Your email was sent successfully. Check your inbox.

An error occurred while sending the email. Please try again.

Proceed reservation?

Export
  • 1
    In: Journal of Cleaner Production, Elsevier BV, Vol. 112 ( 2016-01), p. 3820-3829
    Type of Medium: Online Resource
    ISSN: 0959-6526
    Language: English
    Publisher: Elsevier BV
    Publication Date: 2016
    detail.hit.zdb_id: 1179393-4
    detail.hit.zdb_id: 2029338-0
    Library Location Call Number Volume/Issue/Year Availability
    BibTip Others were also interested in ...
  • 2
    In: Remote Sensing, MDPI AG, Vol. 14, No. 14 ( 2022-07-06), p. 3251-
    Abstract: The intensive development of both interferometric technology and sensors in recent years allows Interferometric Synthetic Aperture Radar (InSAR)-based applications to be accessible to a growing number of users. InSAR-based services now cover entire countries and soon even the whole of Europe. These InSAR systems require massive amounts of computer processing power and significant time to generate a final product. Most, if not all, of these projects have a limited “monitoring component”, aimed at historical analysis but are rarely, if ever, updated. Consequently, the results do not necessarily meet every purpose or specific user requirement. It is now clear that the increasing computing capacity and big data provided by the sensors have initiated the development of new InSAR services. However, these systems are only useful when linked to specific real-world operational problems. Continuous monitoring of a country’s ageing water management infrastructure has become an increasingly critical issue in recent years, in addition to the threats posed by climate change. Our article provides a comprehensive overview of a nationwide, dedicated, operational InSAR application, which was developed to support the operational work of the Hungarian Disaster Management Service (HDMS). The objective was to provide monthly monitoring of 63 water facilities, including 83 individual objects, distributed throughout Hungary, in combination with the development of a near real-time warning system. Our work involved the compilation of a completely new InSAR System as a Service (SaaS) which incorporates user requirements, preparatory work, the compilation of the Sentinel-1 automatic processing pipeline, the installation of corner reflectors, a special early warning system, and a dedicated user interface. The developed system can automatically start to evaluate the S1 measurements within 24 h of downloading the data into the system storage forward the results toward the warning system before the next image arrives. Users are provided with detailed information on the stability of 70% of the 83 water facility objects monitored through the dedicated user interface. The additional early warning system currently operates as a preliminary “spatial decision support system”, but the HDMS is willing to make it fully operational over the next few years.
    Type of Medium: Online Resource
    ISSN: 2072-4292
    Language: English
    Publisher: MDPI AG
    Publication Date: 2022
    detail.hit.zdb_id: 2513863-7
    Library Location Call Number Volume/Issue/Year Availability
    BibTip Others were also interested in ...
  • 3
    In: Remote Sensing, MDPI AG, Vol. 12, No. 21 ( 2020-11-07), p. 3652-
    Abstract: Floodplains are valuable scenes of water management and nature conservation. A better understanding of their geomorphological characteristic helps to understand the main processes involved. We performed a classification of floodplain forms in a naturally developed area in Hungary using a Digital Terrain Model (DTM) of aerial laser scanning. We derived 60 geomorphometric variables from the DTM and prepared a geomorphological map of 265 forms (crevasse channels, point bars, swales, levees). Random Forest classification was conducted with Recursive Feature Elimination (RFE) on the objects (mean pixel values by forms) and on the pixels of the variables. We also evaluated the classification probabilities (CP), the spatial uncertainties (SU), and the overfitting in the function of the number of the variables. We found that the object-based method had a better performance (95%) than the pixel-based method (78%). RFE helped to identify the most important 13–20 variables, maintaining the high model performance and reducing the overfitting. However, CP and SU were not efficient measures of classification accuracy as they were not in accordance with the class level accuracy metric. Our results help to understand classification results and the specific limits of laser scanned DTMs. This methodology can be useful in geomorphologic mapping.
    Type of Medium: Online Resource
    ISSN: 2072-4292
    Language: English
    Publisher: MDPI AG
    Publication Date: 2020
    detail.hit.zdb_id: 2513863-7
    Library Location Call Number Volume/Issue/Year Availability
    BibTip Others were also interested in ...
  • 4
    In: Remote Sensing in Ecology and Conservation, Wiley
    Abstract: Species composition of forests is a very important component from the point of view of nature conservation and forestry. We aimed to identify 10 tree species in a hilly forest stand using a hyperspectral aerial image with a particular focus on two invasive species, namely Ailanthus tree and black locust. Deep learning‐based training data augmentation (TDA) and post‐classification techniques were tested with Random Forest and Support Vector Machine (SVM) classifiers. SVM had better performance with 81.6% overall accuracy (OA). TDA increased the OA to 82.5% and post‐classification with segmentation improved the total accuracy to 86.2%. The class‐level performance was more convincing: the invasive Ailanthus trees were identified with 40% higher producer's and user's accuracies (PA and UA) to 70% related to the common technique (using a training dataset and classifying the trees). The PA and UA did not change in the case of the other invasive species, black locust. Accordingly, this new method identifies well Ailanthus, a sparsely distributed species in the area; while it was less efficient with black locust that dominates larger patches in the stand. The combination of the two ancillary steps of hyperspectral image classification proved to be reasonable and can support forest management planning and nature conservation in the future.
