Modeling and Mapping of Forest Fire Occurrence in the Lower Silesian Voivodeship of Poland Based on Machine Learning Methods
In recent years, forest fires have become an important issue in Central Europe. To model the probability of the occurrence of forest fires in the Lower Silesian Voivodeship of Poland, historical fire data and several types of predictors were collected or generated, including topographic, vegetation,...
Gespeichert in:
| Veröffentlicht in: | Forests 2023-01, Vol.14 (1), p.46 |
|---|---|
| Hauptverfasser: | , , , , , , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | |
|---|---|
| container_issue | 1 |
| container_start_page | 46 |
| container_title | Forests |
| container_volume | 14 |
| creator | Milanović, Slobodan Kaczmarowski, Jan Ciesielski, Mariusz Trailović, Zoran Mielcarek, Miłosz Szczygieł, Ryszard Kwiatkowski, Mirosław Bałazy, Radomir Zasada, Michał Milanović, Sladjan D. |
| description | In recent years, forest fires have become an important issue in Central Europe. To model the probability of the occurrence of forest fires in the Lower Silesian Voivodeship of Poland, historical fire data and several types of predictors were collected or generated, including topographic, vegetation, climatic, and anthropogenic features. The main objectives of this study were to determine the importance of the predictors of forest fire occurrence and to map the probability of forest fire occurrence. The H2O driverless artificial intelligence (DAI) cloud platform was used to model forest fire probability. The gradient boosted machine (GBM) and random forest (RF) methods were applied to assess the probability of forest fire occurrence. Evaluation the importance of the variables was performed using the H2O platform permutation method. The most important variables were the presence of coniferous forest and the distance to agricultural land according to the GBM and RF methods, respectively. Model validation was conducted using receiver operating characteristic (ROC) analysis. The areas under the curve (AUCs) of the ROC plots from the GBM and RF models were 83.3% and 81.3%, respectively. Based on the results obtained, the GBM model can be recommended for the mapping of forest fire occurrence in the study area. |
| doi_str_mv | 10.3390/f14010046 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_journals_2767208450</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2767208450</sourcerecordid><originalsourceid>FETCH-LOGICAL-c292t-9b28de24333c7ce7d68ebe6eb6154d7acc710f66a52755e43e028d6d5bd0ffcf3</originalsourceid><addsrcrecordid>eNpNkE9LxDAQxYsouKx78BsEPHmopkmbNEddXBV2WcE_15ImE5tlTWrSVQQ_vCkr4lzmHd77DfOy7LTAF5QKfGmKEhcYl-wgmxRCiLwUmB_-08fZLMYNTlPxWpBykn2vvIatda9IOo1Wsu9H7Q1a-ABxQAsbAK2V2oUATgGyDg0doKX_hIAe7RailQ69ePuROLGz_Zh98NuRdi0jaORdwqrOupQCGdzIX8HQeR1PsiMjtxFmv3uaPS9unuZ3-XJ9ez-_WuaKCDLkoiW1BlJSShVXwDWroQUGLSuqUnOpFC-wYUxWhFcVlBRwCjBdtRobowydZmd7bh_8-y691Wz8Lrh0siGccYLrssLJdb53qeBjDGCaPtg3Gb6aAjdjv81fv_QHabltYA</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2767208450</pqid></control><display><type>article</type><title>Modeling and Mapping of Forest Fire Occurrence in the Lower Silesian Voivodeship of Poland Based on Machine Learning Methods</title><source>MDPI - Multidisciplinary Digital Publishing Institute</source><source>Elektronische Zeitschriftenbibliothek - Frei zugängliche E-Journals</source><creator>Milanović, Slobodan ; Kaczmarowski, Jan ; Ciesielski, Mariusz ; Trailović, Zoran ; Mielcarek, Miłosz ; Szczygieł, Ryszard ; Kwiatkowski, Mirosław ; Bałazy, Radomir ; Zasada, Michał ; Milanović, Sladjan D.</creator><creatorcontrib>Milanović, Slobodan ; Kaczmarowski, Jan ; Ciesielski, Mariusz ; Trailović, Zoran ; Mielcarek, Miłosz ; Szczygieł, Ryszard ; Kwiatkowski, Mirosław ; Bałazy, Radomir ; Zasada, Michał ; Milanović, Sladjan D.