ESA CCI SM products have provided remotely-sensed surface soil moisture (SSM) content with the best spatial and temporal coverage thus far, although its output spatial resolution of 25 km is too coarse for many regional and local applications. The downscaling methodology presented in this paper improves ESA CCI SM spatial resolution to 1 km using two-step approach. The first step is used as a data engineering tool and its output is used as an input for the Random forest model in the second step. In addition to improvements in terms of spatial resolution, the approach also considers the problem of data gaps. The filling of these gaps is the initial step of the procedure, which in the end produces a continuous product in both temporal and spatial domains. The methodology uses combined active and passive ESA CCI SM products in addition to in situ soil moisture observations and the set of auxiliary downscaling predictors. The research tested several variants of Random forest models to determine the best combination of ESA CCI SM products. The conclusion is that synergic use of all ESA CCI SM products together with the auxiliary datasets in the downscaling procedure provides better results than using just one type of ESA CCI SM product alone. The methodology was applied for obtaining SSM maps for the area of California, USA during 2016. The accuracy of tested models was validated using five-fold cross-validation against in situ data and the best variation of model achieved RMSE, R² and MAE of 0.0518 m³/m³, 0.7312 and 0.0374 m³/m³, respectively. The methodology proved to be useful for generating high-resolution SSM products, although additional improvements are necessary.

Soil erosion is a global problem that negatively affects the quality of the environment, the availability of natural resources, as well as the safety of inhabitants. Soil erosion threatens the functioning of urban areas, which was the reason for choosing the territory of the Master Plan of Belgrade (Serbia) as the research area. The calculation of soil erosion loss was analyzed using the G2 erosion model. The model belongs to a group of empirical models and is based on the synthesis of the equation from the Revised Universal Soil Loss Equation (RUSLE) and the Erosion Potential Method (EPM). The estimation of soil degradation was analyzed in two time periods (2001 and 2019), which represent the time boundaries of the management of the Master Plan of Belgrade. The novel approach used in this research is based on using the land cover inventory as a dynamic indicator of the urbanization process. Land cover was identified using remote sensing, machine learning techniques, and the random forest algorithm applied to multispectral satellite images of the Landsat mission in combination with spectral indices. Climatic parameters were analyzed on the basis of data from meteorological stations (first scenario, i.e., 2001), as well as on simulations of changes based on climate scenario RCP8.5 (representative concentration pathways) concerning the current condition of the land cover (second scenario). A comparative analysis of the two time periods identified a slight reduction in total soil loss. For the first period, the average soil loss value is 4.11 t·ha⁻¹·y⁻¹. The analysis of the second period revealed an average value of 3.63 t·ha⁻¹·y⁻¹. However, the increase in non-porous surfaces has led to a change in the focus of soil degradation. Increased average soil loss as one of the catalysts of torrential flood frequencies registered on natural and semi-natural areas were 43.29% and 16.14%, respectively. These results are a significant contribution to the study of soil erosion in urban conditions under the impact of climate change.

The inventory of woody vegetation is of great importance for good forest management. Advancements of remote sensing techniques have provided excellent tools for such purposes, reducing the required amount of time and labor, yet with high accuracy and the information richness. Sentinel-2 is one of the relatively new satellite missions, whose 13 spectral bands and short revisit time proved to be very useful when it comes to forest monitoring. In this study, the novel spatio-temporal classification framework for mapping woody vegetation from Sentinel-2 multitemporal data has been proposed. The used framework is based on the probability random forest classification, where temporal information is explicitly defined in the model. Because of this, several predictions are made for each pixel of the study area, which allow for specific spatio-temporal aggregation to be performed. The proposed methodology has been successfully applied for mapping eight potential forest and shrubby vegetation types over the study area of Serbia. Several spatio-temporal aggregation approaches have been tested, divided into two main groups: pixel-based and neighborhood-based. The validation metrics show that determining the most common vegetation type classes in the neighborhood of 5 × 5 pixels provides the best results. The overall accuracy and kappa coefficient obtained from five-fold cross validation of the results are 82.97% and 0.75, respectively. The corresponding producer’s accuracies range from 36.74% to 97.99% and user’s accuracies range from 46.31% to 98.43%. The proposed methodology proved to be applicable for mapping woody vegetation in Serbia and shows a potential to be implemented in other areas as well. Further testing is necessary to confirm such assumptions.

Numerous semi- and fully-automatic algorithms have been developed for individual tree detection from airborne laser-scanning data, but different rates of falsely detected treetops also accompany their results. In this paper, we proposed an approach that includes a machine learning-based refinement step to reduce the number of falsely detected treetops. The approach involves the local maxima filtering and segmentation of the canopy height model to extract different segment-level features used for the classification of treetop candidates. The study was conducted in a mixed temperate forest, predominantly deciduous, with a complex topography and an area size of 0.6 km × 4 km. The classification model’s training was performed by five machine learning approaches: Random Forest (RF), Extreme Gradient Boosting, Artificial Neural Network, the Support Vector Machine, and Logistic Regression. The final classification model with optimal hyperparameters was adopted based on the best-performing classifier (RF). The overall accuracy (OA) and kappa coefficient (κ) obtained from the ten-fold cross validation for the training data were 90.4% and 0.808, respectively. The prediction of the test data resulted in an OA = 89.0% and a κ = 0.757. This indicates that the proposed method could be an adequate solution for the reduction of falsely detected treetops before tree crown segmentation, especially in deciduous forests.

Savremene geoprostorne tehnologije, poput fotogrametrije i laserskog skeniranja, omogućavaju brzo i precizno prikupljanje prostornih podataka o objektima visokogradnje. U radu je prikazana primena navedenih tehnika u cilju inspekcije, dokumentovanja i 3D modelovanja dela krovne konstrukcije zgrade Građevinskog fakulteta. Rad obuhvata prikupljanje prostornih podataka bespilotnom letelicom i terestričkim laserskim skenerom, obradu oblaka tačaka, generisanje 3D modela i analizu dobijenih rezultata. Posebna pažnja posvećena je prednostima fuzije fotogrametrijskih podataka i podataka terestričkog laserskog skeniranja (TLS) u cilju izrade digitalnog modela objekta. Rezultati pokazuju da kombinacija navedenih metoda omogućava dobijanje visokokvalitetnih prostornih informacija koje se mogu koristiti za potrebe inspekcije, kontinuiranog monitoringa, analize dobijene geometrije i poređenja sa projektovanom geometrijom, procene stanja konstrukcije, planiranja sanacionih aktivnosti i upravljanja objektima.