Informacja

Drogi użytkowniku, aplikacja do prawidłowego działania wymaga obsługi JavaScript. Proszę włącz obsługę JavaScript w Twojej przeglądarce.

English (EN)·Polski (PL)·Yкраїнський (UK)
Przejdź do strony domowej biblioteki Centralna Biblioteka Wojskowa Link otwiera się w nowym oknie Logo biblioteki Prolib Integro - strona głównaCentralna Biblioteka Wojskowa

Wyszukujesz frazę "landsat" wg kryterium: Temat

  Lista filtrów
Wyrównaj
    Wyświetlanie 1-9 z 9
    Tytuł:
    Geostatistical Methods as a Tool Supporting Revitalization of Industrially Degraded and Post-Mining Areas
    Autorzy:
    Zawadzki, Jarosław
    Fabijańczyk, Piotr
    Przeździecki, Karol
    Powiązania:
    https://bibliotekanauki.pl/articles/2064365.pdf
    Data publikacji:
    2020
    Wydawca:
    STE GROUP
    Tematy:
    geostatistics
    landsat
    post-mining areas
    post-industrial areas
    remote sensing
    revitalization
    soil pollution
    geostatystyka
    Landsat
    tereny pogórnicze
    tereny poprzemysłowe
    teledetekcja
    rewitalizacja
    zanieczyszczenie gleby
    Opis:
    Post-industrial and post-mining areas have often been under strong anthropogenic pressure for a long time. As a result, such areas, after the ending of industrial activity require taking steps to revitalize them. It may cover many elements of the natural or urban environment, such as water, soil, vegetated areas, urban development etc. To carry out revitalization, it is necessary to determine the initial state of such areas, often using selected chemical, geophysical or ecological. After that it is also important to properly monitor the state of such areas to assess the progress of the revitalization process. For this purpose a variety of change detection technics were developed. Post-industrial areas are very often characterized by a large extent, are difficult to access, have complicated land cover. For this reason, it is particularly important to choose appropriate methods to assess the degree of pollution of such areas. Such methods should be as economical as possible and time-effective. A very desirable feature of such methods is that they should allow a quick assessment of the entire area. Geostatistics supplemented by modern remote sensing can be effective for this purpose. Nowadays, using remote sensing, it is possible to gather information simultaneously from the entire, even vast area, with high spatial, spectral and temporal resolution. Geostatistics in turn provides many tools that are able to enable rapid analysis and inference based on even very complicated often scarce spatial data sets obtained from ground measurement and satellite observations. The goal of the article was to present selected results obtained using geostatistical methods also related to remote sensing, which may be helpful for decision makers in revitalizing post-industrial and post-mining areas. The results described in this paper were based mostly on the previous studies, carried out by authors.
    Źródło:
    New Trends in Production Engineering; 2020, 3, 1; 30--40
    2545-2843
    Pojawia się w:
    New Trends in Production Engineering
    Dostawca treści:
    Biblioteka Nauki
    Artykuł
    Tytuł:
    An Investigation of The Forests of Pernik Province (Western Bulgaria) by The Use of The Perpendicular Vegetation Index (PVI)
    Autorzy:
    Grigorov, Borislav
    Powiązania:
    https://bibliotekanauki.pl/articles/27314834.pdf
    Data publikacji:
    2022
    Wydawca:
    Uniwersytet Zielonogórski. Oficyna Wydawnicza
    Tematy:
    remote sensing
    biomass
    vegetation index
    Landsat
    teledetekcja
    biomasa
    wskaźnik roślinności
    Bułgaria zachodnia
    Opis:
    The current research represents a pilot study for application of the Perpendicular Vegetation Index (PVI) for an area with forests in Bulgaria. It is the first of its kind when it comes to forest studying in the country to the best knowledge of the author. When it comes to soil background Landsat images and other spectral data may be used for monitoring forest territories as well. The study area is Pernik Province which is located in the western parts of Bulgaria. The main aim is to investigate the PVI for the forests of Pernik Province. The index has been calculated by the application of Landsat 8 bands. The PVI has been processed for several months of different years. The main focus is both on the beginning and the end of the growing season when there are significant changes in leaf biomass. The results are promising and show typical vegetation features in the beginning of the growing season (April), a well-developed vegetation (July) and a steadily decreasing biomass in November.
