Spatial Prediction and Mapping of Cold-Season Temperatures in Salah Al-Din Governorate for 2030 Using Remote Sensing and Geospatial Artificial Intelligence (GeoAI)

Ibrahim, Saad Thamer

doi:10.37653/juah.2026.168140.1396

	Spatial Prediction and Mapping of Cold-Season Temperatures in Salah Al-Din Governorate for 2030 Using Remote Sensing and Geospatial Artificial Intelligence (GeoAI)
Journal of University of Anbar for Humanities
Volume 2026, Issue 3, September 2026, Pages 842-812 PDF (5.48 M)
Document Type: Research Paper
DOI: 10.37653/juah.2026.168140.1396
Author
Saad Thamer Ibrahim^*
‎University of Tikrit -College of Arts, Iraq
Abstract
Aims: This study aims to employ Artificial Intelligence (AI) and Remote Sensing (RS) techniques to develop an advanced cartographic modeling framework for analyzing low temperatures and predicting their spatial distribution across Salah Al-Din Governorate, with particular emphasis on the cold months and the associated climatic variables. It also seeks to identify the spatiotemporal patterns of temperature during previous years and to utilize historical climate data to develop a predictive model capable of estimating future temperatures. Particular attention is given to the application of the Random Forest Regression algorithm to generate predictive maps of expected cold-season temperatures for 2030. The study is intended to contribute to climatological and geographical research requiring a more precise understanding of the spatial and temporal variability of temperature. Methodology: The study adopted a quantitative analytical approach integrating Remote Sensing, Artificial Intelligence, and Geographic Information Systems (GIS), while taking advantage of the capabilities of the Google Earth Engine (GEE) platform for processing and analyzing large volumes of climatic and spatial data within a cloud-based computing environment. Historical climate data covering the period from 2010 to 2025 were used to examine thermal patterns and identify the spatial and temporal variations in low temperatures across Salah Al-Din Governorate. Climate and reanalysis data obtained from the European Centre for Medium-Range Weather Forecasts (ECMWF) through the Copernicus Climate Change Service were also utilized. Following data preprocessing and organization, a Random Forest Regression machine-learning model was developed to predict low temperatures and generate spatial maps of projected temperatures for 2030. The Entropy Index was additionally employed to assess the degree of spatial and temporal consistency and coherence in the model's predictive outputs. Results: The findings demonstrate the effectiveness of integrating Artificial Intelligence and Remote Sensing techniques in the analysis of climatic data and the development of cartographic models capable of representing the spatial and temporal variability of low temperatures. The Random Forest Regression model proved capable of capturing complex patterns within the climatic data and producing predictions characterized by a high degree of spatial and temporal consistency. The evaluation results showed an entropy value of H = 1.080, compared with a maximum value of Hmax = 1.099, indicating a high degree of regularity and homogeneity in the model's predictive outputs across the study area. These findings demonstrate the model's ability to effectively represent the spatiotemporal variability of low temperatures and its potential for generating future-oriented maps that identify possible patterns in the spatial distribution of cold temperatures across Salah Al-Din Governorate in 2030. Conclusions: The study concludes that integrating Artificial Intelligence and Remote Sensing within the Google Earth Engine environment provides an effective framework for analyzing large-scale climatic datasets and developing predictive cartographic models of atmospheric phenomena. The Random Forest Regression model demonstrated a strong capacity to represent the spatiotemporal variability of low temperatures and to predict their future spatial distribution patterns. The relatively high entropy value, H = 1.080 compared with Hmax = 1.099, further indicates a high degree of consistency and coherence in the model's cartographic outputs. Accordingly, AI- and Remote Sensing-based modeling can serve as an important tool for future climatological research, particularly for generating predictive maps that support the interpretation of thermal variations and inform climate-related planning and decision-making in Salah Al-Din Governorate.
Keywords
Cartographic Prediction; Remote Sensing; Artificial Intelligence; Machine Learning; Cartographic Modeling

References
[1] - عبدالرحمن مصطفى دبس. (2017). تحليل المتغيرات البصرية للرموز النقطية الكارتوكرافية. مجلة البحوث والدراسات، سلسلة العلوم الإنسانية والاجتماعية، 32(4). 2- Hersbach, H., Bell, B., Berrisford, P., Hirahara, S., Horányi, A., Muñoz-Sabater, J., Nicolas, J., Peubey, C., Radu, R., Schepers, D., Simmons, A., Soci, C., Abdalla, S., Abellan, X., Balsamo, G., Bechtold, P., Biavati, G., et al. (2020). The ERA5 global reanalysis. Quarterly Journal of the Royal Meteorological Society, 146(730), 1999–2049. https://doi.org/10.1002/qj.3803 3- Oke, T. R. (1987). Boundary layer climates (2nd ed.). Routledge. 4- Wikle, C. K. (2003). Hierarchical Bayesian models for predicting the spread of ecological processes. Ecology, 84(6), 1382–1394. https://www.jstor.org/stable/3107956 5- Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5–32. https://doi.org/10.1023/A:1010933404324 6- Barry, R. G., & Chorley, R. J. (2010). Atmosphere, weather and climate. Routledge. 7- Al Mashagbah, A. F. (2016). The use of GIS, remote sensing and Shannon’s entropy statistical techniques to analyze and monitor the spatial and temporal patterns of urbanization and sprawl in Zarqa City, Jordan. Journal of Geographic Information System, 8(2), 249. https://www.scirp.org/journal/paperinformation?paperid=66123 8- Yang, N., Wang, Y., Wei, Z., & Wu, F. (2025). MapColorAI: Designing contextually relevant choropleth map color schemes using a large language model. Cartography and Geographic Information Science.https://doi.org/10.1080/15230406.2025.2531055.
Statistics Article View: 27 PDF Download: 28