Search

Southern France is frequently hit with severe flash floods. These events have caused numerous casualties as well as considerable economic losses. In France, crisis inducing floods are managed at a local scale by municipalities. Current forecasting models are rarely used by these crisis managers. This is due to the fact that these models often fail to convey relevant information in an appropriate form. This work aims to determine the adequate output variable in a crisis management context with a special focus on the needs and vision of local crisis managers.The study area is the 545 sq. km. sized Gardon in Anduze in the Cévennes range, France, which is often subject to important flash floods. A feed-forward multilayer perceptron, a type of neural networks where one of the inputs is the measured output, is used to forecast water discharge. Neural networks are good candidates to model nonlinear phenomenon. Both the properties of parsimony - they provide relevant results while requiring a limited number of parameters – and of universal approximation are very helpful in hydrology. Various rainfall and discharge measurements are considered as inputs. The output variable for this model is water flow. Data ranges from 2002 to 2019 at a 30 minutes’ time step. Events are extracted from this database to compose a training set, a test set and an early stopping set. Complexity and variable selection is made using cross-validation, allowing to select the most robust model. To make the model easier to understand by end users, discharges are replaced by water levels. Both these results are compared, especially regarding their ability to reach crisis management plans levels without delay. Secondly, ensemble models based on different initializations of the parameters of the neural model during the training step are developed. They give an uncertainty margin, often desired by end users.The results are enriched through the collection of background information (end users’ opinions and habits) in order to enhance the assessment of performance. Further analysis is carried to determine the pros and cons of each approach (discharge or levels to crisis management plans levels and uncertainties representation and communication).

The use of artificial intelligence models to simulate and forecast groundwater has become more and more popular since the early 1990ies. These models able to forecast groundwater levels are increasingly being used to support decision making for water resources management and climate change impact local assessments. This study presents a comparison of different algorithms to simulate and forecast the piezometry of the Astian sands aquifer in the Occitanie region (France) at sub seasonal to seasonal scales. The aim is to set up a transferable methodology allowing quick implementation on different aquifers, to lay the foundations for a tool for water resources management focusing on droughts.Different models were tested in this study with prediction horizons from a few weeks and up to the hydrological year. Models used include (1) Multi-layer Perceptron (MLP), (2) recurrent models such as Long short-term memory models, Gated Recurrent Unit (GRU), Non-Linear Regressive Neural Networks (NARX), Dual Stage Attention Based Recurrent Networks (DA-RNN); (3) a Temporal Convolutional Network (TCN); (4) a Reservoir Computing Network (Echo State Network). Pre-processing methods were tested to increase performance and attempt to better reproduce higher frequencies, especially the Ensemble Empirical Modal Decomposition (EEMD). Input variables were the daily rainfall data, temperature data and piezometry. To validate the model and assess the performance of the simulations, different metrics were used (Nash Sutcliffe Efficiency, Kling Gupta Efficiency, Coefficient of persistency). The loss function was a combination of RMSE and NSE, the optimizer used was Adam, the training was done on two thirds of the time series and validation and testing on the remaining data.Several models achieved high performances: DA-RNN, the GRU, MLP and NARX (NSE>0.91 and Cp>0.6 at 20 days). Predictions were carried out iteratively with a 20-days window, reinjecting the predicted data and re-training the model (adaptative model) until a prediction of more than 400 days was reached (using observed rainfall and temperature). The stability and robustness of the model is further investigated through additional cross validation, estimation of confidence intervals, and simulations in different hydrogeological contexts, to aim toward a transferable tool for various aquifers.