    Źródło:
    Civil and Environmental Engineering Reports; 2022, 32, 4; 96--104
    2080-5187
    2450-8594
    Pojawia się w:
    Civil and Environmental Engineering Reports
    Dostawca treści:
    Biblioteka Nauki
    Artykuł
    Tytuł:
    Analysis of multitemporal changes in the environment using GIS and remote sensing in the aspect of construcion projects
    Autorzy:
    Głowienka, E.
    Hejmanowska, B.
    Michałowska, K.
    Pękala, A.
    Powiązania:
    https://bibliotekanauki.pl/articles/100692.pdf
    Data publikacji:
    2017
    Wydawca:
    Uniwersytet Rolniczy im. Hugona Kołłątaja w Krakowie
    Tematy:
    environmental protection
    Landsat
    remote sensing
    construction project
    ochrona środowiska
    teledetekcja
    projekt konstrukcyjny
    Opis:
    Modern changes of environment are the result of many factors, of which anthropogenic activities and the development of infrastructure play the leading role in environmental, morphometric changes. The dynamics of expansion of construction lands, which until recently have changed only as a result of natural factors, makes it invariably important to analyse time changes and forecast potential effects of construction projects on the environment. A good source of information about changes, for example the course of rivers, hydrological conditions, diversity of vegetation in the areas of investment, are cartographic sources, in particular GIS techniques, satellite images, and aerial photographs. Proper assessing of the territory using GIS techniques may allow constructing roads not only with less damage to the environment and human health, but also avoiding technical problems, such as low bearing capacity of soils. The main objective of the study is to evaluate multitemporal changes of the environment in the course of the ongoing construction project, which is the construction of the A4 motorway in its Rzeszów Wschód – Jarosław Zachód section, in the area of the Wierzbna junction. The analysis was carried out on the basis of Landsat satellite images recorded in two different investment periods of the tested object: in 2006 – prior to the start of construction works, in 2015 – in the course of the ongoing construction works. In addition, the analysis of the obtained Landsat multitemporal satellite images made it possible to examine the morphology of the substrate conditions of river valleys of the San, Wislok, and Mleczka.
    Źródło:
    Geomatics, Landmanagement and Landscape; 2017, 2; 61-69
    2300-1496
    Pojawia się w:
    Geomatics, Landmanagement and Landscape
    Dostawca treści:
    Biblioteka Nauki
    Artykuł
    Tytuł:
    Application of satellite remote sensing methods in mineral prospecting in Kosovo, area of Selac
    Wykorzystanie metod teledetekcji satelitarnej w poszukiwaniu złóż surowców mineralnych w rejonie Selac, Kosowo
    Autorzy:
    Lupa, Michał
    Adamek, Katarzyna
    Leśniak, Andrzej
    Pršek, Jaroslav
    Powiązania:
    https://bibliotekanauki.pl/articles/216678.pdf
    Data publikacji:
    2020
    Wydawca:
    Polska Akademia Nauk. Instytut Gospodarki Surowcami Mineralnymi i Energią PAN
    Tematy:
    remote sensing
    GIS
    geology
    mineral mapping
    Landsat 8
    teledetekcja
    geologia
    poszukiwania geologiczne
    surowce mineralne
    Opis:
    Traditional methods of mineral exploration are mainly based on very expensive drilling and seismic methods. The proposed approach assumes the preliminary recognition of prospecting areas using satellite remote sensing methods. Maps of mineral groups created using Landsat 8 images can narrow the search area, thereby reducing the costs of geological exploration during mineral prospecting. This study focuses on the identification of mineralized zones located in the southeastern part of Europe (Kosovo, area of Selac) where hydrothermal mineralization and alterations can be found. The article describes all the stages of research, from collecting in-situ rock samples, obtaining spectral characteristics with laboratory measurements, preprocessing and analysis of satellite images, to the validation of results through field reconnaissance in detail. The authors introduce a curve-index fitting technique to determine the degree of similarity of a rock sample to a given pixel of satellite imagery. A comparison of the reflectance of rock samples against surface reflectance obtained from satellite images allows the places where the related type of rock can be found to be determined. Finally, the results were compared with geological and mineral maps to confirm the effectiveness of the method. It was shown that the free multispectral data obtained by the Landsat 8 satellite, even with a resolution of 30 meters, can be considered as a valuable source of information that helps narrow down the exploration areas.