</creatorcontrib><description>In recent years, forest fires have become an important issue in Central Europe. To model the probability of the occurrence of forest fires in the Lower Silesian Voivodeship of Poland, historical fire data and several types of predictors were collected or generated, including topographic, vegetation, climatic, and anthropogenic features. The main objectives of this study were to determine the importance of the predictors of forest fire occurrence and to map the probability of forest fire occurrence. The H2O driverless artificial intelligence (DAI) cloud platform was used to model forest fire probability. The gradient boosted machine (GBM) and random forest (RF) methods were applied to assess the probability of forest fire occurrence. Evaluation the importance of the variables was performed using the H2O platform permutation method. The most important variables were the presence of coniferous forest and the distance to agricultural land according to the GBM and RF methods, respectively. Model validation was conducted using receiver operating characteristic (ROC) analysis. The areas under the curve (AUCs) of the ROC plots from the GBM and RF models were 83.3% and 81.3%, respectively. Based on the results obtained, the GBM model can be recommended for the mapping of forest fire occurrence in the study area.</description><identifier>ISSN: 1999-4907</identifier><identifier>EISSN: 1999-4907</identifier><identifier>DOI: 10.3390/f14010046</identifier><language>eng</language><publisher>Basel: MDPI AG</publisher><subject>Agricultural land ; Algorithms ; Anthropogenic factors ; Artificial intelligence ; Coniferous forests ; Fire prevention ; Fire protection ; Forest & brush fires ; Forest fires ; Humidity ; Machine learning ; Mapping ; Permutations ; Population density ; Precipitation ; Risk assessment ; Topography ; Variables ; Vegetation</subject><ispartof>Forests, 2023-01, Vol.14 (1), p.46</ispartof><rights>2022 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c292t-9b28de24333c7ce7d68ebe6eb6154d7acc710f66a52755e43e028d6d5bd0ffcf3</citedby><cites>FETCH-LOGICAL-c292t-9b28de24333c7ce7d68ebe6eb6154d7acc710f66a52755e43e028d6d5bd0ffcf3</cites><orcidid>0000-0001-7688-1201 ; 0000-0002-2726-583X ; 0000-0002-8260-999X ; 0000-0003-2580-2897 ; 0000-0002-1215-140X ; 0000-0003-1633-5115 ; 0000-0002-4881-296X</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,776,780,27901,27902</link.rule.ids></links><search><creatorcontrib>Milanović, Slobodan</creatorcontrib><creatorcontrib>Kaczmarowski, Jan</creatorcontrib><creatorcontrib>Ciesielski, Mariusz</creatorcontrib><creatorcontrib>Trailović, Zoran</creatorcontrib><creatorcontrib>Mielcarek, Miłosz</creatorcontrib><creatorcontrib>Szczygieł, Ryszard</creatorcontrib><creatorcontrib>Kwiatkowski, Mirosław</creatorcontrib><creatorcontrib>Bałazy, Radomir</creatorcontrib><creatorcontrib>Zasada, Michał</creatorcontrib><creatorcontrib>Milanović, Sladjan D.</creatorcontrib><title>Modeling and Mapping of Forest Fire Occurrence in the Lower Silesian Voivodeship of Poland Based on Machine Learning Methods</title><title>Forests</title><description>In recent years, forest fires have become an important issue in Central Europe. To model the probability of the occurrence of forest fires in the Lower Silesian Voivodeship of Poland, historical fire data and several types of predictors were collected or generated, including topographic, vegetation, climatic, and anthropogenic features. The main objectives of this study were to determine the importance of the predictors of forest fire occurrence and to map the probability of forest fire occurrence. The H2O driverless artificial intelligence (DAI) cloud platform was used to model forest fire probability. The gradient boosted machine (GBM) and random forest (RF) methods were applied to assess the probability of forest fire occurrence. Evaluation the importance of the variables was performed using the H2O platform permutation method. The most important variables were the presence of coniferous forest and the distance to agricultural land according to the GBM and RF methods, respectively. Model validation was conducted using receiver operating characteristic (ROC) analysis. The areas under the curve (AUCs) of the ROC plots from the GBM and RF models were 83.3% and 81.3%, respectively. Based on the results obtained, the GBM model can be recommended for the mapping of forest fire occurrence in the study area.