Search

Human practices and industrial activities are increasingly becoming critical sources of water contamination, leading to groundwater quality deterioration. Unlike most studies in the literature that focus on chemical analyses, using prior knowledge on the deterioration phenomenon and predefined contaminating parameters, this works aims at defining a general method for water quality contamination detection. Thereafter, it will allow decision makers in charge of water resource management to predict its quality deterioration and anticipate any consequence on human health. To this end, Prognostics and Health Management, which is usually applied on industrial systems, has been transposed to water to continuously monitor it, detect and predict anomalous cases. Due to a high rate of missing values, a model selection method for multiple imputation has been implemented in order to reduce the induced uncertainty of the observations, while a dimensionality reduction method has been performed to mitigate the noise induced by the large amount of parameters of interest (more than fifty). To process the detection, unsupervised and supervised learning methods have been combined, which allowed to determine four classes of water quality and to provide relevant insights on the anomalous cases. Finally, the homogeneity of the resulting classes has been evaluated using a Support Vector Machine classifier. The proposed method does not depend on a specific context and therefore, can be generalized to provide accurate rules for water quality classification of any source of data.

Bone geochemistry of pre-Dogon (11th–16th cent. AD) and Dogon (17th–20th cent. AD) populations buried in two caves of the Bandiagara Cliff (Mali) was examined for the purpose of exploring their diet and mobility. While the Dogon were the subject of extensive ethnographic studies, the lifestyle of the pre-Dogon, so-called “Tellem” is not known. We therefore compared the geochemical composition of Dogon bones with the results obtained from modern dietary surveys in Mali, to establish the parameters of a dietary model that was further applied to the pre-Dogon in order to expand our knowledge concerning their way of life.