Survey Ship Research Articles

Data mining-based machine learning methods for improving hydrological data: a case study of salinity field in the Western Arctic Ocean

The Beaufort Gyre is the largest freshwater reservoir in the Arctic Ocean. Long-term changes in freshwater reservoirs are critical for understanding the Arctic Ocean, and data from various sources, particularly observation or reanalysis data, must be used to the greatest extent possible. Over the past two decades, a large number of intensive field observations and ship surveys have been conducted in the western Arctic Ocean to obtain a large amount of CTD (Conductivity, Temperature, and Depth) data. Multi-machine learning methods were assessed and merged to reconstruct the annual salinity product in the Western Arctic Ocean over the period 2003-2022. Data mining-based machine learning methods reconstructed salinity product based on input variables determined by physical processes, such as sea level pressure, bathymetry, sea ice concentration, and sea ice drift. The root-mean-square error of sea surface salinity, in comparison to deep water, was effectively managed during machine learning, which exhibits higher sensitivity to variations in the atmosphere, sea ice, and ocean. The mean absolute errors in freshwater content and halocline depth within the Beaufort Gyre region for the salinity product from 2003 to 2022 are 0.98 m and 1.31 m, respectively, when compared to observational data. The salinity product provides reliable characterizations of freshwater content in the Beaufort Gyre and its variations at halocline depth. In polar regions where lacking observed data, we can build data mining-based machine learning methods to generate reliable data products to compensate for the inconvenience. Furthermore, the application potential of this multi-machine learning results approach for evaluating and integrating extends beyond the salinity field, encompassing hydrometeorology, sea ice thickness, polar biogeochemistry, and other related fields.

Fishing in the gene-pool: implementing trawl-associated eDNA metaprobe for large scale monitoring of fish assemblages

Marine biodiversity monitoring in the Mediterranean’s increasingly threatened ecosystems is crucial for effective ecosystem conservation and management. Here, we leveraged the Mediterranean International Trawl Survey program (MEDITS) to implement eDNA sampling through the recently tested ‘metaprobe’ procedure and characterize fish assemblages in three separate areas off the Italian coasts: Northern Adriatic Sea (NoAS), Ligurian and Northern Tyrrhenian Sea (LNTS), and Sardinian Sea (SaS). By combining the information from two homologous mitochondrial 12S metabarcodes––i.e., Elas02 and Tele02 targeting elasmobranchs and teleosts, respectively––we identified 108 species, over 60% of which overlapped with those caught by the trawl net. We produced an accurate reconstruction of fish community composition of the examined sites, reflecting differences in species assemblages linked with both geographic area and depth range. Metaprobe eDNA data consistently returned a biodiversity ‘bonus’ mostly consisting of pelagic taxa not captured through bottom trawl surveys, including rare and endangered taxa (e.g., elasmobranchs). Overall, the spatial characterisation of the assemblages across the surveyed areas was better delineated and more robust using eDNA metabarcoding than trawl data. Our results support the operationalisation of the metaprobe as a simple, inexpensive, versatile sampling tool, in association with pre-existing ship surveys, to overcome many of the limitations of marine data collection and strengthen marine management.

An UAV system for visual inspection and wall thickness measurements in ship surveys

This article presents the development of a UAV system designed to perform visual inspections and thickness measurements in ships’ cargo tanks. That includes the conception and evolution of the different components and subsystems of this UAV system and several tests, including some carried out in actual operating conditions. It also presents a near-wall positioning and propulsion system designed and developed to improve stability and avoid collisions. The paper also describes an articulated arm designed around an EMAT probe for wall thickness measurement. The measurement chain developed for this purpose includes all the electronics and computing necessary to send data in real-time to a ground station. Flying near walls poses challenges that compromises accuracy when approaching each measurement target points. Therefore, the wall approach and departure flight maneuvers are fully automatic. That facilitates and speeds up the inspection task that may require measurements on thousands of locations specified by the surveyor. The proposed UAV system aims to automate and improve the long and expensive surveys and inspections in the marine industry by reducing their time and costs.

