Search

International audience; The complexity of karst groundwater flow modelling is reflected by the amount of simulation approaches. The goal of the Karst Modelling Challenge (KMC) is comparing different approaches on one single system using the same data set. Thirteen teams with different computational models for simulating discharge variations at karst springs have applied their respective models on one single data set coming from the Milandre Karst Hydrogeological System (MKHS). The approaches include neural networks, reservoir models, semi-distributed models and fully distributed groundwater models. Four and a half years of hourly or daily meteorological input and hourly discharge data were provided for model calibration. The validation comprised forecasting one year of discharge, without the observed discharge data. The model performance was evaluated using the volume conservation, Nash-Sutcliffe efficiency (NSE) and the Kling-Gupta efficiency (KGE) applied on the total discharge and individual flow components. As a result, the comparison of model performances is a challenging task due to the differences in the model architecture but also required time steps: some of the models require aggregated daily steps while others could be run using hourly data, which provided some interesting differences depending on how the data was transformed. The use of instantaneous data (e.g. value at noon) produces less bias that averaging hourly data over one day. The transformation of hourly into daily data produces a decrease of Nash and KGE of 0.05 to 0.08 (i.e. from 1 to ~0.93). The resulting simulations (forecasted values for year 2016) produced KGEs ranging between 0.83 and 0.37 (0.83 to −0.24 for NSE). Although the simulations matched the monitored flows reasonably well, most models struggled to simulate baseflow conditions accurately. In general, the models that performed the best for this exercise were the global ones (Gardenia and Varkarst), with a limited number of parameters, which can be calibrated using automatic calibration procedures. The neural network models also showed a fair potential, with one providing reasonable results despite the relatively short dataset available for warming-up (4.5 years). Semi-and fully distributed models also suggested that with some more effort they could perform well. The accuracy of model predictions does not seem to increase by using models with more than 9–12 calibration parameters. An evaluation of the relative errors between the forecasted and the observed values revealed that for most models, 50% of the forecasted values contained more than 50% of difference against the observed discharge rate, with 25% having a difference larger than 100%. A significant part of the poorly forecasted values corresponded to base-flow which was surprising given that as base-flow is generally much easier to predict than peak flow. Hence, this shows that modelling approaches and criteria for the calibration are too oriented towards peak-flow sections of the hydrographs, and that improvements could be gained by more focus on the base-flow.

Understanding, simulating and forecasting dynamic and nonlinear natural phenomena are necessary in a climate change context and increased sensitivity of societies to natural hazards. Nevertheless, even though powerful computing tools and algorithms have been widely used to understand and to predict natural disasters, these tasks are still challenging for scientists. Indeed, one of the most dangerous natural phenomena, flash floods keep being a challenge for modelers, despite (i) the existence of some effective hydrological simulating tools, and (ii) the increasing availability of descriptive data, especially rainfall and discharge. In particular, on one hand, environmental data contain an important amount of noise leading to additional uncertainties and on the other hand, physically based models strongly depend on assumptions about the behavior of the basin, that is often more variable in space and time than what is modelled. With the objective of applying data assimilation to improve forecasting properties of the physical model, it is necessary to dispose of a differentiable model. In order to mitigate this issue, a hybrid physical and statistical approach is proposed in this study. It was shown in previous works that deep neural networks are able to identify any differentiable function by using the universal approximation property. Deep neural networks are also good candidates to perform the digital twin of the physical model. Thus, three different neural networks models were designed in this study, and each one is implementing a different type of non-linear filter model, in order to achieve the dynamic character of the catchment area (recurrent, feedforward and static models). The study area is located in the Gardon de Sainte-Croix basin (France), which is known for its sudden and violent floods that caused casualties and a lot of damage. The chosen physical-based model is semi distributed conceptual hydrological SOCONT model, RS Minerve (https://www.crealp.ch/down/rsm/install2/archives.html). Neural networks design was done by using a rigorous complexity selection and regularization methods to promote a good generalization. The three models obtained were thus compared. The feed forward model gave the best results on tests events (Nash score=0.98−0.99), making full use of the inputs with previous observed discharges whereas the recurrent model gave interesting results representing satisfactorily the dynamics of the physical model (Nash score=0.8−0.97). The static model, whose inputs contain only rainfall, is less efficient, showing the importance of dynamics in that kind of system (Nash score=0.62−0.84). Beyond data assimilation, these results open paths of inquiry for building digital twins of physical model, allowing also a great reduction of computing time.