    Tradycyjne metody poszukiwania surowców mineralnych opierają się głównie na bardzo kosztownych metodach, takich jak wiercenia oraz metody sejsmiczne. Proponowane przez autorów podejście zakłada wstępne rozpoznanie obszarów perspektywicznych z wykorzystaniem metod teledetekcji satelitarnej. Mapy grup minerałów stworzone przy użyciu zobrazowań dostarczonych przez satelitę Landsat 8 mogą zawęzić obszar poszukiwań, a przez to doprowadzić do redukcji kosztów rozpoznania geologicznego podczas poszukiwania surowców mineralnych. Niniejsze badanie skupia się na identyfikacji stref zmineralizowanych znajdujących się w południowo-wschodniej Europie (Kosowo, rejon Selac) gdzie znajdują się mineralizacje hydrotermalne oraz strefy alteracji. Artykuł opisuje szczegółowo wszystkie etapy badań, od pozyskania próbek terenowych, badań laboratoryjnych mających na celu pozyskanie charakterystyk spektralnych, przez wstępne przetwarzanie oraz analizę zobrazowań satelitarnych do walidacji wyników poprzez rozpoznanie terenowe. Autorzy przedstawili technikę wykorzystującą wskaźnik dopasowania krzywej pozwalający na określenie stopnia podobieństwa próbki do piksela zobrazowania satelitarnego. Porównanie współczynnika odbicia dla próbek względem współczynnika odbicia zarejestrowanego przez satelitę pozwala na określenie miejsc, gdzie mogą występować określone typy skał. W celu określenia skuteczności metody wyniki zostały porównane z mapami geologicznymi. Wykazano, że darmowe dane multispektralne dostarczone przez satelitę Landsat 8, nawet z rozdzielczością 30 m, mogą stanowić cenne źródło informacji, które pozwala na zawężenie obszaru poszukiwań.
    Źródło:
    Gospodarka Surowcami Mineralnymi; 2020, 36, 1; 5-22
    0860-0953
    Pojawia się w:
    Gospodarka Surowcami Mineralnymi
    Dostawca treści:
    Biblioteka Nauki
    Artykuł
    Tytuł:
    Methodology for determining deforestation areas in Lviv region using remote sensing data
    Autorzy:
    Chetverikov, Borys
    Trevoho, Ihor
    Babiy, Lubov
    Malanchuk, Mariia
    Powiązania:
    https://bibliotekanauki.pl/articles/43852817.pdf
    Data publikacji:
    2022
    Wydawca:
    Polska Akademia Nauk. Czasopisma i Monografie PAN
    Tematy:
    teledetekcja
    monitoring satelitarny
    obraz satelitarny
    Landsat 8
    remote sensing
    space image
    satellite monitoring system
    Opis:
    The object of the study is the processing of space images on the territory of the Carpathian territory in the Lviv region, obtained from the Landsat-8 satellite. The work aims to determine the area of deforestation in the Carpathian territory of the Lviv region from different time-space images obtained from the Landsat-8 satellite. Methods of cartography, photogrammetry, aerospace remote sensing of the Earth and GIS technology were used in the experimental research. The work was performed in Erdas Imagine software using the unsupervised image classification module and the DeltaCue difference detection module. The results of the work are classified as three images of Landsat-8 on the territory of the Carpathian territory in the Lviv region. The areas of forest cover for each of them for the period of 2016-2018 have been determined. During the three years, the area of forests has decreased by 14 hectares. Our proposed workflow includes six stages: analysis of input data, band composition of space images on the research territory, implementation of unsupervised classification in Erdas Imagine software and selection of forest class and determination of implementing this workflow, the vector layers of the forest cover of the Carpathians in the Lviv region for 2016, 2017, 2018 were obtained, and on their basis, the corresponding areas were calculated and compared.
