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


Experimental and modelling evidence of splash effects on manure borne Escherichia coli washoff

In tropical montane South-East Asia, recent changes in land use have induced increased runoff, soil erosion and instream suspended sediment loads. Land use change is also contributing to increased microbial pathogen dissemination and contamination of stream waters. Escherichia coli (E. coli) is frequently used as an indicator of faecal contamination. Field rain simulations were conducted […]



Special Issue “Multiscale Impacts of Anthropogenic and Climate Changes on Tropical and Mediterranean Hydrology”

This Special Issue published in the Water journal and co-authored by Olivier Ribolzi (IRD-GET) shows the great interest of the scientific community in investigating how to characterize the environmental impact of anthropogenic and climatic changes on Tropical and Mediterranean hydrology, and also in determining which is the main source of changes depending on the regional […]



Effects of hydrological regime and land use on in-stream Escherichia coli concentration in the Mekong basin, Lao PDR

In the basin of Mekong, over 70 million people rely on unimproved surface water for their domestic requirements. Surface water is often contaminated with fecal matter and yet little information exists on the underlying mechanisms of fecal contamination in tropical conditions at large watershed scales. The objectives of this paper were to (1) investigate the […]