Machine learning algorithms for optimization of image classification in spatially constrained regions: A case of Eritrea, East Africa

Article Sidebar

PDF
Published: Sep 15, 2025
DOI: https://doi.org/10.5937/engtoday2500008L
Keywords:
Machine learning, Image analysis, Africa, GRASS GIS, Remote sensing

Main Article Content

Polina Lemenkova
University of Bologna, Department of Biological, Geological and Environmental Sciences, Bologna, Italy

Abstract

This paper presents the application of Machine Learning (ML) algorithms to solve the problem of optimization of classification tasks in Remote Sensing (RS) data processing. RS data is effective in spatial environmental monitoring since it enables detection of areas affected by natural hazards: droughts, desertification, coastal floods and deforestation. Vulnerable regions can be identified using analysis of spaceborne images for strategic land planning and decision making. The effectiveness of several ML models was tested using Geographic Resources Analysis Support System (GRASS) GIS software for satellite image analysis. Employing ML enabled to perform image classification tasks based on similarity of spectral reflectance of pixels. The following algorithms were tested and compared: Gaussian Naive Bayes (GNB), Decision Tree Classifier (DTC), and Linear Discriminant Analysis (LDA). The ML models were adopted to classify a time series of the Landsat 8-9 OLI/TIRS images and evaluate changes in land cover types in coastal and desert areas of Eritrea. This region encompasses the protected Semenawi Bahri National Park, notable for a diverse range of unique wildlife near the Massawa Channel, Red Sea. The results demonstrated changes in land cover types over the period of 2014-2024 which proved the climate-related effects on landscape dynamics. This paper demonstrated the efficiency of the ML methods in Geographic Information Systems (GIS) tailored to solve specific spatially constrained problems of land cover type identifying using scripting in GRASS GIS.

Article Details

How to Cite
[1]
P. Lemenkova, “Machine learning algorithms for optimization of image classification in spatially constrained regions: A case of Eritrea, East Africa”, ET, vol. 4, no. 2, pp. 13–27, Sep. 2025.
Issue
Vol. 4 No. 2 (2025): Engineering TODAY
Section
Original Scientific Papers

References

[1] D. Karssenberg and K. De Jong, “Dynamic environmental modelling in GIS: 1. Modelling in three spatial dimensions”. International Journal of Geographical Information Science, Vol. 19(5), pp. 559–579, https://doi.org/10.1080/13658810500032362, (2005)

[2] P. Lindh and P. Lemenkova, “Utilising Pareto efficiency and RSM to adjust binder content in clay stabilisation for Yttre Ringvägen, Malmö”. Acta Polytechnica, Vol. 63(2), pp. 140-157. https://doi.org/10.14311/AP.2023.63.0140, (2023)

[3] T. Li, X. Chen, X. Wang, L. Zhao, X. Zhou, A. Zou, and H.O. Ikhumhen, “Grid computing method for atmospheric environmental capacity coupled with ventilation coefficient using CALPUFF simulation and GIS spatial analysis technology”. Environmental Technology, Vol. 45(2), pp. 294–305. https://doi.org/10.1080/09593330.2022.2109993, (2022)

[4] P. Lindh and P. Lemenkova, "Shear bond and compressive strength of clay stabilised with lime/cement jet grouting and deep mixing: A case of Norvik, Nynäshamn". Nonlinear Engineering, Vol. 11(1), pp. 693-710. https://doi.org/10.1515/nleng-2022-0269, (2022)

[5] P. Lemenkova, “Tanzania Craton, Serengeti Plain and Eastern Rift Valley: mapping of geospatial data by scripting techniques”, Estonian Journal of Earth Sciences, Vol. 71, 2, pp. 61–79, https://doi.org/10.3176/earth.2022.05, (2022)

[6] V. Kumar, K. V. Sharma, T. Caloiero, D. J. Mehta, and K. Singh, “Comprehensive overview of flood modeling approaches: A Review of Recent Advances”, Hydrology, Vol. 10(7), p. 141, https://doi.org/10.3390/hydrology10070141, (2023)

[7] M. Xie, W. Wang, W. Yin, and J. Dong, "IFAO-Simo: A spatial-simulation based facility network optimization framework", 2007 Winter Simulation Conference, Washington DC (USA), pp. 2221-2226, https://doi.org/10.1109/WSC.2007.4419857, (2007)

