Araştırma Makalesi
BibTex RIS Kaynak Göster

İklimsel ve ekonomik değişkenlerle ürün verimi tahmini: Türkiye için makine öğrenmesine dayalı bir yaklaşım

Yıl 2025, Cilt: 31 Sayı: 2, 271 - 283, 19.12.2025
https://doi.org/10.24181/tarekoder.1699618

Öz

Amaç: Bu çalışma, Türkiye’de buğday, arpa, mısır, ayçiçeği ve pamuk gibi beş temel tarım ürününün yıllık verimleri ile iklim değişkenleri arasındaki tahmine dayalı ilişkiyi 1962–2022 dönemi için incelemektedir. Sadece iklim verilerini kullanan modeller ile iklim verilerine ekonomik girdilerin (gübre kullanımı, sermaye stoku, işgücü) eklendiği modeller karşılaştırılmıştır.
Tasarım/Metodoloji /Yaklaşım: Yıllık ürün verimlerinin, mevsimsel ve yıllık sıcaklık/yağış değişkenleri ile gecikmeli iklim göstergeleriyle eşleştirildiği panel bir veri seti oluşturulmuştur. İki farklı modelleme yapılandırması uygulanmıştır: (i) yalnızca iklim verilerine dayalı ve (ii) iklim + ekonomik kontrol değişkenlerini içeren modeller. Doğrusal regresyon, rastgele orman (Random Forest) ve Gradient Boosting algoritmaları, zaman serisi özellikli ileri zincirleme çapraz doğrulama ile değerlendirilmiştir.
Bulgular: Gradient Boosting modeli, ekonomik kontrol değişkenleriyle birlikte kullanıldığında örneklem dışı performans açısından en başarılı sonuçları vermiştir. (R² = 0.44, MAE = 547.8 kg/ha). Sadece iklim verileriyle çalışan aynı modelin başarımı belirgin şekilde daha düşüktür (örneğin, R² = 0.16). Özellik önem analizleri, büyüme dönemindeki sıcaklığın iklim değişkenleri arasında en belirleyici unsur olduğunu; gübre, sermaye ve işgücünün ise eklendiğinde tahmin gücünü önemli ölçüde artırdığını göstermektedir.
Özgünlük/Değer: Bu çalışma, iklim değişkenlerine ekonomik yapısal girdileri entegre eden, zamana duyarlı ve güçlü bir makine öğrenmesi çerçevesi sunmayı amaçlamaktadır. Bu sayede tarımsal üretimin iklimsel belirsizliklere karşı hassasiyeti daha doğru tahmin edilebilmekte ve veriye dayalı tarımsal planlama süreçlerine katkı sağlanmaktadır.