Research on Multi-Beam Sounding Based on Local Optimal Model

Multi-beam sounding technology can provide higher spatial resolution than single-beam sounding by transmitting fan-shaped acoustic signals from the transducer of a survey ship along the normal plane of the survey line to measure the sea depth. It is of great significance to study the line design scheme of multi-beam sounding for uneven seabed topography to improve the efficiency of underwater terrain mapping. This paper mainly studies the optimization of multi-beam sounding line under ideal slope. Firstly, a single angle model of ideal slope is established, and the flat seabed overlap ratio formula is extended to slope seabed to calculate the coverage width of beam sounding. Secondly, an angle model of ideal slope is established to calculate the corresponding coverage width under different positions of the slope sea area. Finally, the optimal routing model of ideal slope is established. The design scheme of the local optimal survey line is obtained through comprehensive analysis. In engineering practice, the optimal routing of real terrain can be solved by using the ideal slope optimal routing model through the idea of plane approximation, which provides a new idea for the optimal route selection of underwater terrain mapping.

Integrated survey methodologies provide process-driven framework for marine renewable energy environmental impact assessment

Environmental interactions of marine renewable energy developments vary from fine-scale direct (e.g. potential collision) to indirect wide-scale hydrodynamic changes altering oceanographic features. Current UK Environmental Impact Assessment (EIA) and associated Habitats Regulations Appraisal (HRA) guidelines have limited focus on underlying processes affecting distribution and movements (hence vulnerability) of top predators. This study integrates multi-trophic ship survey (active acoustics and observer data) with an upward-facing seabed platform and 3-dimensional hydrodynamic model as a process-driven framework to investigate predator-prey linkages between seabirds and fish schools. Observer-only data highlighted the need to measure physical drivers of variance in species abundances and distributions. Active acoustics indicated that in situ (preferable to modelled) data were needed to identify temporal changes in hydrodynamics to predict prey and consequently top predator presence. Revising methods to identify key habitats and environmental covariates within current regulatory frameworks will enable more robust and transferable EIA and HRA processes and outputs, and at larger scales for cumulative and strategic-level assessments, enabling future modelling of ecosystem impacts from both climate change and renewable energy extraction.

Classification of optical water groups in the subarctic pacific and adjacent seas using satellite-derived light absorption spectra of chromophoric dissolved organic matter

The characteristics of the water masses that contribute to high biological production in the subarctic Pacific and adjacent seas (SPA) could change because of recent climate change. This study reports on a method to classify water in the SPA into distinct optical water groups using the light absorption coefficient of chromophoric dissolved organic matter (CDOM), aCDOM(λ), captured using an ocean color satellite. In situ samples obtained from ship surveys between 2006 and 2021 were classified into five optical group numbers (OGN1–OGN5) based on aCDOM parameters in the ultraviolet (UV) region: aCDOM(λ) at 350 nm (aCDOM(350)) and the spectral slopes at 275–295 nm (S275–295) and at 350–400 nm (S350–400). We were also able to identify OGN with a new method using machine learning technique developed in this study that adopted satellite-derived aCDOM(λ) in the visible (VIS) region. The distribution and characteristics of OGN classified using the in situ aCDOM parameters in the UV region supplement the interpretation of the origin and mixing of the water masses classified by temperature and salinity. Relative to in situ samples, the accuracy of the OGN estimation from the ocean color satellites was 83.3%. The satellite-derived OGN were able to distinguish high chlorophyll-a areas where high phytoplankton productivity is expected. In addition, identifying the distribution of OGN from satellites supports improved understanding of the bloom process. This method has potential to help to understand the impact of phenomena from accelerating ocean warming (e.g., sea ice decline, enhancement of stratification and increase in riverine input) on water masses structure and the consequent changes in the phytoplankton productivity in the SPA.

Seafloor topography of Huangyan seamount chain based on GA-BP algorithm from ship survey and gravity anomaly data

Seabed topography is important for marine geophysics and geodesy. However, conventional seabed topography inversion methods based on gravity data are constrained to a linear fitting, neglecting the impact of nonlinear terms. In this paper, we propose an innovative method for seabed topography inversion by establishing fresh mathematical relationships through machine learning techniques based on the Smith and Sandwell (SAS) method. Utilizing global sea depth data from the National Geophysical Data Center (NGDC) and gravity anomaly data from satellite altimetry, our study employs the SAS method for seabed topography inversion. The improved SAS method, enhanced by the Genetic Algorithm-Backpropagation (GA-BP) algorithm, is specifically applied to invert the Huangyan Seamount Chain topography in the South China Sea. The accuracy is evaluated by seabed topography models, including EOTPO1, GEBCO-2023, and S & S V19.1. The results show the GA-BP method significantly reduces residuals and improves the accuracy estimated by the SAS inversion method. The Root Mean Square Error (RMSE) and Mean Absolute Error (MAE) are decreased by 14.98% and 5.07%, respectively. The proposed method has valuable reference significance for future marine exploration endeavours around the world.