    Źródło:
    Advances in Geodesy and Geoinformation; 2022, 71, 1; art. no. e21, 2022
    2720-7242
    Pojawia się w:
    Advances in Geodesy and Geoinformation
    Dostawca treści:
    Biblioteka Nauki
    Artykuł
    Tytuł:
    Earth observation and geospatial techniques for soil salinity and land capability assessment over Sundarban Bay of Bengal Coast, India
    Autorzy:
    Das, S.
    Choudhury, M. R
    Nagarajan, M.
    Powiązania:
    https://bibliotekanauki.pl/articles/145537.pdf
    Data publikacji:
    2016
    Wydawca:
    Polska Akademia Nauk. Czytelnia Czasopism PAN
    Tematy:
    właściwości gleby
    teledetekcja
    dane satelitarne
    Landsat
    GIS and Remote Sensing
    kriging
    soil properties
    land capability
    Opis:
    To guarantee food security and job creation of small scale farmers to commercial farmers, unproductive farms in the South 24 PGS, West Bengal need land reform program to be restructured and evaluated for agricultural productivity. This study established a potential role of remote sensing and GIS for identification and mapping of salinity zone and spatial planning of agricultural land over the Basanti and Gosaba Islands(808.314sq. km) of South 24 PGS. District of West Bengal. The primary data i.e. soil pH, Electrical Conductivity (EC) and Sodium Absorption ratio (SAR) were obtained from soil samples of various GCP (Ground Control Points) locations collected at 50 mts. intervals by handheld GPS from 0–100 cm depths. The secondary information is acquired from the remotely sensed satellite data (LANDSAT ETM+) in different time scale and digital elevation model. The collected field samples were tested in the laboratory and were validated with Remote Sensing based digital indices analysisover the temporal satellite data to assess the potential changes due to over salinization. Soil physical properties such as texture, structure, depth and drainage condition is stored as attributes in a geographical soil database and linked with the soil map units. The thematic maps are integrated with climatic and terrain conditions of the area to produce land capability maps for paddy. Finally, The weighted overlay analysis was performed to assign theweights according to the importance of parameters taken into account for salineareaidentification and mapping to segregate higher, moderate, lower salinity zonesover the study area.
    Źródło:
    Geodesy and Cartography; 2016, 65, 2; 163-192
    2080-6736
    2300-2581
    Pojawia się w:
    Geodesy and Cartography
    Dostawca treści:
    Biblioteka Nauki
    Artykuł
    Tytuł:
    Przykład wykorzystania zobrazowań Landsat TM do oceny stanu zagrożenia pożarowego lasów
    A case study of using Landsat TM imagery to determine the risk of forest fire
    Autorzy:
    Walczykowski, P.
    Orych, A.
    Łysenko, J.