International audience; Peatlands are habitats for a range of fragile flora and fauna species. Their eco-physicochemical characteristics make them as outstanding global carbon and water storage systems. These ecosystems occupy 3% of the worldwide emerged land surface but represent 30% of the global organic soil carbon and 10% of the global fresh water volumes. In such systems, carbon speciation depends to a large extent on specific redox conditions which are mainly governed by the depth of the water table. Hence, understanding their hydrological variability, that conditions both their ecological and biogeochemical functions, is crucial for their management, especially when anticipating their future evolution under climate change. This study illustrates how long-term monitoring of basic hydro-meteorological parameters combined with statistical modeling can be used as a tool to evaluate i) the horizontal (type of peat), ii) vertical (acrotelm/catotelm continuum) and iii) future hydrological variability. Using cross-correlations between meteorological data (precipitation, potential evapotranspiration) and water table depth (WTD), we primarily highlight the spatial heterogeneity of hydrological reactivity across the Sphagnum-dominated Frasne peatland (French Jura Mountain). Then, a multiple linear regression model allows performing hydrological projections until 2100, according to regionalized IPCC RCP4.5 and 8.5 scenarios. Although WTD remains stable during the first half of 21th century, seasonal trends beyond 2050 show lower WTD in winter and markedly greater WTD in summer. In particular, after 2050, more frequent droughts in summer and autumn should occur, increasing WTD. These projections are completed with risk evaluations for peatland droughts until 2100 that appear to be increasing especially for transition seasons, i.e. May–June and September–October. Comparing these trends with previous evaluations of phenol concentrations in water throughout the vegetative period, considered as a proxy of plant functioning intensity, highlights that these hydrological modifications during transitional seasons could be a great ecological perturbation, especially by affecting Sphagnum metabolism.

Issu de : ITISE 2019 - International Conference on Time Series and Forecasting, Granada, Spain, 25-27 September 2019; International audience; Flash floods frequently hit Southern France and cause heavy damages and fatalities. To enhance persons and goods safety, official flood forecasting services in France need accurate information and efficient models to optimize their decisions and policy in crisis management. Their forecasting is a serious challenge as heavy rainfalls that cause such floods are very heterogeneous in time and space. Such phenomena are typically nonlinear and more complex than classical flood events. This analysis had led to consider complementary alternatives to enhance the management of such situations. For decades, artificial neural networks have been proved very efficient to model nonlinear phenomena, particularly rainfall-discharge relations in various types of basins. They are applied in this study with two main goals: first, modeling flash floods on the Gardon de Mialet basin (Southern France); second, extract internal information from the model by using the KnoX: knowledge extraction method to provide new ways to improve models. The first analysis shows that the kind of nonlinear predictor strongly influences the representation of information, e.g., the main influent variable (rainfall) is more important in the recurrent and static models than in the feed-forward one. For understanding “long-term” flash floods genesis, recurrent and static models appear thus as better candidates, despite their lower performance. Besides, the distribution of weights linking the exogenous variables to the first layer of neurons is consistent with the physical considerations about spatial distribution of rainfall and response time of the hydrological system.

espanolEn las ultimas decadas el uso de redes neuronales en la modelizacion hidrologica ha aumentado, debido a su propiedad fundamental como aproximador universal y parsimonico de funciones no lineales. En el campo de la prevision de inundaciones, los perceptrones de alimentacion directa (feed-forward) y de tipo multicapa recurrentes (recurrent multilayer) han confirmado su eficiencia. Sin embargo, la capacidad predictiva depende de los parametros de inicializacion del sistema neuronal. La eficacia del metodo de validacion cruzada para seleccionar las condiciones optimas de inicializacion que conducen a las mejores predicciones ha sido analizada. La dependencia de la inicializacion en los modelos de retroalimentacion y de multicapa recurrente ha sido comparada para las predicciones con antelacion de una hora. Nuestro trabajo demuestra que la validacion cruzada no permite la seleccion de la mejor inicializacion. Un modelo mas robusto ha sido desarrollado gracias al uso de la mediana de los resultados de varios modelos; en ese contexto, este trabajo analiza la estructura de los meta modelos tanto para los sistemas basados en redes retroalimentadas como para aquellos basados en redes multicapa recurrentes. EnglishDuring the last few decades neural networks have been increasingly used in hydrological modelling for their fundamental property of parsimony and of universal approximation of non-linear functions. For the purpose of flash flood forecasting, feed-forward and recurrent multi-layer perceptrons appear to be efficient tools. Nevertheless, their forecasting performances are sensitive to the initialization of the network parameters. We have studied the cross-validation efficiency to select initialization providing the best forecasts in real time situation. Sensitivity to initialization of feed-forward and recurrent models is compared for one-hour lead-time forecasts. This study shows that cross-validation is unable to select the best initialization. A more robust model has been designed using the median of several models outputs; in this context, this paper analyses the design of the ensemble model for both recurrent and feed-forward models.

