Research Article
BibTex RIS Cite

Uzun Kısa Süre Bellek (LSTM) ile Toprak Sıcaklığının Tahmini

Year 2022, Volume: 9 Issue: 3, 779 - 785, 23.07.2022
https://doi.org/10.30910/turkjans.1101753

Abstract

Toprak sıcaklığı, toprağın birçok özelliğini etkilediği gibi bitki gelişimi süreçlerinde de önemli düzeyde etki yapmaktadır. Toprak sıcaklığının bilinmesi ve doğru tahmini hem toprak yönetimi hem de bitkisel üretim için önem arzetmektedir. Özelliklede tarıma dayalı ekonomileriyle öne çıkan ülkeler için sıcaklık tahminlerinin doğrululuğu çok önemlidir. Bu yüzden son yıllarda toprak sıcaklık tahminlerinde farklı yapay zeka yöntemleri kullanılmaya başlanmıştır. Derin öğrenme yöntemleri yüksek tahmin doğruluğu elde etmede bu konuda öncülük etmektedir. Bu çalışmada toprak sıcaklığı tahmininde etkin bir model oluşturmak için derin öğrenme (DL) alt mimarisi olan Uzun Kısa Süreli Bellek (LSTM) ağı önerilmiştir. Çalışmada kullanılan veriler Bingöl İline ait 2013-2021 yıllarına ait 50 cm derinlikteki günlük toprak sıcaklıklarıdır. Çalışma kapsamındaki veri setinin %80’ni önerilen LSTM modelinin eğitimi için kullanılmıştır. Geriye kalan %20’si ise model tarafından tahmin edilerek model başarısı ölçülmüştür. Eğitilen LSTM modelinin yapmış olduğu tahmin sonucundaki RMSE değeri 1.25 olarak elde edilmiştir. Önerilen modelin tahmin doğruluğunun yüksek olması, sıcaklık verileri tahmini çalışmalarında bu modelin başarılı bir şekilde uygulanabileceğini göstermiştir.

Thanks

Bingöl İli Meteoroloji Müdürlüğü’nün bilimsel çalışmaları destek amacıyla, bu çalışma için sunmuş olduğu meteorolojik bilgiler için teşekkür ediyoruz.