Kaynakça

  • Açci, Y., Uçar, E., Uçar, M. and Açci, R.C. (2024), “Evaluating the relationship between climate change, food prices, and poverty: empirical evidence from underdeveloped countries”, Environment Development and Sustainability
  • Altinsoy, H., Kurt, C. and Kurnaz, M.L. (2012), “Analysis of the effect of climate change on the yield of crops in Turkey using a statistical approach”, Springer Atmospheric Sciences, pp. 379–384.
  • Bakırcı, G.T. and Çakır, Ö. (2023), “Evaluation of climate change in the scope of agriculture and food”, Akademik Gıda, 2024, pp. 57-64.
  • Bozdağ, A. (2021), “Local-based mapping of carbon footprint variation in Turkey using artificial neural networks”, Arabian Journal of Geosciences, 14(6), pp.486.
  • Breiman, L. (2001), “Random forests”, *Machine Learning*, Vol. 45 No. 1, pp.5–32.
  • Cramer, W., Guiot, J., Fader, M., Garrabou, J., Gattuso, J.-P., Iglesias, A., Lange, M.A., Lionello, P., Llasat, M.C., Paz, S. et al. (2018), “Climate change and interconnected risks to sustainable development in the Mediterranean”, Nature Climate Change, 8(11), pp.972–980.
  • Deschênes, O. and Greenstone, M. (2007), “The Economic Impacts of Climate Change: Evidence from Agricultural Output and Random Fluctuations in Weather”, American Economic Review, Vol. 97 No. 1, pp. 354–385.
  • FAO (2023) FAOSTAT: Turkey – Crops and Livestock Products, Food and Agriculture Organization of the United Nations, Rome. Available at: https://www.fao.org/faostat/en/#country/223 (Accessed: 29 April 2025).
  • Friedman, J.H. (2001), “Greedy function approximation: A gradient boosting machine”, Annals of Statistics, 29(5), pp.1189–1232.
  • IPCC (2021), Climate Change 2021: The Physical Science Basis, Intergovernmental Panel on Climate Change, Geneva. Available at: https://www.ipcc.ch/report/ar6/wg1/ (Accessed: 1 April 2025).
  • Jeong, J.H., Resop, J.P., Mueller, N.D., Fleisher, D.H., Yun, K., Butler, E.E., Timlin, D.J., et al. (2016), “Random forests for global and regional crop yield predictions”, PLoS ONE, Vol. 11 No. 6, p. e0156571.
  • Kamilaris, A. and Prenafeta-Boldú, F.X. (2018), “Deep learning in agriculture: A survey”, Computers and Electronics in Agriculture, Vol. 147, pp. 70–90.
  • Khaki, S. and Wang, L. (2019), “Crop yield prediction using deep neural networks”, Frontiers in Plant Science, Vol. 10.
  • Kuwata, K. and Shibasaki, R. (2015), “Estimating Crop Yields with Deep Learning and Remotely Sensed Data”, Proceedings of the 2015 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), pp. 858–861.
  • Ortaş, İ. (2024), “Under Long-Term Agricultural Systems, the role of mycorrhizae in climate change and food security”, Manas Journal of Agriculture Veterinary and Life Sciences, 14(1), pp. 101–115.
  • Osman, B.M., Mohamud, M.H., Omar, A.F., Yabarow, A.A., Omar, O.M., Jirow, M.S.A., Dahir, A.N., et al. (2025), “The impact of climate change on economic growth in Somalia: using random forest and Bayesian approach”, Cogent Economics & Finance, 13(1).
  • Özbek, S. and Özbek, B. (2024), “Does Climate Change Strengthen the Link between Environmental Degradation and Agricultural Output? Empirical Evidence on the Turkish Economy”, Tarım Ekonomisi Dergisi, 30(1) pp. 49–60.
  • Rossini, A., Ruggeri, R., Belocchi, A. and Rossini, F. (2024), “Response of durum wheat cultivars to climate change in a Mediterranean environment: Trends of weather and crop variables at the turn of 21st century”, Journal of Agronomy and Crop Science, 210(6).
  • Shahhosseini, M., Hu, G. and Archontoulis, S.V. (2020), “Forecasting corn yield with machine learning ensembles”, Frontiers in Plant Science, Vol. 11.
  • TÜİK (2023), Labour Force Statistics 2022, Turkish Statistical Institute, Ankara. Available at: https://data.tuik.gov.tr/Bulten/Index?p=Labor-Force-Statistics-2022-49167 (Accessed: 25 April 2025).
  • Van Klompenburg, T., Kassahun, A. and Catal, C. (2020), “Crop yield prediction using machine learning: A systematic literature review”, Computers and Electronics in Agriculture, Vol. 177, p. 105709.
  • Yaraşır, N., Yiğit, A. and Erekul, O. (2024), “Yield and quality responses of soybean (Glycine max L. Merr.) varieties inoculated with rhizobia strains under drought stress”, Turkish Journal of Field Crops, 29(2), 165-176.
  • Zampieri, M., Ceglar, A., Dentener, F. and Toreti, A. (2017), “Wheat yield loss attributable to heat waves, drought and water excess at the global, national and subnational scales”, Environmental Research Letters, Vol. 12 No. 6, p. 064008.

Forecasting crop yields with climate and economic variables: A machine learning approach for Türkiye

Yıl 2025, Cilt: 31 Sayı: 2, 271 - 283, 19.12.2025
https://doi.org/10.24181/tarekoder.1699618

Öz

Purpose: This study forecasts the agricultural productivity of five major crops—wheat, barley, maize, sunflower, and cotton—in Türkiye from 1962 to 2022, using climate variables alone and in combination with economic inputs.
Design/Methodology/Approach: A panel dataset was constructed by matching annual crop yields with seasonal and annual temperature and precipitation variables, including lagged climate indicators. Two model configurations were tested: (i) climate-only and (ii) climate plus economic controls (fertilizer use, capital stock, labor). Three supervised learning models—Linear Regression, Random Forest, and Gradient Boosting—were evaluated using forward-chaining time-series cross-validation.
Findings: Gradient Boosting with economic controls achieved the best out-of-sample performance (R² = 0.44, MAE = 547.8 kg/ha), followed by Random Forest. Climate-only versions of the same models yielded substantially lower accuracy (e.g., Gradient Boosting R² = 0.16), highlighting the added predictive value of structural inputs. Feature importance analysis identified growing season temperature as the most influential climate variable, while fertilizer, capital, and labor emerged as key predictors when included.
Originality/Value: This study introduces a robust, time-aware machine learning framework for forecasting crop yields under climate variability. By integrating economic inputs, it enhances predictive accuracy and offers practical insights to support data-driven agricultural planning under climate uncertainty.