Biologically Important Areas II for cetaceans within U.S. and adjacent waters - West Coast Region

Here we update U.S. West Coast Biologically Important Areas (BIAs) that were published in 2015 using new data and approaches. Additionally, BIAs were delineated for two species that were not delineated in the 2015 BIAs: fin whales and Southern Resident killer whales (SRKW). While harbor porpoise BIAs remained the same, substantial changes were made for other species including identifying both larger overall areas (parent BIAs) and smaller core areas (child BIAs). For blue, fin, and humpback whales we identified, delineated, and scored BIAs using the overlap between the distribution and relative density from three data sources, leveraging the strengths and weaknesses of these approaches: 1) habitat density models based on Southwest Fisheries Science Center (SWFSC) line-transect data from systematic ship surveys conducted through 2018, 2) satellite tag data from deployments conducted by three research groups, and 3) sightings of feeding behavior from non-systematic effort mostly associated with small-boat surveys for photo-identification conducted by Cascadia Research Collective. While the previous BIAs were based solely on a more subjective assignment from only the small boat sightings, here we incorporate the other two data sources and use a more rigorous, quantitative approach to identify higher density areas and integrate the data types. This resulted in larger, better-supported, objective BIAs compared to the previous effort. Our methods are also more consistent with the delineation of BIAs in other regions. For SRKWs, the parent BIA was based on a modification of the Critical Habitat boundaries defined by the National Oceanographic and Atmospheric Administration (NOAA) and the Department of Fisheries and Oceans (DFO) Canada; a core BIA highlighting areas of intensified use was identified using both NOAA’s Critical Habitat and kernel density analyses of satellite tag data. Gray whale BIAs were re-evaluated for the migratory corridor of Eastern North Pacific gray whales, for Pacific Coast Feeding Group feeding areas, and for gray whales that feed regularly in Puget Sound.

Quiet uncrewed surface vessels assess fish avoidance to motorized survey ships with varying noise levels in the Great Lakes

Acoustic surveys are a foundational component of many fisheries monitoring programs because they allow assessment of spatially extensive stocks. They are widely used to evaluate prey fish throughout the Great Lakes by numerous coordinating vessels. Traditionally, these surveys have been conducted by crewed and motorized vessels, but fish avoidance of motorized platforms has been reported in multiple studies and may bias survey estimates. Quiet uncrewed platforms are becoming increasingly available and offer the opportunity to explore bias in traditional surveys. Several identical quiet uncrewed surface vehicles (USVs) operated by Saildrone were equipped with 120 kHz Simrad EK80 transducers and deployed in Lakes Erie, Huron, Michigan, and Superior in the summers of 2021, 2022, and 2023. The USVs were overtaken by numerous motorized vessels over 2 km transects using transducers with the same frequency. Fishes showed a limited response to approaching vessels, and acoustic measures were similar between the USVs and motorized vessels. Therefore, acoustic surveys in the Great Lakes appear unbiased and are widely comparable. Findings from this work will inform interpretation of acoustic data in the Great Lakes and provide the largest scale testing of fish avoidance during acoustic surveys to date.

A variational optimization algorithm for Secchi disk depth based on Multi-satellite data

A Secchi depth is a basic parameter to describe the optical properties of water, which is related to the composition and content of chlorophyll, suspended solids and yellow substances in water, and is also closely related to solar radiation on the surface of water, physical and chemical properties of water and meteorological conditions. The most direct way to obtain the spatiotemporal distribution of water Secchi depth is to use ships to regularly measure the Secchi depth of the base-stations, but this method can only obtain the Secchi depth of the measurement station state, and it is impossible to obtain the Secchi depth characteristics of seawater with large spatiotemporal distribution. As a brand-new observation method, remote sensing technology can obtain the distribution characteristics of ocean parameters in large time and space. In recent years, with the rapid development of remote sensing technology, especially the development of water-colored remote sensors and the improvement of the accuracy of inversion algorithms, many remote sensing products for water Secchi depth have been provided. However, due to the difference in orbit operation and observation parameters of different remote sensing loads, water Secchi depth products are affected by clouds and meteorological climate environment, and there is no same standard for verification and evaluation, which limit the promotion and application of water Secchi depth products. At the same time, data integrated technology has been widely recognized by many disciplines and has been greatly developed in recent years, and pixel-level, feature-level, decision-level integrated technology and development are also popular research directions in the world. Therefore, based on an improved variational optimization algorithm, this article integrates SDD retrieval products on multiple satellite data t such as SNPP, MODIS, and MERIS, and verifies them with ship survey data. The correlation is better than 0.9, proving that this method can improve the accuracy of SDD inversion products.