Karst environments can be subject to rising water tables leading to rapid kinetic floods (a few hours) of great amplitude (about tens of meters) due to heavy rainfall. The Cadarache centre of the French Alternative Energies & Atomic Energy Commission (CEA), located in the French Mediterranean region (Bouches-du-Rhône), is subject to this type of underground flooding. For example, in November 2011, a cumulative rainfall of 225 mm in 72 hours was recorded at the centre, leading the Cretaceous limestone water table to a rise of nearly 40m, locally. The Cadarache centre of 1,600 hectares, has an exceptional hydrogeological monitoring network of 8 rain gauges and more than 400 piezometers, including 230 equipped with pressure/temperature sensors (115 measuring the Cretaceous aquifer). This dense monitoring network has enabled the acquisition of a large database (rainfall, water-level and temperature) over more than 15 years.The goal of this study is to improve the understanding of the Cretaceous karst aquifer hydrodynamic behaviour by analysing temperature data. This would allow an improvement of groundwater floods prediction on the site. This variable is little studied but it can provide interesting information on the aquifer hydrodynamic response and specifically the role of karst structures on pressure and mass transfers at kilometer scale.For this purpose, statistical analyses were conducted on measured temperature data in various piezometers defined as representative of the aquifer. Sorted temperature data and correlations analyses were made for different types of rainy events. This study aims to: i. Identify potential flow dynamics (deep or superficial flows), ii. Compare the temperature signal with those of rainfall and water levels.

International audience; Located in the French Mediterranean region, the French Alternative Energies and Atomic Energy Commission (CEA) Cadarache Centre is subject to significant rainfall events which can lead to groundwater floods with rapid kinetics and high amplitude. This study aims to improve the understanding of the aquifer’s heterogeneity and piezometric responses at the scale of the Cadarache centre (900 ha) in order to better apprehend the groundwater floods. The deployed method consists in: (i) taking an inventory of reliable data; (ii) conducing a preliminary study of the spatial variability of rainfall at the centre scale with the method of double-mass curves and the comparison of the rainfall amounts of the different stations; and (iii) conducting a comprehensive statistical study of piezometric data (graphs of sorted piezometric data for three different flood events, definition of an original clustering method using an automatic feature detection). The results are of two kinds: (i) several clusters were identified; three appeared to be representative of specific areas; (ii) for each specific area, piezometers were linked with different plurikilometric NW–SE and NE–SW lineaments identified by previous bibliographic studies. This extensive study on nearly 80 piezometers has thus allowed to define a method of automatic feature extraction of the sorted groundwater levels, and to establish a clustering of piezometers according to their statistical behaviour. Even if the statistical “black box” method was applied without any prerequisite on the location of the boreholes, it allowed establishing a very relevant relation between sorted water height and geological structure constraining the flows.

