- Kraków, Malopolskie, Poland
Research Interests:
Research Interests:
Mapa zmian pokrycia terenu małwpolski 1986-2011 wykonana w oparciu o klasyfikację obiektową obrazów satelitarnych Landsat oraz RapidEye;Mapa zmian pokrycia terenu małwpolski 1986-2011 wykonana w oparciu o klasyfikację obiektową obrazów satelitarnych Landsat oraz RapidEye;Map of land use / land co...more
Research Interests:
Research Interests:
Research Interests:
Research Interests:
The lichen Scots pine forests habitats are undergoing rapid disappearance across Europe. Due to the semi-natural character of this habitat and an increase of the nitrification as a result of air pollution, determination of factors... more
The lichen Scots pine forests habitats are undergoing rapid disappearance across Europe. Due to the semi-natural character of this habitat and an increase of the nitrification as a result of air pollution, determination of factors responsible for the decrease in lichen field layer cover requires a comprehensive approach. Our study aimed to investigate environmental factors necessary for the determination of active protection measures in order to maintain this vulnerable habitat. Specifically, we aimed to investigate: 1) the environmental factors influencing lichen cover in the lichen Scots pine forests of Bory Tucholskie National Park; 2) the differences in habitat variables between sites with lichen-rich and bryophyte-rich field layers. In our study, we used vegetation and microhabitat properties data collected over three years of surveys, as well as ALS LiDAR data. Our results indicated that lichen and bryophyte cover, tree height, tree cover, thickness of organic matter layer, soil temperature and soil water content differed between lichen-rich and bryophyte-rich sites. We found a significant negative relationship between lichen cover recorded within the field layer and tree height. The lichen-rich field layer developed better in areas with lower tree height and thinner layer of organic matter, which created a favorable habitat conditions for lichen development. Our research revealed the previously unknown impact of tree height for the development of lichen field layer. These findings can be used to plan the active conservation measures of lichen Scots pine forests.
Research Interests:
Research Interests:
Obserwowane w ostatnich latach globalne zmiany klimatu i towarzyszące mu ekstremalne zjawiska pogodowe (wysoka temperatura, susza atmosferyczna i glebowa, gwaltowne wiatry itp.) prowadzą bezpośrednio (np. wiatrowaly) lub pośrednio (np.... more
Obserwowane w ostatnich latach globalne zmiany klimatu i towarzyszące mu ekstremalne zjawiska pogodowe (wysoka temperatura, susza atmosferyczna i glebowa, gwaltowne wiatry itp.) prowadzą bezpośrednio (np. wiatrowaly) lub pośrednio (np. gradacje szkodliwych owadow) do dynamicznych przemian w drzewostanach, szczegolnie we wrazliwych ekosystemach gornoreglowego boru świerkowego. Celem prezentowanej pracy bylo opracowanie aktualnej cyfrowej mapy uzytkowania i pokrycia terenu (ang. Land Use Land Cover; LULC) obejmującego fragmenty: Doliny Kamienicy, masywu Kudlonia oraz Jaworzyny Kamienickiej w centralnej cześci Gorczanskiego Parku Narodowego (GPN), ze szczegolnym uwzglednieniem klas drzewostanow bedących w fazie zamierania lub juz zniszczonych. Pozyskane w procesie fotointerpretacji dane w postaci wektorow zasilic mialy bazy danych systemu GIS w GPN w celu wykonania analiz przestrzennych. W ramach prac kameralnych dokonano fotointerpretacji archiwalnych stereomodeli zdjec lotniczych CIR...
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Forest lichen communities develop on dry and poor in biogens sandy areas. The center of occurrence of this plant community in Europe coincides with Natura 2000 sites located in Poland, including the Bory Tucholskie National Park (BT NP ).... more
Forest lichen communities develop on dry and poor in biogens sandy areas. The center of occurrence of this plant community in Europe coincides with Natura 2000 sites located in Poland, including the Bory Tucholskie National Park (BT NP ). The aim of the study was to determine the spatial structure of selected Scots pine stands of BT NP , where a program of active protection of lichen communities was initiated. The research area included two forest compartments : 18 and 19. The analysis was performed in the following sub - compartments: 18c, 19d, 19g, 19h, 19i, 19j and 19 k. The research was carried out using airborne (ALS) and terrestrial (TLS) laser scanning (LiDAR). Thanks to the use of LiDAR technology, it was possible to make a very precise description of the structure of stands in 2D and 3D space. As a result of the conducted study , a number of stand parameters have been defined, such as: number of trees, tree density in the stand, number of live trees, average distance betwee...
