Recently, Caribbean coasts have experienced atypical massive arrivals of pelagic Sargassum with negative consequences both ecologically and economically. Based on deep learning techniques, this study proposes a novel algorithm for floating and accumulated pelagic Sargassum detection along the coastline of Quintana Roo, Mexico. Using convolutional and recurrent neural networks architectures, a deep neural network (named ERISNet) was designed specifically to detect these macroalgae along the coastline through remote sensing support. A new dataset which includes pixel values with and without Sargassum was built to train and test ERISNet. Aqua-MODIS imagery was used to build the dataset. After the learning process, the designed algorithm achieves a 90% of probability in its classification skills. ERISNet provides a novel insight to detect accurately algal blooms arrivals.
The atypical arrival of pelagic Sargassum to the Mexican Caribbean beaches has caused considerable economic and ecological damage. Furthermore, it has raised new challenges for monitoring the coastlines. Historically, satellite remote-sensing has been used for Sargassum monitoring in the ocean; nonetheless, limitations in the temporal and spatial resolution of available satellite platforms do not allow for near real-time monitoring of this macro-algae on beaches. This study proposes an innovative approach for monitoring Sargassum on beaches using Crowdsourcing for imagery collection, deep learning for automatic classification, and geographic information systems for visualizing the results. We have coined this collaborative process “Collective View”. It offers a geotagged dataset of images illustrating the presence or absence of Sargassum on beaches located along the northern and eastern regions in the Yucatan Peninsula, in Mexico. This new dataset is the largest of its kind in surrounding areas. As part of the design process for Collective View, three convolutional neural networks (LeNet-5, AlexNet and VGG16) were modified and retrained to classify images, according to the presence or absence of Sargassum. Findings from this study revealed that AlexNet demonstrated the best performance, achieving a maximum recall of 94%. These results are good considering that the training was carried out using a relatively small set of unbalanced images. Finally, this study provides a first approach to mapping the Sargassum distribution along the beaches using the classified geotagged images and offers novel insight into how we can accurately map the arrival of algal blooms along the coastline.
Coastal settings variations are linked to composition, structural, and functional differences among mangrove ecotypes. Basin mangroves undergo larger flooding and salinity fluctuations, yet remain understudied, compared to other ecotypes. We evaluated the effect of flooding and air temperature (T a) on the surface energy balance and eddy covariance‐derived net CO2 ecosystem exchange (NEE) of a basin mangrove with sporadic freshwater flooding. During the study period (June 2017–November 2018) the site was more frequently not flooded. Under these conditions, in combination with high T a (>27°C), daytime CO2 uptake was significantly lower, while evapotranspiration and sensible heat flux were higher than when flooded. CO2 uptake increased with T a and vapor pressure deficit, but after exceeding a threshold (29°C and 1.4 kPa), uptake declined. Flooding extended this T a threshold by 3°C and increased the radiation saturation point of NEE. The ecosystem is a net sink of CO2 annually (709 ± 09 g C m−2 yr−1), however, it turned a net source of CO2 for 3 months of prolonged rainfall deficit. Most of the precipitation input is returned to the atmosphere (evaporative index: 0.94) and on average, for each gram of atmospheric carbon assimilated into the ecosystem, 2.21 ± 0.50 kg of water was returned to the atmosphere. This ecosystem‐level water‐use efficiency decreased with flooding, but the correlation was not strong. Future temperature increases and lower precipitation (local and regional), combined with lower water table (and/or stronger saline intrusion), imply important losses of primary productivity and stored soil carbon in basin mangroves of northeast Yucatan Peninsula.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.