The issue of population dataset reliability is of particular importance when it comes to broadening the understanding of spatial structure, pattern and configuration of humans’ geographical location. The aim of the paper was to estimate the reliability of LandScan based on the official Polish Population Grid. The adopted methodology was based on the change detection approach, spatial pattern and continuity analysis, as well as statistical analysis at the grid-cell level. Our results show that the LandScan data can estimate the Polish population very well. The number of grid cells with equal people counts in both datasets amounts to 10.5%. The most and highly reliable data cover 72% of the country territory, while less reliable ones cover only 4.3%. The LandScan algorithm tends to underestimate people counts, with a total value of 79,735 people (0.21%). The highest underestimation was noticed in densely populated areas as well as in the transition areas between urban and rural, while overestimation was observed in moderately populated regions, along main roads and in city centres. The underestimation results mainly from the spatial pattern and size of Polish rural settlements, namely a big number of shadowed single households dispersed over agricultural areas and in the vicinity of forests. An excessive assessment of the number of people may be a consequence of the well-known blooming effect.

Population data are generally provided by state census organisations at the predefi ned census enumeration units. However, these datasets very are often required at userdefi ned spatial units that differ from the census output levels. A number of population estimation techniques have been developed to address these problems. This article is one of those attempts aimed at improving county level population estimates by using spatial disaggregation models with support of buildings characteristic, derived from national topographic database, and average area of a fl at. The experimental gridded population surface was created for Opatów county, sparsely populated rural region located in Central Poland. The method relies on geolocation of population counts in buildings, taking into account the building volume and structural building type and then aggregation the people total in 1 km quadrilateral grid. The overall quality of population distribution surface expressed by the mean of RMSE equals 9 persons, and the MAE equals 0.01. We also discovered that nearly 20% of total county area is unpopulated and 80% of people lived on 33% of the county territory.

Population density is one of the key parameters for assessing the magnitude of population exposed to risk, and the better quality data we have, the better the assessment of risk. The aim of this study is to elaborate a high-resolution spatially distributed population density grid, which estimates population at the commune scale with a reliability of over 90%. The novelty of the approach is population density estimation in a regular European grid, based on buildings vector data collected in the national topographic database. Using abductive reasoning in combination with statistics and spatial analysis, the authors extract approximate information about a population from the large-scale topographic data. Moreover, linking the obtained population data with the cadastral databy unique building identifierallows for regular, quick and census surveyindependent updates of the population surface. A shortcoming of the approach is the issue of the possible existence of two houses per family, which leads to an overestimation of population. However, in the study area it affected only two of the total 14 communes by 7%-9%.

The article presents a two-stage model for estimating the value of residential property. The research is based on the application of a sequence of known methods in the process of developing property value maps. The market is divided into local submarkets using data mining, and, in particular, data clustering. This process takes into account only a property’s non-spatial (structural) attributes. This is the first stage of the model, which isolates local property markets where properties have similar structural attributes. To estimate the impact of the spatial factor (location) on property value, the second stage involves performing an interpolation for each cluster separately using ordinary kriging. In this stage, the model is based on Tobler’s first law of geography. The model results in property value maps, drawn up separately for each of the clusters. Experimental research carried out using the example of Siedlce, a city in eastern Poland, proves that the estimation error for a property’s value using the proposed method, evaluated using the mean absolute percentage error, does not exceed 10%. The model that has been developed is universal and can be used to estimate the value of land, property, and buildings.