Transformatör modelleri ile zaman serisi analizi tabanlı toprak sıcaklığı tahmini

Yıl 2026, Cilt: 41 Sayı: 1 , 579 - 594 , 31.03.2026

Muhammet Mücahit Enes Yurtsever , Zeynep Hilal Kilimci , Ayhan Küçükmanisa

https://doi.org/10.17341/gazimmfd.1662870

https://izlik.org/JA96XG59XN

Öz

Toprak sıcaklığı; buzulların enerji dengesi, kütle dengesi, ekolojik istikrar ve tarımsal verimlilik üzerinde belirleyici bir değişken olup, karmaşık ve doğrusal olmayan etkileşimler nedeniyle doğru biçimde tahmin edilmesi güçtür. Mevcut yöntemler bu karmaşıklıkları yeterince temsil edemediğinden, daha gelişmiş modellere ihtiyaç duyulmaktadır. Bu çalışma, toprak sıcaklığı tahmini için transformatör tabanlı yeni bir çerçeve önermektedir. Transformatör mimarilerinin uzun vadeli bağımlılıkları ve zamansal örüntüleri yakalama konusundaki üstün yeteneklerinden yararlanılarak çevresel veriler üzerinde yüksek doğruluklu bir tahmin modeli geliştirilmiştir. Modelin geliştirilmesi ve değerlendirilmesi için altı farklı FLUXNET istasyonundan elde edilen veriler kullanılmıştır. Karşılaştırmalı analizler; ağaç tabanlı yöntemler, klasik derin öğrenme mimarileri ve beş gelişmiş transformatör modeli (Vanilla Transformer, Informer, Autoformer, Reformer ve ETSformer) ile gerçekleştirilmiştir. Sonuçlar, transformatör tabanlı modellerin tahmin doğruluğu bakımından geleneksel yaklaşımlara kıyasla belirgin üstünlük sağladığını göstermektedir. Ayrıca önerilen yöntemin farklı çevresel koşullarda tutarlı, sağlam ve genelleştirilebilir performans sergilediği doğrulanmıştır. Bulgular, transformatör modellerinin çevresel tahmin problemlerinde, özellikle toprak sıcaklığı öngörüsünde, yüksek potansiyele sahip olduğunu ortaya koymakta hem bilimsel anlayışa katkı sağlamakta hem de ölçeklenebilir, güvenilir ve pratik uygulamalara uygun bir araç sunmaktadır.

Anahtar Kelimeler

Derin öğrenme , FLUXNET , Toprak sıcaklığı tahmini , Transformatör modeller , Zaman serisi kestirimi

