Published Paper Details:

Efficient highway route planning requires minimizing construction cost, reducing environmental disturbance, and adapting to complex terrain conditions--tasks that traditional GIS-based and manual planning methods often struggle to accomplish. This study presents a comprehensive review of satellite image-driven techniques for highway route optimization using high-resolution imagery collected from Google Earth. A set of 25 peer-reviewed studies published between 2019 and 2024 are analysed to examine advancements in deep learning-based semantic segmentation, terrain analysis, and multi-objective optimization algorithms. The survey highlights modern approaches such as U-Net-based land cover classification, graph-based shortest-path algorithms, and multi-criteria decision-making frameworks that enable the identification of eco-friendly and cost-efficient high- way alignments. Key challenges--including data preprocessing complexity, regulatory constraints, and the lack of real-time adaptability--are discussed in detail. The findings also outline promising future directions in AI-driven geospatial modelling, automated environmental impact assessment, and sustainable route planning. This review serves as a valuable reference for researchers and policymakers seeking environmentally conscious and technically reliable highway route optimization solutions using satellite imagery from platforms like Google Earth.