References

  • Akyüz AÖ, Kumaş K, Ayan M, Güngör A (2020) Antalya İli Meteorolojik Verileri Yardımıyla Hava Sıcaklığının Yapay Sinir Ağları Metodu ile Tahmini. Gümüşhane Üniversitesi Fen Bilimleri Enstitüsü Dergisi 10: 146-154.
  • Aslay F, Üstün Ö (2013) Meteorolojik Parametreler Kullanılarak Yapay Sİnir Ağları ile Toprak Sıcaklığının Tahmini. Politeknik Dergisi 16: 139-145. Avcı V, Esen F, Kıranşan K (2018) Bingöl İlinin Fiziki Çoğrafya Özellikleri. The Journal of Bingöl Studies 4.
  • Bond-Lamberty B, Wang C, Gower ST (2005) Spatiotemporal measurement and modeling of stand-level boreal forest soil temperatures. Agricultural and Forest Meteorology 131: 27-40.
  • Buckman HO, Brady NC (1922) The nature and properties of soils. Macmillan.
  • Demiralay İ (1993) Toprak fiziksel analizleri. Atatürk Üniversitesi Ziraat Fakültesi Yayınları 143: 13-19.
  • Demirezen S (2020) Türkiye'de Gün Öncesi Piyasası İçin Elektrik Fiyatlarının Tahmini.
  • Dinç U, Şenol S (1998) Toprak etüd ve haritalama ders kitabı. Çukurova Üniversitesi Ziraat Fakültesi Genel Yayın.
  • Ekberli İ, Gülser C, Özdemir N (2017) Farklı toprak derinliklerindeki sıcaklığın tahmininde parabolik fonksiyonun kullanımı. Toprak Bilimi ve Bitki Besleme Dergisi 5: 34-38.
  • Ekberli İ, Sarılar Y (2015) Toprak sıcaklığı ve ısısal yayınımın belirlenmesi. Anadolu Tarım Bilimleri Dergisi 30: 74-85.
  • Filipović N, Brdar S, Mimić G, Marko O, Crnojević V (2022) Regional soil moisture prediction system based on Long Short-Term Memory network. Biosystems Engineering 213: 30-38.
  • Fischer T, Krauss C (2018) Deep learning with long short-term memory networks for financial market predictions. European Journal of Operational Research 270: 654-669.
  • Gao Z, Bian L, Hu Y, Wang L, Fan J (2007) Determination of soil temperature in an arid region. Journal of arid environments 71: 157-168.
  • Guntiñas ME, Leirós M, Trasar-Cepeda C, Gil-Sotres F (2012) Effects of moisture and temperature on net soil nitrogen mineralization: A laboratory study. European Journal of Soil Biology 48: 73-80.
  • Guo J, Yang Y, Chen G, Xie J, Yang Z (2014) Carbon mineralization of Chinese fir (Cunninghamia lanceolata) soils under different temperature and humidity conditions. Acta Ecologica Sinica 34: 66-71.
  • Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural computation 9: 1735-1780.
  • İnik Ö, Turan B (2018) Classification of animals with different deep learning models. Journal of New Results in Science 7: 9-16.
  • Inik Ö, Ülker E (2022) Optimization of deep learning based segmentation method. Soft Computing: 1-16.
  • Kara A (2019) Global Solar Irradiance Time Series Prediction Using Long Short-Term Memory Network. Gazi Üniversitesi Fen Bilimleri Dergisi, Part C: Tasarım ve Teknoloji, vol 4: 7.
  • Kreuzer D, Munz M, Schlüter S (2020) Short-term temperature forecasts using a convolutional neural network—An application to different weather stations in Germany. Machine Learning with Applications 2: 100007.
  • Li L-J, You M-Y, Shi H-A, Ding X-L, Qiao Y-F, Han X-Z (2013) Soil CO2 emissions from a cultivated Mollisol: Effects of organic amendments, soil temperature, and moisture. European Journal of Soil Biology 55: 83-90.
  • Li Q, Zhu Y, Shangguan W, Wang X, Li L, Yu F (2022) An attention-aware LSTM model for soil moisture and soil temperature prediction. Geoderma 409: 115651.
  • Liu H, Yang Y, Wan X, Cui J, Zhang F, Cai T (2021) Prediction of soil moisture and temperature based on deep learning. 2021 IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA). IEEE.
  • Migała K, Wojtuń B, Szymański W, Muskała P (2014) Soil moisture and temperature variation under different types of tundra vegetation during the growing season: A case study from the Fuglebekken catchment, SW Spitsbergen. Catena 116: 10-18.
  • Sagheer A, Kotb M (2019) Time series forecasting of petroleum production using deep LSTM recurrent networks. Neurocomputing 323: 203-213.
  • Schütt M, Borken W, Spott O, Stange CF, Matzner E (2014) Temperature sensitivity of C and N mineralization in temperate forest soils at low temperatures. Soil Biology and Biochemistry 69: 320-327.
  • Sevinç A, Kaya B (2021) Derin Öğrenme Yöntemleri ile Sıcaklık Tahmini: Diyarbakır İli Örneği. Computer Science: 217-225.
  • Seyfried M, Flerchinger G, Murdock M, Hanson C, Van Vactor S (2001) Long‐Term Soil Temperature Database, Reynolds Creek Experimental Watershed, Idaho, United States. Water Resources Research 37: 2843-2846.
  • Süzen A, Kayaalp K (2018) Derin Öğrenme Yöntemleri İle Sıcaklık Tahmini: Isparta İli Örneği. International Academic Research Congress INES.
  • Tenge AJ, Kaihura F, Lal R, Singh B (1998) Diurnal soil temperature fluctuations for different erosion classes of an oxisol at Mlingano, Tanzania. Soil and Tillage Research 49: 211-217.
  • Wang C, Wan S, Xing X, Zhang L, Han X (2006) Temperature and soil moisture interactively affected soil net N mineralization in temperate grassland in Northern China. Soil Biology and Biochemistry 38: 1101-1110.
  • Xiao Y, Yin Y (2019) Hybrid LSTM neural network for short-term traffic flow prediction. Information 10: 105.