    Powiązania:
    https://bibliotekanauki.pl/articles/130430.pdf
    Data publikacji:
    2012
    Wydawca:
    Stowarzyszenie Geodetów Polskich
    Tematy:
    teledetekcja
    klęska żywiołowa
    pożar
    zobrazowania satelitarne
    Landsat 5
    remote sensing
    natural disaster
    fire
    satellite imagery
    Opis:
    Pożar lasu jest jedną z wielu klęsk żywiołowych, która może spowodować olbrzymie straty i zniszczenia na powierzchni ziemi. W przypadku zagrożenia pożarowego istotne jest szybkie działanie. W takich sytuacjach skuteczne są metody teledetekcyjne. Wykorzystanie technik satelitarnych stanowi użyteczny instrument wspomagający ocenę zagrożenia pożarowego lasów. W ramach pracy przeanalizowano stan zagrożenia pożarowego wybranego obszaru na podstawie zdjęć satelitarnych. Obszar badań objętych analizą obejmował teren niedaleko Kuźni Raciborskiej, znajdujący się w obrębie trzech nadleśnictw: Kędzierzyn, Rudy Raciborskie i Rudziniec. W pracy przedstawione zostały metody, przy pomocy których wykonano mapę zagrożenia pożarowego. W celu wykonania mapy zagrożenia pożarowego wykorzystane zostały metody umożliwiające określenie temperatury powierzchni Ziemi oraz operacje NDVI na zobrazowaniach satelitarnych zarejestrowanych przed pożarem. Wszystkie te analizy wykonano w celu wydzielenia i oceny określonych czynników mających wpływ na zagrożenie pożarowe. Badanie przestrzennego rozkładu poziomu temperatury powierzchni, poprzez określenie radiacyjnej temperatury roślinności, okazało się pomocne przy wyznaczaniu obszarów o różnym stopniu zagrożenia pożarowego. Jednak określenie tylko temperatury roślin nie wystarcza do oceny stresu roślin spowodowanym suszą. Z kolei badanie przestrzennego rozkładu poziomu wilgotności ściółki, poprzez określenie stopnia pokrycia roślinności za pomocą wskaźnika NDVI, przyniosło oczekiwany efekt wyróżnienia obszarów o zróżnicowanej podatności na pożar. Opisane metody oceny zagrożenia pożarowego pomagają w szybki sposób pozyskać informację o stanie obszaru lasu oraz przeprowadzić analizę jego zmian na zobrazowaniach. W wyniku obliczonych wskaźników NDVI oraz obliczenia temperatury radiacyjnej, uzyskano mapę zagrożenia pożarowego, która może okazać się przydatna w wielu opracowaniach mających szczególnie duże znaczenie dla ochrony przeciwpożarowej, jak również dla aktualizowania i stałego sprawdzania zagrożenia pożarowego w kompleksach leśnych. Określenie stopnia takiego zagrożenia z wykorzystaniem danych satelitarnych jest jednym z przedsięwzięć podejmowanych w celu zapobiegania powstawaniu pożarów.
    Forest fires are one of many natural disasters which can cause huge loses and damage to the environment. When dealing with such fires, a quick response is crucial. Remote sensing methods can be very helpful in such situations. Satellite images can be a useful tool in classifying the risk of forest fires occurring. In our research we set out to categorize the risk of forest fires of a chosen area based on satellite imagery. The area of interest was located close Kuźnia Raciborska, in the vicinity of the Kędzierzyn, Rudy Raciborskie and Rudziec forest inspectorates. During the research a number of methods, used to develop a risk map of forest fires, were presented. Two methods were used in order to generate risk maps of forest fires: determining the surface temperature and calculating the NDVI from satellite images from before the fires. These operations were conducted in order to incorporate different factors which have an impact on the potential risk of fire. Determining the spatial distribution of the surface temperature, by determining the radiation temperature of the vegetation was very useful in identifying different levels of fire hazard risk. However, using only this one parameter is not sufficient as it does not incorporate plan stress caused by very low humidity (drought). Determining the spatial distribution of the forest bed, by calculating the intensity of vegetation using the NDVI algorithm, allowed for a more precise conclusion of areas which are more or less at risk of forest fires. The described methods of determining the risk of forest fires can be helpful in rapidly acquiring information about the forest’s condition as well asenabling the possibility of analysing any changes which had occurred within the forest due to such natural disasters. As a result of calculating the NDVI and radiation temperature, it as possible to obtain a fire risk map which can be useful for many purposes such as fire risk management systems. Determining the level of fire risk using satellite data is one of the most efficient methods of preventing such natural disasters from occurring.