Kaynakça

  • Açci, Y., Uçar, E., Uçar, M. and Açci, R.C. (2024), “Evaluating the relationship between climate change, food prices, and poverty: empirical evidence from underdeveloped countries”, Environment Development and Sustainability
  • Altinsoy, H., Kurt, C. and Kurnaz, M.L. (2012), “Analysis of the effect of climate change on the yield of crops in Turkey using a statistical approach”, Springer Atmospheric Sciences, pp. 379–384.
  • Bakırcı, G.T. and Çakır, Ö. (2023), “Evaluation of climate change in the scope of agriculture and food”, Akademik Gıda, 2024, pp. 57-64.
  • Bozdağ, A. (2021), “Local-based mapping of carbon footprint variation in Turkey using artificial neural networks”, Arabian Journal of Geosciences, 14(6), pp.486.
  • Breiman, L. (2001), “Random forests”, *Machine Learning*, Vol. 45 No. 1, pp.5–32.
  • Cramer, W., Guiot, J., Fader, M., Garrabou, J., Gattuso, J.-P., Iglesias, A., Lange, M.A., Lionello, P., Llasat, M.C., Paz, S. et al. (2018), “Climate change and interconnected risks to sustainable development in the Mediterranean”, Nature Climate Change, 8(11), pp.972–980.
  • Deschênes, O. and Greenstone, M. (2007), “The Economic Impacts of Climate Change: Evidence from Agricultural Output and Random Fluctuations in Weather”, American Economic Review, Vol. 97 No. 1, pp. 354–385.
  • FAO (2023) FAOSTAT: Turkey – Crops and Livestock Products, Food and Agriculture Organization of the United Nations, Rome. Available at: https://www.fao.org/faostat/en/#country/223 (Accessed: 29 April 2025).
  • Friedman, J.H. (2001), “Greedy function approximation: A gradient boosting machine”, Annals of Statistics, 29(5), pp.1189–1232.
  • IPCC (2021), Climate Change 2021: The Physical Science Basis, Intergovernmental Panel on Climate Change, Geneva. Available at: https://www.ipcc.ch/report/ar6/wg1/ (Accessed: 1 April 2025).
  • Jeong, J.H., Resop, J.P., Mueller, N.D., Fleisher, D.H., Yun, K., Butler, E.E., Timlin, D.J., et al. (2016), “Random forests for global and regional crop yield predictions”, PLoS ONE, Vol. 11 No. 6, p. e0156571.
  • Kamilaris, A. and Prenafeta-Boldú, F.X. (2018), “Deep learning in agriculture: A survey”, Computers and Electronics in Agriculture, Vol. 147, pp. 70–90.
  • Khaki, S. and Wang, L. (2019), “Crop yield prediction using deep neural networks”, Frontiers in Plant Science, Vol. 10.
  • Kuwata, K. and Shibasaki, R. (2015), “Estimating Crop Yields with Deep Learning and Remotely Sensed Data”, Proceedings of the 2015 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), pp. 858–861.
  • Ortaş, İ. (2024), “Under Long-Term Agricultural Systems, the role of mycorrhizae in climate change and food security”, Manas Journal of Agriculture Veterinary and Life Sciences, 14(1), pp. 101–115.
  • Osman, B.M., Mohamud, M.H., Omar, A.F., Yabarow, A.A., Omar, O.M., Jirow, M.S.A., Dahir, A.N., et al. (2025), “The impact of climate change on economic growth in Somalia: using random forest and Bayesian approach”, Cogent Economics & Finance, 13(1).
  • Özbek, S. and Özbek, B. (2024), “Does Climate Change Strengthen the Link between Environmental Degradation and Agricultural Output? Empirical Evidence on the Turkish Economy”, Tarım Ekonomisi Dergisi, 30(1) pp. 49–60.
  • Rossini, A., Ruggeri, R., Belocchi, A. and Rossini, F. (2024), “Response of durum wheat cultivars to climate change in a Mediterranean environment: Trends of weather and crop variables at the turn of 21st century”, Journal of Agronomy and Crop Science, 210(6).
  • Shahhosseini, M., Hu, G. and Archontoulis, S.V. (2020), “Forecasting corn yield with machine learning ensembles”, Frontiers in Plant Science, Vol. 11.
  • TÜİK (2023), Labour Force Statistics 2022, Turkish Statistical Institute, Ankara. Available at: https://data.tuik.gov.tr/Bulten/Index?p=Labor-Force-Statistics-2022-49167 (Accessed: 25 April 2025).
  • Van Klompenburg, T., Kassahun, A. and Catal, C. (2020), “Crop yield prediction using machine learning: A systematic literature review”, Computers and Electronics in Agriculture, Vol. 177, p. 105709.
  • Yaraşır, N., Yiğit, A. and Erekul, O. (2024), “Yield and quality responses of soybean (Glycine max L. Merr.) varieties inoculated with rhizobia strains under drought stress”, Turkish Journal of Field Crops, 29(2), 165-176.
  • Zampieri, M., Ceglar, A., Dentener, F. and Toreti, A. (2017), “Wheat yield loss attributable to heat waves, drought and water excess at the global, national and subnational scales”, Environmental Research Letters, Vol. 12 No. 6, p. 064008.
Toplam 23 adet kaynakça vardır.