[8] B. Saeidian, M. S. Mesgari, B. Pradhan, and M. Ghodousi, "Optimized location-allocation of earthquake relief centers using PSO and ACO, complemented by GIS, clustering, and TOPSIS", ISPRS International Journal of Geo-Information, Vol. 7(8), p. 292, https://doi.org/10.3390/ijgi7080292, (2018)

[9] B. Y. Chen, H. Yuan, Q. Li, S. L. Shaw, W. H. K. Lam, and X. Chen, “Spatiotemporal data model for network time geographic analysis in the era of big data”, International Journal of Geographical Information Science, Vol. 30(6), pp. 1041–1071, https://doi.org/10.1080/13658816.2015.1104317, (2015)

[10] P. Lemenkova, “Mapping Ghana by GMT and R scripting: advanced cartographic approaches to visualize correlations between the topography, climate and environmental setting”, Advances in Geodesy and Geoinformation, Vol. 71(1), e16, pp. 1-20, https://doi.org/10.24425/gac.2022.141169, (2022)

[11] P. Yue, F. Gao, B. Shangguan, and Z. Yan, “A machine learning approach for predicting computational intensity and domain decomposition in parallel geoprocessing” International Journal of Geographical Information Science, Vol. 34(11), pp. 2243–2274, https://doi.org/10.1080/13658816.2020.1730850, (2020)

[12] A. Lakhouit, G. M. T. Abdalla, E. H. O. Elsadig, W. S. Al-Rashed, I. Abdel-Magid, A. Ben Messaoud, A. H. A. Yassin, O. A. Sayed, M. B. Elsawy, and G. Hayder, "Sustainable airport planning using a multi-criteria decision-making approach with fuzzy logic and GIS integration”, Buildings, Vol. 15(10), p. 1749. https://doi.org/10.3390/buildings15101749, (2025)

[13] N. Tavoularis, “Soil Erosion and Landslide Susceptibility Mapping in Western Attica, Greece: A Rock Engineering System Approach. Geosciences, 13(11), 338. https://doi.org/10.3390/geosciences13110338, (2023).

[14] P. Lemenkova, “Machine Learning algorithms of remote sensing data processing for mapping changes in land cover types over central Apennines, Italy”, Journal of Imaging, Vol. 11(5), p. 153. https://doi.org/10.3390/jimaging11050153, (2025)

[15] D. Zinner, F. Peláez, and F. Torkler, “Distribution and habitat of grivet monkeys (Cercopithecus aethiops aethiops) in eastern and central Eritrea”, African Journal of Ecology, Vol. 40, pp. 151-158. https://doi.org/10.1046/j.1365-2028.2002.00360.x, (2002)

[16] M. Fessehaye, Y. Brugnara, M. J. Savage and S. Brönnimann, “A note on air temperature and precipitation variability and extremes over Asmara: 1914–2015”, Internatioanl Journal of Climatology, Vol. 39, pp. 5215–5227, https://doi.org/10.1002/joc.6134, (2019)

[17] M.G. Ghebrezgabher, T. Yang, X. Yang, and C. Wang, "Assessment of desertification in Eritrea: land degradation based on Landsat images", Journal of Arid Land, Vol. 11, pp. 319–331, https://doi.org/10.1007/s40333-019-0096-4, (2019)

[18] P. Lemenkova, “Evapotranspiration, vapour pressure and climatic water deficit in Ethiopia mapped using GMT and TerraClimate dataset”, Journal of Water and Land Development, Vol. 54(7-9), pp. 201–209, https://doi.org/10.24425/jwld.2022.141573, (2022)

[19] P. Billi, “Geomorphology of Eritrean river systems”, in: Landscapes and Landforms of the Horn of Africa, P. Billi, Ed., World Geomorphological Landscapes. Springer (Switzerland), https://doi.org/10.1007/978-3-031-05487-7_4, (2022)

[20] M. Ionita, T. Felis, G. Lohmann, N. Rimbu, and J. Pätzold, “Distinct modes of East Asian winter monsoon documented by a southern Red Sea coral record”, Journal of Geophysical Research: Oceans, Vol. 119, pp. 1517–1533, https://doi.org/10.1002/2013JC009203, (2014)

[21] Z. Girma, Y. Mamo, G. Mengesha, A. Verma, and T. Asfaw, “Seasonal abundance and habitat use of bird species in and around Wondo Genet Forest, south-central Ethiopia”, Ecology and Evolution, Vol. 7, pp. 3397–3405. https://doi.org/10.1002/ece3.2926, (2017)