[Departement_IRSTEA]Eaux [TR1_IRSTEA]GEUSI [ADD1_IRSTEA]Gestion intégrée de la ressource et des infrastructures; International audience; In order to better manage complex situations of natural resource management, models are built in a participative way, involving the stakeholders of these situations in participatory modelling activities. The impact that this activity of participatory modelling has on the stakeholders is at the heart of the Companion Modelling approach but this impact is hardly possible to evaluate on the field. In this paper we propose a general framework to study in vitro the impact of participatory modelling on natural resources management. We illustrate our framework by proposing an experimental setting that looks at participatory modelling in the context of water management. We realized a pilot experiment and show that this experimental setting can be used to test, in the laboratory, the hypothesis that participatory modelling of a common pool resource situation has an impact on the way the resource is managed and increases the cooperative behaviour of stakeholders.

The risk of drought impacting the drinking water and agricultural production is worrying in the developed countries, especially in a changing climate context. To manage and prevent this phenomenon, real-time monitoring and predictive systems are emerging as the key solutions. In the field of artificial intelligence, neural networks are one of these predictive systems. This family of parameterized models is a composition of neuronal functions, which apply a non-linear transformation from their inputs to their outputs. These networks are able to learn a hydro(geo)logical system behaviour using a database composed of observed inputs (rainfall, evapotranspiration, etc.) and outputs (groundwater level, discharge, etc.), thanks to an algorithm minimizing a cost function between observed and simulated outputs. However, it remains difficult to assess the uncertainty generated by these models, possibly leading to misinterpretations by the end users. These uncertainties are mainly of three types. The first is related to the input data. Indeed, hydrosystems are surface elements whereas meteorological inputs are punctual elements. The interpolation error can, therefore, be significant because of the lack of knowledge between gauging stations. The second is the neural network model architecture itself. It is possible to deal with this source of uncertainty using regularization methods. Finally, the neural networks are submitted to uncertainties related to parameter initialization, before the training step. The initial parameters may have an important impact on the results. In this paper, we address the prediction of the Blavet groundwater level (Bretagne, France). In order to assess uncertainties, we will first focus on the parameters initialization of the model. Neuronal models are optimized using cross-validation and early stopping. Then, an ensemble model is realized, in which each member is the result of a unique set of parameters initialization. The purpose of the study is to define how many initializations are necessary to obtain a reasonable confidence interval for forecasts, with the smallest interval and the higher rate of observed points inside this interval. The best model will be determined using cross-validation scores thereby ensuring optimal robustness. We show that, in this case study, an ensemble model of 20 different initializations is sufficient to estimate uncertainty while preserving quality. In the second part, the resulting ensemble model will be used to estimate the global model uncertainty using probability density functions (pdf) applied to the distribution of groundwater level data and cross-validation scores of forecasts. It reveals that the groundwater level predictions are composed of two mixed distributions. Therefore, we will use the expectation-maximization algorithm (EM) to obtain parameters of mixed models. Mixed normal and mixed Gumbel laws, among five mixed distributions assessed, give the best groundwater distribution and are able to generate an abacus drawing uncertainty of model.

Selon de nombreuses prévisions, les rivières méditerranéennes devraient être soumises dans les années à venir à de fortes pressions environnementales liées aux changements climatiques, ce qui laisse entrevoir des conséquences certaines pour la faune qu'elles hébergent. Pour tenter de percevoir ces conséquences, la faune invertébrée de l'une de ces rivières, la Cèze, a été étudiée en période d'étiage. La biodiversité des assemblages de la Cèze a été estimée en tenant compte de l'hétérogénéité des échanges entre la rivière et sa nappe. Ainsi trois habitats ont été échantillonnés : le fond de la rivière (habitat benthique), la zone d'interface entre la rivière et l'aquifère poreux (zone hyporhéique) et celle d'interface avec l'aquifère karstique (sources). Les résultats montrent que la composition des assemblages d'espèces récoltées est différente dans les trois habitats, avec seulement 11 % de taxons communs. L'habitat benthique se révèle plus riche en Éphéméroptères et en Trichoptères, l'habitat hyporhéique en Oligochètes, Crustacés et Plécoptères, et les sources en Diptères. Les espèces stygobies (spécialisées à la vie en milieu souterrain) sont totalement absentes de l'habitat benthique, alors qu'elles sont bien représentées dans les sources et la zone hyporhéique. Les deux habitats situés à l'interface entre le cours d'eau et les systèmes souterrains produisent un enrichissement considérable de la biodiversité du cours d'eau, qui se traduit par un doublement du nombre de taxons par rapport à l'habitat benthique. Ce travail montre que l'intégration des zones situées à l'interface entre la rivière et les eaux souterraines est cruciale pour l'obtention d'une estimation aussi complète que possible de la biodiversité des hydrosystèmes. In a close future, Mediterranean rivers will support strong disturbances due to climate changes, with inexorable consequences for their fauna. The invertebrate biodiversity of the Cèze River (South of France) was studied in a karstic area. The benthic layer (river bottom), the hyporheic layer (interface with the groundwater inside river sediment) and the lateral springs (interface with the karstic systems) were sampled in early summer. Only 11 % of the taxa were sampled simultaneously in the three habitats. Ephemeroptera and Trichoptera were more species rich in the benthic zone; Oligochaetes, crustaceans and Plecoptera in the hyporheic zone and Diptera in the lateral springs. Stygobite species lack in the benthic layer, they were more diversified in the springs and in the hyporheic zone. When all habitats are considered together, the total taxonomic richness is twice of the benthic one. The habitats located at the interface between river and groundwater thus must be included in the river biodiversity estimations.

