Branislav Bajat

Spatio-temporal interpolation of daily temperatures for global land areas at 1 km resolution

Combined Global Surface Summary of Day and European Climate Assessment and Dataset daily meteorological data sets (around 9000 stations) were used to build spatio-temporal geostatistical models and predict daily air temperature at ground resolution of 1km for the global land mass. Predictions in space and time were made for the mean, maximum, and minimum temperatures using spatio-temporal regression-kriging with a time series of Moderate Resolution Imaging Spectroradiometer (MODIS) 8 day images, topographic layers (digital elevation model and topographic wetness index), and a geometric temperature trend as covariates. The accuracy of predicting daily temperatures was assessed using leave-one-out cross validation. To account for geographical point clustering of station data and get a more representative cross-validation accuracy, predicted values were aggregated to blocks of land of size 500x500km. Results show that the average accuracy for predicting mean, maximum, and minimum daily temperatures is root-mean-square error (RMSE) =2 degrees C for areas densely covered with stations and between 2 degrees C and 4 degrees C for areas with lower station density. The lowest prediction accuracy was observed at high altitudes (>1000m) and in Antarctica with an RMSE around 6 degrees C. The model and predictions were built for the year 2011 only, but the same methodology could be extended for the whole range of the MODIS land surface temperature images (2001 to today), i.e., to produce global archives of daily temperatures (a next-generation repository) and to feed various global environmental models. Key Points Global spatio-temporal regression-kriging daily temperature interpolation Fitting of global spatio-temporal models for the mean, maximum, and minimum temperatures Time series of MODIS 8 day images as explanatory variables in regression part

Mapping average annual precipitation in Serbia (1961–1990) by using regression kriging

The appearence of geostatistics and geographical information systems has made it possible to analyze complex spatial patterns of meteorological elements over large areas in the applied climatology. The objective of this study is to use geostatistics to characterize the spatial structure and map the spatial variation of average values of precipitation for a 30-year period in Serbia. New, recently introduced, geostatistical algorithms facilitate utilization of auxiliary variables especially remote sensing data or freely available global datasets. The data from Advanced Spaceborn Thermal Emission and Reflection Radiometer global digital elevation model are incorporated as ancillary variables into spatial prediction of average annual precipitation using geostatistical method known as regression kriging. The R2 value of 0.842 proves high performance result of the prediction of the proposed method.

Spatial analysis of the temperature trends in Serbia during the period 1961–2010

The spatial analysis of annual and seasonal temperature trends in Serbia during the period 1961–2010 was carried out using mean monthly data from 64 meteorological stations. Change year detection was achieved using cumulative sum charts. The magnitude of trends was derived from the slopes of linear trends using the least square method. The same formalism of least square method was used to assess the statistical significance of the determined trends. Maps of temperature trends were generated by applying a spatial regression method to visualize the detected tendencies. The obtained results indicate a negative temperature trend for the period before the change year except for winter and a more pronounced positive trend after the change year. Besides being more pronounced, the vast majority of trends after the change year were also clearly statistically significant. Our estimate of the average temperature trend over Serbia is in agreement with those obtained at the global and European scale. Calculated global autocorrelation statistics (Moran’s I) indicate an apparent random spatial pattern of temperature trends across the Serbia for both periods before and after the change year.

Landslide Susceptibility Assessment with Machine Learning Algorithms

Case study addresses NW slopes of Fruška GoraMountain, Serbia. Landslide activity is quite notorious in this region, especially along the Danube’s right river bank, and recently intensified seismicity coupled with atmospheric precipitation might be critical for triggering new landslide occurrences. Hence, it is not a moment too soon for serious landslide susceptibility assessment in this region. State-of-the-art approaches had been taken into consideration, cutting down to the Support Vector Machine (SVM) and k-Nearest Neighbor (k-NN) algorithms, trained upon expert based model of landslide susceptibility (a multi-criteria analysis). The latter involved Analytical Hierarchy Process (AHP) for weighting influences of different input parameters. These included elevation, slope angle, aspect, distance from flows, vegetation cover, lithology, and rainfall, to represent the natural factors of the slope stability. Processed in a GIS environment (as discrete or float raster layers) trough AHP, those parameters yielded susceptibility pattern, classified by the entropy model into four classes. Subsequently the susceptibility pattern has been featured as training set in SVM and k-NN algorithms. Detailed fitting involved several cases, among which SVM with Gaussian kernel over geo-dataset (coordinates and input parameters) reached the highest accuracy (88%)outperforming other considered cases by far.

Geological Units Classification of Multispectral Images by Using Support Vector Machines

Quantitative techniques for spatial prediction and classification in geological survey are developing rapidly. The recent applications of machine learning techniques confirm possibilities of their application in this field of research. The paper introduces Support Vector Machines, a method derived from recent achievements in the statistical learning theory, in classification of geological units based on the source of the Landsat multispectral images. The initial experiments suggest the usefulness of the proposed classification approach.