    Type of Medium: Online Resource
    ISSN: 2056-3485 , 2056-3485
    Language: English
    Publisher: Wiley
    Publication Date: 2023
    detail.hit.zdb_id: 2825232-9
    Library Location Call Number Volume/Issue/Year Availability
    BibTip Others were also interested in ...
  • 5
    Online Resource
    Online Resource
    University of Debrecen/ Debreceni Egyetem ; 2004
    In:  Acta Agraria Debreceniensis , No. 13 ( 2004-05-04), p. 123-126
    In: Acta Agraria Debreceniensis, University of Debrecen/ Debreceni Egyetem, , No. 13 ( 2004-05-04), p. 123-126
    Abstract: Hyper and multispectral imaging systems are widely used in agricultural and environmental protection. Remote sensing techniques are suitable for evaluating environmental protection hazarsd, as well as for agriculture resource exploration. In our research we compared aerial hyper and multispectral images, as well as multispectral digital camera images with the background data from the test site. Hyperspectral records were obtained using a new 80-channeled aerial spectrometer (Digital Airborne Imaging Spectrometer /DAIS 7915/. We have chosen two farms where intensive crop cultivation takes place, as test sites, so soil degradation and spreading of weeds can be intensive as a result of land use and irrigation. We took additional images of air and ground with a TETRACAM ADC wide band multispectral camera, which can sense blue, green and near infrared bands. We had detailed GIS database about the test site. Weed and vegetation map of the area in the spring and the summer was made in 2002. For soil salt content analysis, we gathered detailed data frome an 80x100 m area. When analyzing the images, we evaluated image reliability, and the connection between the bands and the soil type, pH and salt content, and weed mapping. In the case of hyperspectral images, our aim was to choose and analyze the appropriate band combinations. With a TETRACAM ADC camera, we made images at different times, and we calculated canopy, NDVI and SAVI indexes. Using the background data mentioned above, the aim of our study was to develop a spectral library, which can be used to analyze the environmental effects of agricultural land use.
    Type of Medium: Online Resource
    ISSN: 2416-1640 , 1587-1282
    Language: Unknown
    Publisher: University of Debrecen/ Debreceni Egyetem
    Publication Date: 2004
    Library Location Call Number Volume/Issue/Year Availability
    BibTip Others were also interested in ...
  • 6
    Online Resource
    Online Resource
    American Chemical Society (ACS) ; 2011
    In:  The Journal of Physical Chemistry A Vol. 115, No. 36 ( 2011-09-15), p. 10154-10158
    In: The Journal of Physical Chemistry A, American Chemical Society (ACS), Vol. 115, No. 36 ( 2011-09-15), p. 10154-10158
    Type of Medium: Online Resource
    ISSN: 1089-5639 , 1520-5215
    RVK:
    Language: English
    Publisher: American Chemical Society (ACS)
    Publication Date: 2011
    detail.hit.zdb_id: 2006031-2
    detail.hit.zdb_id: 1357795-5
    Library Location Call Number Volume/Issue/Year Availability
    BibTip Others were also interested in ...
  • 7
    Online Resource
    Online Resource
    Magyar Agrar- es Elettudomanyi Egyetem ; 2016
    In:  Tájökológiai Lapok Vol. 14, No. 1 ( 2016-07-13), p. 1-12
    In: Tájökológiai Lapok, Magyar Agrar- es Elettudomanyi Egyetem, Vol. 14, No. 1 ( 2016-07-13), p. 1-12
    Abstract: Munkánk során egy szikes táj vegetációtípusainak osztályozását végeztük el, légi hiperspektrális adatok felhasználásával. A munka célja a hiperspektrális adatok alkalmazhatóságának vizsgálata volt e komplex társulásoknál, eltérő képosztályozási módszerek alkalmazásával. Vizsgálatunkban hagyományos osztályozó eljárások (Maximum Likelihood Classifier – MLC, Random Forest – RF és Support Vector Machine – SVM) eredményességét teszteltük 10 és 30 pixeles tanítóterületek felhasználásával. A mozaikolt hiperspektrális felvételen a zajszűrés és az információnyerés céljából MNF transzformációt alkalmaztunk. A légi hiperspektrális felvétel AISA EAGLE II szenzorral készült 1m terepi felbontásban. Társulástani besorolás és felszínborítás alapján összesen 20 vegetációosztályt alakítottunk ki. Az osztályokat további négy főbb élőhelykategóriába soroltuk: sztyeppék, nyílt szikes gyepek, szikes rétek, szikes és nem szikes mocsarak. Az SVM és az RF osztályozó eljárások, a pixelek számától függetlenül, majdnem minden vegetációosztálynál megbízhatóan működtek, nagy osztályozási pontosságot adtak. Az MLC bár nagy mintaszámnál nagy pontosságú osztályozást eredményezett, kis mintaszámnál számos osztály esetében alacsony megbízhatósággal működött. Az eredmények alapján elmondható, hogy a komplex fátlan táji környezetben a vegetáció osztályozásra az SVM megfelelő osztályozó lehet, mivel nagyobb pontosságot nyújt, mint az RF és az MLC. Az SVM bizonyult a legkevésbé érzékenynek a tanító területek mintáinak méretére, így alkalmas lehet azokban az esetekben, amikor néhány osztálynál az elérhető pixelek száma korlátozottan áll rendelkezésre.
