Awa Niang

Automatic neural classification of ocean colour reflectance spectra at the top of the atmosphere with introduction of expert knowledge

We propose an automatic neural classification method for ocean colour (OC) reflectance measurements taken at the top of the atmosphere (TOA) by satellite-borne sensors. The goal is to identify aerosol types and cloud contaminated pixels. This information is of importance when selecting appropriate atmospheric correction algorithms for retrieving ocean parameters such as phytoplankton concentrations. The methodology is based on the use of Topological Neural network Algorithms (TNA, so-called Kohonen maps). The pixels of the remotely sensed image are characterised by a vector whose components are the spectral TOA measurement and the standard deviation of a small spatial structure. The method is a three-step method. The first step is an unsupervised classification built from a learning data set; it clusters pixel vectors which are similar into a certain number of groups. Each group is characterised by a specific vector, the so-called reference vector (rv), which summarises the information contained in all the pixels belonging to that group. The second step of the method consists of labeling the reference vectors with the help of an expert in ocean optics. The groups are then clustered into classes corresponding to physical characteristics provided by the expert. The third step consists of analyzing full images and classifying them by using the classifier which has been determined during the first two steps. The method was applied to the Cape Verde region, which exhibits important seasonal variability in terms of aerosols, cloud coverage and ocean chlorophyll-a concentration. We processed POLDER data to test the algorithm. We considered four classes: pixels contaminated by clouds; two types of pixels containing mineral dusts; and pixels containing maritime aerosols only. The method was able to take into account the information given by the expert and apply it to unlabeled pixels. This methodology could easily be extended to a larger number of classes, the major problem being to find adequate expertise to label the classes.

An intelligent decision support system for irrigation system management

Considers the design of a decision support system for the short term water resource management of an irrigation system. The operations of similar systems are often impaired by different stochastic events like device failure, heavy rains or dry periods and new long term goals. To be effective, such a decision support system which is based on knowledge techniques (state identification) and adaptive optimization (short term plans), requires the development of an information system based on water resource demand and supply. This information system gathers data from different fields (hydrology, meteorology and agriculture) so that accurate predictions about available reserves and demand levels can be performed. So, this communication presents the structure of the decision support system and focuses on tactical management information needs. The case study considered deals with a three-reach irrigation system.

Neural approach to inverting complex system

A neural network model is proposed for reconstructing ocean salinity profiles from sea surface parameters only. The method is applied to the tropical Atlantic. Prior data mining on a complete dataset shows that latitude and sea surface salinity are the most relevant surface parameters in the prediction of salinity profiles. A classification using a self-organizing map learned on a large multivariate dataset is able to retrieve the most probable vertical salinity profiles from the surface parameters only. Both in situ and modelled oceanic data are used to evaluate the results. The reconstruction misses some salinity features in areas with high time-space variability in which the limited available dataset was unable to provide the complete variability ranges during the learning process. However, apart from these restricted areas, the salinity profiles are reproduced with correlations greater than 0.95 for most of the profiles of the test set. HighlightsReconstructing ocean salinity profiles from sea surface parameters.Latitude and SSS are the most relevant in the prediction of salinity profiles.Both in situ and modelled oceanic data are used to evaluate the results.The salinity profiles are reproduced with high correlations (0.95) in the test set.

Spatial Distribution of Aerosol Optical Thickness Retrieved from SeaWiFS Images by a Neural Network Inversion over the West African Coast

Aerosol optical thickness (AOT) was provided by SeaWiFS over oceans from October 1997 to December 2010. Weekly, monthly, and annually maps might help scientifics to better understand climate change and its impacts. Making average of several images to get these maps is not suitable on West African coast. A particularity of this area is that it is constantly traversed by desert dust. The algorithm used by SeaWiFS inverts the reflectance measurements to retrieve the aerosol optical thickness at 865 nm. For the poorly absorbing aerosol optical thickness less than 0.35, the standard algorithm works very well. On the west African coast that is often crossed by desert aerosol plumes characterized by high optical thicknesses. In this paper we study the spatial and temporal variability of aerosols on the West African coast during the period from December 1997 to November 2009 by using neural network inversion. The neural network method we used is mixed method of neuro-variational inversion called SOM-NV. It is an evolution of NeuroVaria that is a combination of a variational inversion and multilayer perceptrons, multilayer perceptrons (MLPs). This work also enables validation of the optical thickness retrieved by SOM-NV with AOT in situ measurements collected at AErosol RObotic NETwork (AERONET) stations.

Universities as Solutions to Twenty-First Century Coastal Challenges: Lessons from Cheikh Anta Diop Dakar University

The past 30 years have brought radical changes to coastal zones in West Africa. These areas have experienced rapid urban expansion and business growth, along with widespread overexploitation of natural resources. This chapter illustrates the process undertaken by a Senegalese university to shift its goals in order to increase understanding of the complex social-ecological systems affecting one another in West African coastal areas. This adjustment in university priorities has led to valuable contributions to national research and development systems, helping to facilitate sustainable management of coastal areas in this region.

Morphological and Hydrodynamic Changes in the Lower Estuary of the Senegal River: Effects on the Environment of the Breach of the ‘Langue De Barbarie’ Sand Spit in 2003

The Senegal River estuary and its coastal interface, the ‘Langue de Barbarie’, a long sandy spit shaped by the littoral dynamics, are located in Sahelian zone. Their instability results in considerable risk to their hydrological, climatic and ecological balances. The ecosystems there have suffered severely from the effects of drought and reduced freshwater inflows. Dams have partly dealt with the problem of water availability, especially in the upper basin. But the effects of their management on the environment have often been criticized. The breaching of the Langue de Barbarie sand spit on 4 October 2003 was justified by the imminent flooding of the city of St. Louis. It allowed the rapid escape of the flood waters of the Senegal River and thus saved St. Louis. The initial channel of 4 m width is now 2 km wide, with significant changes to the environment. This rapid evolution of the breach was accompanied by major impacts on the environment. Today, the lower estuary of the Senegal River is at a critical stage of its history with the accumulation of vulnerability factors such as the development of a marine dynamic, the over-salinization of water and lands and the rapid morphological change of the Langue de Barbarie sand spit caused by severe coastal erosion. In socioeconomic terms, despite the attempts of the communities to adapt through the development of activities such as salt extraction or the move of market-gardening activities towards less disadvantaged areas, the situation remains alarming, in view of the impoverishment of the local communities.

Analysis of the Senegalo-Mauritanian upwelling by processing satellite remote sensing observations with topological maps.

The Senegalo-Mauritanian upwelling is a very productive upwelling occurring along the West coast of Africa. Its seasonal and inter-annual variability south of 20°N was analyzed by processing ocean color data and sea surface temperature provided by satellite sensors. We used a classification methodology consisting in a neural network topological map and a hierarchical ascendant classification. Four classes can explain most of the variability of the upwelling. Its extent is maximum in February-March, minimum in August September. The variability is linked to that of the wind. The classes can be considered as statistical indices allowing us to investigate the variability of the upwelling.