Red Tide Detection Research Articles

Enhancing the reliability of GCOM-C/SGLI data for red tide detection in the upper Gulf of Thailand

ABSTRACT With the upcoming completion of the Moderate Resolution Imaging Spectroradiometer mission, this study applied 250-m-spatial-resolution ocean colour products from the Second-Generation Global Imager (SGLI) on the Global Change Observation Mission-Climate (GCOM-C) platform to continue monitoring red tides in the upper Gulf of Thailand. However, inaccuracies of GCOM-C/SGLI data on red tide detection were observed. To enhance its reliability, we first improved the accuracy of GCOM-C/SGLI remote sensing reflectance (R rs) data by adjusting it to in situ data using wavelength-specific regression functions. This method significantly reduced the mean absolute percentage difference between in situ and GCOM-C/SGLI data by 25%–87% for single SGLI wavelengths and by 46%–83% for R rs( λ )/R rs(565) of the original data. Subsequently, we employed the corrected data of SGLI R rs( λ ) at 565 nm and the ratios of R rs(490)/R rs(565), R rs(530)/R rs(565), and R rs(673)/R rs(565) in local empirical algorithms to estimate chlorophyll-a(chl-a) concentration and identify red tide waters. SGLI chl-a improved substantially in areas affected by red tides, particularly as chl-a concentrations increased. Additionally, the corrected GCOM-C/SGLI accurately identified red tides caused by green Noctiluca, diatoms, and dinoflagellate blooms consistent with local reports, confirming the GCOM-C/SGLI reliability enhancement. This method may serve as an alternative strategy for monitoring the red tides.

The Evaluation of MII/SDGSAT-1 in Red Tide Detection Along the Guangdong Middle Coast

The Evaluation of MII/SDGSAT-1 in Red Tide Detection Along the Guangdong Middle Coast

Red Tide Detection Method Based on Improved U-Net Model-Taking GOCI Data in East China Sea as an Example.

In the coastal areas of China, the eutrophication of seawater leads to the continuous occurrence of red tide, which has caused great damage to Marine fisheries and aquatic resources. Therefore, the detection and prediction of red tide have important research significance. The rapid development of optical remote sensing technology and deep-learning technology provides technical means for realizing large-scale and high-precision red tide detection. However, the difficulty of the accurate detection of red tide edges with complex boundaries limits the further improvement of red tide detection accuracy. In view of the above problems, this paper takes GOCI data in the East China Sea as an example and proposes an improved U-Net red tide detection method. In the improved U-Net method, NDVI was introduced to enhance the characteristic information of the red tide to improve the separability between the red tide and seawater. At the same time, the ECA channel attention mechanism was introduced to give different weights according to the influence of different bands on red tide detection, and the spectral characteristics of different channels were fully mined to further extract red tide characteristics. A shallow feature extraction module based on Atrous Spatial Pyramid Convolution (ASPC) was designed to improve the U-Net model. The red tide feature information in a multi-scale context was fused under multiple sampling rates to enhance the model's ability to extract features at different scales. The problem of limited accuracy improvement in red tide edge detection with complex boundaries is solved via the fusion of deep and shallow features and multi-scale spatial features. Compared with other methods, the method proposed in this paper achieves better results and can detect red tide edges with complex boundaries, and the accuracy, precision, recall, and F1-score are 95.90%, 97.15%, 91.53%, and 0.94, respectively. In addition, the red tide detection experiments in other regions with relatively concentrated distribution also prove that the method has good applicability.

