Research Article
BibTex RIS Cite

TÜRKİYE’DE FARKLI DENİZ MEVKİLERİNDEKİ DENİZ SUYU SICAKLIĞININ LSTM VE ANFIS MAKİNE ÖĞRENMESİ ALGORİTMALARI KULLANILARAK TAHMİN EDİLMESİ

Year 2025, Volume: 28 Issue: 1, 322 - 333, 03.03.2025

Akın İlhan , Sergen Tümse , Mehmet Bilgili , Alper Yıldırım , Beşir Şahin

Abstract

Dünyanın sıcaklığında hızlı bir artış yaşanmaktadır ve bu durum, yağış düzenlerinde değişimlere, deniz akıntısı dolaşımında bozulmalara ve deniz yaşamında olumsuz etkilere neden olur. Ayrıca, bu durumun, okyanuslar, denizler, göller ve nehirler gibi su ekosistemleri üzerinde diğer olumsuz etkileri de bulunmaktadır. Sonuçta, birbiriyle bağlantılı olan bu çevresel değişiklikleri anlamak ve ele almak için deniz sıcaklıklarının dikkatli bir şekilde izlenmesine ve yorumlanmasına zorunlu bir ihtiyaç vardır. Diğer taraftan, deniz suyunun günlük sıcaklıkları (SWT), denizlerdeki ve okyanuslardaki hem suyun hem de su yaşamının kimyasal bileşimini değiştiren çok önemli bir abiyotik değişkendir. Bu çerçevede, bu çalışma, bir gün sonrası SWT tahminlerinde yapay zekâ tekniklerinin kabiliyetlerini araştırmıştır. Bu teknikler, bulanık c-ortalamalar uyarlamalı nöro-bulanık çıkarım sistemi (ANFIS-FCM), çıkarımlı kümeleme ANFIS (ANFIS-SC), ızgara bölümleme ANFIS (ANFIS-GP) ve uzun kısa süreli bellek (LSTM) sinir ağı ve yapay sinir ağıdır (ANN). Bu doğrultuda, Türkiye'nin Akdeniz’de yer alan Alanya, Ege’de bulunan Bodrum ve Karadeniz’de kurulmuş olan Akçakoca ölçüm istasyonlarından elde edilen günlük SWT verileri kullanılmıştır. Beş farklı tahmin yöntemi kullanılarak üretilen tahmin sonuçları, gerçek gözlemlenen değerlere göre dört farklı istatistiksel ölçüm yaklaşımı kullanılarak karşılaştırıldı ve yorumlandı. Neticede, en doğru tahminlerin, ANFIS’in bulanık c-ortalamalar (FCM) yöntemi kullanıldığında elde edildiği sonucuna varılmıştır. Bu modeli en yakından takip eden ikinci en iyi modelin ise; LSTM yaklaşımı olduğu sonucuna varılmış ve bulunan sonuçlar rapor edilmiştir. Önerilen bu iki model de %0,34’lük MAPE, 0,0765 oC’lik MAE, 0,1585 oC’lik RMSE ve 0,9990’lık R'ye karşılık gelen üstün istatistiksel doğruluk sonuçlarını üretmiştir. Bu sonuçlar, gerçek ölçülen verilere en yakın eşleşmelerin ANFIS-FCM ve LSTM modelleri ile elde edildiğini göstermiştir.