Flash floods pose significant hazards in urbanised zones and have important implications financially and for humans alike in both the present and future due to the likelihood that global climate change will exacerbate their consequences. It is thus of crucial importance to improve the models of these phenomena especially when they occur in heterogeneous and karst basins where they are difficult to describe physically. Toward this goal, this paper applies a recent methodology (Knowledge eXtraction (KnoX) methodology) dedicated to extracting knowledge from a neural network model to better determine the contributions and time responses of several well-identified geographic zones of an aquifer. To assess the interest of this methodology, a case study was conducted in southern France: the Lez hydrosystem whose river crosses the conurbation of Montpellier (400 000 inhabitants). Rainfall contributions and time transfers were estimated and analysed in four geologically delimited zones to estimate the sensitivity of flash floods to water coming from the surface or karst. The Causse de Viols-le-Fort is shown to be the main contributor to flash floods and the delay between surface and underground flooding is estimated to be 3 h. This study will thus help operational flood warning services to better characterise critical rainfall and develop measurements to design efficient flood forecasting models. This generic method can be applied to any basin with sufficient rainfall–run-off measurements.

International audience; The Liane River is a small costal river, famous for its floods, which can affect the city of Boulogne-sur-Mer. Due to the complexity of land cover and hydrologic processes, a black-box non-linear modelling was chosen using neural networks. The multilayer perceptron model, known for its property of universal approximation is thus chosen. Four models were designed, each one for one forecasting horizon using rainfall forecasts: 24h, 12h, 6h, 3h. The desired output of the model is original: it represents the maximal value of the water level respectively 24h, 12h, 6h, 3h ahead. Working with best forecasts of rain (the observed ones during the event in the past), on the major flood of the database in test set, the model provides excellent forecasts. Nash criteria calculated for the four lead times are 0.98 (3h), 0.97 (6h), 0.91 (12h), 0.89 (24h). Designed models were thus estimated as efficient enough to be implemented in a specific tool devoted to real time operational use. The software tool is described hereafter: designed in Java, it presents a friendly interface allowing applying various scenarios of future rainfalls, and a graphical visualization of the predicted maximum water levels and their associated real time observed values.

International audience; Measurement of characteristics of particles in suspensions without dilution has a practical interest in formulation, mineral processing, material sciences and environmental technologies. These characteristics are the size, shape, and surface properties of the primary particles, and also the size, structure and the number of primary particles in the agglomerates. In this work, the multiple light-scattering model through the optical analyzer, Turbiscan MA 2000 is used to determine the mean settling velocities of monodisperse glass beads and two polydisperse samples of powders, kaolin D and alumina, differing by their particle size distribution, their shape and their surface properties. Beyond the experimental validation of theoretical and empirical predictions, the nonlinear adjustment of experimental settling data gives the number of primary particles per agglomerate and the agglomerate size. These two characteristics lead to the determination of the fractal dimension of the agglomerates. The latter was found in the range of 2.5-2.7 for all suspensions examined. The calculation of permeability and spherical factor reveals the nonspherical impermeable agglomerates.

Artificial neural networks (ANN) are nonlinear models widely investigated in hydrology due to their properties of universal approximation and parsimony. Their performance during the training phase ...

