Araştırma Makalesi
BibTex RIS Kaynak Göster

Yapay Zeka Kullanılarak Orta-Güney Anadolu Bölgesi Tarım Alanlarına Ait Topraklarının Toplam Mikro Element ve Toplam Ağır Metal İçeriklerinin Tahmin Edilmesi: Bir Pilot Çalışma

Yıl 2025, Cilt: 13 Sayı: 1, 12 - 31, 07.07.2025
https://doi.org/10.33202/comuagri.1586063

Öz

Mutlak gerekli besin elementlerinden olan mikro besin element içerikleri ve doğal oluşum veya antropojenik etkiler sonucunda topraklarda bulunan ağır metal içeriklerinin Türkiye'nin Orta-Güney Anadolu Bölgesi'nden alınan toprak örnekleri üzerinde toplam mikro element ve toplam ağır metal konsantrasyonlarının tahmini, yapay zekâ modelleri kullanılarak yapılmıştır. Topraktan elde edilen mikro element ve ağır metal verilerinin doğru şekilde tahmin edilmesi, tarımsal üretkenlik ve çevre sağlığı açısından büyük önem taşımaktadır. Toplam 62 toprak numunesi üzerinde Bor (B), Demir (Fe), Çinko (Zn), Mangan (Mn), Bakır (Cu), Kadmiyum (Cd), Krom (Cr), Nikel (Ni) ve Kurşun (Pb) elementleri analiz edilmiştir. Yapay zekâ modelleri olarak Random Forest (RF), Gradient Boosting (GB) ve Support Vector Regressor (SVR) kullanılmıştır. Modellerin performansı, Ortalama Mutlak Hata (MAE), Ortalama Kare Hatası (MSE) ve R² skorları ile değerlendirilmiştir. En iyi performans, Bor (B) ve Bakır (Cu) elementleri için elde edilmiştir. Bor (B) tahmininde, GB modeli en iyi sonuçları vermiştir (MAE: 4.89, MSE: 28.01, R²: 0.55). Bakır (Cu) tahmininde ise RF modeli (MAE: 3.20, MSE: 16.80 ve R²: 0.75) en yüksek performansı sergilemiştir. Sonuçlar, kullanılan yapay zekâ modellerinin toprak numunelerinden mikro element ve ağır metal tahmininde umut verici bir potansiyel taşıdığını göstermektedir.

Etik Beyan

Çalışmamızda herhangi bir etik unsuru bulunmamaktadır.

Destekleyen Kurum

Selçuk üniversitesi ve YÖK

Proje Numarası

MEV-2017-36, 18401058

Teşekkür

Selçuk üniversitesi ve YÖK' e bu çalışmaya fon desteği sağladığı için teşekkür ederiz.