Keywords

Makine öğrenmesi yapay sinir ağı deniz suyu sıcaklığının tahmini

References

  • Alver, A., Baştürk, E., Tulun, Ş., & Şimşek, İ. (2020). Adaptive neuro‐fuzzy inference system modeling of 2, 4‐dichlorophenol adsorption on wood-based activated carbon. Environmental Progress and Sustainable Energy, 39(5). https://doi.org/10.1002/ep.13413
  • Benmouiza, K., & Cheknane, A. (2019). Clustered ANFIS network using fuzzy c-means, subtractive clustering, and grid partitioning for hourly solar radiation forecasting. Theoretical and Applied Climatology, 137, 31–43. https://doi.org/10.1007/s00704-018-2576-4
  • Bilgili, M. (2010). Prediction of soil temperature using regression and artificial neural network models. Meteorology and Atmospheric Physics, 110, 59–70. 10.1007/s00703-010-0104-x
  • Bilgili, M. (2023). Time series forecasting on cooling degree-days (CDD) using SARIMA model. Nat Hazards, 118(3), 2569–2592. https://doi.org/10.1007/s11069-023-06109-4
  • Bilgili, M., & Sahin, B. (2010). Comparative analysis of regression and artificial neural network models for wind speed prediction. Meteorology and Atmospheric Physics, 109, 61–72. https://doi.org/10.1007/s00703-010-0093-9
  • Bowles, D. S., Grenney, W. J., & Fread, D. L. (1977). Coupled dynamic streamflow-temperature models. Journal of the Hydraulics Division,103(5), 515–530. https://doi.org/10.1061/JYCEAJ.0004750
  • Chen, J., Zeng, G. Q., Zhou, W., Du, W., & Lu, K. D. (2018). Wind speed forecasting using nonlinear-learning ensemble of deep learning time series prediction and extremal optimization. Energy Conversion and Management, 165, 681–695. https://doi.org/10.1016/j.enconman.2018.03.098
  • Gooseff, M. N., Strzepek, K., & Chapra, S. C. (2005). Modeling the potential effects of climate change on water temperature downstream of a shallow reservoir, lower madison river, MT. Climatic Change, 68(3), 331–353. 10.1007/s10584-005-9076-0
  • Gupta, S. M., & Malmgren, B. A. (2009). Comparison of the accuracy of SST estimates by artificial neural networks (ANN) and other quantitative methods using radiolarian data from the Antarctic and Pacific Oceans. Earth Science India, 2(2), 52–75.
  • Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural Computation, 9(8), 1735–1780. 10.1162/neco.1997.9.8.1735
  • Ilhan, A. (2023). Forecasting of volumetric flow rate of Ergene river using machine learning. Engineering Applications of Artificial Intelligence, 121, 105983. https://doi.org/10.1016/j.engappai.2023.105983
  • Jang, J. S. R. (1993). ANFIS: Adaptive-network-based fuzzy inference system. IEEE Transactions on Systems, Man, and Cybernetics, 23(3), 665–685. 10.1109/21.256541
  • Kayhan, F. E., Kaymak, G., Tartar, Ş., Akbulut, C., Esmer, H. E., & Ertuğ, N. D. Y. (2015). Effects of global warming on fish and marine ecosystems. Erciyes University Journal of the Institute of Science and Technology, 31(3), 128–134. https://dergipark.org.tr/tr/download/article-file/236029
  • Khosravi, A., Koury, R. N. N., Machado, L., & Pabon, J.J.G. (2018). Prediction of hourly solar radiation in Abu Musa Island using machine learning algorithms. Journal of Cleaner Production, 176, 63–75. https://doi.org/10.1016/j.jclepro.2017.12.065
  • Kisi, O., Genc, O., Dinc, S., & Zounemat-Kermani, M. (2016). Daily pan evaporation modeling using chi-squared automatic interaction detector, neural networks, classification, and regression tree. Computers and Electronics in Agriculture, 122, 112–117. https://doi.org/10.1016/j.compag.2016.01.026
  • Kisi, O., Sanikhani, H., Zounemat-Kermani, M., & Niazi, F. (2015). Long-term monthly evapotranspiration modeling by several data-driven methods without climatic data. Computers and Electronics in Agriculture, 115, 66–77. https://doi.org/10.1016/j.compag.2015.04.015