International audience; Karst aquifers are highly susceptible to pollution transport, particularly turbidity, because these aquifers do not filter water to any significant degree. This may occasionally induce sanitary issues for the population and, therefore, it is operationally important to predict the mobility of water with high turbidity. In this study, deep specific architectures, recurrent and feed-forward, inspired from a multilayer perceptron, are used to predict the turbidity peak and the 100 NTU threshold exceedance at the Yport pumping well in Normandy (France), used by the Le Havre Seine Métropole urban conglomeration to supply water to 240,000 inhabitants. This abstraction well pumps water from the chalk karst aquifer. For this purpose, 32 architectures were designed, with different sampling rates and numbers of used rain gauges, which, using a cross-test procedure, provided 288 different models. This arrangement represented directly the rainfall–turbidity relationship. The study also assessed model quality using original criteria defined specifically for this study. Rigorous model selection makes it possible to design models that can, with limited uncertainty, predict the threshold exceedance and the maximum turbidity peak up to 24 h in advance. More interestingly, the main outcome associated with this methodology is that the complexity of the models (i.e. the number of free parameters) behaved like a high-level parameter, controlling the quality of the results independently from field considerations. This result is consistent with the well-known bias-variance tradeoff.; Los acuíferos kársticos son altamente susceptibles al transporte de contaminación, en particular la turbidez, porque estos acuíferos no filtran el agua en un grado significativo. Esto puede provocar problemas sanitarios a la población y, por lo tanto, es operativamente importante predecir la movilidad del agua con alta turbidez. En el presente estudio, se utilizan arquitecturas específicas profundas, recurrentes y de avance, inspiradas en un perceptrón multicapa, para predecir el pico de turbidez y la superación del umbral de 100 NTU en el pozo de bombeo de Yport en Normandía (Francia), utilizado por la zona urbana de Le Havre Seine Métropole para abastecer de agua a 240,000 habitantes. Este pozo de extracción bombea agua del acuífero kárstico de caliza. Para ello se diseñaron 32 arquitecturas, con diferentes velocidades de muestreo y número de pluviómetros utilizados, que mediante un procedimiento de prueba cruzada proporcionaron 288 modelos diferentes. Esta disposición representaba directamente la relación lluvia-turbidez. En el estudio también se evaluó la calidad de los modelos utilizando criterios originales definidos específicamente para este estudio. La rigurosa selección de los modelos permite diseñar modelos que pueden, con una incertidumbre limitada, predecir la superación del umbral y el pico máximo de turbidez con hasta 24 horas de antelación. Lo que es más interesante, el principal resultado asociado a esta metodología es que la complejidad de los modelos (es decir, el número de parámetros libres) se comportó como un parámetro de alto nivel, controlando la calidad de los resultados independientemente de las consideraciones de campo. Este resultado es coherente con el conocido equilibrio entre sesgo y varianza.; Les aquifères karstiques sont fortement vulnérables au transport de polluants, particulièrement la turbidité, du fait que ces aquifères ne permettent pas la filtration de l’eau de manière significative. Ceci peut occasionnellement entrainer des problèmes sanitaires pour la population et, il est donc important de prévoir la mobilité de l’eau fortement turbide. Dans cette étude, des architectures spécifiques profondes, récurrentes et non récurrentes, inspirées des perceptrons multicouches sont utilisées pour prévoir le pic de turbidité et le dépassement de la valeur seuil de 100 NTU sur le forage d’Yport en Normandie (France) utilisé par La Métropole Le Havre Seine pour l’alimentation en eau potable de ses 240 000 habitants. Ce forage exploite un aquifère crayeux karstique. A cette fin, 32 architectures ont été conçues, avec différents pas d’échantillonnage et différents nombres de pluviomètres, qui, à l’aide d’une procédure de “test croisé”, ont fourni 288 modèles différents. Cees modèles implémentent directement la relation pluie-turbidité. Cette étude évalue également la qualité du modèle par l’utilisation de critères originaux spécialement définis pour cette étude. Une sélection rigoureuse des modèles a permis de créer des modèles qui peuvent, avec une incertitude réduite, prédire le dépassement d’une valeur seuil et le pic maximum de turbidité jusqu’à 24 h en avance. Plus intéressant encore, le principal résultat associé à cette méthodologie est que la complexité des modèles (par ex. le nombre de paramètres libres) se comporte comme un hyperparamètre, contrôlant la qualité des résultats de manière indépendante des considérations de terrain. Ce résultat est conforme au dilemme bien connu entre le biais et la variance.; Os aquíferos cársticos são altamente susceptíveis ao transporte de poluição, particularmente à turbidez, porque estes aquíferos não filtram a água em grau significativo. Isto pode ocasionalmente induzir problemas sanitários para a população e, portanto, é operacionalmente importante prever a mobilidade da água com elevada turbidez. Neste estudo, arquiteturas de aprendizado profundo, recorrentes e de pré-alimentação, inspiradas num perceptron de várias camadas, são utilizadas para prever o pico de turbidez e a ultrapassagem do limiar de 100 NTU no poço de bombeamento de Yport na Normandia (França), utilizado pelo conglomerado urbano Metrópole de Le Havre Seine para fornecer água a 240,000 habitantes. Este poço de captação bombeia água do aquífero de carstes de calcário. Para isso foram concebidas 32 arquiteturas de aprendizado, com diferentes taxas de amostragem e números de pluviômetros usados, que, utilizando um procedimento de teste cruzado, forneceram 288 modelos diferentes. Este arranjo representava diretamente a relação chuva-turbidez. O estudo também avaliou a qualidade do modelo utilizando critérios originais definidos especificamente para este estudo. A rigorosa seleção do modelo permite projetar modelos que podem, com incerteza limitada, prever a ultrapassagem do limiar e o pico máximo de turbidez com até 24 horas de antecedência. Mais interessante ainda: o principal resultado associado a esta metodologia é que a complexidade dos modelos (ou seja, o número de parâmetros livres) comportou-se como um parâmetro de alto nível, controlando a qualidade dos resultados independentemente de considerações feitas em campo. Este resultado é consistente com o conhecido conflito de escolha entre variância e viés.; 岩溶含水层极易受到污染运移,尤其是浊度,因为这些含水层不会对水进行任何明显的过滤。这有时会引起人群的卫生问题,因此预测高浊度水的流动性十分重要。在这项研究中,从多层感知器得到灵感,使用递归和前馈的深层特定架构来预测浊度峰值,诺曼底(法国)的Yport抽水井从白垩喀斯特含水层中抽水,浊度超过了100 NTU,Le Havre Seine Métropole都市集团使用该水井为24万居民供水。为此,设计了32种具有不同采样率和不同数量的雨量计的架构,通过交叉验证提供了288种不同的模型。这种安排直接代表了降雨-浊度的关系。本研究还使用了专门为该研究定义的原始标准评估模型质量。严格的模型选择使得设计模型能够在有限的不确定性下,提前24小时预测阈值超出和最大浊度峰值。更重要的是,与此方法相关的主要结果是,模型的复杂性(即自由参数的数量)表现得像一个高维参数,独立于现场条件而控制结果的质量。这一结果与众所周知的偏方差权衡一致。