    Type of Medium: Online Resource
    ISSN: 1589-4673
    Language: Unknown
    Publisher: Magyar Agrar- es Elettudomanyi Egyetem
    Publication Date: 2016
    Library Location Call Number Volume/Issue/Year Availability
    BibTip Others were also interested in ...
  • 8
    Online Resource
    Online Resource
    Springer Science and Business Media LLC ; 2022
    In:  Scientific Reports Vol. 12, No. 1 ( 2022-12-03)
    In: Scientific Reports, Springer Science and Business Media LLC, Vol. 12, No. 1 ( 2022-12-03)
    Abstract: Tree species’ composition of forests is essential in forest management and nature conservation. We aimed to identify the tree species structure of a floodplain forest area using a hyperspectral image. We proposed an efficient novel strategy including the testing of three dimension reduction (DR) methods: Principal Component Analysis, Minimum Noise Fraction (MNF) and Indipendent Component Analysis with five machine learning (ML) algorithms (Maximum Likelihood Classifier, Support Vector Classification, Support Vector Machine, Random Forest and Artificial Neural Network) to find the most accurate outcome; altogether 300 models were calculated. Post-classification was applied by combining the multiresolution segmentation and filtering. MNF was the most efficient DR technique, and at least 7 components were needed to gain an overall accuracy (OA) of  〉  75%. Forty-five models had  〉  80% OAs; MNF was 43, and the Maximum Likelihood was 19 times among these models. Best classification belonged to MNF with 10 components and Maximum Likelihood classifier with the OA of 83.3%. Post-classification increased the OA to 86.1%. We quantified the differences among the possible DR and ML methods, and found that even  〉  10% worse model can be found using popular standard procedures related to the best results. Our workflow calls the attention of careful model selection to gain accurate maps.
    Type of Medium: Online Resource
    ISSN: 2045-2322
    Language: English
    Publisher: Springer Science and Business Media LLC
    Publication Date: 2022
    detail.hit.zdb_id: 2615211-3
    Library Location Call Number Volume/Issue/Year Availability
    BibTip Others were also interested in ...
  • 9
    Online Resource
    Online Resource
    University of Debrecen/ Debreceni Egyetem ; 2004
    In:  Acta Agraria Debreceniensis , No. 13 ( 2004-05-04), p. 161-165
    In: Acta Agraria Debreceniensis, University of Debrecen/ Debreceni Egyetem, , No. 13 ( 2004-05-04), p. 161-165
    Abstract: Our department is involved in ongoing research into the hydrological and ecological interplay of the Berettyó River.In the first part of our study we classified the Hungarian section of the river from ecological and hydrological standpoints. We determined three typical parts of the river: a sandy and gravely bottom, a middle part with a sandy and muddy bottom, and a lower part, with muddy bottom. In theese sampling areas we measured and established the more important static and dynamic hydrological, physical and chemical characteristics.For the planned research we did a primary estimation of the environmental condition of theese sampling areas, on the basis of applicable biological and ecological indication methods.
    Type of Medium: Online Resource
    ISSN: 2416-1640 , 1587-1282
    Language: Unknown
    Publisher: University of Debrecen/ Debreceni Egyetem
    Publication Date: 2004
    Library Location Call Number Volume/Issue/Year Availability
    BibTip Others were also interested in ...
  • 10
    Online Resource
    Online Resource
    Springer Science and Business Media LLC ; 2007
    In:  Cereal Research Communications Vol. 35, No. 2 ( 2007-06), p. 805-808
    In: Cereal Research Communications, Springer Science and Business Media LLC, Vol. 35, No. 2 ( 2007-06), p. 805-808
    Type of Medium: Online Resource
    ISSN: 0133-3720 , 1788-9170
    Language: English
    Publisher: Springer Science and Business Media LLC
    Publication Date: 2007
    detail.hit.zdb_id: 2296169-0
    Library Location Call Number Volume/Issue/Year Availability
    BibTip Others were also interested in ...
Close ⊗
This website uses cookies and the analysis tool Matomo. Further information can be found on the KOBV privacy pages