This paper presents a study of vertical land movements conducted in northwestern Poland, covering the city of Szczecin. The land of Szczecin is made up of organic soils, covered in many places by water (lagoons, rivers, and lakes), which are susceptible to displacement; therefore, benchmarks in this area are susceptible to changes in height. The analysis of the geological structure of the near-surface layer of the Szczecin area, such as organic soils, sands, and clays, was carried out. The detailed recognition of geological structure in connection with height changes of benchmarks made it possible to locate stable benchmarks in the researched area. In the first step, the authors chose benchmarks in a stable geological structure based on archive data from the Polish Geodesy Documentation Center. In the second step, precise GNSS 3D measurements were performed in the direct vicinity of these benchmarks in order to verify their stability. Verified stations provided a reference for the reliable monitoring of the deformation of other surfaces resulting, for example, from changes in organic sediments. Existing and new engineering structures erected in the area of the Oder River Szczecin islands were selected for the final research of vertical land motions. Static GNSS observations were conducted in November 2020 and May 2021.

This paper presents the challenges encountered in the dimensional control of ships, platforms, and offshore units. This novel approach utilizes machine learning (MLP—Multilayer Perceptron Neural Network) for three-dimensional (3D) spatial coordinate transformations when only three common points are known. The proposed method was verified based on laboratory and field data. The main issue was to provide a sufficient number of valid training points. The oversampling method was used to meet this criterion. The achieved results indicate equal or better accuracy when the points were located inside the adjustment points array. In the case where the points lay outside this array, no improvement in the accuracy of the transformation was observed. The neural approach restores the transformation symmetry, and in some cases, such as the study of deformation of engineering objects, breaks the symmetry rather than restoring it.