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Due to the observed impacts of climate change on the natural environment, the demand for energy from renewable sources is growing, especially in the last decades. One of the possibilities in this respect is the use of forest biomass,... more
Due to the observed impacts of climate change on the natural environment, the demand for energy from renewable sources is growing, especially in the last decades. One of the possibilities in this respect is the use of forest biomass, especially that one which comes from logging residues. This type of wood raw material is obtained primarily in mature forests and during late thinnings. Estimation of the expected volume of logging residues from a particular cutting site is currently carried out in the State Forests, National Forest Holding with an accuracy oscillating at an acceptable level of ±40%. The purpose of this study was to estimate the share of logging residues in the total volume of the harvested biomass and to determine the difference and error between the estimated volume to be sold and actually harvested. The research was carried out at the 164 logging sites located in 10 forest districts of north−eastern part of Poland. The average volume of logging residues was 37.7 ±14....
Research Interests:
The aim of the research carried out in 2018 and financed by the Forest Fund was the analysis of biometric features and parameters of pine stands in the area of the “Bory Tucholskie” National Park (PNBT), where a program of active... more
The aim of the research carried out in 2018 and financed by the Forest Fund was the analysis of biometric features and parameters of pine stands in the area of the “Bory Tucholskie” National Park (PNBT), where a program of active protection of lichen was initiated in 2017. Environmental analyses were conducted in relation to selected biometric features of trees and stands using laser scanning (LiDAR), including ULS (Unmanned Laser Scanning; RIEGL VUX-1) and TLS (Terrestrial Laser Scanning; FARO FOCUS 3D; X130). Thanks to the application of LiDAR technology, the structure of pine stands was precisely determined by means of a series of descriptive statistics characterizing the 3D spatial structure of vegetation. Using the Trees Crown Model (CHM), the analysis of the volume of tree crowns and the volume of space under canopy was performed. For the analysed sub-compartments, GIS solar analyses were carried out for the solar energy reaching the canopy and the ground level due to active p...
Research Interests:
Research Interests:
Studies on society and the environment interface are often based on simple questionnaires that do not allow for an in-depth analysis. Research conducted with geo-questionnaires is an increasingly common method. However, even if data... more
Studies on society and the environment interface are often based on simple questionnaires that do not allow for an in-depth analysis. Research conducted with geo-questionnaires is an increasingly common method. However, even if data collected via a geo-questionnaire are available, the shared databases provide limited information due to personal data protection. In the article, we present open databases that overcome those limitations. They are the result of the iTre-es project concerning public opinion on the benefits provided by trees and shrubs in four different research areas. The databases provide information on the location of trees that are valuable to the residents, the distances from the respondents’ residence place, their attitude toward tree removal, socio-demographic variables, attachment to the place of life, and environmental attitudes. The presentation of all these aspects was possible thanks to the appropriate aggregation of the results. A method to anonymize the resp...
Research Interests:
This article features the airborne laser scanning (ALS) data applicability for classification and modelling of 3D objects in a landscape architecture related professions. In order to validate the practicality and efficiency of ALS,... more
This article features the airborne laser scanning (ALS) data applicability for classification and modelling of 3D objects in a landscape architecture related professions. In order to validate the practicality and efficiency of ALS, classification of selected objects of the Krakow Fortress has been carried out (defence objects from the time of Austro-Hungarian partition annexation period were the subject of this analysis). With ALS data this study identifies forms of fortifications, visualizes data and analyzes visibility to be the base of contemporary decisions and planning of landscape of the Krakow Fortress. 3D GIS analysis showed the high usefulness to identify fortification, visualize these objects and perform visibility analysis. In contrast to traditional methods (inventories and historical documentation), laser scanning data are the new generation of geospatial data. They offer an opportunity to develop a new, faster technology used for the needs of restoration, preservation ...
