Prediction of Reservoir Temperatures Using Hydrogeochemical Data, Western Anatolia Geothermal Systems (Turkey): A Machine Learning Approach
Küçük Resim Yok
Tarih
2020
Yazarlar
Dergi Başlığı
Dergi ISSN
Cilt Başlığı
Yayıncı
Springer
Erişim Hakkı
info:eu-repo/semantics/closedAccess
Özet
Geothermal fluids can be used for purposes such as power production, district heating/cooling, agriculture, and industrial and thermal tourism. Although using geothermal fluids is beneficial, it requires detailed exploration studies of a region. These exploration studies mainly involve geology, geophysics and geochemistry disciplines to understand the location, dimensions, possible capacity and temperature of a reservoir before beginning drilling operations. Because of the high operational costs, the exploration phase of a geothermal project is of great importance to reduce project costs. Evaluation of existing earth sciences data, detailed geology studies, mapping and some geochemical studies, such as using geothermometers, can provide information about a potential geothermal reservoir in a geothermal field. Machine learning is a technology for data analysis which identifies patterns in data and uses them to make predictions about new data points automatically. In this study, a deep learning model is developed to predict geothermal reservoir temperatures based on selected hydrogeochemistry data from different geothermal systems. Two traditional regression approaches, linear regression and linear support vector machine, are performed to compare the prediction performance of our proposed deep learning model. The objective of the study is to obtain the algorithm having the lowest root-mean-square error and mean absolute error. The results show that the deep neural network (DNN) algorithm generated the lowest errors. The DNN model provided the most accurate values close to geothermometer calculations for reservoir temperature. The performance comparison showed that our deep learning model achieved the best prediction performance compared to traditional machine learning techniques.
Açıklama
Anahtar Kelimeler
Machine Learning, Deep Learning, Hydrogeochemistry, Reservoir Temperature Prediction, Geothermal Exploration, Waters, Scale, Brine
Kaynak
Natural Resources Research
WoS Q Değeri
Q1
Scopus Q Değeri
Q1
Cilt
29
Sayı
4