Ayrıntılar

Birincil Dil İngilizce
Konular Tarım Politikaları, Tarım Ekonomisi (Diğer)
Bölüm Araştırma Makalesi
Yazarlar

Burç Arslan Kaleli 0009-0009-1060-1137

Gönderilme Tarihi 15 Mayıs 2025
Kabul Tarihi 1 Eylül 2025
Yayımlanma Tarihi 19 Aralık 2025
Yayımlandığı Sayı Yıl 2025 Cilt: 31 Sayı: 2

Kaynak Göster

APA Kaleli, B. A. (2025). Forecasting crop yields with climate and economic variables: A machine learning approach for Türkiye. Tarım Ekonomisi Dergisi, 31(2), 271-283. https://doi.org/10.24181/tarekoder.1699618
AMA Kaleli BA. Forecasting crop yields with climate and economic variables: A machine learning approach for Türkiye. TED - TJAE. Aralık 2025;31(2):271-283. doi:10.24181/tarekoder.1699618
Chicago Kaleli, Burç Arslan. “Forecasting crop yields with climate and economic variables: A machine learning approach for Türkiye”. Tarım Ekonomisi Dergisi 31, sy. 2 (Aralık 2025): 271-83. https://doi.org/10.24181/tarekoder.1699618.
EndNote Kaleli BA (01 Aralık 2025) Forecasting crop yields with climate and economic variables: A machine learning approach for Türkiye. Tarım Ekonomisi Dergisi 31 2 271–283.
IEEE B. A. Kaleli, “Forecasting crop yields with climate and economic variables: A machine learning approach for Türkiye”, TED - TJAE, c. 31, sy. 2, ss. 271–283, 2025, doi: 10.24181/tarekoder.1699618.
ISNAD Kaleli, Burç Arslan. “Forecasting crop yields with climate and economic variables: A machine learning approach for Türkiye”. Tarım Ekonomisi Dergisi 31/2 (Aralık2025), 271-283. https://doi.org/10.24181/tarekoder.1699618.
JAMA Kaleli BA. Forecasting crop yields with climate and economic variables: A machine learning approach for Türkiye. TED - TJAE. 2025;31:271–283.
MLA Kaleli, Burç Arslan. “Forecasting crop yields with climate and economic variables: A machine learning approach for Türkiye”. Tarım Ekonomisi Dergisi, c. 31, sy. 2, 2025, ss. 271-83, doi:10.24181/tarekoder.1699618.
Vancouver Kaleli BA. Forecasting crop yields with climate and economic variables: A machine learning approach for Türkiye. TED - TJAE. 2025;31(2):271-83.

              

Dergimiz 2020 yılından itibaren Scopus veri tabanında taranmaya başlanmıştır.

Tarım Ekonomisi Dergisi, DergiPark'ın sunduğu LOCKSS sistemini kullanır. Arşivleme sistemi hakkında daha fazla bilgi için LOCKSS web sitesini ziyaret edebilirsiniz.
Depo Politikası : Arşiv Dünyasında, hakemli makalelere CrossRef tarafından sağlanan bir DOI numarası atanır.

 This website is licensed under the Creative Commons Attribution 4.0 International License.