Research Interests:
Research Interests:
Research Interests:
Abstract In this paper we propose a methodology for combining remotely sensed data with field measurements to assess selected tree parameters (diameter at breast height (DBH) and tree species) required by the i-Tree Eco model to estimate... more
Abstract In this paper we propose a methodology for combining remotely sensed data with field measurements to assess selected tree parameters (diameter at breast height (DBH) and tree species) required by the i-Tree Eco model to estimate ecosystem services (ES) provided by urban trees. We determined values of ES provided by trees in 2017 in Raciborz (a city in South Poland) and estimated the loss of ES from January 1, 2017 to March 5, 2017, a period of changing legislation that temporarily allowed removal of trees on private property without any permission from city authorities. We applied Canopy Height Models (CHM; GSD 1.0 m) generated from two sets of ALS LiDAR point clouds (acquisitions on June 11, 2011 and March 5, 2017) and performed tree crown segmentations using the GEOBIA approach. Physical attributes were estimated for each tree using predictive models, developed based on field tree inventory . The reference areas for parameterizing the segmentation algorithm and assessing tree species composition were established in Raciborz, while reference data required for assessment of DBH were obtained from the MONIT-AIR project (from Municipality of Krakow). We found that in 2017, 988.79 ha of Raciborz (13.2 % of city area) was covered by the crowns of 264 471 trees, providing ES structural values worth over 384 mil €. The structural value of ES lost in the first months of 2017 (during which 5 075 trees were removed) was about 3.5 mil €. We concluded that in the face of information on tree crown cover that is often missing from city databases, tree inventories require application of a combination of multi-source and multi-resolution spatial analyses, including: administrative decisions for tree removal with exact location, predictive modelling of selected biometrical tree information, automatic crown segmentation on CHM and interpretation of regularly updated color infrared (CIR) aerial orthophotos.
Research Interests:
Reliable information concerning stand volume is fundamental to making strategic decisions in sustainable forest management. A variety of remotely sensed data and different inventory methods have been used for the estimation of forest... more
Reliable information concerning stand volume is fundamental to making strategic decisions in sustainable forest management. A variety of remotely sensed data and different inventory methods have been used for the estimation of forest biometric parameters. Particularly, airborne laser scanning (ALS) point clouds are widely used for the estimation of stand volume and forest biomass using an area-based approach (ABA) framework. This method relies on the reference measurements of field plots with the necessary prerequisite of a precise co-registration between ground reference plots and the corresponding ALS samples. In this research, the allometric area-based approach (AABA) is proposed in the context of stand volume estimation of Scots pine (Pinus sylvestris L.) stands. The proposed method does not require detailed information about the coordinates of the field plots. We applied Polish National Forest Inventory data from 9400 circular field plots (400 m2) to develop a plot level stand ...
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
In April 2013, the Laboratory of Geomatics launched the project under the acronym “Bartek 3D” in cooperation with the Research Section of Students from the AGH in Krakow, Pedagogical University and the Jagiellonian University as well. The... more
In April 2013, the Laboratory of Geomatics launched the project under the acronym “Bartek 3D” in cooperation with the Research Section of Students from the AGH in Krakow, Pedagogical University and the Jagiellonian University as well. The main aim of the project is to monitor the biggest and probably one of the oldest trees in Poland Oak Bartek in Zagnańsk (N 5059’14”; E 2038’59”), based on multi-temporal Terrestrial Laser Scanning (TLS) technology. One of the results of the project should be a 3D model of Oak Bartek and detection of the changes in the shape of the tree. Terrestrial Laser Scanning and the traditional forest inventory measurements were performed during the Leaf-OFF season in April 2013 and April 2014 and repeated in Leaf-ON period in July 2013 and October 2014 with using scanners: FARO FOCUS 3D, RIEGL VZ-400, LEICA C10 and RevScan (HandyScan). The results based on TLS technology showed some differences comparing to existing data obtained by traditional measurements f...
Research Interests:
In recent years the term "precise forestry" has been used more and more often, referring to a modern and sustainable model of forest management. Functioning of such management of wood biomass resources is based, among others, on... more
In recent years the term "precise forestry" has been used more and more often, referring to a modern and sustainable model of forest management. Functioning of such management of wood biomass resources is based, among others, on precisely defined and log-term monitored selected forest taxation parameters of single trees and whole forest stands based on modern geoinformation technologies, including Airborne Laser Scanning (ALS) and digital photogrammetry. The purpose of the work was the analysis of the usefulness of the CHM (Canopy Height Model) generated from the image-based point cloud or ALS technology to define the number of trees using the method of the segmentation of single Scots pine (Pinus sylvestris L.) crowns. The study was carried out in the Scots pine stands located in the Bory Tucholskie National Park (Poland). Due to the intentional lack of certain silviculture treatments, over the recent decades, these forest stands have been characterized by relatively high...