Mapping population change index in Southern Serbia (1961-2027) as a function of environmental factors

Niche analysis methods developed within the biogeography community are routinely used for species distribution modeling of wildlife and endangered species. So far, such techniques have not been used to explain distribution of people in an area, nor to assess spatio-temporal dynamics of human populations. In this paper, the MaxEnt approach to species distribution modeling and publicly available gridded predictors were used to analyze the population dynamics in Southern Serbia (South Pomoravlje Region) for the period 1961-2027. Population values from the census administrative units were first downscaled to 200 m grid using a detailed map of populated places and dasymetric interpolation. In the second step, a point pattern representing the whole population (468,500 inhabitants in 2002) was simulated using the R package spatstat. MaxEnt was then used to derive habitat suitability index (HSI) as a function of gridded predictors: distance to roads, elevation, slope, topographic wetness index, enhanced vegetation index and land cover classes. HSI and environmental predictors were further used to explain spatial patterns in the population change index (PCI) through regression modeling. The results show that inhabiting preference for year 1961 is mainly a function of topography (TWI, elevation). The HSI for year 2027 shows that large portions of remote areas are becoming less preferred for inhabiting. The results of cross-validation in MaxEnt show that distribution of population is distinctly controlled by environmental factors (AUC > 0.84). Population decrease is particularly significant in areas >25 km distant from the main road network. The results of regression analysis show that 40% of variability in the PCI values can be explained with these environmental maps, distance to roads and urban areas being the main drivers of migration process. This approach allows precise mapping of demographic patterns that otherwise would not be visible from the census data alone.

Modeling Urban Land Use Changes Using Support Vector Machines

Support Vector Machines (SVM) is a machine learning (ML) algorithm commonly applied to the classification of remotely sensing data and more recently for modeling land use changes. However, in most geospatial applications the current literature does not elaborate on specifications of the SVM method with respect to data sampling, attribute selection and optimal parameters choices. Therefore the main objective of this study is to present and investigate the SVM technique for modeling urban land use change. The SVM model building procedure is presented together with the detailed evaluation of the output results with respect to the choice of datasets, attributes and the change of SVM parameters. Geospatial datasets containing nine land use classes and spatial attributes for the Municipality of Zemun, Republic of Serbia were used for years 2001, 2003, 2007 and 2011. The Correlation-based Feature Subset method, kappa coefficient, Area Under Receiver Operating Characteristic Curve (AUC) and kappa simulation were used to perform the model evaluation and compare the model outputs with the real land use datasets. The obtained results indicate that the SVM-based models perform better when implementing balanced data sampling, reduced data sets to informative subsets of attributes and properly identify the optimal learning parameters.

Estimating the Performance of Random Forest versus Multiple Regression for Predicting Prices of the Apartments

The goal of this study is to analyse the predictive performance of the random forest machine learning technique in comparison to commonly used hedonic models based on multiple regression for the prediction of apartment prices. A data set that includes 7407 records of apartment transactions referring to real estate sales from 2008–2013 in the city of Ljubljana, the capital of Slovenia, was used in order to test and compare the predictive performances of both models. Apparent challenges faced during modelling included (1) the non-linear nature of the prediction assignment task; (2) input data being based on transactions occurring over a period of great price changes in Ljubljana whereby a 28% decline was noted in six consecutive testing years; and (3) the complex urban form of the case study area. Available explanatory variables, organised as a Geographic Information Systems (GIS) ready dataset, including the structural and age characteristics of the apartments as well as environmental and neighbourhood information were considered in the modelling procedure. All performance measures (R2 values, sales ratios, mean average percentage error (MAPE), coefficient of dispersion (COD)) revealed significantly better results for predictions obtained by the random forest method, which confirms the prospective of this machine learning technique on apartment price prediction.

Dasymetric Mapping of Population Distribution in Serbia Based on Soil Sealing Degrees Layer

This paper outlines a methodology used to disaggregate a census population in order to more accurately determine the population distribution over a regional area or a state scale. Data regarding population distributions are usually accessible at the level of individual census designation places and are usually mapped as aggregated polygons by the choropleth method with the assumption of a homogeneous distribution of population within a cartographic unit. In contrast, dasymetric mapping provides a more reliable view into the allocation of inhabitants, which can be of significant importance when estimating population distributions. Coupling this methodology with the GIS environment and a free open access database of soil sealing facilitates the acquisition of population surface models for human and urban geography applications.

Machine Learning and Landslide Assessment in a GIS Environment

This chapter introduces theoretical and practical aspects for applying GIS and geocomputation methods in landslide assessment problems. Machine Learning techniques in combination with GIS are proven useful for computation and building of complex non-linear spatial models, which is why they have been chosen in our work. Modeling principles that include basic Machine Learning techniques (Artificial Neural Networks, Decision trees, Support Vector Machines) and additional useful procedures are described to show how they can be applied to address a complex problem such as landslide assessment. Two types of models are proposed in the work herein that are useful for describing landslide susceptibility and landslide prediction. The region of Halenkovice in Czech Republic is presented as a case study to illustrate and bring closer the practical aspects of landslide assessment. These aspects consider data preparation and preprocessing, scale effects, model optimization, and evaluation. The results show that Support Vector Machines and similar Machine Learning (ML) techniques can be successfully applied to address the zoning of landslide susceptibility, which might be an important breakthrough for potential applications in regional planning and decision-making.