Soil Temperature Prediction with Long Short Term Memory (LSTM)

Year 2022, Volume: 9 Issue: 3, 779 - 785, 23.07.2022
https://doi.org/10.30910/turkjans.1101753

Abstract

Soil temperature not only affects many soil properties, but also has a significant effect on plant development. Knowing and correct estimation of soil temperature is important for both soil management and crop production. The accuracy of temperature forecasts is very important, especially for the countries that stand out with their agriculture-based economies. Therefore, in recent years, different artificial intelligence methods have been used in soil temperature predictions. Deep learning methods lead the way in achieving high prediction accuracy. In this study, a Long Short-Term Memory (LSTM) network, which is a deep learning (DL) sub-architecture, is proposed to create an effective model for soil temperature prediction. The data used in the study are the daily soil temperatures at a depth of 50 cm for the years 2013-2021 of Bingöl province. For the training of the proposed LSTM model, 89% of the data set within the scope of the study was used, and. The remaining 11% was estimated by the model for assessing model success. The RMSE value as a result of the estimation made by the trained LSTM model was obtained as 1,25. The high estimation accuracy of the proposed model showed that this model could be successfully applied in temperature data estimation studies.

References

  • Akyüz AÖ, Kumaş K, Ayan M, Güngör A (2020) Antalya İli Meteorolojik Verileri Yardımıyla Hava Sıcaklığının Yapay Sinir Ağları Metodu ile Tahmini. Gümüşhane Üniversitesi Fen Bilimleri Enstitüsü Dergisi 10: 146-154.
  • Aslay F, Üstün Ö (2013) Meteorolojik Parametreler Kullanılarak Yapay Sİnir Ağları ile Toprak Sıcaklığının Tahmini. Politeknik Dergisi 16: 139-145. Avcı V, Esen F, Kıranşan K (2018) Bingöl İlinin Fiziki Çoğrafya Özellikleri. The Journal of Bingöl Studies 4.
  • Bond-Lamberty B, Wang C, Gower ST (2005) Spatiotemporal measurement and modeling of stand-level boreal forest soil temperatures. Agricultural and Forest Meteorology 131: 27-40.
  • Buckman HO, Brady NC (1922) The nature and properties of soils. Macmillan.
  • Demiralay İ (1993) Toprak fiziksel analizleri. Atatürk Üniversitesi Ziraat Fakültesi Yayınları 143: 13-19.
  • Demirezen S (2020) Türkiye'de Gün Öncesi Piyasası İçin Elektrik Fiyatlarının Tahmini.
  • Dinç U, Şenol S (1998) Toprak etüd ve haritalama ders kitabı. Çukurova Üniversitesi Ziraat Fakültesi Genel Yayın.
  • Ekberli İ, Gülser C, Özdemir N (2017) Farklı toprak derinliklerindeki sıcaklığın tahmininde parabolik fonksiyonun kullanımı. Toprak Bilimi ve Bitki Besleme Dergisi 5: 34-38.
  • Ekberli İ, Sarılar Y (2015) Toprak sıcaklığı ve ısısal yayınımın belirlenmesi. Anadolu Tarım Bilimleri Dergisi 30: 74-85.
  • Filipović N, Brdar S, Mimić G, Marko O, Crnojević V (2022) Regional soil moisture prediction system based on Long Short-Term Memory network. Biosystems Engineering 213: 30-38.
  • Fischer T, Krauss C (2018) Deep learning with long short-term memory networks for financial market predictions. European Journal of Operational Research 270: 654-669.
  • Gao Z, Bian L, Hu Y, Wang L, Fan J (2007) Determination of soil temperature in an arid region. Journal of arid environments 71: 157-168.
  • Guntiñas ME, Leirós M, Trasar-Cepeda C, Gil-Sotres F (2012) Effects of moisture and temperature on net soil nitrogen mineralization: A laboratory study. European Journal of Soil Biology 48: 73-80.