  • Liang, S., Nguyen, L., & Jin, F. (2018). A Multi-variable stacked long-short term memory network for wind speed forecasting. 2018 IEEE International Conference on Big Data (Big Data), Seattle, WA, USA.
  • Mahongo, S. B., & Deo, M. C. (2013). Using artificial neural networks to forecast monthly and seasonal sea surface temperature anomalies in the western Indian Ocean. International Journal of Ocean and Climate Systems, 4(2), 133–150. https://doi.org/10.1260/1759-3131.4.2.133
  • Mansouri, I., Ozbakkaloglu, T., Kisi, O., & Xie, T. (2016). Predicting behavior of FRP-confined concrete using neuro fuzzy, neural network, multivariate adaptive regression splines and M5 model tree techniques. Materials and Structures, 49, 4319–4334. 10.1617/s11527-015-0790-4
  • Mashaly, A. F., & Alazba, A. A. (2017). Membership function comparative investigation on productivity forecasting of solar still using adaptive neuro-fuzzy inference system approach. Environmental Progress and Sustainable Energy, 37(1), 249–259. https://doi.org/10.1002/ep.12664
  • Mathworks. Long short-term memory networks. (2020). https://www.mathworks.com/help/deeplearning/ug/long-short-term-memory-networks.html. Accessed 06.10.2024.
  • Morse, W. L. (1970). Stream temperature prediction model. Water Resources Research, 6(1), 290–302. https://doi.org/10.1029/WR006i001p00290
  • Patil, K., & Deo, M. C. (2017). Prediction of daily sea surface temperature using efficient neural networks. Ocean Dynamics, 67(3-4), 357–368. 10.1007/s10236-017-1032-9
  • Reddy, K. Y., & Krishna, K. V. S. G. M. (2023). Vehicular pollution prediction using HWTO‐ANFIS model in urban areas of Hyderabad City. Environmental Progress and Sustainable Energy, 42(4). https://doi.org/10.1002/ep.14082
  • Saghafi, H., & Arabloo, M. (2017). Estimation of carbon dioxide equilibrium adsorption isotherms using adaptive neuro-fuzzy inference systems (ANFIS) and regression models. Environmental Progress and Sustainable Energy, 36(5), 1374–1382. https://doi.org/10.1002/ep.12581
  • Sharma, V., Dhanya, J., Gade, M., & Sivasubramonian, J. (2023). New generalized ANN-based hybrid broadband response spectra generator using physics-based simulations. Natural Hazards, 116, 1879–1901. https://doi.org/10.1007/s11069-022-05746-5
  • Sinokrot, B. A., & Stefan, H. G. (1993). Stream temperature dynamics: Measurements and modeling. Water Resources Research, 29(7), 2299–2312. https://doi.org/10.1029/93WR00540
  • Şişman, E. (2019). Trend analysis for the cooling period for sea water temperatures in Aegean and Mediterranean coasts. Journal of Natural Hazards and Environment, 5(2), 291–304. https://doi.org/10.21324/dacd.492730
  • Tangang, F. T., Hsieh, W. W., & Tang, B. (1997). Forecasting the equatorial Pacific sea surface temperatures by neural network models. Climate Dynamics, 13, 135–147. 10.1007/s003820050156
  • Tanvir, M. S., & Mujtaba, I. M. (2006). Neural network based correlations for estimating temperature elevation for seawater in MSF desalination process. Desalination, 195(1-3), 251–272. https://doi.org/10.1016/j.desal.2005.11.013
  • Webb, B. W., & Zhang, Y. (1998). Spatial and seasonal variability in the components of the river heat budget. Hydrological Processes, 11(1), 79–101. https://doi.org/10.1002/(SICI)1099-1085(199701)11:1<79::AID-HYP404>3.0.CO;2-N
  • Wu, A., Hsieh, W. W., & Tang, B. (2006). Neural network forecasts of the tropical Pacific sea surface temperatures. Neural Networks, 19(2), 145–154. https://doi.org/10.1016/j.neunet.2006.01.004
  • Yücel, İ., Önen, A., Yılmaz, & K. K. (2016). Bir taşkın tahmin sisteminin değerlendirilmesi: Nümerik hava tahmin modeli, veri asimilasyonu ve uydu yağışlarının kullanımı. Dicle University, Engineering Faculty, Journal of Engineering, 7, 201–216. https://hdl.handle.net/11511/74347

