This research paper aims to analyze the minimax approach used in the semivariogram fitting process that forms one stage of the kriging operation performed for interpolation. The conventional method uses the weighted least squares fit for various theoretical functions such as stable, exponential, spherical. However, several recent approaches have been developed using machine learning regression techniques. This research employs the ordinary kriging technique where the proposed minimax approach is expected to increase the accuracy of the interpolation resulted by reducing the error of the final result. Kriging, which is based on the stochastic method, is widely used for spatial values and has been proven to be a better predicting process than deterministic methods. The novel approach to ordinary kriging discussed here, the minimax approach, is able to increase result accuracy based on the experiments performed. Minimax can predict the weights of the semivariogram values better than the weighted least-squares method and performs faster than machine learning approaches.

The North Java coastal area, known as the Pantura region, is experiencing significant land subsidence, with certain areas sinking up to 10 cm per year. Pekalongan is among the most affected, with subsidence rates between 10 and 19 cm annually, mainly due to groundwater extraction, sediment compaction, and coastal erosion. Other coastal cities, like Semarang and Demak, show rates averaging 4 to 10 cm per year. This rapid subsidence is due to favorable geological conditions and ongoing urban development. This study investigates land subsidence in Pekalongan using the PS-InSAR method and dynamic visualization of time-series land cover data. PS-InSAR was applied to 45 scenes from ALOS-2 PALSAR-2 to monitor subsidence from 2014 to 2022. The results were validated with in situ subsidence benchmarks. Urban development dynamics were analyzed through land cover and land use change (LULC) and population density over the same period, using the GLC_FCS30D dataset in the GEE to detect non-natural LULC. The PS-InSAR results indicated that over 60.9% of investigation points experienced subsidence, up to 100 cm between 2014 and 2022. Ground validation showed an 83% agreement with PS-InSAR results. A statistical analysis of LULC from 2014 to 2022 did not show significant built-up area development, but the extension of salt marshes and water bodies indicated subsidence expansion. The population density reached 6873 people per square km by 2022, causing extensive groundwater use for domestic and industrial purposes, further aggravating the subsidence.

Multispectral data and hyperspectral data acquired from satellite sensor have the ability in detecting various objects on the earth ranging from low scale to high scale modeling. These data are increasingly being used to produce geospatial information for rapid analysis by running feature extraction or classification process. Applying the most suited model for this data mining is still challenging because there are issues regarding accuracy and computational cost. This research aim is to develop a better understanding regarding object feature extraction and classification applied for satellite image by systematically reviewing related recent research projects. A method used in this research is based on PRISMA statement. After deriving important points from trusted sources, pixel based and texture-based feature extraction techniques are promising technique to be analyzed more in recent development of feature extraction and classification.

Data fusion from two sources of data could develop better output since the process may minimise any inherent disadvantages of the data. Cokriging data fusion requires a semivariogram fitting process, which is an important step for weight determination in the fusion process. The traditional method of cokriging fusion usually applies a specific model of semivariogram fitting based on the available options, such as circular or tetraspherical. This research aims to fuse height point data from two different sources using ordinary kriging based on LS-SVM regression, which is applied to the semivariogram fitting process. The data used are height points generated from stereo satellite imagery, GPS measurement, and topographic map points to generate DEMs. The research experiment begins by calculating the semivariogram model for all the data, and then the fitting process is performed by applying the same approach of functional approach for both sets of data. The following process is an ordinary cokriging interpolation, whose results are analysed and compared to the ordinary kriging interpolation. The experiment results prove that the ordinary cokriging fusion process could reduce interpolation error. The LS-SVM approach offers better precision in the semivariogram modelling by determining more precise weight calculation for cokriging fusion process.

DEM (Digital Elevation Model) as a digital model of the earth’s surface elevation could be generated from remote sensing technology such as stereo imaging for various applications. To generate DEM from stereo imagery, interpolation or approximation process stage is required. Stochastic interpolation e.g. ordinary kriging uses semivariogram fitting to calculate weights of interpolation values based on known points. This research is applying regression types of machine learning for semivariogram fitting to interpolate DEM. Previous research conducted was LS-SVM (Least Square-Support Vector Machine) and SVR (Support Vector Regression) for semivariogram fitting process. Types of SVM and GPR (Gaussian Process Regression) are adopted for semivariogram fitting for ordinary kriging interpolation in this experiment. The result showed that in general SVM types could predict accuracy better than other types of regression, and GPR types produce better DEM accuracy based on the experiment.

DEM as a representation of the earth's surface has many functions for spatial analysis. DEM can be produced from several kinds of techniques such as satellite technology stereo optical or radar technology. Problems when using the optical stereo data is at the high point density level that is not distributed evenly. In regions with homogeneous character, the height point is becoming sparse. This will affect to DEM accuracy. In order to solve the problem, performing fusion techniques using interpolation method cokriging involving data points ALOS PRISM and SRTM height point was conducted. The sparse height point derived from ALOS PRISM on some object is expected to be enhanced by using SRTM data. There were several aspects to enhance the accuracy of DEM-derived from this process: the character of topography, land cover types, density in height point of the data and the precise type of interpolation method used.