International audience; Aqueous mineral suspensions and pastes are greatly used in industry and waste treatment processes. But unfortunately due to their inherent complexity (numerous parameters to consider and non-linearity of temporal behaviour), their physicochemical stability, controlled by their dispersion state, is difficult to predict. A way to have a better understanding of these systems is to apprehend stability by studying settling behaviour of suspensions in function of solid concentration and interparticle interactions. To this purpose, previous works on settling optical analysis were used in addition to rheological approach, to determine in some mineral systems, a suspension typology in function of solid mass fraction and predominant particle interaction. In order to generalize this work to various mineral aqueous suspensions, a modelling study is proposed in this paper. The aim of this work is to predict the stability of mineral suspensions based on a specific index: phase separation index (PSI) previously established using 10 discriminating parameters currently measured in industrial and academic areas. Because of their well-known ability to model non-linear processes, a neural networks-based procedure was used to classify the settling behaviour in four classes: diluted, concentrated (cohesive and non cohesive) and solid suspension. The method was proved to be very efficient, delivering 100% of good classification on various sets of test sets up to 60% of the database allowing thus to predict the suspension stability for applications such as inks, paints, cosmetics. In this research, the predominant influence of mass fraction parameter was showed. (C) 2014 Elsevier B.V. All rights reserved.

Artificial neural networks for hydrodynamic modeling of karst aquifers : overview and illustrations. Karst aquifers provide fresh water for about 25 % of the global population. Around the Mediterranean Sea, they are sometimes considered as natural water castles or as dams, able to minimize floodings. The high level of heterogeneity found in such aquifers and the difficulties encountered in delimiting their subterranean catchment area make it a challenge to fully understand their hydrological behavior, and accurately simulate and forecast their evolution. In this context, this article presents how hydrodynamic modeling of karst aquifers can be usefully performed using a new approach issued from machine learning : neural networks. Thanks to an automatic way to calculate their parameters, called learning, neural networks can model unknown functions using a representative database. Increasingly used in hydrology, neural networks are first introduced in this article to perform discharge simulation and flood forecasting. The training ability of neural networks is given in the framework of the systemic paradigm, not only restricted to black box modeling, but also to increase information related to the basin behavior (time transfer and water origin). Illustrations are provided on two well-known French karst basins : the Baget (Ariège) and the Lez (Hérault), both associated with extensive datasets., Les aquifères karstiques permettent d'alimenter en eau potable près de 25 % de la population mondiale. Sur le pourtour méditerranéen, ils sont considérés parfois comme des châteaux d'eau naturels ou bien comme des barrages écrêteurs de crue. Ces propriétés remarquables, stimulantes par les enjeux soulevés sont cependant difficiles à quantifier et à appréhender objectivement du fait de la complexité du karst, due à une forte hétérogénéité de structure induisant également des non-linéarités. Dans ce contexte cet article propose d'aborder la modélisation hydrodynamique des karsts par une nouvelle approche appartenant à l'apprentissage statistique : les réseaux de neurones artificiels. Ces derniers sont des modèles mathématiques issus de l'intelligence artificielle qui peuvent identifier toute fonction dynamique non linaire au moyen d'un apprentissage. Ils sont ainsi parfaitement à même de modéliser les fonctions inconnues des aquifères karstiques pourvu que l'on dispose d'une base de données. Très utilisés en hydrologie et appliqués également à la modélisation hydrodynamique des aquifères karstiques, les réseaux de neurones sont tout d'abord abordés dans cet article pour effectuer des fonctions de prévision des crues ou de simulation de débit. Leur capacité d'apprentissage est présentée dans le cadre du paradigme systémique, non seulement pour réaliser la fonction de boîte noire, mais également pour améliorer la connaissance des aquifères karstiques. Ainsi, l'origine des eaux et les temps de transferts peuvent être mieux appréhendés grâce à une méthodologie originale. Cet article présente les études menées sur deux bassins karstiques bien connus, et disposant de nombreuses données de pluie et de débit : le Baget (Ariège) et le Lez (Hérault)., Johannet Anne, Taver Virgile, Kong-A-Siou Line, Borrell Valérie, Pistre Severin, Mangin Alain, Vayssade Bernard, Vinches Marc, Bertin Dominique. Les réseaux de neurones artificiels pour la modélisation hydrodynamique des aquifères karstiques : présentation générale et illustrations. In: Karstologia : revue de karstologie et de spéléologie physique, n°60, 2e semestre 2012. Dynamique sédimentaire dans le siphon de Chevaline. pp. 45-59.

