Araştırma Makalesi
BibTex RIS Kaynak Göster

Makine Öğrenmesi Algoritmaları ile Yaz Sezonu Ortalama Akım Değerlerinin Tahmini

Yıl 2024, Cilt: 6 Sayı: 2, 73 - 81, 31.12.2024
https://doi.org/10.60093/jiciviltech.1497771

Öz

Akarsu akım verilerinin tahmini su bilimi açısından kritik konuların başında gelmektedir. Özellikle yaz aylarında yağışların azalmasına ek olarak su kullanımın artması her yıl iklimsel değişikliklerin etkisinin arttığı dünyamızda tüm canlıları kuraklık riskiyle yüz yüze getirmektedir. Bu yüzden yaz aylarındaki suyun kullanımın önceden planlanması ve bu konuya daha hassas bir şekilde yaklaşılması her geçen gün daha da zorunlu hale gelmektedir. Bu planlamanın yapılmasında ise akarsu akım debilerinin tahmini, su ihtiyacının karşılanması açısından önemlidir. Bu çalışmada Beyşehir Gölünü besleyen üç akarsu üzerinde bulunan, akarsu gözlem istasyonlarından temin edilen veriler ile makine öğrenmesi modelleri kurulmuştur. Rastgele Orman (RO) ve Adaptive Yükseltme (AdaBoost) algoritmalarının kullanıldığı bu modeller ile üç girdi ve bir çıktı olacak şekilde; sonbahar, kış, ilkbahar mevsimsel ortalama akış değerlerinden yaz mevsimi ortalama akışı tahmin edilmeye çalışılmıştır. RO algoritması test ve tahmin arasındaki belirleme katsayısı (R^2) 0.9368 değerindedir. Kök ortalama kare hatası (RMSE) değeri ise 0.0275 olarak bulunmuştur. AdaBoost algoritması ise RO algoritmasına göre daha güçlü tahminde bulunarak test ve tahmin arasındaki R^2 değeri 0.981, RMSE değeri ise 0.05 olarak bulunmuştur.

Kaynakça

  • Bayrakçı, H., Keşkekçi, A. B., & Arslan, R. (2022). Classification of iris flower by random forest algorithm. Advances in Artificial Intelligence Research, 2(1), 7-14. https://doi.org/10.54569/aair.1018444
  • Breiman, L. (2001). Random forests. Machine learning, 45, 5-32. http://dx.doi.org/10.1023/A:1010933404324
  • Cheng, M., Fang, F., Kinouchi, T., Navon, I. M., & Pain, C. C. (2020). Long lead-time daily and monthly streamflow forecasting using machine learning methods. Journal of Hydrology, 590, 125376. https://doi.org/10.1016/j.jhydrol.2020.125376
  • Çubukçu, E. A., Demir, V., & Sevimli, M. F. (2022). Akım Verilerinin Makine Öğrenmesi Teknikleriyle Tahmin Edilmesi. Gazi Mühendislik Bilimleri Dergisi, 8(2), 257-272.
  • Di Bucchianico, A. (2008). Coefficient of determination (R 2). Encyclopedia of statistics in quality and reliability. https://doi.org/10.1002/9780470061572.eqr173
  • Dirlik, C., Kandemir, H., Çetin, N., Şen, S., Güler, B., & Gürel, A. (2022). Effects of different culture media compositions on in vitro micropropagation from paradox walnut rootstock nodes. Gazi University Journal of Science Part A: Engineering and Innovation, 9(4), 500-515. https://doi.org/10.54287/gujsa.1194822
  • Freund, Y., & Schapire, R. E. (1997). A decision-theoretic generalization of on-line learning and an application to boosting. Journal of computer and system sciences, 55(1), 119-139. https://doi.org/10.1006/jcss.1997.1504
  • Güçlü, Y. S., Yeleğen, M. Ö., Dabanlı, İ., & Şişman, E. (2014). Solar irradiation estimations and comparisons by ANFIS, Angström–Prescott and dependency models. Solar Energy, 109, 118-124. https://doi.org/10.1016/j.solener.2014.08.027
  • Lu, P., Deng, Q., Zhao, S., Wang, Y., & Wang, W. (2023). Deep learning for seasonal prediction of summer precipitation levels in eastern China. Earth and Space Science, 10(11), e2023EA003129. https://doi.org/10.1029/2023EA003129
  • Özel, A., & Büyükyıldız, M. (2019). Usability of artificial intelligence methods for estimation of monthly evaporation. Niğde Ömer Halisdemir University Journal of Engineering Sciences, 8(1), 244-254. https://doi.org/10.28948/ngumuh.516891
  • Rasouli, K., Hsieh, W. W., & Cannon, A. J. (2012). Daily streamflow forecasting by machine learning methods with weather and climate inputs. Journal of Hydrology, 414, 284-293. https://doi.org/10.1016/j.jhydrol.2011.10.039
  • Saplıoğlu, K. (2023). Monthly streamflow prediction using ANN, KNN and ANFIS models: Example of Gediz River Basin. Teknik Bilimler Dergisi, 13(2), 42-49. https://doi.org/10.35354/tbed.1298296
  • Şişman, E., & Kizilöz, B. (2020). Artificial neural network system analysis and Kriging methodology for estimation of non-revenue water ratio. Water Supply, 20(5), 1871-1883. https://doi.org/10.2166/ws.2020.095
  • Wang, X. J., Zhang, J. Y., Shahid, S., Guan, E. H., Wu, Y. X., Gao, J., & He, R. M. (2016). Adaptation to climate change impacts on water demand. Mitigation and Adaptation Strategies for Global Change, 21, 81-99. https://doi.org/10.1007/s11027-014-9571-6
  • Yang, S., Ling, F., Li, Y., & Luo, J. J. (2023). Improving Seasonal Prediction of Summer Precipitation in the Middle–Lower Reaches of the Yangtze River Using a TU-Net Deep Learning Approach. Artificial Intelligence for the Earth Systems, 2(2), 220078. https://doi.org/10.1175/AIES-D-22-0078.1
  • Ziervogel, G., New, M., Archer van Garderen, E., Midgley, G., Taylor, A., Hamann, R., ... & Warburton, M. (2014). Climate change impacts and adaptation in South Africa. Wiley Interdisciplinary Reviews: Climate Change, 5(5), 605-620. https://doi.org/10.1002/wcc.295