Research on the problem of multi-beam line measurement based on the cattle plowing traversal algorithm

In order to study the depth and coverage width of sea water measured by the multi-beam detection system and the control of the overlap ratio range of the detection strip, the full coverage path optimization of the survey ship is carried out. In this paper, firstly, a model is established for the depth of the sea and the coverage width of the multi-beam detection system under the premise that the overlap rate is controlled within the range of 10%````~20% by using the property theorem of trigonometric function and geometric relation. Secondly, the Angle between the direction of the survey line and the projection of the normal direction of the submarine slope on the horizontal plane is analyzed, and the model for the depth of the sea area and the coverage width of the multi-beam detection system is further established under the constraint of the rolling attitude of the survey ship. Finally, the measured sea area is divided into molecular areas according to the overlap rate range and coverage width as standards, and then the coverage width and the number of survey lines are measured based on the cattle plowing traversal algorithm. The following results are obtained: When the survey ship starts and ends in the east-west direction and meets the requirement of 10%````~20% overlap rate, the number of survey lines is stable at 23, the total coverage width of the survey lines is 8.7852x108m, and the spacing of each survey line is 340.50m.

Research on multi-beam problems based on geometric modeling and underwater detection

This paper aims to establish and solve the mathematical model of coverage width under multi-beam bathymetry, rising from a one-dimensional sea area measurement problem to a two-dimensional sea area measurement problem. First, this paper takes the center of the sea area as the coordinate origin, establishes a one-dimensional coordinate system, and derives the functional relationship between the coordinate position of the measured ship axis and the angle of the seabed slope through the triangle edge relationship. At the same time, the mathematical relationship between the depth of the water body and the position of the measuring ship is constructed, and the relationship between the single coverage width of the detection system and the depth of the water body is found using the sine theorem. Subsequently, this paper established a two-dimensional sea area measurement model. Taking the center point of the sea area to be measured as the coordinate origin, a three-dimensional coordinate system was constructed. The normal vector projection direction was taken into account to obtain the new slope angle, and the two-dimensional sea area measurement was converted into a one-dimensional sea area. Measurement. Finally, this article uses MATLAB to conduct simulation experiments and gives the relationship between the coverage width and the position of the survey ship at different angles between survey line directions, providing an effective reference for the multi-beam sounding strategy.

Research on optimization model based on multi-beam sounding technology

Multi-beam sounding technology is a technology that can obtain the detailed information of underwater terrain quickly and accurately, and is widely used in the fields of ocean survey, seabed geological survey, underwater engineering construction and so on. In this paper, based on the actual scene of the survey ship, the coverage width of the survey line is divided into the left and right parts. Firstly, the parameter expressions of each section are obtained through geometric relation operation, and the mathematical model of the coverage depth of multi-beam sounding is established. Then, the paper considers the mathematical model of multi-beam sounding coverage width in a rectangular sea area to be measured, when the angle between the direction of the measured line and the normal direction of the seabed slope is β. Finally, this paper designs a set of measuring lines with the shortest measuring length in a rectangular sea area with known area, sea water depth at the center point of the sea area and the open angle of the multi-beam transducer, which can completely cover the whole sea area to be measured, and the overlap rate between adjacent strips can meet 10%~20%. With the help of MATLAB for iterative calculation, we obtain the shortest measuring length of the measuring ship. At the same time, this paper also give a set of measuring beam position distribution table.

A Reconstructing Model Based on Time–Space–Depth Partitioning for Global Ocean Dissolved Oxygen Concentration

Dissolved oxygen (DO) is essential for assessing and monitoring the health of marine ecosystems. The phenomenon of ocean deoxygenation is widely recognized. Nevertheless, the limited availability of observations poses a challenge in achieving a comprehensive understanding of global ocean DO dynamics and trends. The study addresses the challenge of unevenly distributed Argo DO data by developing time–space–depth machine learning (TSD-ML), a novel machine learning-based model designed to enhance reconstruction accuracy in data-sparse regions. TSD-ML partitions Argo data into segments based on time, depth, and spatial dimensions, and conducts model training for each segment. This research contrasts the effectiveness of partitioned and non-partitioned modeling approaches using three distinct ML regression methods. The results reveal that TSD-ML significantly enhances reconstruction accuracy in areas with uneven DO data distribution, achieving a 30% reduction in root mean square error (RMSE) and a 20% decrease in mean absolute error (MAE). In addition, a comparison with WOA18 and GLODAPv2 ship survey data confirms the high accuracy of the reconstructions. Analysis of the reconstructed global ocean DO trends over the past two decades indicates an alarming expansion of anoxic zones.

