A NEW APPROACH TO DETERMINE THE INFLUENCE OF WEATHER CONDITIONS ON FOREST FIRE RISK IN THE MEDITERRANEAN REGION OF TÜRKİYE

Semra Türkan; Gamze Özel; Coşkun Okan Güney; Ceren Ünal; Özdemir Şentürk; Kürşad Özkan

Makale detayları

A NEW APPROACH TO DETERMINE THE INFLUENCE OF WEATHER CONDITIONS ON FOREST FIRE RISK IN THE MEDITERRANEAN REGION OF TÜRKİYE

Yazarlar:

Semra Türkan | Gamze Özel | Coşkun Okan Güney | Ceren Ünal | Özdemir Şentürk | Kürşad Özkan

Yayıncı:

Mugla Sitki Kocman University

Ana Başlıklar:

Mühendislik

Dergi:

Mugla Journal of Science and Technology Vol.9 Issue 2, pp.1-10

Belge Tipi:

Makale

Yayın Tarihi:

12/2023

Belge Dili:

İngilizce

Document ID (Org No.):

2001305081

pISSN:

2149-3596

Anahtar kelimeler:

Özet:

 The risk of forest fires is a major problem in Türkiyes Mediterranean region and has a significant impact on ecosystems and atmospheric conditions. Throughout the previous century, a significant portion of Türkiyes Mediterranean Region has been destroyed by forest fires. This study aims to determine the meteorological covariates, such as relative humidity, maximum temperature, and wind speed, that affect forest fires. We classified forest fires into two groups. The first group F1 refers to small forest fires, with burned forest areas of less than 10 hectares. The second group F2, representing rare events, corresponds to burned areas of more than 10 hectares. The data is composed of binary values F10 and F21 taken between the years 2015-2019 from different locations in the Mediterranean Region of Türkiye. For binary data modeling, the ordinary logistic regression LR has been frequently used. However, such a method tends to give biased results when using rare event data. Therefore, we employed three different modeling techniques specifically designed for rare event data. According to the results obtained from the best model, Firths Logistic Regression FLR, wind speed, and maximum temperature are found to be statistically significant variables in the occurrence of forest fires greater than 10 hectares.

 The risk of forest fires is a major problem in Türkiyes Mediterranean region and has a significant impact on ecosystems and atmospheric conditions. Throughout the previous century, a significant portion of Türkiyes Mediterranean Region has been destroyed by forest fires. This study aims to determine the meteorological covariates, such as relative humidity, maximum temperature, and wind speed, that affect forest fires. We classified forest fires into two groups. The first group F1 refers to small forest fires, with burned forest areas of less than 10 hectares. The second group F2, representing rare events, corresponds to burned areas of more than 10 hectares. The data is composed of binary values F10 and F21 taken between the years 2015-2019 from different locations in the Mediterranean Region of Türkiye. For binary data modeling, the ordinary logistic regression LR has been frequently used. However, such a method tends to give biased results when using rare event data. Therefore, we employed three different modeling techniques specifically designed for rare event data. According to the results obtained from the best model, Firths Logistic Regression FLR, wind speed, and maximum temperature are found to be statistically significant variables in the occurrence of forest fires greater than 10 hectares.

 The risk of forest fires is a major problem in Türkiyes Mediterranean region and has a significant impact on ecosystems and atmospheric conditions. Throughout the previous century, a significant portion of Türkiyes Mediterranean Region has been destroyed by forest fires. This study aims to determine the meteorological covariates, such as relative humidity, maximum temperature, and wind speed, that affect forest fires. We classified forest fires into two groups. The first group F1 refers to small forest fires, with burned forest areas of less than 10 hectares. The second group F2, representing rare events, corresponds to burned areas of more than 10 hectares. The data is composed of binary values F10 and F21 taken between the years 2015-2019 from different locations in the Mediterranean Region of Türkiye. For binary data modeling, the ordinary logistic regression LR has been frequently used. However, such a method tends to give biased results when using rare event data. Therefore, we employed three different modeling techniques specifically designed for rare event data. According to the results obtained from the best model, Firths Logistic Regression FLR, wind speed, and maximum temperature are found to be statistically significant variables in the occurrence of forest fires greater than 10 hectares.

