• Chayan Biswas
• Sushmita Ghosh
• Anirban Maity

Preliminary geotechnical site investigation is a fundamental component of infrastructure planning because decisions concerning foundations, earthworks, slopes, and excavation, drainage and construction methods depend on an adequate understanding of subsurface conditions. Conventional investigation methods, including boreholes, trial pits, standard penetration tests, cone penetration tests, geophysical surveys and laboratory testing, provide essential ground-truth information but are spatially discrete, relatively expensive and often insufficient to fully represent heterogeneous geological environments. Recent advances in remote sensing, geographic information systems (GIS), spatial data analytics and artificial intelligence (AI) create an opportunity to complement conventional investigation through spatially continuous preliminary assessment and uncertainty-informed investigation planning. This paper proposes a conceptual framework for AI-assisted preliminary geotechnical site investigation that integrates multisource remote sensing, digital elevation models, geological and geomorphological information, hydrological and land-use data, legacy geotechnical records, GIS-based spatial databases, machine-learning algorithms, spatial statistics and uncertainty quantification. The framework comprises seven principal stages: (1) multisource data acquisition, (2) data quality control and spatial harmonization, (3) geotechnical feature engineering, (4) AI-assisted spatial prediction, (5) hazard and uncertainty assessment, (6) investigation-priority optimization, and (7) field validation and iterative model updating. Particular emphasis is placed on the distinction between remotely observable proxies and actual engineering parameters. Remote sensing and AI are therefore positioned as preliminary screening and decision-support technologies rather than substitutes for direct subsurface investigation.

Artificial intelligence; Geo AI; geotechnical investigation; remote sensing; GIS; machine learning; spatial analytics; uncertainty quantification; digital ground model.

"A Conceptual Framework for AI-Assisted Preliminary Geotechnical Site Investigation Using Remote Sensing, GIS and Spatial Data Analytics", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.13, Issue 9, page no.b670-b677, September-2026, Available :http://www.jetir.org/papers/JETIR2609174.pdf

"A Conceptual Framework for AI-Assisted Preliminary Geotechnical Site Investigation Using Remote Sensing, GIS and Spatial Data Analytics", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.13, Issue 9, page no. ppb670-b677, September-2026, Available at : http://www.jetir.org/papers/JETIR2609174.pdf