Estimation of Summer Season Average Flow Values with Machine Learning Algorithms

Yıl 2024, Cilt: 6 Sayı: 2, 73 - 81, 31.12.2024
https://doi.org/10.60093/jiciviltech.1497771

Öz

Estimation of stream flow data is one of the critical issues in hydrology. In addition to the decrease in precipitation, especially in the summer months, the increase in water use puts all living things in our world at risk of drought, where the impact of climatic changes increases every year. Therefore, it is becoming more and more necessary to plan the use of water in the summer months in advance and approach this issue more sensitively. In making this planning, estimation of stream flow rates is important in terms of meeting water needs. In this study, machine learning models were established with data obtained from stream observation stations on three streams feeding Beyşehir Lake. With these models using Random Forest (RF) and Adaptive Boosting (AdaBoost) algorithms, there are three inputs and one output; An attempt was made to estimate the summer average flow from the autumn, winter and spring seasonal average flow values. The coefficient of determination (R^2) between RF algorithm test and prediction is 0.9368. The root mean square error (RMSE) value was found to be 0.0275. The AdaBoost algorithm made a stronger prediction than the RF algorithm, and the R^2 value between test and prediction was found to be 0.981 and the RMSE value was 0.05.

Kaynakça

  • Bayrakçı, H., Keşkekçi, A. B., & Arslan, R. (2022). Classification of iris flower by random forest algorithm. Advances in Artificial Intelligence Research, 2(1), 7-14. https://doi.org/10.54569/aair.1018444
  • Breiman, L. (2001). Random forests. Machine learning, 45, 5-32. http://dx.doi.org/10.1023/A:1010933404324
  • Cheng, M., Fang, F., Kinouchi, T., Navon, I. M., & Pain, C. C. (2020). Long lead-time daily and monthly streamflow forecasting using machine learning methods. Journal of Hydrology, 590, 125376. https://doi.org/10.1016/j.jhydrol.2020.125376
  • Çubukçu, E. A., Demir, V., & Sevimli, M. F. (2022). Akım Verilerinin Makine Öğrenmesi Teknikleriyle Tahmin Edilmesi. Gazi Mühendislik Bilimleri Dergisi, 8(2), 257-272.
  • Di Bucchianico, A. (2008). Coefficient of determination (R 2). Encyclopedia of statistics in quality and reliability. https://doi.org/10.1002/9780470061572.eqr173
  • Dirlik, C., Kandemir, H., Çetin, N., Şen, S., Güler, B., & Gürel, A. (2022). Effects of different culture media compositions on in vitro micropropagation from paradox walnut rootstock nodes. Gazi University Journal of Science Part A: Engineering and Innovation, 9(4), 500-515. https://doi.org/10.54287/gujsa.1194822
  • Freund, Y., & Schapire, R. E. (1997). A decision-theoretic generalization of on-line learning and an application to boosting. Journal of computer and system sciences, 55(1), 119-139. https://doi.org/10.1006/jcss.1997.1504
