Different Animal Models and Levels of Sophistication for Sensing the Sea Environment

Lewis Keats^*
*Correspondence: Lewis Keats, Department of Biology Science, University of London, London, UK, Email:

Introduction

There is a lot of study being done right now. Capable of finding marine debris here is the first dataset built using multispectral satellite imagery to separate marine debris from other marine characteristics. Events involving plastic debris have occurred in numerous locations across the globe across a range of sea state conditions, seasons, and years. The dataset has undergone a rigorous statistical and spectral analysis. Weakly supervised semantic segmentation and multi-label classification tasks with wellestablished ML baselines are provided [1].

Description

Design and test marine debris detection methods based on artificial intelligence and deep learning architectures, as well as satellite preprocessing pipelines. an open access dataset that the spectral behaviour of certain floating materials, sea state characteristics, and water kinds. For instance, plastics are a major global problem with serious repercussions for the environment, the economy, human health, and aesthetics. Plastics are found in a range of marine life and stay in the ocean for a very long period harming marine life at different trophic levels in diverse places around the world [2]. There are a number of developed and tested methods for locating and preventing marine debris [3]. Most research and development efforts currently are concentrated on identifying and tracking floating debris. Marine debris has been specifically detected and tracked using earth observation data from governmental and private satellite projects, as well as remote sensing data from manned aircraft, unmanned aerial vehicles, bridgemounted cameras, and underwater cameras. It has also been suggested to use spectral indices to enhance the detection of marine debris using multispectral satellite data, such as the Floating Debris and the Plastic that have been developed based on phoney plastic targets [4].

In order to better understand the spectrum behaviour of marine waste and to test the ability of sensors to distinguish plastics from other features including vegetation, natural materials, and water, hyperspectral measurements have also been made. Using multispectral satellite data, researchers have also examined the spectral behaviour of marine debris, showing that it is challenging to distinguish marine debris from other sea surface items like ships and foam. In fact, it is now thought to be very difficult to separate floating plastic trash from bright features like waves, sunlight, and clouds. This is due to plastics' complex properties, which include variations in colour, chemical makeup, size, and water-submergence depth. The aforementioned issues can be resolved while also supporting in the growth and advancement with a high quality dataset of algorithms for identifying marine debris [5].

Conclusion

Despite the challenging and persistent problem of marine debris, there are currently only a small number of datasets that are widely accessible and frequently use open-access high-resolution satellite data. These facts make it impossible for ML frameworks and operational solutions to exploit satellite data. Additionally, the majority of the marine remote sensing datasets that are currently accessible are designed to identify particular objects, such vessels. Datasets for Sargasso microalgae extraction and cloud identification over the ocean have also been created, however with fewer classifications. To that end, our research uses the S2 multispectral satellite and a brand-new, freely accessible benchmark dataset called the Debris Archive to try to close the gap. By integrating sea features that cohabit in the ocean, the produced dataset advances in a novel way. A total of theme categories were produced from the remote sensing images. Baselines for the weakly supervised semantic segmentation problem are also provided, including shallow and deep neural network designs.

References

1. Anderson, Donald M., Allan D. Cembella and Gustaaf M. Hallegraeff. "Progress in understanding harmful algal blooms (HABs): Paradigm shifts and new technologies for research, monitoring and management."Ann Rev Mar Sci4 (2012): 143.

Google Scholar, Crossref, Indexed at

2. Mayer, Michael and Antje J. Baeumner. "A megatrend challenging analytical chemistry: biosensor and chemosensor concepts ready for the internet of things."Che Rev119 (2019): 7996-8027.

Google Scholar, Crossref, Indexed at

3. Chakraborty, Chiranjib, Ashish Ranjan Sharma, Garima Sharma and Sang Soo Lee. "Zebrafish: A complete animal model to enumerate the nanoparticle toxicity."J Nanobiotechnol14 (2016): 1-13.

Google Scholar, Crossref, Indexed at

4. Wilson, Rory P., David Grémillet, Jon Syder, Mandy AM Kierspel and Stefan Garthe, et al. "Remote-sensing systems and seabirds: their use, abuse and potential for measuring marine environmental variables."Mar Ecol Prog Ser228 (2002): 241-261.

Google Scholar, Crossref, Indexed at

5. Brown, Craig J., Stephen J. Smith, Peter Lawton and John T. Anderson. "Benthic habitat mapping: A review of progress towards improved understanding of the spatial ecology of the seafloor using acoustic techniques."Estu Coa Sh Sci92 (2011): 502-520.

Google Scholar, Crossref, Indexed at