  • Guo J, Yang Y, Chen G, Xie J, Yang Z (2014) Carbon mineralization of Chinese fir (Cunninghamia lanceolata) soils under different temperature and humidity conditions. Acta Ecologica Sinica 34: 66-71.
  • Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural computation 9: 1735-1780.
  • İnik Ö, Turan B (2018) Classification of animals with different deep learning models. Journal of New Results in Science 7: 9-16.
  • Inik Ö, Ülker E (2022) Optimization of deep learning based segmentation method. Soft Computing: 1-16.
  • Kara A (2019) Global Solar Irradiance Time Series Prediction Using Long Short-Term Memory Network. Gazi Üniversitesi Fen Bilimleri Dergisi, Part C: Tasarım ve Teknoloji, vol 4: 7.
  • Kreuzer D, Munz M, Schlüter S (2020) Short-term temperature forecasts using a convolutional neural network—An application to different weather stations in Germany. Machine Learning with Applications 2: 100007.
  • Li L-J, You M-Y, Shi H-A, Ding X-L, Qiao Y-F, Han X-Z (2013) Soil CO2 emissions from a cultivated Mollisol: Effects of organic amendments, soil temperature, and moisture. European Journal of Soil Biology 55: 83-90.
  • Li Q, Zhu Y, Shangguan W, Wang X, Li L, Yu F (2022) An attention-aware LSTM model for soil moisture and soil temperature prediction. Geoderma 409: 115651.
  • Liu H, Yang Y, Wan X, Cui J, Zhang F, Cai T (2021) Prediction of soil moisture and temperature based on deep learning. 2021 IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA). IEEE.
  • Migała K, Wojtuń B, Szymański W, Muskała P (2014) Soil moisture and temperature variation under different types of tundra vegetation during the growing season: A case study from the Fuglebekken catchment, SW Spitsbergen. Catena 116: 10-18.
  • Sagheer A, Kotb M (2019) Time series forecasting of petroleum production using deep LSTM recurrent networks. Neurocomputing 323: 203-213.
  • Schütt M, Borken W, Spott O, Stange CF, Matzner E (2014) Temperature sensitivity of C and N mineralization in temperate forest soils at low temperatures. Soil Biology and Biochemistry 69: 320-327.
  • Sevinç A, Kaya B (2021) Derin Öğrenme Yöntemleri ile Sıcaklık Tahmini: Diyarbakır İli Örneği. Computer Science: 217-225.
  • Seyfried M, Flerchinger G, Murdock M, Hanson C, Van Vactor S (2001) Long‐Term Soil Temperature Database, Reynolds Creek Experimental Watershed, Idaho, United States. Water Resources Research 37: 2843-2846.
  • Süzen A, Kayaalp K (2018) Derin Öğrenme Yöntemleri İle Sıcaklık Tahmini: Isparta İli Örneği. International Academic Research Congress INES.
  • Tenge AJ, Kaihura F, Lal R, Singh B (1998) Diurnal soil temperature fluctuations for different erosion classes of an oxisol at Mlingano, Tanzania. Soil and Tillage Research 49: 211-217.
  • Wang C, Wan S, Xing X, Zhang L, Han X (2006) Temperature and soil moisture interactively affected soil net N mineralization in temperate grassland in Northern China. Soil Biology and Biochemistry 38: 1101-1110.
  • Xiao Y, Yin Y (2019) Hybrid LSTM neural network for short-term traffic flow prediction. Information 10: 105.
There are 31 citations in total.

Details

Primary Language English
Subjects Agricultural, Veterinary and Food Sciences
Journal Section Research Articles
Authors

Orhan İnik 0000-0003-1473-1392

Özkan İnik 0000-0003-4728-8438

Taşkın Öztaş 0000-0001-5001-103X

Alaaddin Yuksel 0000-0003-4760-1092

Publication Date July 23, 2022
Submission Date April 12, 2022
Published in Issue Year 2022 Volume: 9 Issue: 3

Cite

APA İnik, O., İnik, Ö., Öztaş, T., Yuksel, A. (2022). Soil Temperature Prediction with Long Short Term Memory (LSTM). Türk Tarım Ve Doğa Bilimleri Dergisi, 9(3), 779-785. https://doi.org/10.30910/turkjans.1101753