In southern France, flash flood episodes frequently cause fatalities and severe damage. In order to inform and warn populations, the French flood forecasting service (SCHAPI, Service Central d'Hydrométéorologie et d'Appui à la Prévision des Inondations) initiated the BVNE (Bassin Versant Numérique Expérimental, or Experimental Digital Basin) project in an effort to enhance flash flood predictability. The target area for this study is the Gardon d'Anduze basin, located in the heart of the Cévennes range. In this Mediterranean mountainous setting, rainfall intensity can be very high, resulting in flash flooding. Discharge and rainfall gauges are often exposed to extreme weather conditions, which undermines measurement accuracy and continuity. Moreover, the processes governing rainfall-discharge relations are not well understood for these steeply-sloped and heterogeneous basins. In this context of inadequate information on both the forcing variables and process knowledge, neural networks are investigated due to their universal approximation and parsimony properties. We demonstrate herein that thanks to a rigorous variable and complexity selection, efficient forecasting of up to two-hour durations, without requiring rainfall forecasting as input, can be derived using the measured discharges available from a feedforward model. In the case of discharge gauge malfunction, in degraded mode, forecasting may result using a recurrent neural network model. We also observe that neural network models exhibit low sensitivity to uncertainty in rainfall measurements since producing ensemble forecasting does not significantly affect forecasting quality. In providing good results, this study suggests close consideration of our main purpose: generating forecasting on ungauged basins.

International audience; “Cévenol flash floods” are famous in the field of hydrology, because they are archetypical of flash floods that occur in populated areas, thereby causing heavy damages and casualties. As a consequence, their prediction has become a stimulating challenge to designers of mathematical models, whether physics based or machine learning based. Because current, state-of-the-art hydrological models have difficulty performing forecasts in the absence of rainfall previsions, new approaches are necessary. In the present paper, we show that an appropriate model selection methodology, applied to neural network models, provides reliable two-hour ahead flood forecasts.

In karst hydrosystems, the heterogeneity and the complexity of the transfer processes within the different compartments (soil, epikarst, unsaturated zone, saturated zone) control the recharge-discharge relationship. The MEDYCYSS observatory (Multi scalE observatory of flooD dYnamiCs and hYdrodynamicS in karSt) has been set up to better understand these transfers in a Mediterranean context. This observatory consists in a large karst hydrosystem located between the Herault River, the Vidourle River and the Mediterranean Sea (Southern France, north and west from Montpellier). It comprises two main hydrogeological sites and three main hydrological sites where karst/river interactions occur. The challenges of the MEDYCYSS observatory are i) to better characterize the karst/river interactions for the risk assessment of floods and water resource contamination; ii) to discriminate and quantify flow distribution (rapid and slow transfers) between the recharge catchment and the outlets of the hydrosystem; iii) to understand the role of the unsaturated zone on the long term storage of the aquifer and quantify the water storage variation with time; iv) to characterize groundwater hydrodynamics in karst watersheds under climatic and anthropogenic forcing at nested observation scales; and v) to quantify the recharge, which is a key variable for the assessment and management of groundwater resources in karsts. Accordingly, a continuous monitoring of the hydrochemistry and hydrodynamics (wells, karst network, permanent and temporary springs), as well as of the river and spring discharges has been constructed to characterize transfer processes and parameterize local and regional scale models. Meteorological variables are also monitored at various points where measurements of soil humidity and evapotranspiration recently started.

International audience; A neural network model is applied to simulate the rainfall-runoff relation of a karst spring. The input selection for such a model becomes a major issue when deriving a parsimonious and efficient model. The present study is focused on these input selection methods; it begins by proposing two such methods and combines them in a subsequent step. The methods introduced are assessed for both simulation and forecasting purposes. Since rainfall is very difficult to forecast, especially in the study area, we have chosen a forecasting mode that does not require any rainfall forecast assumptions. This application has been implemented on the Lez karst aquifer, a highly complex basin due to its structure and operating conditions. Our models yield very good results, and the forecasted discharge values at the Lez spring are acceptable up to a 1-day forecasting horizon. The combined input selection method ultimately proves to be promising, by reducing input selection time while taking into account: i) the model's ability to accommodate nonlinearity, and ii) the forecasting horizon.

International audience; The present study focuses on the modeling of the Lez karstic system (France) using artificial neural networks. Two methods of variable selection were compared: cross-correlation and cross-validation. In both cases, the artificial neural network forecasts closely matched the measured discharge, giving Nash criteria higher than 0.8, which can thus provide satisfactory 2-day forecasts.

International audience; This paper addresses the definition of the requirements for the design of a neural network associative memory, with on-chip training, in standard digital CMOS technology. We investigate various learning rules which are integrable in silicon, and we study the associative memory properties of the resulting networks. We also investigate the relationships between the architecture of the circuit and the learning rule, in order to minimize the extra circuitry required for the implementation of training. We describe a 64-neuron associative memory with on-chip training, which has been manufactured, and we outline its future extensions. Beyond the application to the specific circuit described in the paper, the general methodology for determining the accuracy requirements can be applied to other circuits and to other auto-associative memory architectures.

International audience; After a presentation of the nonlinear properties of neural networks, their applications to hydrology are described. A neural predictor is satisfactorily used to estimate a flood peak. The main contribution of the paper concerns an original method for visualising a hidden underground flow Satisfactory experimental results were obtained that fitted well with the knowledge of local hydrogeology, opening up an interesting avenue for modelling using neural networks.