LSTM AND ANFIS MACHINE LEARNING ALGORITHMS IN ESTIMATING THE SEA WATER TEMPERATURE IN TÜRKİYE AT VARIOUS SEA LOCATIONS

Year 2025, Volume: 28 Issue: 1, 322 - 333, 03.03.2025

Akın İlhan , Sergen Tümse , Mehmet Bilgili , Alper Yıldırım , Beşir Şahin

Abstract

The World's temperature is experiencing a rapid increase, leading to negative consequences for aquatic ecosystems such as oceans, seas, lakes, and rivers. There are also other negative influences consisting of changing precipitation patterns, disruptions in marine current circulation, and formation of negative impacts on marine life. Ultimately, there is a compelling need for careful monitoring of sea temperatures to understand and address these interconnected environmental changes. The daily temperature of seawater (SWT) is a crucial abiotic variable that changes both the chemical composition of water and aquatic life in seas and oceans. The present study explored the capabilities of artificial intelligence techniques in one-day-ahead SWT predictions. These techniques are fuzzy c-means adaptive neuro-fuzzy inference system (ANFIS-FCM), subtractive clustering ANFIS (ANFIS-SC), grid segmentation ANFIS (ANFIS-GP), and long short-term memory (LSTM) and artificial neural network (ANN). Accordingly, daily SWT data that was collected from Alanya, Bodrum, and Akcakoca measurement stations located in Türkiye's Mediterranean, Aegean, and Black Sea locations were used in SWT predictions. Estimated results obtained by these five estimation methods were compared to the real observed values by interpreting four statistical metrics. Consequently, the most accurate estimates were obtained utilizing the fuzzy c-means (FCM) of ANFIS. Besides, it was reported that the LSTM approach closely followed the accuracy of this prediction of FCM. Both proposed models have generated superior statistical accuracy results corresponding to 0.34% MAPE, 0.0765 oC MAE, 0.1585 oC RMSE, and 0.9990 R. Those results have indicated the closest match of the predictions on the real measured data that have been acquired by ANFIS-FCM and LSTM models.

