<p>With the increasing integration of artificial intelligence (AI) in several scientific domains, there is a rising demand for advanced AI tools capable of addressing advanced research challenges. A challenge of paramount importance lies in accurately predicting the streamflow within river basins. Effective river flow prediction holds significant relevance, particularly given the substantial societal implications of river usage, encompassing areas such as transportation, agriculture, and power generation. The present study introduces a novel approach to streamflow prediction involving the development of a Deep Learning (DL) model that combines a convolutional neural network with Transfer Learning (TL) techniques to predict streamflow in river systems. With the aim of training the developed DL model, the study employed a time-series dataset containing hydrological data related to two distinct river basins, i.e., Paraíba do Sul, in Brazil, and Zambezi in the state of Mozambique. The developed DL models exhibited the capability to effectively predict the river flow with a one-day horizon, relying on the preceding three or seven days of historical data. To overcome the limited availability of training data and reduce the training time of DL models, TL was leveraged to incorporate two additional distinct time-series datasets, i.e., historical streamflow data from the São Francisco River in Brazil, and climate data from Delhi, India. The application of TL significantly reduced training time, leading only to a minimal decrease in prediction performance. Indeed, in the case DL models were trained on data collected from the Paraíba do Sul River, a substantial reduction in training time was observed - up to 27% - with a modest percentage decrease of 0.31% in test predictive performance (<InlineEquation ID="IEq1"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="41598_2025_7088_Article_IEq1.gif" Format="GIF" Height="17" Rendition="HTML" Resolution="72" Type="Linedraw" Width="19" /> </InlineMediaObject> <EquationSource Format="TEX">\(\hbox {R}^2\)</EquationSource> </InlineEquation>). Similarly, TL induced a significant reduction in training time of up to 48%, while resulting in a modest 2% reduction in test predictive performance (<InlineEquation ID="IEq2"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="41598_2025_7088_Article_IEq1.gif" Format="GIF" Height="17" Rendition="HTML" Resolution="72" Type="Linedraw" Width="19" /> </InlineMediaObject> <EquationSource Format="TEX">\(\hbox {R}^2\)</EquationSource> </InlineEquation>) for the Zambezi dataset. The findings underscore the significance of TL as a strategic and viable approach to improve the efficiency of river flow prediction models in the context of basins with limited hydrological data available.</p>

Convolutional neural networks with transfer learning for natural river flow prediction in ungauged basins

期刊论文
出版模式：

开放获取
发表日期：

2025年7月4日

查看全文

Henrique Echternacht,
Luciana Campos,
Alfeu Dias de Martinho,
Danilo Pinto Moreira de Souza,
Rodrigo Barbosa de Santis,
Tiago Silveira Gontijo,
Matteo Bodini,
Angela Gorgoglione,
Camila Martins Saporetti,
Leonardo Goliatt

摘要

With the increasing integration of artificial intelligence (AI) in several scientific domains, there is a rising demand for advanced AI tools capable of addressing advanced research challenges. A challenge of paramount importance lies in accurately predicting the streamflow within river basins. Effective river flow prediction holds significant relevance, particularly given the substantial societal implications of river usage, encompassing areas such as transportation, agriculture, and power generation. The present study introduces a novel approach to streamflow prediction involving the development of a Deep Learning (DL) model that combines a convolutional neural network with Transfer Learning (TL) techniques to predict streamflow in river systems. With the aim of training the developed DL model, the study employed a time-series dataset containing hydrological data related to two distinct river basins, i.e., Paraíba do Sul, in Brazil, and Zambezi in the state of Mozambique. The developed DL models exhibited the capability to effectively predict the river flow with a one-day horizon, relying on the preceding three or seven days of historical data. To overcome the limited availability of training data and reduce the training time of DL models, TL was leveraged to incorporate two additional distinct time-series datasets, i.e., historical streamflow data from the São Francisco River in Brazil, and climate data from Delhi, India. The application of TL significantly reduced training time, leading only to a minimal decrease in prediction performance. Indeed, in the case DL models were trained on data collected from the Paraíba do Sul River, a substantial reduction in training time was observed - up to 27% - with a modest percentage decrease of 0.31% in test predictive performance ( \(\hbox {R}^2\) ). Similarly, TL induced a significant reduction in training time of up to 48%, while resulting in a modest 2% reduction in test predictive performance ( \(\hbox {R}^2\) ) for the Zambezi dataset. The findings underscore the significance of TL as a strategic and viable approach to improve the efficiency of river flow prediction models in the context of basins with limited hydrological data available.