<?xml version="1.0" encoding="utf-8"?>
<export-example>
  <doc>
    <id>665</id>
    <completedYear>2022</completedYear>
    <publishedYear/>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>57</pageFirst>
    <pageLast>62</pageLast>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume/>
    <type>conferenceobject</type>
    <publisherName>Gesellschaft für Informatik e.V.</publisherName>
    <publisherPlace>Bonn</publisherPlace>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>1</belongsToBibliography>
    <completedDate>--</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Indicator plant species detection in grassland using EfficientDet object detector</title>
    <abstract language="eng">Extensively used grasslands (meadows and pastures) are ecologically valuable areas in the agricultural landscape and part of the multifunctional agriculture. In Germany, the quality of these grasslands is assessed based on the occurrence of certain plant species known as indicator or character species, with indicators being defined at regional level. Therefore, the recognition of these indicators on a spatial level is a prerequisite for monitoring grassland biodiversity. The identification of indicator species for the status quo of grassland using traditional methods was found to be challenging and tedious. Deep learning-algorithms applied to high-resolution UAV imagery could be the key solution, where UAV with remote sensors can map a large area of grassland in comparison to manual or ground mapping methods and deep learning-algorithms can automate the detection process. In this research work, we use an EfficientDet based algorithm to train an object detection model capable of recognizing indicators on RGB data. The experimental results show that this approach is very promising in contrast to the difficult and time-consuming manual recognition methods. The model was trained with the momentum-SGD optimizer with a momentum value of 0.9 and a learning rate of 0.0001. The model was trained and tested on 1200 images and achieves 45.7 AP (and 85.7 AP50) on test data set. The dataset includes images of four distinct indicator plant species: Armeria maritima, Campanula patula, Cirsium oleraceum, and Daucus carota</abstract>
    <parentTitle language="deu">42. GIL-Jahrestagung, Künstliche Intelligenz in der Agrar- und Ernährungswirtschaft</parentTitle>
    <identifier type="urn">urn:nbn:de:kobv:eb1-opus-6656</identifier>
    <identifier type="isbn">978-3-88579-711-1</identifier>
    <identifier type="issn">1617-5468</identifier>
    <enrichment key="opus.doi.autoCreate">false</enrichment>
    <enrichment key="opus.urn.autoCreate">false</enrichment>
    <licence>Urheberrechtsschutz</licence>
    <author>Deepak Hanike Basavegowda</author>
    <author>Paul Mosebach</author>
    <author>Inga Schleip</author>
    <author>Cornelia Weltzien</author>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>digital agriculture; biodiversity in grassland; HNV farming; deep learning; object detection</value>
    </subject>
    <collection role="institutes" number="">Fachbereich Landschaftsnutzung und Naturschutz</collection>
    <collection role="Hochschulbibliographie" number=""/>
    <collection role="Hochschulbibliographie" number="">Zweitveröffentlichung</collection>
    <collection role="Hochschulbibliographie" number="">Referiert</collection>
    <thesisPublisher>Hochschule für nachhaltige Entwicklung Eberswalde</thesisPublisher>
    <file>https://opus4.kobv.de/opus4-hnee/files/665/GIL2022_Basavegowda_57-62.pdf</file>
  </doc>
  <doc>
    <id>882</id>
    <completedYear>2024</completedYear>
    <publishedYear/>
    <thesisYearAccepted/>
    <language>deu</language>
    <pageFirst/>
    <pageLast/>
    <pageNumber>65</pageNumber>
    <edition/>
    <issue/>
    <volume/>
    <type>report</type>
    <publisherName/>
    <publisherPlace/>
    <creatingCorporation>Ministerium für Landwirtschaft, Umwelt und Klimaschutz des Landes Brandenburg (MLUK)</creatingCorporation>
    <contributingCorporation/>
    <belongsToBibliography>1</belongsToBibliography>
    <completedDate>2024-10-08</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="deu">Biodiversitätsfördernde Maßnahmen und Bewirtschaftungstechnik für eine standortgerechte Niedermoornutzung</title>
    <abstract language="deu">Standortgerechte Nutzung von Niedermooren bedeutet, sie so zu bewirtschaften, dass sie langfristig ohne weitere Qualitätseinbußen eine an den Lebensraum angepasste Pflanzendecke tragen, die eine stabile Biomasseproduktion liefert. Für Moorstandorte ist eine standortgerechte Nutzung nur unter nassen Verhältnissen gegeben. &#13;
Jedoch greift jede Form der Bewirtschaftung in den Lebensraum von Tier- und Pflanzenarten ein. Um möglichen negativen Wirkungen vorzubeugen, sollten deshalb nasse und sehr feuchte Bewirtschaftungsverfahren von Beginn an naturschutzfachlich flankiert, kontrolliert und gegebenenfalls angepasst werden. Im Teil 1 dieser Broschüre wird ein Katalog mit naturschutzfachlichen Maßnahmen für Bewirtschaftungsverfahren auf Niedermoor unterschiedlicher Feuchtestufen vorgestellt.&#13;
Die landwirtschaftliche Nutzung nasser und sehr feuchter Moorflächen ist nur mit daran angepasster Landtechnik oder Spezialmaschinen möglich. Im Teil 2 der Broschüre werden daher Empfehlungen zum Technikeinsatz in der moorschonenden Grünlandbewirtschaftung gegeben.</abstract>
    <identifier type="doi">10.57741/opus4-882</identifier>
    <enrichment key="opus.source">publish</enrichment>
    <enrichment key="opus.doi.autoCreate">true</enrichment>
    <enrichment key="opus.urn.autoCreate">false</enrichment>
    <licence>Creative Commons - CC BY - Namensnennung 4.0 International</licence>
