث منشور، مجلة آداب الفراهيدي-كلية الآداب- جامعة تكريت، مجلد 12،عدد42، العراق،2020، ص 156.