Variations and Depth of Formation of Submesoscale Eddy Structures in Satellite Ocean Color Data in the Southwestern Region of the Peter the Great Bay

The aim of this study was to develop methods for determining the most significant contrasts in satellite ocean color data arising in the presence of a submesoscale eddy structure, as well as to determine the corresponding depths of the upper layer of the sea where these contrasts are formed. The research was carried out on the example of the chain of submesoscale eddies identified in the Tumen River water transport area in the Japan/East Sea. MODIS Aqua/Terra satellite data of the remotely sensed reflectance (Rrs) and Rrs band ratio at various wavelengths, chlorophyll-a concentration, and, for comparison, sea surface temperature (sst) were analyzed. Additionally, the results of ship surveys in September 2009 were used to study the influence of eddy vertical structure on the obtained remote characteristics. The best characteristic for detecting the studied eddies in satellite ocean color data was the MODIS chlor_a standard product, which is an estimate of chlorophyll-a concentration obtained by a combination of the three-band reflectance difference algorithm (CI) for low concentrations and the band-ratio algorithm (OCx) for high concentrations. At the same time, the weakest contrasts were in sst data due to similar water heating inside and outside the eddies. The best eddy contrast-to-noise ratio according to Rrs spectra is achieved at 547 nm in the spectral region of seawater with maximum transparency and low relative errors of measurements. The Rrs at 678 nm and associated products may be a significant characteristic for eddy detection if there are many phytoplankton in the eddy waters. The maximum depth of the remotely sensed contrast formation of the considered eddy vertical structure was ~6 m, which was significantly less than the maximum spectral penetration depth of solar radiation for remote sensing, which was in the 14–17 m range. The results obtained can be used to determine the characteristics that provide the best contrast for detecting eddy structures in remotely sensed reflectance data and to improve the interpretation of remote spectral ocean color data in the areas of eddies activity.

A light-weight neural network for marine acoustic signal recognition suitable for fiber-optic hydrophones

Fiber-optic hydrophones based on optical fiber sensing and communication technology have developed rapidly in recent years. With the advantages of high sensitivity, small size, and large dynamic range, they are easy to detect underwater acoustic signals, showing great potential in the field of marine ecological protection. Researchers can monitor the marine ecological environment by recognizing underwater optical fiber sensing signals collected by fiber-optic hydrophones in real-time. Deep learning models can achieve high recognition accuracy, but they usually have large amounts of parameters that makes them difficult to be deployed in mobile terminals of marine survey ships. To solve the key problem, this paper discussed the design of the Deep Light-Weight Attention Residual Network (DLA-ResNet). It introduces the depth-wise separable convolution (DSC) and the convolutional block attention module (CBAM) into ResNet18 to make its performance better. ResNet18 is a two-dimensional convolutional network (CNN) model applying residual blocks. Experiments verify that the accuracy of DLA-ResNet improved from ResNet18 is increased by about 2.04% and its size is reduced by 85.67%. The proposed scheme in this paper realizes an average recognition rate of 96.50% for eight types of underwater optical fiber sensing signals in the application of marine ecological environment monitoring. Moreover, its model size is only 6.12 MB and it only takes 27.90 ms, which is available to meet the needs of reliability and effectiveness.

Design of a Wireless, Inexpensive Ocean of Things System for Volunteer Bathymetry

Although much progress has been made in recent years to fully map the world ocean, only approximately 20% is adequately mapped to modern standards. Filling in the remainder must by necessity be a multi-modal effort, with traditional ocean mapping technologies such as crewed survey ships with multibeam echosounders being mixed with newer systems such as uncrewed, sail-powered mapping systems. Volunteer data from any ship with an echosounder can also be used, but although there have been commercial efforts in this field, most of these systems do not contribute data into the public arena and public entities have largely avoided this field due to complexities of costs, data processing, and uncertainty on how to handle the effort. This paper describes the design of an end-to-end system for managed volunteer bathymetric collection consisting of an inexpensive (~$20) wireless “ocean of things” data logger for NMEA0183 and NMEA2000 data, associated firmware to manage the collection, a mobile device application to off-load, aggregate, and transfer the data into the cloud, and a cloud segment to process the data and submit it to an international data repository. All of the design has been released under an Open Hardware or Open Source license, allowing independent organizations to initiate data collection efforts without having to do any of the design work themselves. The goal is to provide a simple, approachable implementation, encouraging greater adoption of these ideas in hard-to-reach areas of the world with minimal effort on the part of the host organization.

