Long short-term memory (LSTM) recurrent neural network for low-flow hydrological time series forecasting

Acta Geophysica

article

Sahoo, Bibhuti Bhusan¹  Jha, Ramakar¹  Singh, Anshuman¹  Kumar, Deepak¹ 

[1] Department of Civil Engineering, National Institute of Technology

关键词: Artificial intelligence;    Long short-term memory recurrent neural network;    Low flow;    Hydrological time series forecasting;    naïve method;   

DOI  :  10.1007/s11600-019-00330-1

学科分类：地球科学(综合)

来源: Polska Akademia Nauk * Instytut Geofizyki

【 摘 要 】

This article explores the suitability of a long short-term memory recurrent neural network (LSTM-RNN) and artificial intelligence (AI) method for low-flow time series forecasting. The long short-term memory works on the sequential framework which considers all of the predecessor data. This forecasting method used daily discharged data collected from the Basantapur gauging station located on the Mahanadi River basin, India. Different metrics [root-mean-square error (RMSE), Nash–Sutcliffe efficiency (ENS), correlation coefficient (R) and mean absolute error] were selected to assess the performance of the model. Additionally, recurrent neural network (RNN) model is also used to compare the adaptability of LSTM-RNN over RNN and naïve method. The results conclude that the LSTM-RNN model (R = 0.943, ENS = 0.878, RMSE = 0.487) outperformed RNN model (R = 0.935, ENS = 0.843, RMSE = 0.516) and naïve method (R = 0.866, ENS = 0.704, RMSE = 0.793). The finding of this research concludes that LSTM-RNN can be used as new reliable AI technique for low-flow forecasting.

【 授权许可】

Unknown