[22] J. Nyssen, M. Haile, J. Naudts, N. Munro, J. Poesen, J. Moeyersons, A. Frankl, J. Deckers, and R. Pankhurst, “Desertification? Northern Ethiopia re-photographed after 140 years”, Science of The Total Environment, Vol. 407(8), pp. 2749–2755, https://doi.org/10.1016/j.scitotenv.2008.12.016, (2009)

[23] R. Klaus, “Coral reefs and communities of the Central and Southern Red Sea (Sudan, Eritrea, Djibouti, and Yemen)”, in: The Red Sea. Springer Earth System Sciences, N. Rasul, I. Stewart, Eds., Springer, Berlin(Germany), https://doi.org/10.1007/978-3-662-45201-1_25, (2015)

[24] T. D. Bhaga, T. Dube, M. D. Shekede, and C. Shoko, “Investigating the effectiveness of Landsat-8 OLI and Sentinel-2 MSI satellite data in monitoring the effects of drought on surface water resources in the Western Cape Province, South Africa”, Remote Sensing Applications: Society and Environment, Vol. 32, p. 101037, https://doi.org/10.1016/j.rsase.2023.101037, (2023)

[25] G. L. Feyisa, H. Meilby, R. Fensholt, and S. R. Proud, “Automated water extraction index: a new technique for surface water mapping using Landsat imagery”, Remote Sensing of Environment, Vol. 140, pp. 23–35, https://doi.org/10.1016/j.rse.2013.08.029, (2014)

[26] P. Lemenkova, “Random forest classifier algorithm of geographic resources analysis support system geographic information system for satellite image processing: Case study of Bight of Sofala, Mozambique”, Coasts, Vol. 4(1), pp. 127-149. https://doi.org/10.3390/coasts4010008, (2024)

[27] M. Neteler, M. Hamish Bowman, M. Landa and M. Metz, “GRASS GIS: A multi-purpose open source GIS”, Environmental Modelling & Software, Vol. 31, pp. 124-130, https://doi.org/10.1016/j.envsoft.2011.11.014, (2012)

[28] P. Lemenkova, “Support vector machine algorithm for mapping land cover dynamics in Senegal, West Africa, using Earth observation data”, Earth, Vol. 5(3), pp. 420-462. https://doi.org/10.3390/earth5030024, (2024)

[29] P. Lemenkova, “Console-based mapping of Mongolia using GMT cartographic scripting toolset for processing TerraClimate data”, Geosciences, Vol. 12(3), pp. 140. https://doi.org/10.3390/geosciences12030140, (2022)

[30] P. Lemenkova, “Automation of image processing through ML algorithms of GRASS GIS using embedded Scikit-Learn library of Python”, Examples and Counterexamples, Vol. 7(100180), https://doi.org/10.1016/j.exco.2025.100180, (2025)

[31] J. Wang, Y. Yang, and B. Xia, “A simplified Cohen’s Kappa for use in binary classification data annotation tasks”, IEEE Access, Vol. 7, pp. 164386-164397, https://doi.org/10.1109/ACCESS.2019.2953104, (2019)

[32] D. Sudiana, S. H. Putri, D. Kushardono, A. S. Prabuwono, J. T. Sri Sumantyo, and M. Rizkinia, “CNN-random forest hybrid method for phenology-based paddy rice mapping using Sentinel-2 and Landsat-8 satellite images”, Computers, Vol. 14(8), p. 336, https://doi.org/10.3390/computers14080336, (2025)

[33] P. Lemenkova, “Artificial neural networks for mapping coastal lagoon of Chilika Lake, India, using Earth observation data”, Journal of Marine Science and Engineering, Vol. 12(5), p. 709, https://doi.org/10.3390/jmse12050709, (2024).

[34] V. Sood, R. K. Tiwari, S. Singh, R. Kaur, and B. R. Parida, “Glacier Boundary mapping using deep learning classification over Bara Shigri glacier in western Himalayas”, Sustainability, Vol. 14(20), p. 13485, https://doi.org/10.3390/su142013485, (2022)

[35] P. Lemenkova, “Deep learning methods of satellite image processing for monitoring of flood dynamics in the Ganges Delta, Bangladesh”, Water, Vol. 16(8), p. 1141, https://doi.org/10.3390/w16081141, (2024)

[36] Global Forest Watch report, https://www.globalforestwatch.org/dashboards/country/ERI/?category=land-cover