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.

International audience; Approximately, 25% of the world population drinking water depends on karst aquifers. Nevertheless, due to their poor filtration properties, karst aquifers are very sensitive to pollution and specifically to turbidity. As physical processes involved in transport of solid/suspended particles (advection, diffusion, deposit…) are complicated and badly known in underground conditions, a black-box modeling approach using neural networks is promising. Despite the well-known ability of universal approximation of multilayer perceptron, it appears difficult to efficiently take into account hydrological conditions of the basin. Indeed, these conditions depend both on the initial state of the basin (schematically wet or dry: long timescale component), and on the intensity of rainfall, usually associated to short timescale component. In this context, the present paper addresses the application of the multiresolution analysis to decompose the turbidity on several timescales in order to better consider various phenomena at various timescales (flow in thin or wide fissures for example). Because of “boundary effects”, usually neglected by authors, a specific adaptation was shown as necessary that diminishes the quality of results for real-time forecasting. Decomposing turbidity using multiresolution analysis adds thus questionable improvements.

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.

IEEE International Conference on Environmental Engineering (EE), Milan, ITALY, MAR 12-14, 2018; International audience; This paper investigates the way to adapt neural network design to non-Gaussian environmental data. The process of model selection is specifically investigated in order to make the model more robust. It appears that the standard method of cross-validation gains to be applied on an ensemble model, rather than a unique model, in order to apply additional regularization. Specific architectures of neural networks based on multilayer perceptron were used simultaneously with various methods of complexity selection. Prediction results on floods and droughts show that the sensitivity to the initial value of parameters could be greatly reduced. A case-study is chosen on a exceptionally complex hydrosystem, subjected to critical water resource conflicts.