Research Interests:
Research Interests:
The study was performed on two former sulphur mines located in Southeast Poland: Jeziórko, where 216.5 ha of afforested area was reclaimed after borehole exploitation and Machów, where 871.7 ha of dump area was reclaimed after open cast... more
The study was performed on two former sulphur mines located in Southeast Poland: Jeziórko, where 216.5 ha of afforested area was reclaimed after borehole exploitation and Machów, where 871.7 ha of dump area was reclaimed after open cast strip mining. The areas were characterized by its terrain structure and vegetation cover resulting from the reclamation process. The types of reclamation applied in these areas were forestry in Jeziórko and agroforestry in the Machów post-sulphur mine. The study investigates the possibility of applying the most recent Sentinel-2 (ESA) satellite imageries for land cover mapping, with a primary focus on detecting and monitoring afforested areas. Airborne laser scanning point clouds were used to derive precise information about the spatial (3D) characteristics of vegetation: the height (95th percentile), std. dev. of relative height, and canopy cover. The results of the study show an increase in afforested areas in the former sulphur mines. For the enti...
Research Interests:
Research Interests:
Land Use and Land Cover (LULC) maps play an important role in an environmental modelling, and for many years efforts have been made to improve and streamline the expensive mapping process. The aim of the study was to create LULC maps of... more
Land Use and Land Cover (LULC) maps play an important role in an environmental modelling, and for many years efforts have been made to improve and streamline the expensive mapping process. The aim of the study was to create LULC maps of three selected water catchment areas in South Poland using a Geographic Object-Based Image Analysis (GEOBIA) in order to highlight the advantages of this innovative, semi-automatic method of image analysis. the classification workflow included: multi-stage and multi-scale analyses based on a data fusion approach. Input data consisted mainly of BlackBridge (RapidEye) high resolution satellite imagery, although for distinguishing particular LULC classes, additional satellite images (LANDSAT TM5) and GIS-vector data were used. Accuracy assessment of GEOBIA classification results varied from 0.83 to 0.87 (kappa), depending on the specific catchment area. The main recognized advantages of GEOBIA in the case study were: performing of multi-stage and multi-...
Research Interests:
The aim of this study was to investigate the possible use of geoinformatics tools and generally available geodata for mapping land cover/use on the reclaimed areas. The choice of subject was dictated by the growing number of such areas... more
The aim of this study was to investigate the possible use of geoinformatics tools and generally available geodata for mapping land cover/use on the reclaimed areas. The choice of subject was dictated by the growing number of such areas and the related problem of their restoration. Modern technology, including GIS, photogrammetry and remote sensing are relevant in assessing the reclamation effects and monitoring of changes taking place on such sites. The LULC classes mapping, supported with thorough knowledge of the operator, is useful tool for the proper reclamation process evaluation.The study was performed for two post-mine sites: reclaimed external spoil heap of the sulfur mine Machów and areas after exploitation of sulfur mine Jeziórko, which are located in the Tarnobrzeski district. The research materials consisted of aerial orthophotos, which were the basis of on-screen vectorization; LANDSAT satellite images, which were used in the pixel and object based classification; and t...
Research Interests:
The purpose of this study was to determine the spatial structure of vegetation on the repository of the mine “Fryderyk” in Tarnowskie Góry. Tested area was located in the Upper Silesian Industrial Region (a large industrial region in... more
The purpose of this study was to determine the spatial structure of vegetation on the repository of the mine “Fryderyk” in Tarnowskie Góry. Tested area was located in the Upper Silesian Industrial Region (a large industrial region in Poland). It was a unique refuge habitat – Natura2000; PLH240008. The main aspect of this elaboration was to investigate the possible use of geotechniques and generally available geodata for mapping LULC changes and determining the spatial structure of vegetation. The presented study focuses on the analysis of a spatial structure of vegetation in the research area. This exploration was based on aerial images and orthophotomaps from 1947, 1998, 2003, 2009, 2011 and airborne laser scanning data (2011, ISOK project). Forest succession changes which occurred between 1947 and 2011 were analysed. The selected features of vegetation overgrowing spoil heap “Fryderyk” was determined. The results demonstrated a gradual succession of greenery on soil heap. In 1947,...