[37] E. Symeonakis and N. Drake, “Monitoring desertification and land degradation over sub-Saharan Africa”, International Journal of Remote Sensing, Vol. 25(3), pp. 573–592. https://doi.org/10.1080/0143116031000095998, (2004)

[38] J. A. Mabbutt, “Desertification and the future of the arid lands” Australian Geographer, Vol. 14(3), pp. 141–150. https://doi.org/10.1080/00049187908702754, (1979)

[39] L. Hua, W. Man, Q. Wang, and X. Zhao, "A new decision tree classification approach for extracting urban land from Landsat TM in a Coastal City, China," 2012 Fourth International Symposium on Information Science and Engineering, Shanghai (China), pp. 282-286, https://doi.org/10.1109/ISISE.2012.71, (2012)

[40] H. C. Verma, T. Ahmed, and S. Rajan, “An approach to estimate the instability and growth trends of Mango Crop area by using the optical satellite images”, IGARSS 2022 – 2022 IEEE International Geoscience and Remote Sensing Symposium, Kuala Lumpur (Malaysia), pp. 4887-4890, https://doi.org/10.1109/IGARSS46834.2022.9884462, (2022)

[41] P. Lemenkova, “Handling dataset with geophysical and geological variables on the Bolivian Andes by the GMT scripts”, Data, Vol. 7(6), p. 74, https://doi.org/10.3390/data7060074, (2022)

[42] P. Lemenkova, “Machine learning methods of remote sensing data processing for mapping salt pan crust dynamics in Sebkha de Ndrhamcha, Mauritania”, Artificial Satellites, Vol. 60(2), pp. 37-69, https://doi.org/10.2478/arsa-2025-0003, (2025)

[43] Y. Bo and D. Song, “The effect of landscape patterns on the accuracy of land cover map from multi-resolution remote sensing data classification”, IGARSS 2008 - 2008 IEEE International Geoscience and Remote Sensing Symposium, Boston (USA), pp. III - 1008-III - 1011, https://doi.org/10.1109/IGARSS.2008.4779523, (2008)

[44] R. Islam, M. Khatun, and S. H. Popy, “TL-GAN: transfer learning with generative adversarial network model for satellite image resolution enhancement”, 26th International Conference on Computer and Information Technology (ICCIT), Cox's Bazar (Bangladesh), pp. 1-5, https://doi.org/10.1109/ICCIT60459.2023.10441504, (2023)

[45] A. K. Venkat and K. Kulkarni, “Enhanced super-resolution with EDSR: Optimizing image quality across multiple scaling factors”, 2025 International Conference on Intelligent and Innovative Technologies in Computing, Electrical and Electronics (IITCEE), Bangalore (India), pp. 1-6, https://doi.org/10.1109/IITCEE64140.2025.10915430, (2025)

[46] P. Lemenkova, “Improving bimonthly landscape monitoring in Morocco, North Africa, by integrating machine learning with GRASS GIS”, Geomatics, Vol. 5(1), p. 5, https://doi.org/10.3390/geomatics5010005, (2025)

[47] G. Thiyagarajan and V. Vijayalakshmi, “Classification of land cover using machine learning models in Landsat satellite data”, 15th International Conference on Computing Communication and Networking Technologies (ICCCNT), Kamand (India), pp. 1-6, https://doi.org/10.1109/ICCCNT61001.2024.1072549, (2024)

[48] S. Sourav, N. Kaur, and B. Kaur, “A comprehensive review of machine learning for remote sensing: Current state, challenges, and future directions”, First International Conference on Technological Innovations and Advance Computing (TIACOMP), Bali (Indonesia), pp. 283-288, https://doi.org/10.1109/TIACOMP64125.2024.00054, (2024)

[49] P. Gupta and D. P. Shukla, “Combined optical and SAR remote sensing for LULC mapping of Imphal valley using machine learning algorithm”, International Conference on Machine Intelligence for GeoAnalytics and Remote Sensing (MIGARS), Hyderabad (India), pp. 1-4, https://doi.org/10.1109/MIGARS57353.2023.10064582, (2023)

[50] M. Mrithika, R. Vanitha, J. Jagan, D. P. Freeda, and M. Jayapranesh, “Land cover classification using satellite imagery and machine learning algorithm”, International Conference on Advanced Computing Technologies (ICoACT), Sivalasi (India), pp. 1-6, https://doi.org/10.1109/ICoACT63339.2025.11005205, (2025)