    Źródło:
    Archiwum Fotogrametrii, Kartografii i Teledetekcji; 2012, 24; 393-402
    2083-2214
    2391-9477
    Pojawia się w:
    Archiwum Fotogrametrii, Kartografii i Teledetekcji
    Dostawca treści:
    Biblioteka Nauki
    Artykuł
    Tytuł:
    Określanie lesistości Polesia Ukraińskiego na podstawie wyników klasyfikacji sezonowych obrazów kompozytowych Landsat 8 OLI
    Estimation of forest cover in Ukrainian Polissia using classification of seasonal composite Landsat 8 OLI images
    Autorzy:
    Lakyda, P.
    Myroniuk, V.
    Bilous, A.
    Boiko, S.
    Powiązania:
    https://bibliotekanauki.pl/articles/979663.pdf
    Data publikacji:
    2019
    Wydawca:
    Polskie Towarzystwo Leśne
    Tematy:
    lesnictwo
    Ukraina
    Polesie
    lesistosc
    teledetekcja
    zdjecia satelitarne
    satelita Landsat 8 OLI
    forest cover
    remote sensing
    random forest
    ikonos−2
    ndvi
    Opis:
    Training dataset for modelling of forest cover was created after classification of multispectral satel− lite imagery IKONOS−2 with spatial resolution 3.2 m (acquisition date – 12.08.2011). As a result, we created binary forest cover map with 2 categories: ‘forest’ and ‘not−forest’. That allowed us to compute the tree canopy cover for each pixel of Landsat 8 OLI, using vector grid with cell size of 30×30 m. Classification model was developed using training dataset that included 17,000 observations, 10,000 of them represented results of IKONOS−2 classification. Aiming to avoid errors of agricultural lands inclusion into forest mask because of lack of data, additionally we collected about 7000 random observations with canopy cover 0% that had been evenly distributed within unforested area. Random Forest (RF) model we developed allowed us to create continuous map of forests within study area that represents in each pixel value of tree canopy closeness (0−100%). To convert it into a discrete map, we recoded all values less than 30% as ‘no data’ and values from 30 to 100% as 1. Forest mask for two selected administrative districts of Chernihiv region (NE Ukraine) was created after screening map from small pixel groups that covered area less than 0.5 ha. Obtained results were compared with Global Forest Change (GFC) map and proved that GFC data can be used for forest mapping with tree canopy closeness threshold 40%. On considerable areas of abandoned agricultural lands in the analysed regions of Ukraine, forest stands are formed by Scots pine, silver birch, black alder and aspen. Existence of such forests substantially increases (on 6−8%) the forested area of Gorodnya and Snovsk districts of Chernihiv region – comparing to official forest inventory data. However, such stands are not protected and have high risks to be severed by wildfires, illegal cuttings with aim to renew the agricultural production, by diseases, insects and other natural disturbances.
    Źródło:
    Sylwan; 2019, 163, 09; 754-764
    0039-7660
    Pojawia się w:
    Sylwan
    Dostawca treści:
    Biblioteka Nauki
    Artykuł
    Tytuł:
    Znaczenie pola powierzchni i długości obiektów w półautomatycznej klasyfikacji obiektowej użytków zielonych na zdjęciach satelitów serii LANDSAT
    The influence of area and length of objects in semi-automated object classification of grasslands on LANDSAT images
    Autorzy:
    Kosiński, K.