Keywords

Machine learning artificial neural network prediction of seawater temperature

References

  • Alver, A., Baştürk, E., Tulun, Ş., & Şimşek, İ. (2020). Adaptive neuro‐fuzzy inference system modeling of 2, 4‐dichlorophenol adsorption on wood-based activated carbon. Environmental Progress and Sustainable Energy, 39(5). https://doi.org/10.1002/ep.13413
  • Benmouiza, K., & Cheknane, A. (2019). Clustered ANFIS network using fuzzy c-means, subtractive clustering, and grid partitioning for hourly solar radiation forecasting. Theoretical and Applied Climatology, 137, 31–43. https://doi.org/10.1007/s00704-018-2576-4
  • Bilgili, M. (2010). Prediction of soil temperature using regression and artificial neural network models. Meteorology and Atmospheric Physics, 110, 59–70. 10.1007/s00703-010-0104-x
  • Bilgili, M. (2023). Time series forecasting on cooling degree-days (CDD) using SARIMA model. Nat Hazards, 118(3), 2569–2592. https://doi.org/10.1007/s11069-023-06109-4
  • Bilgili, M., & Sahin, B. (2010). Comparative analysis of regression and artificial neural network models for wind speed prediction. Meteorology and Atmospheric Physics, 109, 61–72. https://doi.org/10.1007/s00703-010-0093-9
  • Bowles, D. S., Grenney, W. J., & Fread, D. L. (1977). Coupled dynamic streamflow-temperature models. Journal of the Hydraulics Division,103(5), 515–530. https://doi.org/10.1061/JYCEAJ.0004750
  • Chen, J., Zeng, G. Q., Zhou, W., Du, W., & Lu, K. D. (2018). Wind speed forecasting using nonlinear-learning ensemble of deep learning time series prediction and extremal optimization. Energy Conversion and Management, 165, 681–695. https://doi.org/10.1016/j.enconman.2018.03.098
  • Gooseff, M. N., Strzepek, K., & Chapra, S. C. (2005). Modeling the potential effects of climate change on water temperature downstream of a shallow reservoir, lower madison river, MT. Climatic Change, 68(3), 331–353. 10.1007/s10584-005-9076-0
  • Gupta, S. M., & Malmgren, B. A. (2009). Comparison of the accuracy of SST estimates by artificial neural networks (ANN) and other quantitative methods using radiolarian data from the Antarctic and Pacific Oceans. Earth Science India, 2(2), 52–75.
  • Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural Computation, 9(8), 1735–1780. 10.1162/neco.1997.9.8.1735
  • Ilhan, A. (2023). Forecasting of volumetric flow rate of Ergene river using machine learning. Engineering Applications of Artificial Intelligence, 121, 105983. https://doi.org/10.1016/j.engappai.2023.105983
  • Jang, J. S. R. (1993). ANFIS: Adaptive-network-based fuzzy inference system. IEEE Transactions on Systems, Man, and Cybernetics, 23(3), 665–685. 10.1109/21.256541
  • Kayhan, F. E., Kaymak, G., Tartar, Ş., Akbulut, C., Esmer, H. E., & Ertuğ, N. D. Y. (2015). Effects of global warming on fish and marine ecosystems. Erciyes University Journal of the Institute of Science and Technology, 31(3), 128–134. https://dergipark.org.tr/tr/download/article-file/236029
  • Khosravi, A., Koury, R. N. N., Machado, L., & Pabon, J.J.G. (2018). Prediction of hourly solar radiation in Abu Musa Island using machine learning algorithms. Journal of Cleaner Production, 176, 63–75. https://doi.org/10.1016/j.jclepro.2017.12.065
  • Kisi, O., Genc, O., Dinc, S., & Zounemat-Kermani, M. (2016). Daily pan evaporation modeling using chi-squared automatic interaction detector, neural networks, classification, and regression tree. Computers and Electronics in Agriculture, 122, 112–117. https://doi.org/10.1016/j.compag.2016.01.026
  • Kisi, O., Sanikhani, H., Zounemat-Kermani, M., & Niazi, F. (2015). Long-term monthly evapotranspiration modeling by several data-driven methods without climatic data. Computers and Electronics in Agriculture, 115, 66–77. https://doi.org/10.1016/j.compag.2015.04.015
  • Liang, S., Nguyen, L., & Jin, F. (2018). A Multi-variable stacked long-short term memory network for wind speed forecasting. 2018 IEEE International Conference on Big Data (Big Data), Seattle, WA, USA.
  • Mahongo, S. B., & Deo, M. C. (2013). Using artificial neural networks to forecast monthly and seasonal sea surface temperature anomalies in the western Indian Ocean. International Journal of Ocean and Climate Systems, 4(2), 133–150. https://doi.org/10.1260/1759-3131.4.2.133