Assessment of likely consequences of a potential accident is a major concern for loss prevention and safety promotion in process industry. Loss of confinement on a storage tank, vessel or piping on industrial sites could imply atmospheric dispersion of toxic or flammable gases. Gas dispersion forecasting is a difficult task since turbulence modeling at large scale involves expensive calculations. Therefore simpler models are used but remain inaccurate especially when turbulence is heterogeneous. The present work aims to study if Artificial Neural Networks coupled with Cellular Automata could be relevant to overcome these gaps. Two methods are reviewed and compared. An example database was designed from RANS k- e CFD model. Both methods were then applied. Their efficiencies are compared and discussed in terms of quality, real-time applicability and real-life plausibility.

(IF 3.63; Q1); International audience; Karstaquifers and watersheds represent a major source of drinking water around the world. They are also known as complex and often highly vulnerable hydrosystems due to strong surface-groundwater interactions. Improving the understanding of karst functioning is thus a major issue for the efficient management of karst groundwater resources. A comprehensive understanding of the various processes can be achieved only by studying karst systems across a wide range of spatiotemporal scales under different geological, geomorphological, climatic, and soil cover settings. The objective of the French Karst National Observatory Service (SNO KARST) is to supply the international scientific community with appropriate data and tools, with the ambition of (i) facilitating the collection of long-term observations of hydrogeochemical variables in karst, and (ii) promoting knowledge sharing and developing cross-disciplinary research on karst. This paper provides an overview of the monitoring sites and collective achievements, such as the KarstMod modular modeling platform and the PaPRIKa toolbox, of SNO KARST. It also presents the research questions addressed within the framework of this network, along with major research results regarding (i) the hydrological response of karst to climate and anthropogenic changes, (ii) the influence of karst on geochemical balance of watersheds in the critical zone, and (iii) the relationships between the structure and hydrological functioning of karst aquifers and watersheds.

Approximately 25% of the world's population is supplied by water from karstic aquifers. The understanding and protection of these appears to be essential in the context of drinking water needs increasing. In addition, contamination of drinking water by turbid water can be highly damaging by resulting in possible contamination of the served populations. In the case of Normandy, regular drinking water cut-off are necessary to preserve the health of the inhabitants. The modeling and prediction of turbidity event appears as a challenging work because of the number of phenomenon and parameters involves in turbidity variation as well as the non-linearity of the link between rainfall and turbidity. Actually, few models have been proposed to represent the relationship between turbidity and rainfall. In this context, by focusing on Yport's pumping well which is responsible for Half of Le Havre city drinking water supply, we propose an application of neural networks for turbidity prediction. During this thesis work, we emphasized the need to carry out sampling campaigns for phytosanitary products to enable the identification of possible phytosanitary product proxies such as turbidity, rainfall or conductivity. Subsequently, the work carried out in this thesis enabled us to (i) designed neural network models allow to predict at 12h and 24h the turbidity variations, (ii) test several ways to improve these models, (iii) integrate multiresolution analysis into neural networks models and finally (iiii) identify a semi proxy for phytosanitary product contamination., Près de 25% de la population mondiale est alimentée par de l’eau en provenance d’aquifères karstiques. La compréhension et la protection de ces derniers apparait donc comme essentielle dans le cadre d’une augmentation des besoins en eau potable. De plus, une contamination des forages d'alimentation en eau potable par une eau turbide peut s'avérer fortement dommageable car entrainant une possible contamination des populations desservies. Dans le cas de la Normandie, des coupures régulières son nécessaires afin de préserver la santé des habitants. La modélisation et la prédiction des augmentations de turbidité apparaissent comme un travail difficile du fait des nombreux phénomènes et paramètres régissant la turbidité ainsi que la non-linéarité de la réponse entre les précipitations et la turbidité. Peu de modèles à l'heure actuelle ont été proposés pour représenter la relation liant la turbidité avec les précipitations. C'est ainsi, en s'intéressant au forage AEP d'Yport responsable de l'alimentation en eau potable de la ville du Havre, que nous proposons une application des réseaux de neurones pour la prévision de la turbidité. Durant les travaux de thèse, nous avons mis en avant la nécessité d'effectuer des campagnes d'échantillonnages des produits phytosanitaires afin de permettre l'identification des éventuels proxies des produits phytosanitaires tel que la turbidité, les précipitations ou bien la conductivité. Par la suite, les travaux effectués dans cette thèse nous ont permis (i) de monter que les modèles par réseaux de neurones permettent de prévoir à 12h et 24h les variations de turbidité, (ii) de tester plusieurs voies d'amélioration de ces modèles, (iii) d'intégrer l'analyse multirésolution aux modèles par réseaux de neurones et pour finir (iiii) d'identifier un semi proxy des contaminations en produits phytosanitaires.

