Harnessing LSTM and XGBoost algorithms for storm prediction.

Storms can cause significant damage, severe social disturbance and loss of human life, but predicting them is challenging due to their infrequent occurrence. To overcome this problem, a novel deep learning and machine learning approach based on long short-term memory (LSTM) and Extreme Gradient Boosting (XGBoost) was applied to predict storm characteristics and occurrence in Western France. A combination of data from buoys and a storm database between 1996 and 2020 was processed for model training and testing.

Hepatitis A virus detection by RT-qPCR in shellfish samples from three Moroccan Atlantic coastal areas: Dakhla, Oualidia, and Moulay Bousselham.

This comparative study assessed hepatitis A virus (HAV) contamination in shellfish harvesting areas in Morocco, and the correlations between viral contamination and rainfall. To this aim, HAV contamination was evaluated in 156 shellfish samples collected at three Moroccan coastal areas (52 samples/area): Dakhla (class A), Oualidia (class B), and Moulay Bousselham (class C). Samples were collected monthly between March 2018 and March 2019, and included oysters from different farms at the Oualidia and Dakhla coastal areas, and wild mussels at the Moulay Bousselham lagoon.

Classifying and Mapping Cultural Ecosystem Services Using Artificial Intelligence and Social Media Data.

Quantifying and mapping cultural ecosystem services are complex because of their intangibility. Data from social media, such as geo-tagged photographs, has been proposed for mapping cultural use or appreciation of ecosystems. However, manual content analysis and classification of large numbers of photographs is time-consuming.

Environmental and ecological risk of heavy metals in the marine sediment from Dakhla Bay, Morocco.

Heavy metal assessment in Dakhla Bay (Atlantic coast) was carried out using different environmental and ecological indices. Heavy metal concentrations were measured using ICP-AES and were compared with consensus-based sediment quality guidelines. The distribution of heavy metal concentrations varies for the three groups: (i) lead distribution is dominated by its associations with copper and chromium.

Environmental risk assessment of the Moroccan Atlantic continental shelf: the role of the industrial and urban area.

The present research presents the first large-scale analysis of heavy metal assessment in the Moroccan Atlantic shelf. This work provides scientific basis for future studies on environmental research and fills the gap in knowledge on the worldwide continental platforms. Metal distributions identified three different zones, mainly influenced by industrial and urban sewer (northern areas), agriculture runoffs (central zone), and estuarine discharges (southern areas), respectively.

Evaluation of the anthropogenic influx of metal and metalloid contaminants into the Moulay Bousselham lagoon, Morocco, using chemometric methods coupled to geographical information systems.

Superficial and cored sediment samples from the Moulay Bousselham lagoon and sub-watershed were analyzed for Al, Fe, Cu, Zn, Pb, Mn, Ni, Cr, As, Hg, and Cd. The temporal and spatial distributions of the main contamination sources of heavy metals were identified and described using chemometric and geographic information system (GIS) methods. Sediments from coastal lagoons near urban and agricultural areas are commonly contaminated with heavy metals, and the concentrations found in surface sediments are significantly higher than those from 50-100 years ago.