Kaynakça

  • Awad, M., Khanna, R., 2015. Support vector regression. In: Efficient learning machines: Theories, concepts, and applications for engineers and system designers, pp. 67–80.
  • Bergstra, J., Bengio, Y., 2012. Random search for hyper-parameter optimization. J. Mach. Learn. Res. 13 (2). Breiman, L., 2001. Random forests. Mach. Learn. 45: 5–32.
  • Gee, G.W., 1986. Particle size analysis. In: Methods of soil analysis/ASA and SSSA.
  • Geman, S., Bienenstock, E., Doursat, R., 1992. Neural networks and the bias/variance dilemma. Neural Comput. 4 (1): 1–58.
  • Gezgin, S., Dursun, N., Hamurcu, M., Harmankaya, M., Önder, M., Sade, B., 2002 Boron content of cultivated soils in Central-Southern Anatolia and its relationship with soil properties and irrigation water quality. Boron in plant and animal nutrition. 391-400.
  • Gholamy, A., Kreinovich, V., Kosheleva, O., 2018. Why 70/30 or 80/20 relation between training and testing sets: A pedagogical explanation. Int. J. Intell. Technol. Appl. Stat. 11 (2): 105–111.
  • Günal, H., Acir, N., Budak, M., 2012. Heavy metal variability of a native saline pasture in arid regions of Central Anatolia. Carpathian Journal of Earth and Environmental Sciences. 7: 183–193.
  • Günal, H., Kılıç, O.M., Ersayın, K., Acir, N., 2022. Land suitability assessment for wheat production using analytical hierarchy process in a semi-arid region of Central Anatolia. Geocarto International. 37: 16418–16436.
  • Hastie, T., Tibshirani, R., Friedman, J.H., 2009. The elements of statistical learning: Data mining, inference, and prediction. Springer.
  • Hızalan, E., Ünal, H., 1966. Topraklarda önemli kimyasal analizler. AÜ Ziraat Fakültesi Yayınları. 278: 5–7.
  • Jackson, M., 1958. Soil chemical analysis. Prentice Hall, Englewood Cliffs, NJ, pp. 183–204.
  • Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., Ye, Q., Liu, T.-Y., 2017. LightGBM: A highly efficient gradient boosting decision tree. Adv. Neural Inf. Process. Syst. 30.
  • Khosravi, V., Ardejani, F.D., Yousefi, S., Aryafar, A., 2018. Monitoring soil lead and zinc contents via combination of spectroscopy with extreme learning machine and other data mining methods. Geoderma. 318: 29–41.
  • Koç, Ş., 1987. Karadağ (Karaman) Volkanitlerinin Jeolojisi Ve “Base Surge” Oluşukları. Gazi Üniversitesi Mühendislik Mimarlık Fakültesi Dergisi. 2.
  • Kohavi, R., 1995. A study of cross-validation and bootstrap for accuracy estimation and model selection. In: Proceedings of IJCAI, Montreal, Canada, pp. 1137–1145.
  • Lahn, E., 1949. On the geology of Central Anatolia. Türkiye Jeoloji Bülteni. 2: 90–107.
  • Luce, M.S., Ziadi, N., Gagnon, B., Karam, A., 2017. Visible near-infrared reflectance spectroscopy prediction of soil heavy metal concentrations in paper mill biosolid- and liming by-product-amended agricultural soils. Geoderma. 288: 23–36.
  • MGM, 2025. Meteoroloji Genel İklim Verileri. Meteoroloji Genel Müdürlüğü, Ankara, Turkey.
  • Munnaf, M.A., Mouazen, A.M., 2021. Development of a soil fertility index using on-line Vis-NIR spectroscopy. Comput. Electron. Agric. 188: 106341.
  • Nie, S., Chen, H., Sun, X., An, Y., 2024. Spatial distribution prediction of soil heavy metals based on random forest model. Sustainability. 16 (11): 4358.
  • Ozyazici, M.A., Dengiz, O., Ozyazici, G., 2017 Spatial distribution of heavy metals density in cultivated soils of Central and East Parts of Black Sea Region in Turkey. Eurasian Journal of Soil Science. 6: 197-205.
  • Shi, S., Hou, M., Gu, Z., Jiang, C., Zhang, W., Hou, M., Li, C., Xi, Z., 2022. Estimation of heavy metal content in soil based on machine learning models. Land. 11 (7): 1037.
  • Sigrist, F., 2021. Gradient and Newton boosting for classification and regression. Expert Systems With Applications. 167: 114080.
  • Smith, H.W., Weldon, M.D., 1941. A comparison of some methods for the determination of soil organic matter.
  • T.O.B., 2010. Toprak Kirlilik Parametreleri Yönetmeliği.
  • Taylor, S., 1964. Abundance of chemical elements in the continental crust: A new table. Geochimica et Cosmochimica Acta. 28: 1273–1285.
  • Taylor, S., McLennan, S., 1985. The continental crust: Its composition and evolution. Geoscience Texts. 312.
  • Wang, Y., Zhao, Y., Xu, S., 2022. Application of VNIR and machine learning technologies to predict heavy metals in soil and pollution indices in mining areas. Journal of Soils and Sediments. 22 (10): 2777–2791.