Kaynakça

• 1. Adair E. C., Parton W. J., Del Grosso S. J., Silver W. L., Harmon M. E., Hall S. A., Burke I. C., Hart S. C., Simple three-pool model accurately describes patterns of long-term litter decomposition in diverse climates, Global Change Biology, 14 (11), 2636–2660, 2008.
• 2. Bykova O., Chuine I., Morin X., Higgins S. I., Temperature dependence of the reproduction niche and its relevance for plant species distributions, Journal of Biogeography, 39 (12), 2191–2200, 2012.
• 3. Fabris L., Buddendorf W. B., Soulsby C., Assessing the seasonal effect of flow regimes on availability of Atlantic salmon fry habitat in an upland Scottish stream, Science of The Total Environment, 696, 133857, 2019.
• 4. Davidson E. A., Janssens I. A., Temperature sensitivity of soil carbon decomposition and feedbacks to climate change, Nature, 440 (7081), 165–173, 2006.
• 5. Attri I., Awasthi L. K., Sharma T. P., Rathee P., A review of deep learning techniques used in agriculture, Ecological Informatics, 102217, 2023.
• 6. Khan A., Vibhute A. D., Mali S., Patil C. H., A systematic review on hyperspectral imaging technology with a machine and deep learning methodology for agricultural applications, Ecological Informatics, 69, 101678, 2022.
• 7. Zhang Z., Li Y., Williams R. A., Chen Y., Peng R., Liu X., Qi Y., Wang Z., Responses of soil respiration and its sensitivities to temperature and precipitation: A meta-analysis, Ecological Informatics, 102057, 2023.
• 8. Seifi A., Ehteram M., Nayebloei F., Soroush F., Gharabaghi B., Torabi Haghighi A., GLUE uncertainty analysis of hybrid models for predicting hourly soil temperature and application wavelet coherence analysis for correlation with meteorological variables, Soft Computing, 25, 10723–10748, 2021.
• 9. Singhal M., Gairola A. C., Singh N., Artificial neural network-assisted glacier forefield soil temperature retrieval from temperature measurements, Theoretical and Applied Climatology, 143, 1157–1166, 2021.
• 10. Bayatvarkeshi M., Bhagat S. K., Mohammadi K., Kisi O., Farahani M., Hasani A., Deo R., Yaseen Z. M., Modeling soil temperature using air temperature features in diverse climatic conditions with complementary machine learning models, Computers and Electronics in Agriculture, 185, 106158, 2021.
• 11. Malik A., Tikhamarine Y., Sihag P., Shahid S., Jamei M., Karbasi M., Predicting daily soil temperature at multiple depths using hybrid machine learning models for a semi-arid region in Punjab, India, Environmental Science and Pollution Research, 29 (47), 71270–71289, 2022.
• 12. Guleryuz D., Estimation of soil temperatures with machine learning algorithms—Giresun and Bayburt stations in Turkey, Theoretical and Applied Climatology, 147 (1-2), 109–125, 2022.
• 13. Li Q., Zhu Y., Shangguan W., Wang X., Li L., Yu F., An attention-aware LSTM model for soil moisture and soil temperature prediction, Geoderma, 409, 115651, 2022.
• 14. Wang Y., Zhuang D., Xu J., Wang Y., Soil Temperature Prediction Based on 1D-CNN-MLP Neural Network Model, Journal of the ASABE, 0, 2023.
• 15. Orhan İ., Özkan İ., Öztaş T., Yüksel A., Soil Temperature Prediction with Long Short Term Memory (LSTM), Türk Tarım ve Doğa Bilimleri Dergisi, 9 (3), 779–785, 2022.
• 16. Küçük C., Birant D., Taşer P. Y., A Novel Machine Learning Approach: Soil Temperature Ordinal Classification (STOC), Journal of Agricultural Sciences, 28 (4), 635–649, 2022.
• 17. Imanian H., Shirkhani H., Mohammadian A., Hiedra Cobo J., Payeur P., Spatial Interpolation of Soil Temperature and Water Content in the Land-Water Interface Using Artificial Intelligence, Water, 15 (3), 473, 2023.
• 18. Bilgili M., Şaban Ü., Şekertekin A., Gürlek C., Machine Learning Approaches for One-Day Ahead Soil Temperature Forecasting, Journal of Agricultural Sciences, 29 (1), 221–238, 2023.
• 19. Tüysüzoğlu G., Birant D., Kıranoğlu V., Soil Temperature Prediction via Self-Training: Izmir Case, Journal of Agricultural Sciences, 28 (1), 47–62, 2022.
• 20. Imanian H., Hiedra Cobo J., Payeur P., Shirkhani H., Mohammadian A., A Comprehensive Study of Artificial Intelligence Applications for Soil Temperature Prediction in Ordinary Climate Conditions and Extremely Hot Events, Sustainability, 14 (13), 8065, 2022.
• 21. Khan M. S., Ivoke J., Nobahar M., Amini F., Artificial Neural Network (ANN) based Soil Temperature model of Highly Plastic Clay, Geomechanics and Geoengineering, 17 (4), 1230–1246, 2022.
• 22. Tuysuzoglu G., Birant D., Kıranoğlu V., Multi-view multi-depth soil temperature prediction (MV-MD-STP): a new approach using machine learning and time series methods, International Journal of Intelligent Engineering Informatics, 10 (1), 74–104, 2022.
• 23. Wang X., Li W., Li Q., A new embedded estimation model for soil temperature prediction, Scientific Programming, 2021, 1–16, 2021.
• 24. Abimbola O. P., Meyer G. E., Mittelstet A. R., Rudnick D. R., Franz T. E., Knowledge-guided machine learning for improving daily soil temperature prediction across the United States, Vadose Zone Journal, 20 (5), e20151, 2021.
• 25. Pastorello G., Trotta C., Canfora E., Chu H., Christianson D., Cheah Y.-W., ..., Amiro B., The FLUXNET2015 dataset and the ONEFlux processing pipeline for eddy covariance data, Scientific Data, 7 (1), 1-27, 2020.
• 26. Li Q., Zhu Y., Shangguan W., Wang X., Li L., Yu F., An attention-aware LSTM model for soil moisture and soil temperature prediction, Geoderma, 409, 115651, 2022.
• 27. Vaswani A., Shazeer N., Parmar N., Uszkoreit J., Jones L., Gomez A. N., Kaiser Ł., Polosukhin I., Attention is all you need, Advances in Neural Information Processing Systems, 30, 2017.
• 28. Kitaev N., Kaiser Ł., Levskaya A., Reformer: The efficient transformer, arXiv preprint arXiv:2001.04451, 2020.
• 29. Gomez A. N., Ren M., Urtasun R., Grosse R. B., The reversible residual network: Backpropagation without storing activations, Advances in Neural Information Processing Systems, 30, 2017.
• 30. Zhou H., Zhang S., Peng J., Zhang S., Li J., Xiong H., Zhang W., Informer: Beyond efficient transformer for long sequence time-series forecasting, Proceedings of the AAAI Conference on Artificial Intelligence, 35 (12), 11106–11115, 2021.
• 31. Chatfield C., The analysis of time series: An introduction, Chapman and Hall/CRC, 2003.
• 32. Papoulis A., Unnikrishna Pillai S., Probability, random variables and stochastic processes, McGraw-Hill, 2002.
• 33. Woo G., Liu C., Sahoo D., Kumar A., Hoi S., Etsformer: Exponential smoothing transformers for time-series forecasting, arXiv preprint arXiv:2202.01381, 2022.
• 34. Holt C. C., Forecasting seasonals and trends by exponentially weighted moving averages, International Journal of Forecasting, 20 (1), 5–10, 2004.
• 35. Hao H., Yu F., Li Q., Soil temperature prediction using convolutional neural network based on ensemble empirical mode decomposition, IEEE Access, 9, 4084–4096, 2021.
• 36. Özdoğan İ., Boran F. E., Yıldız O., Fuzzy linguistic summarization of time series with interval type-2 fuzzy c-means: BIST100 sample stock application, Journal of the Faculty of Engineering and Architecture of Gazi University, 40 (3), 1659-1672, 2025.
• 37. Arseven B., Çınar S. M., Solar radiation prediction with extraterrestrial radiation supported multivariate Ridge and Lasso regression methods, Journal of the Faculty of Engineering and Architecture of Gazi University, 40 (3), 1745-1756, 2025.
• 38. Nalkıran M., Altuntaş S., Prediction of heat transfer value using an internet of things and machine learning-based approach in the automotive industry, Journal of the Faculty of Engineering and Architecture of Gazi University, 40 (2), 937-950, 2025.
• 39. Akbulut U., Çifçi M. A., İşler B., Aslan Z., Comparison of different techniques in river flow prediction using machine learning methods, Journal of the Faculty of Engineering and Architecture of Gazi University, 40 (1), 467-486, 2025.