Milutin M. Pejović

Milutin M. Pejović

Auto-generated profile, based on publicly available information

Milutin M. Pejović

Department for Geodesy and Geoinformatics, Faculty of Civil Engineering, University of Belgrade, Belgrade, Serbia

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 January 2023 in Tehnika
Verified
Journal Article
Open access
PDF file
PVPetko R. Vranić
Petko R. Vranić
JPJovan M. Popović
Jovan M. Popović
MPMilutin M. Pejović
Milutin M. Pejović
BMBranko Đ. Milovanović
Branko Đ. Milovanović
AMAnastasija B. Martinenko
Anastasija B. Martinenko
In the new hall of the Institute for Materials and Structures, there was a need to control the geometry of the existing crane rails. In this paper, the methodology for determining the geometry of such a complex structure is presented, and the results of the applied method are also presented. The final product, i.e. the examined geometry of crane rails included numerical and graphical analysis of straightness, analysis of parallelism and analysis of horizontality of crane rails.

1 January 2023 in Tehnika
Verified
Journal Article
Open access
PDF file
VBVladan B. Bošković
Vladan B. Bošković
MPMilutin M. Pejović
Milutin M. Pejović
BBBranko S. Božić
Branko S. Božić
ZGZagorka I. Gospavić
Zagorka I. Gospavić
The topic of the paper deals with the analysis of the stability of the geodetic 2D network of the "Lipovica" dam using the Karlsruhe method of deformation analysis. In the first part of the paper, in a concise manner, a general classification of deformation models that are used in the realization of geodetic observation is given. A separate chapter is dedicated to the description of the Karlsruhe method itself, its algorithm and the method of application. The effectiveness of the method was separately discussed on the practical example of the geodetic 2D network of the "Lipovica" dam, whose control ephe data were simulated. This analysis determined the agreement between the simulated displacement values and the values detected by the Karlsruhe method, with all input data necessary for repeating the procedure available in the work.

1 January 2023 in Tehnika
Verified
Journal Article
Open access
PDF file
VBVladan B. Bošković
Vladan B. Bošković
MPMilutin M. Pejović
Milutin M. Pejović
BMBranko Đ. Milovanović
Branko Đ. Milovanović
The topic of the paper refers to the application of Pelcer's deformation analysis procedure for the purpose of determining the deformations of the control network points of the Lipovica dam. The purpose of geodetic surveying of engineering structures such as high dams, in a concise manner, is given in a separate chapter. For this reason, the paper describes the basic theory of Pelzer's method of determining deformations, the algorithm and the method of application. In addition to the actual method of determining the displacement, the paper also describes the theory related to the minimum value of the magnitude of the displacement, which can be "certainly" determined using geodetic methods.

1 January 2023 in Tehnika
Verified
Journal Article
Open access
PDF file
VBVladan B. Bošković
Vladan B. Bošković
MPMilutin M. Pejović
Milutin M. Pejović
The subject of the paper is the description and application of robust methods of deformation analysis for the purposes of determining the stability of the GNSS control network of the "Mandići" landslide. The paper provides a concise description of the mathematical model of robust methods as well as the procedure for robust evaluation of displacement vectors. A robust estimation of the displacement vectors in the work was performed on the simulated data using L1, L1-L2 , Lp and the Danish objective function. At the end of the paper, the results of the mentioned functions were summarized and compared with the simulated values.

17 August 2026 in Environmental Monitoring and Assessment
Verified
Journal Article
Open access
PDF file
MPMilutin Pejović
Milutin Pejović
MKMilan Kilibarda
Milan Kilibarda
DPDragutin Protić
Dragutin Protić
BBBranislav Bajat
Branislav Bajat
This study evaluates an innovative field-scale targeted sampling strategy within a regional hybrid spatial prediction model that combines machine learning and geostatistics. The framework is designed so that newly collected field observations are incorporated only through the local residual kriging step, while the regional Random Forest trend model remains unchanged, allowing field-scale predictions to be refined without full model refitting. The proposed sampling approach integrates a Normalized Difference Vegetation Index (NDVI)-based Productivity Index, a field-specific index derived from long-term satellite-based NDVI time series, with regional model-derived prediction uncertainty. The approach was evaluated on 28 test agricultural fields containing 7 to 19 in-field soil organic carbon (SOC) observations, which allowed assessment across diverse sampling configurations and levels of within-field variability. The results showed that the regional model alone provided a reasonable baseline prediction (mean root mean square error (RMSE) = 0.24% SOC) but was unable to adequately represent local spatial heterogeneity. Incorporating all available field observations produced the highest accuracy (mean RMSE = 0.17% SOC), while the proposed targeted sampling strategy achieved comparable performance (mean RMSE = 0.18% SOC) using only four strategically selected samples. In contrast, the results also showed that seemingly representative random sampling can lead to poor predictions when informative locations are missed, in some cases performing even worse than the regional model alone. In addition to conventional accuracy metrics, minimum detectable change (MDC) was used to evaluate the capability of the framework to detect meaningful SOC changes beyond prediction error, relevant for SOC monitoring and carbon farming. The results demonstrate that integrating regional models with productivity-based targeted sampling can substantially improve field-scale SOC prediction while avoiding the risks of misleading assessments associated with unfavorable sampling configurations.