AI-Based Prediction of Microelement and Heavy Metal Contents in Central-Southern Anatolian Soils: A Pilot Study

Yıl 2025, Cilt: 13 Sayı: 1, 12 - 31, 07.07.2025
https://doi.org/10.33202/comuagri.1586063

Öz

The estimation of total microelement and heavy metal concentrations in soil samples taken from the Central-Southern Anatolian Region of Turkiye was conducted using artificial intelligence models. The accurate prediction of microelement and heavy metal contents obtained from the soil is of great importance for agricultural productivity and environmental health. A total of 62 soil samples were analyzed for Boron (B), Iron (Fe), Zinc (Zn), Manganese (Mn), Copper (Cu), Cadmium (Cd), Chromium (Cr), Nickel (Ni), and Lead (Pb). The artificial intelligence models used in this study were Random Forest (RF), Gradient Boosting (GB), and Support Vector Regressor (SVR). Model performance was evaluated based on Mean Absolute Error (MAE), Mean Squared Error (MSE), and R² scores. The best performance was achieved for Boron (B) and Copper (Cu). In the case of Boron (B), the GB model provided the best results (MAE: 4.89, MSE: 28.01, R²: 0.55), while the RF model showed the highest performance for Copper (Cu) predictions (MAE: 3.20, MSE: 16.80, R²: 0.75). The results indicate that the artificial intelligence models used in this study hold promising potential for the prediction of microelement and heavy metal concentrations in soil samples.

