{"id":{"repo_id":"vilnius","oai_identifier":"oai:vu.lt:elaba:308333925"},"canonical_url":"https://search.ndltd.org/etd/vilnius/oai:vu.lt:elaba:308333925","repository":{"repo_id":"vilnius","name":"Vilnius University","base_url":"https://epublications.vu.lt/oai"},"display":{"title":"Sosnovskio barščio židinių identifikavimas ir erdvinė analizė Vilniaus mieste taikant mašininio mokymosi metodus /","abstract":"Sosnowsky’s hogweed (Heracleum sosnowskyi) is one of the most dangerous invasive species, spread across the entire territory of Lithuania. The monitoring and removal of this plant are essential since the plant puts human health and biodiversity in danger. Unfortunately, this process is time consuming and demands large amounts of human resources. Therefore, these days the aim is to find effective and innovative ways to ease these processes. The aim of this thesis was to identify the spread of the invasive plant and perform an analysis using hyperspectral data consisting of 430 spectral bands and a machine learning algorithm in the territory of Vilnius. During the study, a Random Forest classifier, with an accuracy of 95%, was created. The model identified 2 682 possible Sosnowsky’s hogweed areas, which covered approximately 5.33 ha of territory. During spatial analysis, it was determined that the spread of these plants was mainly associated with non-built-up areas of land, as well as 30-meter zones around road networks, which can be considered as potential dispersal corridors. River networks and built-up area analysis showed a smaller part of the identified plant territory, therefore, we can conclude that these are not the main causes of the spread of the invasive plants. Hot spot analysis showed that the Pilaitė district is the most problematic area of this study due to the largest concentration of Sosnowsky’s hogweed. Study results show that the developed machine learning algorithm is a promising approach for future studies for the monitoring of Sosnowsky’s hogweed, especially if the training sample is improved.","abstract_html":"Sosnowsky’s hogweed (Heracleum sosnowskyi) is one of the most dangerous invasive species, spread across the entire territory of Lithuania. The monitoring and removal of this plant are essential since the plant puts human health and biodiversity in danger. Unfortunately, this process is time consuming and demands large amounts of human resources. Therefore, these days the aim is to find effective and innovative ways to ease these processes. The aim of this thesis was to identify the spread of the invasive plant and perform an analysis using hyperspectral data consisting of 430 spectral bands and a machine learning algorithm in the territory of Vilnius. During the study, a Random Forest classifier, with an accuracy of 95%, was created. The model identified 2 682 possible Sosnowsky’s hogweed areas, which covered approximately 5.33 ha of territory. During spatial analysis, it was determined that the spread of these plants was mainly associated with non-built-up areas of land, as well as 30-meter zones around road networks, which can be considered as potential dispersal corridors. River networks and built-up area analysis showed a smaller part of the identified plant territory, therefore, we can conclude that these are not the main causes of the spread of the invasive plants. Hot spot analysis showed that the Pilaitė district is the most problematic area of this study due to the largest concentration of Sosnowsky’s hogweed. Study results show that the developed machine learning algorithm is a promising approach for future studies for the monitoring of Sosnowsky’s hogweed, especially if the training sample is improved.","abstract_has_math":false,"creators":["Nomgaudytė, Meda,"],"institution":"Institutional Repository of Vilnius University","degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":[],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2026,"date_issued":"2026","date_published":"2026","updated_at":"2026-11-19T10:12:55Z","subjects":[],"languages":["lit"],"rights":["info:eu-repo/semantics/openAccess"],"rights_urls":[],"identifier_entries":[],"person_identifier_entries":[]},"links":{"outbound_url":"https://repository.vu.lt/VU:ELABAETD308333925&prefLang=en_US","outbound_label":"Repository record","outbound_source":"dc:identifier","record_url":"https://repository.vu.lt/VU:ELABAETD308333925&prefLang=en_US","record_label":"Repository record","record_kind":"record","record_source":"dc:identifier","download_url":null,"download_label":null,"download_source":null,"access_status":"open","embargo_until":null,"access_note":null},"source_record":{"url":"https://epublications.vu.lt/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai%3Avu.lt%3Aelaba%3A308333925","prefix":"oai_dc"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:creator","label":"Author","values":["Nomgaudytė, Meda,"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2026"]},{"key":"dc:publisher","label":"Institution","values":["Institutional