RTDNet: red tide detection network for high-resolution satellite images

RTDNet: red tide detection network for high-resolution satellite images

Red Tide Detection Based on Improved DenseNet Network—Example of Red Tide Detection from Geostationary Ocean Color Imager Data in Bohai Sea

Red Tide Detection Based on Improved DenseNet Network—Example of Red Tide Detection from Geostationary Ocean Color Imager Data in Bohai Sea

Molecular taxonomical identification and phylogenetic relationships of some marine dominant algal species during red tide and harmful algal blooms along Egyptian coasts in the Alexandria region

Harmful algal blooms (HABs) threaten the aquatic ecosystems due to either poisonous effects on living organisms or oxygen-consuming. So HABs’ accurate identification, including red tide, is crucial. This study aimed to molecular identification of dominant species during tide period in nine stations along Alexandria region at Egyptian costs during one year. Samples were collected weekly before water discoloration but daily during red tide intensive growth from both 50 cm below the surface and 3 m depth over the bottom from the water surface. The red tide detection was highly from early August to half of September, since its highest peak with a maximum frequency inside the Eastern Harbor. The examined cultures samples isolated during red tide had four dominant species. Peroxidase profile showed an expression pattern of three loci (Px1, Px2, and Px3) in most species. The Px2 was the only heterozygous locus among the three loci in all species. Protein profiling showed that 17 bands out of 65 were specific to the species. The phylogenetic relationships derived from profiles of protein and 18S rRNA gene operon sequences for the four isolated species were mostly similar. We identified the four dominant HABs species as Aplanochytrium sp., Chlamydomonas sp., Cryptophyceae sp., and Psammodictyon sp. based on their 18S rRNA sequences and deposited them at DDBJ/EMBL/GenBank database. Aplanochytrium sp. is recorded as a red tide causative species for the first time in the screened region despite belonging to the defunct fungi.

Red tide detection based on high spatial resolution broad band optical satellite data

Red tide, one of the major ecological disasters in the world, exerts great impact on the marine environment. The ocean color satellite data with low spatial resolution and high spectral resolution is often used for red tide detection, but is insufficient for the fine-scale red tide detection due to its coarse spatial resolution. To address this problem, a new red tide detection method based on pseudo hue angle (PHA-RI) for high spatial resolution broad band satellite data is proposed in this paper. Different from the standard International Commission on Illumination (CIE) system, the false-color bands of near infrared (NIR), red and green are used to calculate the CIE tristimulus X, Y, Z, instead of the true-color bands of red, green and blue. With this method, the red tide can be easily differentiated from non-red tide water, and the distinction between red tide and non-red tide water is doubled compared to that of true-color bands composite. Experiment results show that the PHA-RI method can effectively detect red tide, with an averaged overall accuracy, F1-score and precision of 92%, 0.92 and 0.92 respectively. Compared with the traditional machine learning method support vector machine (SVM) and spectral index algorithm Gaofen-1 (GF-1) red tide detection index (GF-RI), the proposed algorithm has obvious advantages in red tide detection, especially for the strip distributed red tide. Besides, the proposed algorithm has good applicability, and it is proved to be suitable for the detection of red tides with different dominant species including Noctiluca scintillans, Skeletonema costatum and Heterosigma akashiide. Also, it is applicable to different broad band sensors, such as Chinese satellites GF-1 Wide Field of View (WFV), Haiyang 1D (HY-1D) Coastal Zone Imager (CZI), Sentinel-2 MultiSpectral Instrument (MSI) and Landsat 8 Operational Land Imager (OLI). The application experiment indicates that the proposed algorithm is effective in red tide detection, and it can successfully detect fine-scale red tide events, which have not been detected by Moderate Resolution Imaging Spectroradiometer (MODIS) Aqua due to its coarse spatial resolution. The results also shows the advantages of high spatial resolution satellites in fine-scale red tide detection. This work provides a method for red tide detection using high spatial resolution broad band satellite data.

