Identification of spatial and temporal contributions of rainfalls to flash  floods using neural network modelling: case study on the Lez basin (southern  France)

Darras, Thomas; Estupina, Valérie Borrell; Kong-A-Siou, L.; Vayssade, Bernard; Johannet, Anne; Pistre, Séverin

doi:10.5194/hess-19-4397-2015

Cited by 24 publications

(7 citation statements)

References 49 publications

(55 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Other notable examples of karst drainage basin maps include the Mitchell Plateau of Indiana [ 121 ], the Devil’s Icebox Basin of central Missouri [ 208 ], multiple basins in the Devonian limestone of New York [ 209 ]. Karst basins documented internationally include China [ 210 ], France [ 211 ], Mexico [ 212 ], and Puerto Rico [ 213 ].…”

Section: Discussionmentioning

confidence: 99%

Geomorphology of the Mirador-Calakmul Karst Basin: A GIS-based approach to hydrogeologic mapping

et al. 2021

View full text Add to dashboard Cite

This paper classifies the karst landscapes of the Petén Plateau and defines the Mirador-Calakmul Karst Basin by illustrating the distribution of its karst hydrologic features. Archaeological and spatial research of the Mirador-Calakmul area of Guatemala and Mexico has shown it to be a karst basin with geopolitical implications. Current research characterizes the karst landscapes of the Petén Plateau, maps the distribution of karst hydrologic features, and delineates the basin in geomorphological terms. To further this aim, multiple forms of remote sensing data including orthophotographs, a satellite Digital Elevation Model, satellite multispectral images, and Light Detection and Ranging (LiDAR) data have been integrated to interpret the karst features in the study area. Outcrop study and thin section analysis of the upper Buena Vista Formation document that the dominant lithologies are a shallow water algal boundstone interbedded with terrestrial caliche. Karst landforms have been mapped over the Petén Plateau and we identify five karst landscapes, the largest of which is a fluviokarst landscape dominated by karst valleys. We further map karst hydrologic features including seasonal swamps, dolines, intermittent lakes, intermittent streams, solution-enhanced fractures, and springs all of which are characteristic of drainage basins. Boundaries of the karst basin are mapped from multiple lines of evidence including distribution of the karst valleys, a line of springs along the western boundary of the fluviokarst landscape, and a surface drainage analysis. We capture and classify hydrologic data points and develop a regional groundwater map that indicates subsurface flow from east to west within the basin. A drainage map illustrates the extensive system of karst valleys, boundaries, and inferred groundwater flow paths of the Mirador-Calakmul Karst Basin. It was within this geomorphological setting that the ancient Maya developed an extensive civilization during the Middle and Late Preclassic periods (1000 BCE-150 CE).

show abstract

Section: Discussionmentioning

confidence: 99%

Geomorphology of the Mirador-Calakmul Karst Basin: A GIS-based approach to hydrogeologic mapping

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Please refer to Kong A Siou et al (2011) for an overview about older modeling studies at Lez spring with different approaches. In this study, we focus on the most recent studies for comparison, all of which were conducted with ANNs (Kong Siou et al, 2011Siou et al, , 2012Kong-A-Siou et al, 2013, 2014Darras et al, 2015;Kong-A-Siou et al, 2015;Darras et al, 2017).…”

Section: Lez Springmentioning

confidence: 99%

Karst spring discharge modeling based on deep learning using spatially distributed input data

Wünsch

Liesch

Cinkus

et al. 2021

Preprint

View full text Add to dashboard Cite

Abstract. Despite many existing approaches, modeling karst water resources remains challenging and often requires solid system knowledge. Artificial Neural Network approaches offer a convenient solution by establishing a simple input-output relationship on their own. However, in this context, temporal and especially spatial data availability is often an important constraint, as usually no or few climate stations within a karst spring catchment are available. Hence spatial coverage is often unsatisfying and can introduce severe uncertainties. To avoid these problems, we use 2D-Convolutional Neural Networks (CNN) to directly process gridded meteorological data followed by a 1D-CNN to perform karst spring discharge simulation. We investigate three karst spring catchments in the Alpine and Mediterranean region with different meteorologic-hydrological characteristics and hydrodynamic system properties. We compare our 2D-models both to existing modeling studies in these regions and to 1D-models, which use climate station data, as it is common practice. Our results show that our models are excellently suited to model karst spring discharge and rival the simulation results of existing approaches in the respective areas. The 2D-models learn relevant parts of the input data and by performing a spatial input sensitivity analysis we can further show their potential for karst catchment localization and delineation.

show abstract

“…Recent studies Dam or lake water level Hipni et al, 2013;Üneş et al, 2015;Li et al, 2016 Evaporation and evapotranspiration Goyal et al, 2014;Karimi et al, 2016;Güçlü et al, 2017Rainfall-runoff Talei et al, 2013Darras et al, 2015;Londhe et al, 2015;Chithra & Thampi, 2016 Sediment Demirci and Baltaci, 2013;Güner and Yumuk, 2014;Droppo & Krishnappan, 2016;Talebi et al, 2016Streamflow Cigizoglu, 2003Huang et al, 2004;Nourani et al, 2012;Ashrafi et al, 2017 Water quality variables Ay, 2010;Akkoyunlu et al, 2011;Ay & Kisi, 2011;Ay & Kisi, 2012;Ay & Kisi, 2013a;Ay & Kisi, 2013b;Kisi & Ay, 2013;Ay, 2014;Ay & Kisi, 2014;Chang et al, 2014;Alizadeh & Kavianpour, 2015;Khan & Valeo, 2015;Ay & Kisi, 2017…”

Section: Variablesmentioning

confidence: 99%

Artificial Intelligence (AI) Studies in Water Resources

Ay¹,

Özyıldırım²

2018

Natural and Engineering Sciences

View full text Add to dashboard Cite

Artificial intelligence has been extensively used in many areas such as computer science, robotics, engineering, medicine, translation, economics, business, and psychology. Various studies in the literature show that the artificial intelligence in modeling approaches give close results to the real data for solution of linear, non-linear, and other systems. In this study, we reviewed the current state-of-the-art and progress on the modelling of artificial intelligence for water variables: rainfall-runoff, evaporation and evapotranspiration, streamflow, sediment, water quality variables, and dam or lake water level changes. Moreover, the study has also identified some future research possibilities and suggestions for modelling of the water variables.

show abstract

Identification of spatial and temporal contributions of rainfalls to flash floods using neural network modelling: case study on the Lez basin (southern France)

Cited by 24 publications

References 49 publications

Geomorphology of the Mirador-Calakmul Karst Basin: A GIS-based approach to hydrogeologic mapping

Geomorphology of the Mirador-Calakmul Karst Basin: A GIS-based approach to hydrogeologic mapping

Karst spring discharge modeling based on deep learning using spatially distributed input data

Artificial Intelligence (AI) Studies in Water Resources

Contact Info

Product

Resources

About