</description><subject>Agricultural land</subject><subject>Algorithms</subject><subject>Anthropogenic factors</subject><subject>Artificial intelligence</subject><subject>Coniferous forests</subject><subject>Fire prevention</subject><subject>Fire protection</subject><subject>Forest & brush fires</subject><subject>Forest fires</subject><subject>Humidity</subject><subject>Machine learning</subject><subject>Mapping</subject><subject>Permutations</subject><subject>Population density</subject><subject>Precipitation</subject><subject>Risk assessment</subject><subject>Topography</subject><subject>Variables</subject><subject>Vegetation</subject><issn>1999-4907</issn><issn>1999-4907</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>BENPR</sourceid><recordid>eNpNkE9LxDAQxYsouKx78BsEPHmopkmbNEddXBV2WcE_15ImE5tlTWrSVQQ_vCkr4lzmHd77DfOy7LTAF5QKfGmKEhcYl-wgmxRCiLwUmB_-08fZLMYNTlPxWpBykn2vvIatda9IOo1Wsu9H7Q1a-ABxQAsbAK2V2oUATgGyDg0doKX_hIAe7RailQ69ePuROLGz_Zh98NuRdi0jaORdwqrOupQCGdzIX8HQeR1PsiMjtxFmv3uaPS9unuZ3-XJ9ez-_WuaKCDLkoiW1BlJSShVXwDWroQUGLSuqUnOpFC-wYUxWhFcVlBRwCjBdtRobowydZmd7bh_8-y691Wz8Lrh0siGccYLrssLJdb53qeBjDGCaPtg3Gb6aAjdjv81fv_QHabltYA</recordid><startdate>20230101</startdate><enddate>20230101</enddate><creator>Milanović, Slobodan</creator><creator>Kaczmarowski, Jan</creator><creator>Ciesielski, Mariusz</creator><creator>Trailović, Zoran</creator><creator>Mielcarek, Miłosz</creator><creator>Szczygieł, Ryszard</creator><creator>Kwiatkowski, Mirosław</creator><creator>Bałazy, Radomir</creator><creator>Zasada, Michał</creator><creator>Milanović, Sladjan D.</creator><general>MDPI AG</general><scope>AAYXX</scope><scope>CITATION</scope><scope>3V.</scope><scope>7SN</scope><scope>7SS</scope><scope>7X2</scope><scope>8FE</scope><scope>8FH</scope><scope>8FK</scope><scope>ABUWG</scope><scope>AEUYN</scope><scope>AFKRA</scope><scope>ATCPS</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BHPHI</scope><scope>BKSAR</scope><scope>C1K</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>GNUQQ</scope><scope>HCIFZ</scope><scope>M0K</scope><scope>PATMY</scope><scope>PCBAR</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PYCSY</scope><orcidid>https://orcid.org/0000-0001-7688-1201</orcidid><orcidid>https://orcid.org/0000-0002-2726-583X</orcidid><orcidid>https://orcid.org/0000-0002-8260-999X</orcidid><orcidid>https://orcid.org/0000-0003-2580-2897</orcidid><orcidid>https://orcid.org/0000-0002-1215-140X</orcidid><orcidid>https://orcid.org/0000-0003-1633-5115</orcidid><orcidid>https://orcid.org/0000-0002-4881-296X</orcidid></search><sort><creationdate>20230101</creationdate><title>Modeling and Mapping of Forest Fire Occurrence in the Lower Silesian Voivodeship of Poland Based on Machine Learning Methods</title><author>Milanović, Slobodan ; Kaczmarowski, Jan ; Ciesielski, Mariusz ; Trailović, Zoran ; Mielcarek, Miłosz ; Szczygieł, Ryszard ; Kwiatkowski, Mirosław ; Bałazy, Radomir ; Zasada, Michał ; Milanović, Sladjan D.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c292t-9b28de24333c7ce7d68ebe6eb6154d7acc710f66a52755e43e028d6d5bd0ffcf3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Agricultural land</topic><topic>Algorithms</topic><topic>Anthropogenic factors</topic><topic>Artificial intelligence</topic><topic>Coniferous forests</topic><topic>Fire prevention</topic><topic>Fire protection</topic><topic>Forest & brush fires</topic><topic>Forest fires</topic><topic>Humidity</topic><topic>Machine learning</topic><topic>Mapping</topic><topic>Permutations</topic><topic>Population density</topic><topic>Precipitation</topic><topic>Risk assessment</topic><topic>Topography</topic><topic>Variables</topic><topic>Vegetation</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Milanović, Slobodan</creatorcontrib><creatorcontrib>Kaczmarowski, Jan</creatorcontrib><creatorcontrib>Ciesielski, Mariusz</creatorcontrib><creatorcontrib>Trailović, Zoran</creatorcontrib><creatorcontrib>Mielcarek, Miłosz</creatorcontrib><creatorcontrib>Szczygieł, Ryszard</creatorcontrib><creatorcontrib>Kwiatkowski, Mirosław</creatorcontrib><creatorcontrib>Bałazy, Radomir</creatorcontrib><creatorcontrib>Zasada, Michał</creatorcontrib><creatorcontrib>Milanović, Sladjan D.</creatorcontrib><collection>CrossRef</collection><collection>ProQuest Central (Corporate)</collection><collection>Ecology Abstracts</collection><collection>Entomology Abstracts (Full archive)</collection><collection>Agricultural Science Collection</collection><collection>ProQuest SciTech Collection</collection><collection>ProQuest Natural Science Collection</collection><collection>ProQuest Central (Alumni) (purchase pre-March 2016)</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest One Sustainability</collection><collection>ProQuest Central UK/Ireland</collection><collection>Agricultural & Environmental Science Collection</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Natural Science Collection (ProQuest)</collection><collection>Earth, Atmospheric & Aquatic Science Collection</collection><collection>Environmental Sciences and Pollution Management</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>ProQuest Central Student</collection><collection>SciTech Premium Collection</collection><collection>Agricultural Science Database</collection><collection>Environmental Science Database</collection><collection>Earth, Atmospheric & Aquatic Science Database</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Environmental Science Collection</collection><jtitle>Forests</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Milanović, Slobodan</au><au>Kaczmarowski, Jan</au><au>Ciesielski, Mariusz</au><au>Trailović, Zoran</au><au>Mielcarek, Miłosz</au><au>Szczygieł, Ryszard</au><au>Kwiatkowski, Mirosław</au><au>Bałazy, Radomir</au><au>Zasada, Michał</au><au>Milanović, Sladjan D.</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Modeling and Mapping of Forest Fire Occurrence in the Lower Silesian Voivodeship of Poland Based on Machine Learning Methods</atitle><jtitle>Forests</jtitle><date>2023-01-01</date><risdate>2023</risdate><volume>14</volume><issue>1</issue><spage>46</spage><pages>46-</pages><issn>1999-4907</issn><eissn>1999-4907</eissn><abstract>In recent years, forest fires have become an important issue in Central Europe. To model the probability of the occurrence of forest fires in the Lower Silesian Voivodeship of Poland, historical fire data and several types of predictors were collected or generated, including topographic, vegetation, climatic, and anthropogenic features. The main objectives of this study were to determine the importance of the predictors of forest fire occurrence and to map the probability of forest fire occurrence. The H2O driverless artificial intelligence (DAI) cloud platform was used to model forest fire probability. The gradient boosted machine (GBM) and random forest (RF) methods were applied to assess the probability of forest fire occurrence. Evaluation the importance of the variables was performed using the H2O platform permutation method. The most important variables were the presence of coniferous forest and the distance to agricultural land according to the GBM and RF methods, respectively. Model validation was conducted using receiver operating characteristic (ROC) analysis. The areas under the curve (AUCs) of the ROC plots from the GBM and RF models were 83.3% and 81.3%, respectively. Based on the results obtained, the GBM model can be recommended for the mapping of forest fire occurrence in the study area.</abstract><cop>Basel</cop><pub>MDPI AG</pub><doi>10.3390/f14010046</doi><orcidid>https://orcid.org/0000-0001-7688-1201</orcidid><orcidid>https://orcid.org/0000-0002-2726-583X</orcidid><orcidid>https://orcid.org/0000-0002-8260-999X</orcidid><orcidid>https://orcid.org/0000-0003-2580-2897</orcidid><orcidid>https://orcid.org/0000-0002-1215-140X</orcidid><orcidid>https://orcid.org/0000-0003-1633-5115</orcidid><orcidid>https://orcid.org/0000-0002-4881-296X</orcidid><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 1999-4907 |
| ispartof | Forests, 2023-01, Vol.14 (1), p.46 |
| issn | 1999-4907 1999-4907 |
| language | eng |
| recordid | cdi_proquest_journals_2767208450 |
| source | MDPI - Multidisciplinary Digital Publishing Institute; Elektronische Zeitschriftenbibliothek - Frei zugängliche E-Journals |
| subjects | Agricultural land Algorithms Anthropogenic factors Artificial intelligence Coniferous forests Fire prevention Fire protection Forest & brush fires Forest fires Humidity Machine learning Mapping Permutations Population density Precipitation Risk assessment Topography Variables Vegetation |
| title | Modeling and Mapping of Forest Fire Occurrence in the Lower Silesian Voivodeship of Poland Based on Machine Learning Methods |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-13T10%3A31%3A53IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Modeling%20and%20Mapping%20of%20Forest%20Fire%20Occurrence%20in%20the%20Lower%20Silesian%20Voivodeship%20of%20Poland%20Based%20on%20Machine%20Learning%20Methods&rft.jtitle=Forests&rft.au=Milanovi%C4%87,%20Slobodan&rft.date=2023-01-01&rft.volume=14&rft.issue=1&rft.spage=46&rft.pages=46-&rft.issn=1999-4907&rft.eissn=1999-4907&rft_id=info:doi/10.3390/f14010046&rft_dat=%3Cproquest_cross%3E2767208450%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2767208450&rft_id=info:pmid/&rfr_iscdi=true |