AHP and Machine Learning-Based Military Strategic Site Selection: A Case Study of Adea District East Shewa Zone, Ethiopia

• Published in: Journal of sensors 2023-07, Vol.2023 (1)
• Main Authors: Bojer, Amanuel Kumsa, Woldesilassie, Firesew Feyisso, Debelee, Taye Girma, Kebede, Samuel Rahimeto, Esubalew, Sintayehu Zekarias
• Format: Article
• Language: English
• Subjects: Algorithms; Artificial intelligence; Decision making; Decision trees; Geographic information systems; Hierarchies; Land cover; Land use; Machine learning; Multiple criterion; Optimization models; Satellite imagery
• ISSN: 1687-725X; 1687-7268
• DOI: 10.1155/2023/6651486

In dynamic situations, multicriteria decision-making (MCDM) for classification frequently takes place. The selection of suitable land sites and clear criteria is one of the most significant challenges in strategic military site selection around the world and at the national level. The main objectives of the present study are to find out the strategic military site land suitability in Adea District by using AHP, GIS, and machine learning algorithms. To determine the subject weights of criteria, a novel approach for prioritizing the intuitionistic fuzzy judgement matrix is proposed. An optimization model is developed to determine the objective weights that maximize the distance of each alternative to the negative-ideal solution. Machine learning methods are mainly employed for filtering, interpreting, and predicting information from satellite image data. The random forest analysis method is used for patterning the military strategic site selection in the Adea District. The results of the study were able to create models and submodels of military strategic site land suitability using the weighted linear combination (WLC) mechanism. From the entire research area woreda, 87.02 km2 (9.3%), 439.11 km2 (46.9%), 114.59 km2 (12.2%), 196.48 km2 (20.9%), and 99.19 km2 (10.6%) have not suitable, marginally suitable, moderately suitable, suitable, and highly suitable conditions, respectively, for a strategic military site. Changes in the six classes of land use/land cover were assessed with an overall accuracy of above 97% and an overall kappa statistic of 96%. Finally, the study actually suggests that ML, RS, GIS, and AHP algorithms are beneficial for decision-makers (DMs) that will enhance the procedure for strategic military site, supported by multicriteria decision-making and its applications for the study area’s land suitability. Furthermore, security and military authorities will be able to propose a planning protocol and suitable sites for strategic military site selection in the near future based on the study’s basic methodological application and main findings.