Research Interests:
The quarrying industry is changing the local landscape, forming deep open pits and spoil heaps in close proximity to them, especially lignite mines. The impact can include toxic soil material (low pH, heavy metals, oxidations etc.) which... more
The quarrying industry is changing the local landscape, forming deep open pits and spoil heaps in close proximity to them, especially lignite mines. The impact can include toxic soil material (low pH, heavy metals, oxidations etc.) which is the basis for further reclamation and afforestation. Forests that stand on spoil heaps have very different growth conditions because of the relief (slope, aspect, wind and rainfall shadows, supply of solar energy, etc.) and type of soil that is deposited. Airborne laser scanning (ALS) technology deliver point clouds (XYZ) and derivatives as raster height models (DTM, DSM, nDSM=CHM) which allow the reception of selected 2D and 3D forest parameters (e.g. height, base of the crown, cover, density, volume, biomass, etc). The automation of ALS point cloud processing and integrating the results into GIS helps forest managers to take appropriate decisions on silvicultural treatments in areas with failed plantations (toxic soil, droughts on south-facing ...
Research Interests:
Rapid urbanization is causing changes in green spaces and ecological connectivity. So far, urban ecosystem research has mainly focused on using landscape metrics (LM) in two-dimensional (2D) space. Our study proposes three-dimensional... more
Rapid urbanization is causing changes in green spaces and ecological connectivity. So far, urban ecosystem research has mainly focused on using landscape metrics (LM) in two-dimensional (2D) space. Our study proposes three-dimensional (3D) measures of urban forests (UF) and LM calculations using LiDAR technology. First, we estimated the UF volume of Krakow (Poland) and the distribution of vegetation (low, medium, high) using a voxel-based GEOBIA approach based on the ALS LiDAR point cloud, satellite imagery, and aerial orthophotos at specific timestamps: 2006, 2012, 2017. Then, the appropriate landscape metrics were selected (NP, AREA_MN, CONTIG_MN, LPI, PARA_MN, SPLIT, MESH, PD, DIVISION, LSI) to quantify the differences between the 2D- and 3D-derived vegetation structures and detect changes in the urban landscape. The results showed that areas with low vegetation decreased due to the expansion of built-up areas, while areas with medium and high vegetation increased in Krakow betwe...
Research Interests:
To convince new users of the advantages of the Sentinel_2 sensor, a simplification of classic remote sensing tools allows to create a platform of communication among domain specialists of agricultural analysis, visual image interpreters... more
To convince new users of the advantages of the Sentinel_2 sensor, a simplification of classic remote sensing tools allows to create a platform of communication among domain specialists of agricultural analysis, visual image interpreters and remote sensing programmers. An index value, known in the remote sensing user domain as “Zabud” was selected to represent, in color, the essentials of a time series analysis. The color index used in a color atlas offers a working platform for an agricultural field control. This creates a database of test and training areas that enables rapid anomaly detection in the agricultural domain. The use cases and simplifications now function as an introduction to Sentinel_2 based remote sensing, in an area that before relies on VHR imagery and aerial data, to serve mainly the visual interpretation. The database extension with detected anomalies allows developers of open source software to design solutions for further agricultural control with remote sensing.
Research Interests:
Trees growing on private property have become an essential part of urban green policies. In many places, restrictions are imposed on tree removal on private property. However, monitoring compliance of these regulations appears difficult... more
Trees growing on private property have become an essential part of urban green policies. In many places, restrictions are imposed on tree removal on private property. However, monitoring compliance of these regulations appears difficult due to a lack of reference data and public administration capacity. We assessed the impact of the temporary suspension of mandatory permits on tree removal, which was in force in 2017 in Poland, on the change in urban tree cover (UTC) in the case of the municipality of Racibórz. The bi-temporal airborne laser scanning (ALS) point clouds (2011 and 2017) and administrative records on tree removal permits were used for analyzing the changes of UTC in the period of 2011–2017. The results show increased tree removal at a time when the mandatory permit was suspended. Moreover, it appeared that most trees on private properties were removed without obtaining permission when it was obligatory. The method based on LiDAR we proposed allows for monitoring green ...
