PREDICTION OF TÜRKİYE'S BURNED FOREST AREAS USING ARIMA MODEL

Kübra Bağcı

Makale detayları

PREDICTION OF TÜRKİYE'S BURNED FOREST AREAS USING ARIMA MODEL

Yazarlar:

Kübra Bağcı

Yayıncı:

Fırat University

Dergi:

Fırat Üniversitesi Sosyal Bilimler Dergisi Vol.33 Issue 1, pp.347-355

Belge Tipi:

Makale

Yayın Tarihi:

1/2023

Belge Dili:

İngilizce

Document ID (Org No.):

2001282698

pISSN:

1300-9702

Anahtar kelimeler:

Özet:

 Abstract: Large-scale forest fires can cause significant ecological losses. Additionally, preserving forest areas may help to slow down climate change. Statistical models are one of the tools used in planning fire management strategies. In this study, the burned forest area of Türkiye is modeled using the Autoregressive Integrated Moving Average ARIMA method following the identification, estimation, validation, and forecasting steps. As is known the ARIMA analysis is one of the popular techniques used in time series analysis. Annual total burned forest areas in Türkiye over the period 1940-2021 are considered in the analysis. Three preliminary models are considered for evaluation of their modeling and prediction performances. The models validities are investigated with LjungBox statistics, residual analysis, and cross-validation. According to the results, the ARIMA 3,1,0 model is found to be the most suitable model for predicting the future values of the burned forest area time series in Türkiye. Forecasts for Türkiyes burned forest areas series are obtained for the next 3 years accordingly.

 Abstract: Large-scale forest fires can cause significant ecological losses. Additionally, preserving forest areas may help to slow down climate change. Statistical models are one of the tools used in planning fire management strategies. In this study, the burned forest area of Türkiye is modeled using the Autoregressive Integrated Moving Average ARIMA method following the identification, estimation, validation, and forecasting steps. As is known the ARIMA analysis is one of the popular techniques used in time series analysis. Annual total burned forest areas in Türkiye over the period 1940-2021 are considered in the analysis. Three preliminary models are considered for evaluation of their modeling and prediction performances. The models validities are investigated with LjungBox statistics, residual analysis, and cross-validation. According to the results, the ARIMA 3,1,0 model is found to be the most suitable model for predicting the future values of the burned forest area time series in Türkiye. Forecasts for Türkiyes burned forest areas series are obtained for the next 3 years accordingly.

 Abstract: Large-scale forest fires can cause significant ecological losses. Additionally, preserving forest areas may help to slow down climate change. Statistical models are one of the tools used in planning fire management strategies. In this study, the burned forest area of Türkiye is modeled using the Autoregressive Integrated Moving Average ARIMA method following the identification, estimation, validation, and forecasting steps. As is known the ARIMA analysis is one of the popular techniques used in time series analysis. Annual total burned forest areas in Türkiye over the period 1940-2021 are considered in the analysis. Three preliminary models are considered for evaluation of their modeling and prediction performances. The models validities are investigated with LjungBox statistics, residual analysis, and cross-validation. According to the results, the ARIMA 3,1,0 model is found to be the most suitable model for predicting the future values of the burned forest area time series in Türkiye. Forecasts for Türkiyes burned forest areas series are obtained for the next 3 years accordingly.

 Büyük ölçekli orman yangınları önemli ekolojik kayıplara neden olmaktadır. Ayrıca ormanlık alanların korunması iklim değişikliğini yavaşlatmaya yardımcı olabilmektedir. İstatistiksel modeller, yangın yönetimi stratejilerinin planlanmasında kullanılan araçlardan biridir. Bu çalışmada, Türkiyenin yanan orman alanı, tanımlama, tahmin, doğrulama ve öngörü adımları izlenerek Otoregresif Bütünleşik Hareketli Ortalama ARIMA yöntemi kullanılarak analiz edilmiştir. ARIMA yöntemi zaman serileri analizinde kullanılan popüler tekniklerden biridir. Analizde 1940-2021 yılları arasında Türkiyedeki yıllık toplam yanan orman alanı ölçümleri kullanılmıştır. Modelleme ve tahmin performanslarının değerlendirilmesi için üç model ele alınmıştır. Modellerin geçerliliği, LjungBox istatistikleri ve çapraz doğrulama ile araştırılmıştır. Sonuçlara göre, ARIMA 3,1,0 modeli Türkiyenin yanmış orman alanı zaman serilerinin gelecek değerlerinin tahmin edilmesi için en uygun model olarak bulunmuş ve öngörüler önümüzdeki 3 yıl için elde edilmiştir.

Makale detayları

PREDICTION OF TÜRKİYE'S BURNED FOREST AREAS USING ARIMA MODEL

Yazarlar:

Kübra Bağcı

Yayıncı:

Fırat University

Dergi:

Fırat Üniversitesi Sosyal Bilimler Dergisi Vol.33 Issue 1, pp.347-355

Belge Tipi:

Makale

Yayın Tarihi:

1/2023

Belge Dili:

İngilizce

Document ID (Org No.):

2001282698

pISSN:

1300-9702

ARIMA model

burned forest area

forest fires

time series

Türkiye

ARIMA

orman yangını

Türkiye

yanan orman alanı

zaman serisi

Sayı

Makale detayları

Yazarlar: Kübra Bağcı

Yayıncı: Fırat University

Dergi: Fırat Üniversitesi Sosyal Bilimler Dergisi Vol.33 Issue 1, pp.347-355

Belge Tipi: Makale

Yayın Tarihi: 1/2023

Belge Dili: İngilizce

Document ID (Org No.): 2001282698

pISSN: 1300-9702

Sayı

Yazarlar:

Kübra Bağcı

Yayıncı:

Fırat University

Dergi:

Fırat Üniversitesi Sosyal Bilimler Dergisi Vol.33 Issue 1, pp.347-355

Belge Tipi:

Makale

Yayın Tarihi:

1/2023

Belge Dili:

İngilizce

Document ID (Org No.):

2001282698

pISSN:

1300-9702