Proje Numarası

MEV-2017-36, 18401058

Kaynakça

  • Awad, M., Khanna, R., 2015. Support vector regression. In: Efficient learning machines: Theories, concepts, and applications for engineers and system designers, pp. 67–80.
  • Bergstra, J., Bengio, Y., 2012. Random search for hyper-parameter optimization. J. Mach. Learn. Res. 13 (2). Breiman, L., 2001. Random forests. Mach. Learn. 45: 5–32.
  • Gee, G.W., 1986. Particle size analysis. In: Methods of soil analysis/ASA and SSSA.
  • Geman, S., Bienenstock, E., Doursat, R., 1992. Neural networks and the bias/variance dilemma. Neural Comput. 4 (1): 1–58.
  • Gezgin, S., Dursun, N., Hamurcu, M., Harmankaya, M., Önder, M., Sade, B., 2002 Boron content of cultivated soils in Central-Southern Anatolia and its relationship with soil properties and irrigation water quality. Boron in plant and animal nutrition. 391-400.
  • Gholamy, A., Kreinovich, V., Kosheleva, O., 2018. Why 70/30 or 80/20 relation between training and testing sets: A pedagogical explanation. Int. J. Intell. Technol. Appl. Stat. 11 (2): 105–111.
  • Günal, H., Acir, N., Budak, M., 2012. Heavy metal variability of a native saline pasture in arid regions of Central Anatolia. Carpathian Journal of Earth and Environmental Sciences. 7: 183–193.
  • Günal, H., Kılıç, O.M., Ersayın, K., Acir, N., 2022. Land suitability assessment for wheat production using analytical hierarchy process in a semi-arid region of Central Anatolia. Geocarto International. 37: 16418–16436.
  • Hastie, T., Tibshirani, R., Friedman, J.H., 2009. The elements of statistical learning: Data mining, inference, and prediction. Springer.
  • Hızalan, E., Ünal, H., 1966. Topraklarda önemli kimyasal analizler. AÜ Ziraat Fakültesi Yayınları. 278: 5–7.
  • Jackson, M., 1958. Soil chemical analysis. Prentice Hall, Englewood Cliffs, NJ, pp. 183–204.
  • Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., Ye, Q., Liu, T.-Y., 2017. LightGBM: A highly efficient gradient boosting decision tree. Adv. Neural Inf. Process. Syst. 30.
  • Khosravi, V., Ardejani, F.D., Yousefi, S., Aryafar, A., 2018. Monitoring soil lead and zinc contents via combination of spectroscopy with extreme learning machine and other data mining methods. Geoderma. 318: 29–41.
  • Koç, Ş., 1987. Karadağ (Karaman) Volkanitlerinin Jeolojisi Ve “Base Surge” Oluşukları. Gazi Üniversitesi Mühendislik Mimarlık Fakültesi Dergisi. 2.
  • Kohavi, R., 1995. A study of cross-validation and bootstrap for accuracy estimation and model selection. In: Proceedings of IJCAI, Montreal, Canada, pp. 1137–1145.
  • Lahn, E., 1949. On the geology of Central Anatolia. Türkiye Jeoloji Bülteni. 2: 90–107.
  • Luce, M.S., Ziadi, N., Gagnon, B., Karam, A., 2017. Visible near-infrared reflectance spectroscopy prediction of soil heavy metal concentrations in paper mill biosolid- and liming by-product-amended agricultural soils. Geoderma. 288: 23–36.
  • MGM, 2025. Meteoroloji Genel İklim Verileri. Meteoroloji Genel Müdürlüğü, Ankara, Turkey.
  • Munnaf, M.A., Mouazen, A.M., 2021. Development of a soil fertility index using on-line Vis-NIR spectroscopy. Comput. Electron. Agric. 188: 106341.
  • Nie, S., Chen, H., Sun, X., An, Y., 2024. Spatial distribution prediction of soil heavy metals based on random forest model. Sustainability. 16 (11): 4358.
  • Ozyazici, M.A., Dengiz, O., Ozyazici, G., 2017 Spatial distribution of heavy metals density in cultivated soils of Central and East Parts of Black Sea Region in Turkey. Eurasian Journal of Soil Science. 6: 197-205.
  • Shi, S., Hou, M., Gu, Z., Jiang, C., Zhang, W., Hou, M., Li, C., Xi, Z., 2022. Estimation of heavy metal content in soil based on machine learning models. Land. 11 (7): 1037.
  • Sigrist, F., 2021. Gradient and Newton boosting for classification and regression. Expert Systems With Applications. 167: 114080.
  • Smith, H.W., Weldon, M.D., 1941. A comparison of some methods for the determination of soil organic matter.
  • T.O.B., 2010. Toprak Kirlilik Parametreleri Yönetmeliği.
  • Taylor, S., 1964. Abundance of chemical elements in the continental crust: A new table. Geochimica et Cosmochimica Acta. 28: 1273–1285.
  • Taylor, S., McLennan, S., 1985. The continental crust: Its composition and evolution. Geoscience Texts. 312.
  • Wang, Y., Zhao, Y., Xu, S., 2022. Application of VNIR and machine learning technologies to predict heavy metals in soil and pollution indices in mining areas. Journal of Soils and Sediments. 22 (10): 2777–2791.
Toplam 28 adet kaynakça vardır.

Ayrıntılar

Birincil Dil İngilizce
Konular Hayvansal Üretim (Diğer)
Bölüm Makaleler
Yazarlar

Noyan Eken 0000-0001-6609-7106

Enes Efe 0000-0002-6136-6140

Kamer Yazar 0009-0002-3631-088X

Mehmet Hamurcu 0000-0001-7378-4406

Fatma Gökmen Yılmaz 0000-0001-8523-1825

Sait Gezgin 0000-0002-3795-4575

Erdoğan Hakkı 0000-0001-7147-7875

Proje Numarası MEV-2017-36, 18401058
Yayımlanma Tarihi 7 Temmuz 2025
Gönderilme Tarihi 15 Kasım 2024
Kabul Tarihi 13 Mart 2025
Yayımlandığı Sayı Yıl 2025 Cilt: 13 Sayı: 1

Kaynak Göster

APA Eken, N., Efe, E., Yazar, K., … Hamurcu, M. (2025). AI-Based Prediction of Microelement and Heavy Metal Contents in Central-Southern Anatolian Soils: A Pilot Study. ÇOMÜ Ziraat Fakültesi Dergisi, 13(1), 12-31. https://doi.org/10.33202/comuagri.1586063