Surface and sub-surface flow estimation at high temporal resolution using deep neural networks

Recent intensification in climate change have resulted in the rise of hydrological extreme events. Hydrological processes modelling at high temporal resolution is required to better understand flow patterns at catchment scale. A physically-based model called Hydrological Simulated Program-FORTRAN and two deep learning-based models were implemented to model surface runoff and sub-surface flow in the tropical humid headwater catchment of Houay Pano, northern Lao PDR. One deep learning model consisted of only one long short-term memory (simple LSTM), whereas the other model simulated processes in each hydrological response unit (HRU) by defining one separate LSTM for each HRU (HRU-based LSTM). The models use time-series data and two-dimensional spatial data to predict surface and sub-surface flows at 6-minute time step. The simple LSTM model outperformed the other models on surface runoff prediction, whereas HRU-based LSTM model better predicted sub-surface flow. This study demonstrates the performance of a deep learning model when simulating hydrological cycle with high temporal resolution.

The paper is an achievement of the GETiEES ParisUNIST collaboration and was published in the Journal of Hydrology. 50 days’ free access is available here.

More news


Quantifying the effect of overland flow on Escherichia coli pulses during floods: use of a tracer-based approach in an erosion-prone tropical catchment



Understory limits surface runoff and soil loss in teak tree plantations of northern Lao PDR

Many mountainous regions of the humid tropics experience serious soil erosion following rapid changes in land use. In northern Lao PDR, the replacement of traditional crops by tree plantations, such as teak trees, has led to a dramatic increase in floods and soil loss and to the degradation of basic soil ecosystem services. In this […]



Discovery of a new open-air Hoabinhian site in Luang Prabang province (Lao PDR). Dating and technological study of the lithic assemblage

The Hoabinhian is a distinctive lithic techno-complex of mainland and Island Southeast Asia. Knowledge of its relationships with key patterns of technological change at a global scale has progressed over the last two decades. However, our understanding of the Hoabinhian as an indicator of evolution during Prehistory can be substantially enhanced by examiningits regional and […]