Using Machine-Learning Algorithms for Eutrophication Modeling: Case Study of Mar Menor Lagoon (Spain)

The Mar Menor is a hypersaline coastal lagoon with high environmental value and a characteristic example of a highly anthropized hydro-ecosystem located in the southeast of Spain. An unprecedented eutrophication crisis in 2016 and 2019 with abrupt changes in the quality of its waters caused a great social alarm. Understanding and modeling the level of a eutrophication indicator, such as chlorophyll-a (Chl-a), benefits the management of this complex system. In this study, we investigate the potential machine learning (ML) methods to predict the level of Chl-a. Particularly, Multilayer Neural Networks (MLNNs) and Support Vector Regressions (SVRs) are evaluated using as a target dataset information of up to nine different water quality parameters. The most relevant input combinations were extracted using wrapper feature selection methods which simplified the structure of the model, resulting in a more accurate and efficient procedure. Although the performance in the validation phase showed that SVR models obtained better results than MLNNs, experimental results indicated that both ML algorithms provide satisfactory results in the prediction of Chl-a concentration, reaching up to 0.7 R2CV (cross-validated coefficient of determination) for the best-fit models.

Polychaete assemblages in a tropical hypersaline coastal lagoon of the southeastern Gulf of Mexico during the rainy season

Introduction: The Río Lagartos lagoon, located in the Ría Lagartos Biosphere Reserve, Yucatán, Gulf of Mexico, is a coastal hypersaline system ca. 80 km long (east-west). It comprises three basins: western (close to Río Lagartos fishermen village), middle (Las Coloradas) and eastern (close to El Cuyo fishermen village), that communicate through very narrow natural channels. Despite several studies have been performed on the vertebrate fauna, the aquatic invertebrates, and especially polychaetes, remain largely unknown. Objective: The objective of this study is to describe the composition and distribution of the benthic polychaete community, and to analyse potential environmental drivers. Methods: The biological material was collected in 16 stations distributed along the lagoon during the rainy season (September 2017). Two replicates per station were obtained using a Ponar standard dredge or cores (6” diameter). Environmental variables such as grain size, organic carbon content in the sediments, and salinity, among others, were measured. Results: A total of 827 specimens belonging to 26 species and 16 families were identified. Of these, 23 species are new records for the Río Lagartos lagoon. Community composition changed between the different basins associated with strong gradients in salinity, subaquatic vegetation (algae and seagrasses) proportions in the samples and grain size. No polychaetes were recorded at the easternmost basin (El Cuyo basin), where salinity was between 67-80 psu. In the rest of the lagoon, the distribution of polychaetes was heterogeneous, especially near the mouth (western basin), where the highest and lowest density, species richness and diversity were recorded. The highest density was found at station 6, where dense algal mats of the genus Avrainvillea dominated. The families Syllidae and Nereididae were the most abundant and widely distributed families in the lagoon. The species Syllis lagunae and Nereis pelagica dominated the western basin and Prionospio heterobranchia and Sphaerosyllis taylori dominated the middle basin. Conclusions: The salinity records associated with some species were well above the top limits previously reported, establishing the euryhaline character of many species in the region.

Growth of Penaeus aztecus Ives, 1891 and Penaeus duorarum Burkenroad, 1931 in a hypersaline lagoon: relationships with environmental conditions and body size

Growth rates of the brown shrimp Penaeus aztecus Ives, 1891 and pink shrimp Penaeus duorarumBurkenroad, 1931 were estimated using length-frequency data in the hypersaline coastal lagoon, Laguna Madre of Tamaulipas, Mexico. The influence of environmental variables (salinity and temperature) and shrimp body size on the growth of both penaeid species were also evaluated. Shrimps were collected monthly from two fishing zones located at the central part of the lagoon throughout one year. A total of 4458 shrimps were analysed (69.3% P. aztecus and 30.7% P. duorarum) with total lengths (TL) ranging from 50.9 to 131.4 mm in P. aztecus and 59.7 to 134.5 mm in P. duorarum. Mean growth rate (±SD) of P. duorarum (3.10 ±1.78 mm TL per week) was slightly higher than that of P. aztecus (2.71 ±1.37 mm TL per week); however, the interspecific difference was not significant (p>0.05). Growth rates for both the penaeid shrimp species increased as water temperature increased. Additionally, a negative relationship between the growth rate and body length of shrimp was also detected suggesting that the positive effect of water temperature on the increase in shrimp length may be size-dependent.

Richness and diversity of helminth species in eels from a hypersaline coastal lagoon, Mar Menor, south-east Spain

The composition and diversity of parasite communities and intestinal components, as well as infra-community structure, were assessed in eels Anguilla anguilla, from Mar Menor, a permanent Mediterranean hypersaline coastal lagoon. Data were used to determine whether this helminth community differs in composition and structure from that of eels in lagoons with lower salinity regimes and higher freshwater inputs. A total prevalence of 93% was detected. Specifically, parasites were identified as Deropristis inflata, Bucephalus anguillae, Contracaecum sp., Anguillicoloides crassus and two plerocercoid larvae belonging to the order Proteocephalidae, the marine species representing 91% of the isolated helminths. In the total community, digenetic trematodes were the dominant group of helminths, and D. inflata, an eel specialist, dominated both the component community and the infra-community. Richness and diversity were low but similar to those reported in other saline lagoons, and maximum species per eel did not exceed four. At the infra-community level, higher abundance than in other brackish or marine Mediterranean environments was detected. The findings provide further evidence of the similarity in composition and structure of helminth communities in eels from various Mediterranean coastal lagoons. Moreover, salinity-dependent specificities are well supported and reflect the life history of individual eels.