Assessment of Regression and Classification Methods Using Remote Sensing Technology for Detection of Coastal Depth (Case Study of Bushehr Port and Kharg Island)

Any decision-making and planning in coastal areas and ports require a series of basic information in which bathymetry is an important part of it. The concern of most scholars who deal with or research in this area is to access accurate, up-to-date, and cost-effective information. One of the methods to achieve such information is to use remote sensing technologies. The purpose of this study is to use Landsat 8 Operational Land Imager and Random Forest algorithm by using regression and classification methods for depth prediction in a part of Persian Gulf region (Bushehr port, Kharg Island, and its surroundings). For verification of depth prediction in these two methods, two indices of root mean square error and mean absolute error in the regression method and the Kappa index (KAPPA) for classification method were used. The results of these two methods show that in both regression and classification methods, the best combination of bands for depth prediction was the band combination (1–2–3–4) and the Landsat 8 satellite image has the ability to obtain depth with a fairly acceptable accuracy to depth of around 10 m. From the depths of 10 m onward, the measurement error will increase relative to the depth.