Different Tissue Cell 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

An open-access dataset that examines the spectral behavior of specific floating materials, sea state characteristics, and water types also develops and tests satellite pre-processing pipelines and artificial intelligence-based Marine Debris detection solutions. Plastics, for instance, are a major global problem with significant effects on human health, the economy, the environment, and aesthetics. Plastics harm marine life at various trophic levels and remain in the ocean for a long time [2]. They have been found in many places around the world. There have been developed and demonstrated a number of methods for detecting and preventing marine debris [3]. The majority of research and development efforts have recently shifted their attention to floating trash detection and monitoring. For the purpose of specifically detecting and tracking Marine Debris, remote sensing data from manned aircraft, unmanned aerial vehicles, bridge-mounted, and underwater cameras, as well as Earth observation data from government and commercial satellite projects, have been utilized. Using multispectral satellite data, it has also been suggested that spectral indices, such as the Plastic and Floating Debris that have been established on the basis of fake plastic targets, could be used to improve the detection of Marine Debris [4].

In addition, hyperspectral measurements have been carried out in order to acquire a deeper comprehension of the spectral behavior of marine debris. The purpose of these measurements is to investigate the potential of sensors to distinguish plastics from other features such as vegetation, natural materials, and water. Multispectral satellite data have also been used to study the characteristics of marine debris, including its spectral behavior. This shows that it is difficult to distinguish marine debris from other sea surface objects like ships and foam. In point of fact, it is now thought to be extremely difficult to distinguish floating garbage made of plastic from bright features like waves, sunlight, and clouds. This is due to the complex properties of plastics, which vary in color, chemical composition, size, and water immersion depth. Marine Debris Identification Algorithms can benefit from the development and improvement of high-quality datasets, which can address the aforementioned issues [5].

Conclusion

Despite the difficult and ever-increasing problem of marine debris, the datasets that are currently available are rather few and rarely make use of open-access, high-resolution satellite data covering large geographical areas. Satellite data cannot be used in ML frameworks or operational solutions due to these facts. In addition, the majority of the marine remote sensing datasets that are currently available are designed to identify particular objects, such as vessels. Datasets for Sargasso microalgae extraction and cloud detection over the ocean have also been developed with a limited number of classes. Debris Archive, a brand-new open-access benchmark dataset based on the S2 multispectral satellite, is the focus of our study to fill this gap. By including sea features that coexist in the ocean, the newly created dataset takes a unique step forward. Photos taken using remote sensing, this led to a total of thematic groupings. Additionally, baselines for the problem of poorly supervised semantic segmentation, including designs for shallow and deep neural networks, are provided.

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