    <author>Paul Mosebach</author>
    <author>Friedrich Birr</author>
    <author>Franz Wenzl</author>
    <author>Inga Schleip</author>
    <author>Vera Luthardt</author>
    <subject>
      <language>deu</language>
      <type>uncontrolled</type>
      <value>Niedermoor</value>
    </subject>
    <subject>
      <language>deu</language>
      <type>uncontrolled</type>
      <value>Moorgrünland</value>
    </subject>
    <subject>
      <language>deu</language>
      <type>uncontrolled</type>
      <value>Paludikultur</value>
    </subject>
    <subject>
      <language>deu</language>
      <type>uncontrolled</type>
      <value>Moortechnik</value>
    </subject>
    <subject>
      <language>deu</language>
      <type>uncontrolled</type>
      <value>Biodiversität</value>
    </subject>
    <subject>
      <language>deu</language>
      <type>swd</type>
      <value>Moor</value>
    </subject>
    <collection role="ddc" number="630">Landwirtschaft und verwandte Bereiche</collection>
    <collection role="open_access" number="">open_access</collection>
    <collection role="institutes" number="">Fachbereich Landschaftsnutzung und Naturschutz</collection>
    <collection role="Hochschulbibliographie" number=""/>
    <thesisPublisher>Hochschule für nachhaltige Entwicklung Eberswalde</thesisPublisher>
    <file>https://opus4.kobv.de/opus4-hnee/files/882/2024_Standortgerechte_Niedermoornutzung_MLUK-3.pdf</file>
  </doc>
  <doc>
    <id>968</id>
    <completedYear/>
    <publishedYear/>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>37</pageFirst>
    <pageLast>49</pageLast>
    <pageNumber/>
    <edition/>
    <issue>1</issue>
    <volume>93</volume>
    <type>article</type>
    <publisherName>Springer International Publishing</publisherName>
    <publisherPlace>Cham</publisherPlace>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>1</belongsToBibliography>
    <completedDate>--</completedDate>
    <publishedDate>2025-03-01</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Assessing the Effect of Field Disturbances On Biomass Estimation in Grasslands Using UAV-Derived Canopy Height Models</title>
    <abstract language="eng">Abstract&#13;
                Accurate estimation of biomass in grasslands is essential for understanding ecosystem health and productivity. Unmanned Aerial Vehicles (UAVs) have emerged as valuable tools for biomass estimation using canopy height models derived from high-resolution imagery. However, the impact of field disturbances, such as lodging and molehills, on the accuracy of biomass estimation using UAV-derived canopy height models remains underexplored. This study aimed to assess the relationship between UAV-derived canopy height and both reference canopy height measurements and dry biomass, accounting for different management systems and disturbance scenarios. UAV data were collected using a multispectral camera, and ground-based measurements were obtained for validation. The results revealed that UAV-derived canopy height models remained accurate in estimating vegetation height, even in the presence of disturbances. However, the relationship between UAV-derived canopy height and dry biomass was affected by disturbances, leading to overestimation or underestimation of biomass depending on disturbance type and severity. The impact of disturbances on biomass estimation varied across cutting systems. These findings highlight the potential of UAV-derived canopy height models for estimating vegetation structure, but also underscore the need for caution in relying solely on these models for accurate biomass estimation in heterogeneous grasslands. Future research should explore strategies to enhance biomass estimation accuracy by integrating additional data sources and accounting for field disturbances.</abstract>
    <parentTitle language="eng">PFG – Journal of Photogrammetry, Remote Sensing and Geoinformation Science</parentTitle>
    <identifier type="issn">2512-2789</identifier>
    <identifier type="issn">2512-2819</identifier>
    <identifier type="doi">10.1007/s41064-024-00322-x</identifier>
    <identifier type="urn">urn:nbn:de:kobv:eb1-opus-9685</identifier>
    <enrichment key="opus.import.date">2025-02-18T01:55:27+00:00</enrichment>
    <enrichment key="opus.source">sword</enrichment>
    <enrichment key="opus.import.user">deep</enrichment>
    <enrichment key="opus.import.file">attachment; filename=deposit.zip</enrichment>
    <enrichment key="opus.import.checksum">96f5666ec9253b16b8ce93d9b83a6bdd</enrichment>
    <enrichment key="opus.doi.autoCreate">false</enrichment>
    <enrichment key="opus.urn.autoCreate">true</enrichment>
    <licence>Creative Commons - CC BY - Namensnennung 4.0 International</licence>
    <author>Clara Oliva Gonçalves Bazzo</author>
    <author>Bahareh Kamali</author>
    <author>Dominik Behrend</author>
    <author>Hubert Hueging</author>
    <author>Inga Schleip</author>
    <author>Paul Mosebach</author>
    <author>Axel Behrendt</author>
    <author>Thomas Gaiser</author>
    <subject>
      <language>eng</language>
      <type>swd</type>
      <value>-</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Vegetation structure</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Monitoring</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Ecosystem services</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Remote sensing</value>
    </subject>
    <collection role="open_access" number="">open_access</collection>
    <collection role="Import" number="import">Import</collection>
    <file>https://opus4.kobv.de/opus4-hnee/files/968/41064_2024_Article_322.pdf</file>
  </doc>
</export-example>
