Adiyaman University Repository

Recurrent neural network based model development for wheat yield forecasting

Show simple item record

dc.contributor.author Çetiner, Halit
dc.contributor.author Kara, Burhan
dc.date.accessioned 2022-05-20T06:24:04Z
dc.date.available 2022-05-20T06:24:04Z
dc.date.issued 2022
dc.identifier.issn 2149-0309
dc.identifier.uri http://dspace.adiyaman.edu.tr:8080/xmlui/handle/20.500.12414/2987
dc.description.abstract Bu çalışmada 1980-2020 yılları arasında Konya ilinin aylık yağış, nem ve sıcaklık verileri, buğday üretim miktarı ve buğday verimlilik verileri kullanılmıştır. Bu veriler kullanılarak Recurrent Neural Network (RNN) tabanlı algoritmalar olan (Gated Recurrent Units) GRU ve Long Short Term Memory (LSTM) yöntemleri ile buğday verimlilik tahmini yapılmıştır. Gerçekleştirilen GRU tabanlı model ile buğday verimliliği tahmin performansları incelendiğinde R2 puan, MSE, RMSE, MAE ve MAPE değerleri için sırasıyla 0.9550, 0.0059, 0.0280, 0.0623, 7.45 değerleri elde edilmiştir. RNN tabanlı bir diğer yöntem olan LSTM yöntemiyle elde edilen performans sonuçlarında ise R2 puan, MSE, RMSE, MAE ve MAPE değerleri için sırasıyla 0.9667, 0.0054, 0.0280, 0.0614, 7.33 değerleri elde edilmiştir. LSTM yöntemi, GRU yönteminden daha iyi sonuçlar vermesine rağmen LSTM yönteminin eğitim modelleme süresi GRU yönteminden daha fazla sürmüştür. tr
dc.description.abstract In the study carried out in line with the stated purposes, monthly rain, humidity and temperature data, wheat production amount, and wheat productivity data of Konya province between 1980-2020 were used. Using these data, wheat productivity estimation was performed with (Gated Recurrent Units) GRU and Long Short Term Memory (LSTM) methods, which are Recurrent Neural Network (RNN) based algorithms. When wheat productivity estimation performance was examined with the implemented GRU-based model, 0.9550, 0.0059, 0.0280, 0.0623, 7.45 values were obtained for the R2 score, MSE, RMSE, MAE and MAPE values, respectively. In the performance results obtained with the LSTM method, which is another RNN-based method, 0.9667, 0.0054, 0.0280, 0.0614, 7.33 values were obtained for the R2 score, MSE, RMSE, MAE and MAPE values, respectively. Although the LSTM method gave better results than the GRU method, the training modelling time of the LSTM method took longer than that of the GRU method. tr
dc.language.iso en tr
dc.publisher Adıyaman Üniversitesi tr
dc.subject Buğday verimi tr
dc.subject buğday üretimi tr
dc.subject GRU tr
dc.subject LSTM tr
dc.subject regresyon analizi tr
dc.subject Wheat yield tr
dc.subject wheat production tr
dc.subject regression analysis tr
dc.title Recurrent neural network based model development for wheat yield forecasting tr
dc.title.alternative Buğday verim tahmini için yenilemeli sinir ağı tabanlı model geliştirme tr
dc.type Article tr
dc.contributor.authorID 0000-0001-7794-2555 tr
dc.contributor.authorID 0000-0002-4207-0539 tr
dc.contributor.department Isparta University of Applied Sciences, Vocational School of Technical Sciences, Isparta, Turkey tr
dc.contributor.department Isparta University of Applied Sciences, Agriculture Faculty, Department of Field Crops, Isparta, Turkey tr
dc.identifier.endpage 218 tr
dc.identifier.issue 16 tr
dc.identifier.startpage 204 tr
dc.identifier.volume 9 tr
dc.source.title Adıyaman Üniversitesi Mühendislik Bilimleri Dergisi tr


Files in this item

This item appears in the following Collection(s)

Show simple item record

Search DSpace


Advanced Search

Browse

My Account