    Powiązania:
    https://bibliotekanauki.pl/articles/132243.pdf
    Data publikacji:
    2009
    Wydawca:
    Polskie Towarzystwo Geograficzne
    Tematy:
    użytki zielone
    teledetekcja
    Landsat
    wielkość
    kształt
    uwilgotnienie
    siedlisko
    klasyfikacja
    sztuczne sieci neuronowe
    grasslands
    remote sensing
    size
    shape
    habitat
    humidity
    object
    classification
    artificial neural network
    Opis:
    Semi-automatic method for object classification of the grassland procedure involves two stages: 1) the creation of image segments as a representation of natural spatial complexes, 2) classification of the segments. So far, the classification algorithms were used refer to the three categories of characteristics: spectral, panchromatic or geometric. In the first stage of the work segmentation were performed of the composition of the two satellite images Landsat7 acquired at different seasons of the year: in September 1999 and the beginning of May 2001. Panchromatic data were used for distinguishing complexes due to the greater (in comparison with spectral data) spatial resolution. In the area of grasslands landscape-vegetation complexes (Matuszkiewicz, 1990, Kosiński, Hoffmann -Niedek, Zawiła, 2006) were distinguished of approximately a hundred to a few hundred meters in length and of about 20 ÷ 200 panchromatic image pixels. Semi-automated delimitation of complexes were carried out under the visual control, using as auxiliary material aerial photographs and topographic maps. In the second stage (classification of segments) an attempt were taken to assess the suitability of selected geometrical features to distinguish grasslands in use (currently or potentially) from grasslands unfit for production use due to excessive or insufficient moisture. The classification algorithm used GIS tools for measuring area and length of segments and artificial neural networks as a tool for classification. The previous studies of the Piotrkowska Plain show that the complexes of meadows used differ from those abandoned in terms of size and shape of objects (Kosiński, Hoffmann- Niedek, 2006, Fig. 1). Hypothesis that area and length of the landscape -vegetation complex are cues of identification in relation to the use and moisture of grasslands. 43 complexes of the grassland have been established as training samples on the Piotrkowska Plain in the Pilsia valley. In order to avoid overfitting classification algorithm to data from the Piotrkowska Plain, in order to allow the application of the algorithm for another mezoregionu 10 complexes have been selected as a validation set in the Szczercowska valley. To evaluate the classification results 32 complexes have been collected from Szczercowska Basin (test set). All treining set objects were described in terrein. Validation and test set objects were classified by a more accurate metod (based on biteporal image: Kosiński, Hoffmann -Niedek, 2008) and checked at random in the field. Objects of learning, validation and test set have been grouped into five categories according to use and habitat moisture (Kosiński, Hoffmann -Niedek, 2008; Table 1). For learning neural networks fife categories of objects of the learning and validation set were generalised into the three classes. In the Szczercowska Valley combination of characteristics (area and length) of the abandoned complexes is more close to the meadows in use than on the Piotrkowska Plain (Table 2). Therefore, the classification algorithm of the Piotrkowska Plain can not be directly applied to Szczercowska Basin. To obtain the correct result of classification, the classes of test set has been interpreted differently than in the learning and validation sets (Table 3, Figure 2). In the test sample 3/4 of the 23 complexes of meadows potentially used were classified correctly, while of nine abandoned ones due to unfavorable moisture habitats correctly classified 2/3. Thus confirmed the working hypothesis. Application of artificial neural networks can cancel the designation of non parametric empirical indicators of the size and shape of the complexes (Fig. 1). Neural networks auto-uwilgotmatically builds a morpfometric model based on simple indicators such as area and length of the object. Two model types of artificial neural network have been tested: 1) multilayer perceptrons (MLP) wich use hyperplanes to divide up feature space, 2) radial basis function network (RBF) wich use hyperspheres. MLP networks have proved to be more suitable to build the model than the RBF network.
    Źródło:
    Teledetekcja Środowiska; 2009, 42; 35-41
    1644-6380
    Pojawia się w:
    Teledetekcja Środowiska
    Dostawca treści:
    Biblioteka Nauki
    Artykuł
      Wyświetlanie 1-9 z 9

      Ta witryna wykorzystuje pliki cookies do przechowywania informacji na Twoim komputerze. Pliki cookies stosujemy w celu świadczenia usług na najwyższym poziomie, w tym w sposób dostosowany do indywidualnych potrzeb. Korzystanie z witryny bez zmiany ustawień dotyczących cookies oznacza, że będą one zamieszczane w Twoim komputerze. W każdym momencie możesz dokonać zmiany ustawień dotyczących cookies