Improving knowledge of karst hydrodynamics represents a global challenge for water resources because karst aquifers provide approximately 25% of the world population in fresh water. Nevertheless, complexity, anisotropy, heterogeneity, non-linearity and possible non-stationarity of these aquifers make them underexploited objects due to the difficulty to characterize their morphology and hydrodynamics. In this context, the systemic paradigm proposes others methods by studying these hydrosystems through input-output (rainfall-runoff) relations.The approach proposed in this thesis is to use information from field measurement and from systemic analyses to constrain neural network models. The goal is to make these models interpretable in terms of hydrodynamic processes by making model functioning to be similar to natural system in order to obtain a good representation and extract knowledge from model parameters.This work covers the association of information available on the hydrosystem with correlation and spectral analyses to develop a temporal multiresolution decomposition of variables and to constrain neural network models. A new method for variable selection, adapted to represent long term hydrodynamics of the system, has been proposed. These constrained models show very good results and allow, through their parameters, to study the temporal contribution of inputs variables to the output.Modeling nonlinear and non-stationary hydrosystems with neural network has been improved by a novel implementation of data assimilation. More precisely, when non-stationarity is attributed to the catchment, data assimilation is used to modify the model parameters. When the inputs are non-stationary, data assimilation can be used to modify the inputs.The modification of inputs opens considerable scope to: i) fill gaps or homogenizing time series, ii) estimate effective rainfall.Finally, these various analyses and modeling methods, mainly developed on the karst hydrosystem Lez, can improve the knowledge of the rainfall-runoff relationship at different time scales. These methodological tools thus offer perspectives of better management of the aquifer in terms of floods and resources. The advantage of these analyses and modeling tools is that they can be applicable to other systems., La connaissance du fonctionnement hydrodynamique des karsts représente un enjeu planétaire pour la ressource en eau car ils alimentent en eau potable près de 25% de la population mondiale. Néanmoins, la complexité, l’anisotropie, l’hétérogénéité, la non-linéarité et l’éventuelle non-stationnarité de ces aquifères en font des objets encore largement sous-exploités du fait de la difficulté de caractériser leur morphologie et leur fonctionnement hydrodynamique. Dans ce contexte, le paradigme systémique permet d’apporter de nouvelles méthodes en étudiant ces hydrosystèmes au travers de la relation entre leurs signaux d’entrée (pluie) et de sortie (débit).La démarche proposée dans cette thèse consiste à utiliser un maximum d’informations, issues du terrain et des analyses systémiques, pour contraindre les modèles par réseaux de neurones. L’objectif est de les rendre interprétables en termes de processus hydrodynamiques en rapprochant le fonctionnement du modèle à celui du système naturel afin d’obtenir une bonne représentation et d’extraire des connaissances à partir des paramètres du modèle.Ainsi ce travail porte sur l’association des informations disponibles sur l’hydrosystème avec les résultats des analyses corrélatoires et spectrales pour le développement d’une décomposition multirésolution temporelle ainsi que pour contraindre les modèles par réseaux de neurones. Une nouvelle méthode de sélection des variables, plus à même de représenter le fonctionnement hydrodynamique du système à long terme, a ainsi pu être proposée. Ces modèles contrains par l’information présentent de très bons résultats et offrent la possibilité, grâce à leurs paramètres, d’étudier la contribution temporelle des variables d’entrée à l’estimation de la sortie mesurée.La modélisation des hydrosystèmes non-linéaires et non-stationnaires par réseaux de neurones a été enrichie par une implémentation originale de l’assimilation de données qui conduit à l’amélioration des performances. En effet, selon que les non-stationnarités concernent le bassin ou les forçages, l’assimilation a pu être respectivement utilisée pour modifier les paramètres ou les variables d’entrée des modèles.La modification des variables d’entrées ouvre un champ d’application considérable puisque celle-ci peut être utilisée pour i) combler des lacunes ou encore homogénéiser des séries chronologiques, ii) estimer la pluie efficace.Finalement, ces différentes méthodes d’analyse et de modélisation, essentiellement développées sur l’hydrosystème karstique du Lez, permettent d’améliorer la connaissance de la relation pluie-débit à différentes échelles temporelles. Ces outils méthodologiques offrent donc la perspective d’une meilleure gestion de l’aquifère tant en termes de crues que de ressource. L’avantage de ces outils d’analyse et de modélisation est qu’ils peuvent être transposés à d’autres systèmes.