Evaluation of Feature Selection Methods in Estimation of Precipitation Based on Deep Learning Artificial Neural Networks

Sattari M. T., Avram A., APAYDIN H., Matei O.

WATER RESOURCES MANAGEMENT, cilt.37, sa.15, ss.5871-5891, 2023 (SCI-Expanded) identifier identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 37 Sayı: 15
  • Basım Tarihi: 2023
  • Doi Numarası: 10.1007/s11269-023-03563-4
  • Dergi Adı: WATER RESOURCES MANAGEMENT
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus, PASCAL, ABI/INFORM, Agricultural & Environmental Science Database, Aqualine, Aquatic Science & Fisheries Abstracts (ASFA), Biotechnology Research Abstracts, CAB Abstracts, Compendex, Environment Index, Geobase, INSPEC, Pollution Abstracts, Veterinary Science Database, Civil Engineering Abstracts
  • Sayfa Sayıları: ss.5871-5891
  • Anahtar Kelimeler: Artificial intelligence, Deep learning, Feature selection, Feature weights, H2O cluster, Precipitation, Stochastic gradient descent
  • Ankara Üniversitesi Adresli: Evet

Özet

Precipitation is the most important element of the water cycle and an indispensable element of water resources management. This paper's aim is to model the monthly precipitation in 8 precipitation observation stations in the province of Hamadan, Iran. The effects and role of different feature weights pre-processing methods (Weight by deviation, Weight by PCA, Weight by correlation and Weight by Support Vector Machine) on artificial intelligence modeling were investigated. Deep learning method based on a multi-layer feed-forward artificial neural network that is trained with Stochastic Gradient Descent using back-propagation (DL-SGD) and Convolutional Neural Networks (CNN) modelling were applied. The precipitation of each station is modeled using the precipitation values of the other stations. The best result, among all scenarios, at the Vasaj station according to the DL-SGD method (CC = 0.9845, NS = 0.9543 and RMSE = 10.4169 mm) and at the Varayineh station according to the CNN method (CC = 0.9679, NS = 0.9362 and RMSE = 16.0988 mm) were estimated.