Red Tide Detection Method for HY−1D Coastal Zone Imager Based on U−Net Convolutional Neural Network

Existing red tide detection methods have mainly been developed for ocean color satellite data with low spatial resolution and high spectral resolution. Higher spatial resolution satellite images are required for red tides with fine scale and scattered distribution. However, red tide detection methods for ocean color satellite data cannot be directly applied to medium–high spatial resolution satellite data owing to the shortage of red tide responsive bands. Therefore, a new red tide detection method for medium–high spatial resolution satellite data is required. This study proposes the red tide detection U−Net (RDU−Net) model by considering the HY−1D Coastal Zone Imager (HY−1D CZI) as an example. RDU−Net employs the channel attention model to derive the inter−channel relationship of red tide information in order to reduce the influence of the marine environment on red tide detection. Moreover, the boundary and binary cross entropy (BBCE) loss function, which incorporates the boundary loss, is used to obtain clear and accurate red tide boundaries. In addition, a multi−feature dataset including the HY−1D CZI radiance and Normalized Difference Vegetation Index (NDVI) is employed to enhance the spectral difference between red tides and seawater and thus improve the accuracy of red tide detection. Experimental results show that RDU−Net can detect red tides accurately without a precedent threshold. Precision and Recall of 87.47% and 86.62%, respectively, are achieved, while the F1−score and Kappa are 0.87. Compared with the existing method, the F1−score is improved by 0.07–0.21. Furthermore, the proposed method can detect red tides accurately even under interference from clouds and fog, and it shows good performance in the case of red tide edges and scattered distribution areas. Moreover, it shows good applicability and can be successfully applied to other satellite data with high spatial resolution and large bandwidth, such as GF−1 Wide Field of View 2 (WFV2) images.

High Spatial-Resolution Red Tide Detection in the Southern Coast of Korea Using U-Net from PlanetScope Imagery.

Red tides caused by Margalefidinium polykrikoides occur continuously along the southern coast of Korea, where there are many aquaculture cages, and therefore, prompt monitoring of bloom water is required to prevent considerable damage. Satellite-based ocean-color sensors are widely used for detecting red tide blooms, but their low spatial resolution restricts coastal observations. Contrarily, terrestrial sensors with a high spatial resolution are good candidate sensors, despite the lack of spectral resolution and bands for red tide detection. In this study, we developed a U-Net deep learning model for detecting M. polykrikoides blooms along the southern coast of Korea from PlanetScope imagery with a high spatial resolution of 3 m. The U-Net model was trained with four different datasets that were constructed with randomly or non-randomly chosen patches consisting of different ratios of red tide and non-red tide pixels. The qualitative and quantitative assessments of the conventional red tide index (RTI) and four U-Net models suggest that the U-Net model, which was trained with a dataset of non-randomly chosen patches including non-red tide patches, outperformed RTI in terms of sensitivity, precision, and F-measure level, accounting for an increase of 19.84%, 44.84%, and 28.52%, respectively. The M. polykrikoides map derived from U-Net provides the most reasonable red tide patterns in all water areas. Combining high spatial resolution images and deep learning approaches represents a good solution for the monitoring of red tides over coastal regions.

ADVANCED SURFACE-REFLECTED RADIANCE CORRECTION FOR AIRBORNE HYPERSPECTRAL IMAGERY IN COASTAL RED TIDE DETECTION

Abstract. Red tides are among the most common coastal hazards, causing serious damage to the coastal environment. Many satellite sensors can detect red tide blooms, but are limited in their detection of the exact area of the bloom and biological abundance in terms of spatial and spectral resolution. The high spatial and spectral resolutions of hyperspectral airborne remote sensing data may help overcome these limitations to analyze red tide blooms more effectively. To identify potential applications of hyperspectral airborne data in red tide detection, an integrated field campaign was performed in September 2016 off the coast of Tongyeong, South Korea. An AisaEAGLE sensor was installed on a Cessna 208B crewed aircraft to obtain hyperspectral images of an 18 km × 18 km coastal area. To assess the atmospheric correction of the hyperspectral data, in situ optical data and water samples were measured on two vessels concurrent with the flight path. Advanced surface-reflected radiance (Lr) correction and basic atmospheric path radiance (La) correction were performed on the hyperspectral images. