In Brazil, the development of gullies constitutes widespread land degradation, especially in the state of South Mato Grosso, where fighting against this degradation has become a priority for policy makers. However, the environmental and anthropogenic factors that promote gully development are multiple, interact, and present a complexity that can vary by locality, making their prediction difficult. In this framework, a database was constructed for the Rio Ivinhema basin in the southern part of the state, including 400 georeferenced gullies and 13 geo-environmental descriptors. Multivariate statistical analysis was performed using principal component analysis (PCA) to identify the processes controlling the variability in gully development. Susceptibility maps were created through four machine learning models: multivariate discriminant analysis (MDA), logistic regression (LR), classification and regression tree (CART), and random forest (RF). The predictive performance of the models was analyzed by five evaluation indices: accuracy (ACC), sensitivity (SST), specificity (SPF), precision (PRC), and Receiver Operating Characteristic curve (ROC curve). The results show the existence of two major processes controlling gully erosion. The first is the surface runoff process, which is related to conditions of slightly higher relief and higher rainfall. The second also reflects high surface runoff conditions, but rather related to high drainage density and downslope, close to the river network. Human activity represented by peri-urban areas, construction of small earthen dams, and extensive rotational farming contribute significantly to gully formation. The four machine learning models yielded fairly similar results and validated susceptibility maps (ROC curve > 0.8). However, we noted a better performance of the random forest (RF) model (86% and 89.8% for training and test, respectively, with an ROC curve value of 0.931). The evaluation of the contribution of the parameters shows that susceptibility to gully erosion is not governed primarily by a single factor, but rather by the interconnection between different factors, mainly elevation, geology, precipitation, and land use.

Urban flooding is a complex natural hazard, driven by the interaction between several parameters related to urban development in a context of climate change, which makes it highly variable in space and time and challenging to predict. In this study, we apply a multivariate analysis method (PCA) and four machine learning algorithms to investigate and map the variability and vulnerability of urban floods in the city of Tangier, northern Morocco. Thirteen parameters that could potentially affect urban flooding were selected and divided into two categories: geo-environmental parameters and socio-economic parameters. PCA processing allowed identifying and classifying six principal components (PCs), totaling 73% of the initial information. The scores of the parameters on the PCs and the spatial distribution of the PCs allow to highlight the interconnection between the topographic properties and urban characteristics (population density and building density) as the main source of variability of flooding, followed by the relationship between the drainage (drainage density and distance to channels) and urban properties. All four machine learning algorithms show excellent performance in predicting urban flood vulnerability (ROC curve > 0.9). The Classifications and Regression Tree and Support Vector Machine models show the best prediction performance (ACC = 91.6%). Urban flood vulnerability maps highlight, on the one hand, low lands with a high drainage density and recent buildings, and on the other, higher, steep-sloping areas with old buildings and a high population density, as areas of high to very-high vulnerability.

The SISE-Eaux database of water intended for human consumption, archived by the French Regional Health Agency (ARS) since 1990, is a rich source of information. However, more or less regular monitoring over almost 30 years and the multiplication of parameters lead to a sparse matrix (observations × parameters) and a large dimension of the hyperspace of data. These characteristics make it difficult to exploit this database for a synthetic mapping of water quality, and to identify of the processes responsible for its diversity in a complex geological context and anthropized environment. A 10-year period (2006–2016) was selected from the Provence-Alpes- Côte d’Azur region database (PACA, southeastern France). We extracted 5,295 water samples, each with 15 parameters. A treatment by principal component analysis (PCA) followed with orthomax rotation allows for identifying and ranking six principal components (PCs) totaling 75% of the initial information. The association of the parameters with the principal components, and the regional distribution of the PCs make it possible to identify water-rock interactions, bacteriological contamination, redox processes and arsenic occurrence as the main sources of variability. However, the results also highlight a decrease of useful information, a constraint linked to the vast size and diversity of the study area. The development of a relevant tool for the protecting and managing of water resources will require identifying of subsets based on functional landscape units or the grouping of groundwater bodies.

In France, the data resulting from monitoring water intended for human consumption are integrated into a national database called SISE-Eaux, a useful and relevant tool for studying the quality of raw and distributed water. A previous study carried out on all the data from the Provence-Alpes-Côte d’Azur (PACA) region in south-eastern France (1061 sampling points, 5295 analyses and 15 parameters) revealed that the dilution of the information in a heterogeneous environment constitutes an obstacle to the analysis of ongoing processes that are sources of variability. In this article, cross-referencing this information with the compartmentalization into groundwater bodies (MESO) provides a hydrogeological constraint on the dataset that can help to better define more homogeneous subsets and improve the interpretation. The approach involves three steps: (1) A principal component analysis conducted on the whole dataset aimed at eliminating information redundancy; (2) an unsupervised grouping of groundwater bodies having similar sources of variability; (3) a principal component analysis carried out within the main groups and sub-groups identified, aiming to define and prioritize the sources of variability and the associated processes. The results supported by discriminant analysis and machine learning show that the grouping of MESO is the best-suited scale to study ongoing processes due to greater homogeneity. One of the eight main groups identified in PACA, corresponding to the accompanying aquifers of the main rivers, is analyzed by way of illustration. Water–rock interactions, redox processes and their effects on the release of metals, arsenic and fecal contamination along different pathways were specifically identified with varying impacts according to the subgroups. We discussed both the significance of the principal components and the mean values of the bacteriological parameters, which provide information on the causes and on the state of contamination, respectively. Based on the results from two different groups of MESO, some guidelines in terms of a strategy for resource quality monitoring are proposed.

Defining homogeneous units to optimize the monitoring and management of groundwater is a key challenge for organizations responsible for the protection of water for human consumption. However, the number of groundwater bodies (GWBs) is too large for targeted monitoring and recommendations. This study, carried out in the Provence-Alpes-Côte d’Azur region of France, is based on the intersection of two databases, one grouping together the physicochemical and bacteriological analyses of water and the other delimiting the boundaries of groundwater bodies. The extracted dataset contains 8627 measurements from 1143 observation points distributed over 63 GWB. Data conditioning through logarithmic transformation, dimensional reduction through principal component analysis, and hierarchical classification allows the grouping of GWBs into 11 homogeneous clusters. The fractions of unexplained variance (FUV) and ANOVA R² were calculated to assess the performance of the method at each scale. For example, for the total dissolved load (TDS) parameter, the temporal variance was quantified at 0.36 and the clustering causes a loss of information with an R² going from 0.63 to 0.4 from the scale of the sampling point to that of the GWB cluster. The results show that the logarithmic transformation reduces the effect of outliers and improves the quality of the GWB clustering. The groups of GWBs are homogeneous and clearly distinguishable from each other. The results can be used to define specific management and protection strategies for each group. The study also highlights the need to take into account the temporal variability of groundwater quality when implementing monitoring and management programs.