  • Mansouri, I., Ozbakkaloglu, T., Kisi, O., & Xie, T. (2016). Predicting behavior of FRP-confined concrete using neuro fuzzy, neural network, multivariate adaptive regression splines and M5 model tree techniques. Materials and Structures, 49, 4319–4334. 10.1617/s11527-015-0790-4
  • Mashaly, A. F., & Alazba, A. A. (2017). Membership function comparative investigation on productivity forecasting of solar still using adaptive neuro-fuzzy inference system approach. Environmental Progress and Sustainable Energy, 37(1), 249–259. https://doi.org/10.1002/ep.12664
  • Mathworks. Long short-term memory networks. (2020). https://www.mathworks.com/help/deeplearning/ug/long-short-term-memory-networks.html. Accessed 06.10.2024.
  • Morse, W. L. (1970). Stream temperature prediction model. Water Resources Research, 6(1), 290–302. https://doi.org/10.1029/WR006i001p00290
  • Patil, K., & Deo, M. C. (2017). Prediction of daily sea surface temperature using efficient neural networks. Ocean Dynamics, 67(3-4), 357–368. 10.1007/s10236-017-1032-9
  • Reddy, K. Y., & Krishna, K. V. S. G. M. (2023). Vehicular pollution prediction using HWTO‐ANFIS model in urban areas of Hyderabad City. Environmental Progress and Sustainable Energy, 42(4). https://doi.org/10.1002/ep.14082
  • Saghafi, H., & Arabloo, M. (2017). Estimation of carbon dioxide equilibrium adsorption isotherms using adaptive neuro-fuzzy inference systems (ANFIS) and regression models. Environmental Progress and Sustainable Energy, 36(5), 1374–1382. https://doi.org/10.1002/ep.12581
  • Sharma, V., Dhanya, J., Gade, M., & Sivasubramonian, J. (2023). New generalized ANN-based hybrid broadband response spectra generator using physics-based simulations. Natural Hazards, 116, 1879–1901. https://doi.org/10.1007/s11069-022-05746-5
  • Sinokrot, B. A., & Stefan, H. G. (1993). Stream temperature dynamics: Measurements and modeling. Water Resources Research, 29(7), 2299–2312. https://doi.org/10.1029/93WR00540
  • Şişman, E. (2019). Trend analysis for the cooling period for sea water temperatures in Aegean and Mediterranean coasts. Journal of Natural Hazards and Environment, 5(2), 291–304. https://doi.org/10.21324/dacd.492730
  • Tangang, F. T., Hsieh, W. W., & Tang, B. (1997). Forecasting the equatorial Pacific sea surface temperatures by neural network models. Climate Dynamics, 13, 135–147. 10.1007/s003820050156
  • Tanvir, M. S., & Mujtaba, I. M. (2006). Neural network based correlations for estimating temperature elevation for seawater in MSF desalination process. Desalination, 195(1-3), 251–272. https://doi.org/10.1016/j.desal.2005.11.013
  • Webb, B. W., & Zhang, Y. (1998). Spatial and seasonal variability in the components of the river heat budget. Hydrological Processes, 11(1), 79–101. https://doi.org/10.1002/(SICI)1099-1085(199701)11:1<79::AID-HYP404>3.0.CO;2-N
  • Wu, A., Hsieh, W. W., & Tang, B. (2006). Neural network forecasts of the tropical Pacific sea surface temperatures. Neural Networks, 19(2), 145–154. https://doi.org/10.1016/j.neunet.2006.01.004
  • Yücel, İ., Önen, A., Yılmaz, & K. K. (2016). Bir taşkın tahmin sisteminin değerlendirilmesi: Nümerik hava tahmin modeli, veri asimilasyonu ve uydu yağışlarının kullanımı. Dicle University, Engineering Faculty, Journal of Engineering, 7, 201–216. https://hdl.handle.net/11511/74347
There are 33 citations in total.

Details

Primary Language English
Subjects Mechanical Engineering (Other)
Journal Section Mechanical Engineering
Authors

Akın İlhan 0000-0003-3590-5291

Sergen Tümse 0000-0003-4764-747X

Mehmet Bilgili 0000-0002-5339-6120

Alper Yıldırım 0000-0003-2626-1666

Beşir Şahin 0000-0003-0671-0890

Publication Date March 3, 2025
Submission Date October 6, 2024
Acceptance Date February 22, 2025
Published in Issue Year 2025Volume: 28 Issue: 1

Cite

APA İlhan, A., Tümse, S., Bilgili, M., Yıldırım, A., et al. (2025). LSTM AND ANFIS MACHINE LEARNING ALGORITHMS IN ESTIMATING THE SEA WATER TEMPERATURE IN TÜRKİYE AT VARIOUS SEA LOCATIONS. Kahramanmaraş Sütçü İmam Üniversitesi Mühendislik Bilimleri Dergisi, 28(1), 322-333.
 Download Cover Image