Summary of Review Literature on Soil Data Using Satellite Image and Techniques of Artificial Intelligence

The current use of remote sensing allows the analysis of soil moisture levels, surface roughness, and texture. These methods help improve our comprehension of soil processes and facilitate informed decision-making, land management, environmental research, soil classification, and more. Currently, artificial intelligence (AI) techniques, such as machine learning (ML) and deep learning (DL), have the potential to be quite impressive in making accurate and efficient predictions for soil texture classification. The use of AI-based methods and techniques for combining data to process satellite imagery and Earth observation data has recently introduced new opportunities for tracking environmental changes and assessment. In this study, we examine a range of recent applications of AI-based methods and techniques for soil data analysis, including regional classification, continuous mapping with automated algorithms, and the optimization (design/re-design) of monitoring networks. Traditional soil classification and analysis methods have many challenges such as time consuming, very high cost, intrusiveness, among others. By accurately measuring the geotechnical properties and characteristics of soil using these methods combined with suitable ML algorithms will lead to different methods and techniques for soil classification. The integration of AI-based approaches in geotechnical engineering will lead to a new direction in risk assessment. The wide range of applications, from forecasting soil failures and landslides to evaluating structural stability, highlights the significant potential of this synergy.