Research Interests:
Research Interests:
Zespół boru chrobotkowego (Cladonio-Pinetum) jest zbiorowiskiem wykształcającym się na suchych i ubogich w biogeny obszarach piaszczystych. Najlepiej zachowane płaty tego zbiorowiska roślinnego w Europie występują w Polsce północnej, w... more
Zespół boru chrobotkowego (Cladonio-Pinetum) jest zbiorowiskiem wykształcającym się na suchych i ubogich w biogeny obszarach piaszczystych. Najlepiej zachowane płaty tego zbiorowiska roślinnego w Europie występują w Polsce północnej, w tym na terenie Parku Narodowego "Bory Tucholskie" (PNBT). Celem badań było określenie struktury przestrzennej wybranych drzewostanów sosnowych PNBT, w których zainicjowany został program ochronny czynnej borów chrobotkowych. Obszar badań obejmował część dwóch oddziałów leśnych PNBT z wydzieleniami: 18c, 19d, 19g, 19h, 19i, 19j i 19k. Badania przeprowadzono z wykorzystaniem lotniczego (ALS) i naziemnego (TLS) skanowania laserowego (LiDAR). Dzięki zastosowaniu technologii LiDAR możliwe było wykonanie bardzo precyzyjnego opisu struktury drzewostanów w przestrzeni 2D i 3D. W wyniku przeprowadzonych analiz określono szereg cech taksacyjnych i parametrów drzewostanów, takich jak: liczba i zagęszczenie drzew w drzewostanie, średnia odległość pomiędzy drzewami żywymi, liczba drzew martwych, pierśnicowe pole przekroju drzew żywych, zwarcie poziome koron, wskaźnik penetracji koron, wysokość górna drzew w wydzieleniu, wysokość podstawy korony drzewa, długość korony drzewa, objętość warstwy koron, powierzchnia 2D i 3D koron drzew, średni promień korony, współczynnik morfometryczny koron oraz zasięg pionowy martwych gałęzi. Opracowano także mapę występowania luk w wydzieleniach o powierzchni większej niż 2 m2. Badania rozpoczęte w 2017 roku są kontynuowane w 2018 roku z wykorzystaniem skanowania z platformy BSP (UAS) oraz TLS, które posłużą precyzyjnej ocenie zmian struktury przestrzennej drzewostanów, w których przeprowadzono cięcia prześwietleniowe.
Research Interests:
Exploiting of the nanostructure arrays as a promising candidate for excitation of neural cells has been analyzed. Based on the importance of the coupling effect between electrode and neuron, a multiphyscis modeling approach has been... more
Exploiting of the nanostructure arrays as a promising candidate for excitation of neural cells has been analyzed. Based on the importance of the coupling effect between electrode and neuron, a multiphyscis modeling approach has been proposed. The model incorporates theoretically both structural effects (size, geometry) and electrophysiological effects. The system of equations for proposed model has been solved numerically using Finite Element Method for Poisson equation and Finite Difference Method for Cable equation. In this regards we have combined the system of equations in COMSOL platform with Matlab interface accordingly. We have analyzed the effect of excitation of neuron with an extra source of voltage pulse to evoke the action potential. We have performed the simulation for two different cases, an array of nanoelectrode and single microelectrode structure. The results of analysis indicate that nanostructure arrays are of enhanced properties in inducing the displacement curre...
Research Interests:
Forest growing stock volume (GSV) is an important parameter in the context of forest resource management. National Forest Inventories (NFIs) are routinely used to estimate forest parameters, including GSV, for national or international... more
Forest growing stock volume (GSV) is an important parameter in the context of forest resource management. National Forest Inventories (NFIs) are routinely used to estimate forest parameters, including GSV, for national or international reporting. Remotely sensed data are increasingly used as a source of auxiliary information for NFI data to improve the spatial precision of forest parameter estimates. In this study, we combine data from the NFI in Poland with satellite images of Landsat 7 and 3D point clouds collected with airborne laser scanning (ALS) technology to develop predictive models of GSV. We applied an area-based approach using 13,323 sample plots measured within the second cycle of the NFI in Poland (2010–2014) with poor positional accuracy from several to 15 m. Four different predictive approaches were evaluated: multiple linear regression, k-Nearest Neighbours, Random Forest and Deep Learning fully connected neural network. For each of these predictive methods, three se...