 Orman yangınları riski, Türkiyenin Akdeniz bölgesinde önemli bir sorundur ve ekosistemlere ile atmosferik özelliklere büyük etkisi vardır. Geçmiş yüzyıl boyunca Türkiyenin Akdeniz Bölgesinin büyük bir kısmı orman yangınları sonucunda tahrip olmuştur. Bu çalışma, orman yangınlarını etkileyen bağıl nem, maksimum sıcaklık ve rüzgâr hızı gibi meteorolojik değişkenleri belirlemeyi amaçlamaktadır. Orman yangınlarını iki gruba ayırdık. Birinci grup F1, 10 hektardan küçük yanmış orman alanlarını ifade eder. Nadir olayları temsil eden ikinci grup F2, 10 hektardan fazla yanmış alanları temsil eder. Veriler, Türkiyenin Akdeniz Bölgesindeki farklı lokasyonlardan 2015-2019 yılları arasında alınan ikili değerlerden oluşmaktadır F10 ve F21. İkili veri modellemesi için, genellikle sıradan lojistik regresyon LR kullanılmaktadır. Ancak, nadir olay verileri kullanıldığında bu yöntem yanlı sonuçlar verebilmektedir. Bu nedenle, nadir olay verileri için kullanılabilen üç farklı modelleme tekniği kullanıldı. En iyi model olan Firth Lojistik Regresyonu FLR sonuçlarına göre, rüzgâr hızı ve maksimum sıcaklık, 10 hektardan büyük orman yangınlarının oluşumunda istatistiksel olarak önemli değişkenler olarak bulundu.

Makale detayları

A NEW APPROACH TO DETERMINE THE INFLUENCE OF WEATHER CONDITIONS ON FOREST FIRE RISK IN THE MEDITERRANEAN REGION OF TÜRKİYE

Yazarlar:

Semra Türkan | Gamze Özel | Coşkun Okan Güney | Ceren Ünal | Özdemir Şentürk | Kürşad Özkan

Yayıncı:

Mugla Sitki Kocman University

Ana Başlıklar:

Mühendislik

Dergi:

Mugla Journal of Science and Technology Vol.9 Issue 2, pp.1-10

Belge Tipi:

Makale

Yayın Tarihi:

12/2023

Belge Dili:

İngilizce

Document ID (Org No.):

2001305081

pISSN:

2149-3596

Climate Change

Humidity

Natural Hazard

Penalized Regressionİklim Değişikliği

Nem

Doğal Tehlike

Cezalandırılmış Regresyon

Sayı

Makale detayları

Yazarlar: Semra Türkan | Gamze Özel | Coşkun Okan Güney | Ceren Ünal | Özdemir Şentürk | Kürşad Özkan

Yayıncı: Mugla Sitki Kocman University

Ana Başlıklar: Mühendislik

Dergi: Mugla Journal of Science and Technology Vol.9 Issue 2, pp.1-10

Belge Tipi: Makale

Yayın Tarihi: 12/2023

Belge Dili: İngilizce

Document ID (Org No.): 2001305081

pISSN: 2149-3596

Sayı

Yazarlar:

Semra Türkan | Gamze Özel | Coşkun Okan Güney | Ceren Ünal | Özdemir Şentürk | Kürşad Özkan

Yayıncı:

Mugla Sitki Kocman University

Ana Başlıklar:

Mühendislik

Dergi:

Mugla Journal of Science and Technology Vol.9 Issue 2, pp.1-10

Belge Tipi:

Makale

Yayın Tarihi:

12/2023

Belge Dili:

İngilizce

Document ID (Org No.):

2001305081

pISSN:

2149-3596