Repository of Vilnius University"]},{"key":"dc:relation","label":"Dc Relation","values":["https://epublications.vu.lt/object/elaba:308333925/308333925.pdf"]},{"key":"dc:type","label":"Dc Type","values":["info:eu-repo/semantics/bachelorThesis"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["lit"]},{"key":"dc:rights","label":"Dc Rights","values":["info:eu-repo/semantics/openAccess"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://repository.vu.lt/VU:ELABAETD308333925&prefLang=en_US"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Sosnowsky’s hogweed (Heracleum sosnowskyi) is one of the most dangerous invasive species, spread across the entire territory of Lithuania. The monitoring and removal of this plant are essential since the plant puts human health and biodiversity in danger. Unfortunately, this process is time consuming and demands large amounts of human resources. Therefore, these days the aim is to find effective and innovative ways to ease these processes. The aim of this thesis was to identify the spread of the invasive plant and perform an analysis using hyperspectral data consisting of 430 spectral bands and a machine learning algorithm in the territory of Vilnius. During the study, a Random Forest classifier, with an accuracy of 95%, was created. The model identified 2 682 possible Sosnowsky’s hogweed areas, which covered approximately 5.33 ha of territory. During spatial analysis, it was determined that the spread of these plants was mainly associated with non-built-up areas of land, as well as 30-meter zones around road networks, which can be considered as potential dispersal corridors. River networks and built-up area analysis showed a smaller part of the identified plant territory, therefore, we can conclude that these are not the main causes of the spread of the invasive plants. Hot spot analysis showed that the Pilaitė district is the most problematic area of this study due to the largest concentration of Sosnowsky’s hogweed. Study results show that the developed machine learning algorithm is a promising approach for future studies for the monitoring of Sosnowsky’s hogweed, especially if the training sample is improved."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Sosnovskio barščio židinių identifikavimas ir erdvinė analizė Vilniaus mieste taikant mašininio mokymosi metodus /","Identification and spatial analysis of sosnowsky‘s hogweed infestations in vilnius using machine learning methods."]}]}],"canonical_facts":{"dc:creator":["Nomgaudytė, Meda,"],"dc:date":["2026"],"dc:description":["Sosnowsky’s hogweed (Heracleum sosnowskyi) is one of the most dangerous invasive species, spread across the entire territory of Lithuania. The monitoring and removal of this plant are essential since the plant puts human health and biodiversity in danger. Unfortunately, this process is time consuming and demands large amounts of human resources. Therefore, these days the aim is to find effective and innovative ways to ease these processes. The aim of this thesis was to identify the spread of the invasive plant and perform an analysis using hyperspectral data consisting of 430 spectral bands and a machine learning algorithm in the territory of Vilnius. During the study, a Random Forest classifier, with an accuracy of 95%, was created. The model identified 2 682 possible Sosnowsky’s hogweed areas, which covered approximately 5.33 ha of territory. During spatial analysis, it was determined that the spread of these plants was mainly associated with non-built-up areas of land, as well as 30-meter zones around road networks, which can be considered as potential dispersal corridors. River networks and built-up area analysis showed a smaller part of the identified plant territory, therefore, we can conclude that these are not the main causes of the spread of the invasive plants. Hot spot analysis showed that the Pilaitė district is the most problematic area of this study due to the largest concentration of Sosnowsky’s hogweed. Study results show that the developed machine learning algorithm is a promising approach for future studies for the monitoring of Sosnowsky’s hogweed, especially if the training sample is improved."],"dc:format":["application/pdf"],"dc:identifier":["https://repository.vu.lt/VU:ELABAETD308333925&prefLang=en_US"],"dc:language":["lit"],"dc:publisher":["Institutional Repository of Vilnius University"],"dc:relation":["https://epublications.vu.lt/object/elaba:308333925/308333925.pdf"],"dc:rights":["info:eu-repo/semantics/openAccess"],"dc:title":["Sosnovskio barščio židinių identifikavimas ir erdvinė analizė Vilniaus mieste taikant mašininio mokymosi metodus /","Identification and spatial analysis of sosnowsky‘s hogweed infestations in vilnius using machine learning methods."],"dc:type":["info:eu-repo/semantics/bachelorThesis"]},"updated_at":"2026-11-19T10:12:55Z"}