  • Güçlü, Y. S., Yeleğen, M. Ö., Dabanlı, İ., & Şişman, E. (2014). Solar irradiation estimations and comparisons by ANFIS, Angström–Prescott and dependency models. Solar Energy, 109, 118-124. https://doi.org/10.1016/j.solener.2014.08.027
  • Lu, P., Deng, Q., Zhao, S., Wang, Y., & Wang, W. (2023). Deep learning for seasonal prediction of summer precipitation levels in eastern China. Earth and Space Science, 10(11), e2023EA003129. https://doi.org/10.1029/2023EA003129
  • Özel, A., & Büyükyıldız, M. (2019). Usability of artificial intelligence methods for estimation of monthly evaporation. Niğde Ömer Halisdemir University Journal of Engineering Sciences, 8(1), 244-254. https://doi.org/10.28948/ngumuh.516891
  • Rasouli, K., Hsieh, W. W., & Cannon, A. J. (2012). Daily streamflow forecasting by machine learning methods with weather and climate inputs. Journal of Hydrology, 414, 284-293. https://doi.org/10.1016/j.jhydrol.2011.10.039
  • Saplıoğlu, K. (2023). Monthly streamflow prediction using ANN, KNN and ANFIS models: Example of Gediz River Basin. Teknik Bilimler Dergisi, 13(2), 42-49. https://doi.org/10.35354/tbed.1298296
  • Şişman, E., & Kizilöz, B. (2020). Artificial neural network system analysis and Kriging methodology for estimation of non-revenue water ratio. Water Supply, 20(5), 1871-1883. https://doi.org/10.2166/ws.2020.095
  • Wang, X. J., Zhang, J. Y., Shahid, S., Guan, E. H., Wu, Y. X., Gao, J., & He, R. M. (2016). Adaptation to climate change impacts on water demand. Mitigation and Adaptation Strategies for Global Change, 21, 81-99. https://doi.org/10.1007/s11027-014-9571-6
  • Yang, S., Ling, F., Li, Y., & Luo, J. J. (2023). Improving Seasonal Prediction of Summer Precipitation in the Middle–Lower Reaches of the Yangtze River Using a TU-Net Deep Learning Approach. Artificial Intelligence for the Earth Systems, 2(2), 220078. https://doi.org/10.1175/AIES-D-22-0078.1
  • Ziervogel, G., New, M., Archer van Garderen, E., Midgley, G., Taylor, A., Hamann, R., ... & Warburton, M. (2014). Climate change impacts and adaptation in South Africa. Wiley Interdisciplinary Reviews: Climate Change, 5(5), 605-620. https://doi.org/10.1002/wcc.295
Toplam 16 adet kaynakça vardır.

Ayrıntılar

Birincil Dil Türkçe
Konular Su Kaynakları ve Su Yapıları
Bölüm Araştırma Makaleleri
Yazarlar

Erdem Çoban 0000-0002-4526-7273

Erken Görünüm Tarihi 31 Aralık 2024
Yayımlanma Tarihi 31 Aralık 2024
Gönderilme Tarihi 7 Haziran 2024
Kabul Tarihi 7 Temmuz 2024
Yayımlandığı Sayı Yıl 2024 Cilt: 6 Sayı: 2

Kaynak Göster

APA Çoban, E. (2024). Makine Öğrenmesi Algoritmaları ile Yaz Sezonu Ortalama Akım Değerlerinin Tahmini. Journal of Innovations in Civil Engineering and Technology, 6(2), 73-81. https://doi.org/10.60093/jiciviltech.1497771