International Work-Conference on Time Series (ITISE), Granada, SPAIN, JUN 27-29, 2016; International audience; Approximately 25% of the world population drinking water depends on karst aquifers. Nevertheless, due to their poor filtration properties, karst aquifers are very sensitive to pollutant transport and specifically to turbidity. As physical processes involved in solid transport (advection, diffusion, deposit.) are complicated and badly known in underground conditions, a black-box modelling approach using neural networks is promising. Despite the well-known ability of universal approximation of multilayer perceptron, it appears difficult to efficiently take into account hydrological conditions of the basin. Indeed these conditions depend both on the initial state of the basin (schematically wet or dry), and on the intensity of rainfalls. To this end, an original architecture has been proposed in previous works to take into account phenomenon at large temporal scale (moisture state), coupled with small temporal scale variations (rainfall). This architecture, called hereafter as ``two-branches'' multilayer perceptron is compared with the classical two layers perceptron for both kinds of modelling: recurrent and non-recurrent. Applied in this way to the Yport pumping well (Normandie, France) with 12 h lag time, it appears that both models proved crucial information: amplitude and synchronization are better with ``two-branches'' feed forward model when thresholds surpassing prediction is better using classical feed forward perceptron.

Flash floods pose significant hazards in urbanized zones and have important implications that should probably increase due to global changes. Early warning is thus a priority that could be done by using forecast models. When such events occur on karst basins, well known for their intrinsic complexity, anisotropy and heterogeneity, the lack of knowledge regarding the various hydrodynamic behaviours involved in karst systems prevents to use physical models. A generic black box method seems thus to be adequate; specifically, artificial neural network modelling seems to be a relevant method. To model hydrosystem behaviour efficiently, neural networks need to dispose of relevant data sets constituting input and output variables, and rigorous application of regularization methods. In this study, we propose to apply two kinds of models: feedforward and recurrent neural networks to flash flood forecasting. These models are designed using a specific methodology to diminish their complexity. They are applied to the Lez karst aquifer, located in southern France, and their performances are compared. Recurrent model can be used at longer lead time for operational flash flood forecasting. Nevertheless, for short horizon of prevision, performances of feedforward model are higher than those showed by recurrent one. The comparison of both models is then necessary to guide the improvement of operational flash flood forecasting.

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.

Karst hydrosystems constitute important water resource but their recharge and emptying process are poorly known and quantified. Water resource management is thus difficult. Nevertheless, it is a major issue when rainfall is not uniformly distributed during the year, as in Mediterranean climate. This study proposes a method based on neural networks permitting to simulate karst emptying as a function of the pumping volume during the dry period. Applied to the Lez karst system, the model provides excellent simulations of the water level at the main outlet of the system by using mean pumping discharge and zero rainfall hypothesis during dry period. An arbitrary extreme scenario is also provided by introducing a mean pumping volume.

The ability of the multilayer perceptron to model the inverse relation of a fictitious watershed is investigated. Comparison is done between a new formulation of data assimilation and the standard multilayer perceptron applied to three kinds of models: static, feedforward and recurrent. It appears that both techniques are equivalent and allow a very good estimation of the inverse relation. This study aims at proposing methods to supplement or adapt historical databases to modern instrumentation. Datasets will thus be used over a longer time-series to better apprehend the consequences of global warming.

International audience; Karst aquifers provide water resources for a large part of the Mediterranean population and water resources become a strategic problem during summer when the population increases due to tourism. To help managers to optimize the exploitation of karst aquifer waters this paper studies the ability of a neural model to efficiently simulate and forecast water table levels a few months ahead during the dry season. The neural model is a recurrent multilayer perceptron that learns the relations between inputs (mainly rainfall and pumping discharge) and output (water table level). After a training step using several years of data, the model is assessed on a never seen year to be validated. Particular attention is devoted to the dry season (May\textendashSeptember). The model achieved good forecast of the maximal observed drawdown. To investigate the usefulness of the model as an operational tool, various scenarios of future rainfalls and future pumping are proposed and associated forecasts are analysed. Scenarios are the following: zero-rainfall scenario and mean forecast rainfall 1 week ahead; in both cases, the model proposes accurate estimations of the maximal drawdown. In a second step, pumping scenarios are investigated: a mean pumping scenario during the dry season and the maximum pumping scenario taking into account the actual pumps. One more time, it is demonstrated that the maximal drawdown can be efficiently forecast for the dry season. The methodology is generic and can thus be used with profit by managers on other karst aquifers.