Safer Ships and Cleaner Seas: Reducing Vessel Risks through Targeted Inspections and Recognized Organization Oversight

Abstract This article explores the lessons that might be learned from port State con-trol (PSC) inspections for flag States, examining the scholarly literature on vessel risk targeting. It begins by identifying the major classification socie-ties (and recognized organizations or ROs) before discussing the obligations and responsibilities of governments in achieving a global ‘safer ships and cleaner seas’ objective. It then presents a framework for thinking about the relationship between owner/operators, ship classification societies, flag State authorities and PSC parties in order to improve safety, discussing where gaps remain in the execution of the objective. The author draws con-clusions about where the future focus by flag States might achieve addi-tional improvements in their oversight of classification societies when they act as ROs, carrying out ship survey and certification functions on behalf of flag States. Identified challenges include improving the quality of data used in vessel risk targeting, expanding the transparency of that data for RO oversight, and focusing efforts on those flag States and ROs who do not meet their obligations.

The Influence of Strategic Planning and Strategic Resources Base View on the Organization Performance Mediated by Strategic Coordination

The purpose of this study is to investigate the effect of Strategic Planning and Strategic Resources Based View (RBV) on Strategic Organization Performance through mediating Strategic Coordination in Pushidrosal organizations which have two sides of tasks and functions that cannot be separated namely as Military Hydrographic Institutions and also The National Hydrographic Agency with the function of public services and carrying out the hydrographic data support function for military / defense purposes, also includes carrying out the public service function as the National Hydrographic Institution which is the uniqueness of the Pushidrosal organization. Where in the Pushidrosal organization the organizational structure is still underthe command chain ofthe IndonesianNavy Headquarters. Themethodology used in thisresearch istouse a quantitativeapproach and conductdata collection through a questionnaire to be further analyzed using the path analysis method. Respondents in this study were Pushidrosal personnel at officers' rank, in the Makid Pushidrosal environment, Mako Survey unit and Pushidrosal Survey Ship personnel.The population is 252 with a sample of 160 respondents. Data collection was carried out through questionnaires and data analysis techniques using Path Analysis and calculations using SPSS version 20 software. The results of this study, found that: 1) Strategic Planning does not directly affect Organizational Performance, but indirectly affects through Strategic Coordination as mediation, 2) Strategic Resources Base View does not directly affect Organization Performance, but indirect effect through Strategic Coordination, and 3) Variable StrategicCoordination becomes a full mediation of the influence of Strategic Planning on Organization Performance and the influence of Strategic RBV on Organization Performance. This research provides a theoretical contribution to the study ofOrganizations with dual functions where it is found that the influence of the parent organization on the formulation of Strategic Planning, and Strategic Resources Base Viewand the mediating role of Strategic Coordination, which has a full mediating role on Organization Performance, makes theoretical contributions to research on Strategic Planning and Strategic Resources Base View on Organization Performance with mediation Strategic Coordination applied to an organization dual functions and still has influence from the parent organization.

Atmospheric-correction-free red tide quantification algorithm for GOCI based on machine learning combined with a radiative transfer simulation

Satellite ocean color observation has been an effective way to detect red tide in a wide coastal area of many countries. However, red tide water, which has high red and infra-red reflectance, often causes failure in atmospheric correction, making quantification algorithms based on remote sensing reflectance produce large errors. This study proposes a new framework that tackles the difficulties in red tide quantification stemming from atmospheric variability, limited in-situ training data, and image artifacts, through the combined use of radiative simulation, machine learning, and in-situ measurements. The framework was applied to the geostationary ocean color imager (GOCI) to monitor Margalefidinium blooms that are frequent in Korean coasts. The estimation results were validated first quantitatively with independent ship survey data, and then qualitatively with other 3 red tide algorithms. Finally, the operational robustness of the proposed framework was analyzed based on the data acquired in the entire outbreak period in 2018. The results showed that the proposed algorithm produced a high correlation with field data (R2 ∼ 0.89) and high detection rate and low false alarms compared to the other red tide algorithms. The monitoring result for 2018 also demonstrated that the initiation, expansion, peak, and termination of red tide were successfully identified by the satellite data, which coincides with the field survey results provided by the national fishery agency.