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 ...

Karst catchments frequently exhibit complex exchanges between surface and subterranean flow. While the swing between surface flood and underground flood is complex, the ability to predict such behavior would be of great interest for flood forecasting and water recharge assessment. To this end an innovative methodology is proposed to visualize internal variables of a neural network model. It proves to be efficient to extract internal variables highly correlated to measured signals previously identified as proxy of the karst-river exchanges. The study focuses on a small Mediterranean catchment where karst/river interactions control the dynamic and genesis of surface floods. But the methodology is generic and can be applied to any catchment provided the availability of a sufficient database.

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.

Summary As it is the case with many karst aquifers, the Lez basin (southern France) is heterogeneous and thus difficult to model. Due to its supply of fresh water and its ability to reduce flooding however, more in-depth knowledge of basin behavior has proven critical. In addressing this challenging issue, an original methodology based on neural networks is presented herein so as to better understand the hydrodynamic behavior of such systems. Dedicated architecture containing several sub-networks, each being associated to a specific “homogeneous” geological zone that corresponds to a sub-basin contributing discharge, is described. A method, previously proposed for variable selection, has been applied to determine both the relative contribution of the considered zone and its response time. Given the difficulty of verifying such non-observable knowledge, a specific validation step has also been provided. This methodology has been successfully applied to the difficult case of the Lez karst basin, yielding improved knowledge on basin behavior and a revised delimitation of its feeding basin. A new approach has been adopted for the basin, leading the way to additional fieldwork and revised methodologies, particularly regarding the protection of water supply. It should be emphasized that the proposed methodology is generic and applicable to all kinds of aquifers with available and sufficient rainfall and discharge data.

The development of a high potential for out-door or hostile environment ability necessitates an adaptive and versatile control system in order to avoid the difficulties of complex and unpredictable behaviour modelling. Self-organisation allows artificial machines to approach these goals. For that, reinforcement methods are investigated: considering that the relations between the task to perform and the environment may act as a supervisor, efficient learning is performed. Starting from a very simple structure inspired by insect behaviour, the study presented in this paper is devoted to a neural-network-based control system which allows a simulated six-legged robot to walk and avoid obstacles even when it is partially damaged.

Neural networks are increasingly used in the field of hydrology due to their properties of parsimony and universal approximation with regard to nonlinear systems. Nevertheless, as a result of the non stationarity of natural variables (rainfalls and consequently discharges) it appeared as difficult to capture both dynamics (roughly slow and fast) in a same neural network while their respective behaviors cannot be fully dissociated. For this reason the identification of the behavior of a complex aquifer, such as the aquifer of the Lez spring addressed in this study, is not yet fully achieved. Taking profit of such an analysis this paper presents an original way to decompose the behavior of the aquifer in several independent components using the powerful tool of multiresolution analysis. The method allows thus to perform discharge prediction without rainfalls prediction up to three days ahead increasing considerably the performance of the predictive methods.

Neural networks are increasingly used in the field of hydrology due to their properties of parsimony and universal approximation with regard to nonlinear systems. Nevertheless, as a result of the existence of noise and approximations in hydrological data, which are very significant in some cases, such systems are particularly sensitive to increased model complexity. This dilemma is known in machine learning as bias–variance and can be avoided by suitable regularization methods. Following a presentation of the bias–variance dilemma along with regularization methods such as cross-validation, early stopping and weight decay, an application is provided for simulating and forecasting karst aquifer outflows at the Lez site. The efficiency of this regularization process is thus demonstrated on a nonlinear, partially unknown basin. As a last step, results are presented over the most intense rainfall event found in the database, which allows assessing the capability of neural networks to generalize with rare or extreme events.

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.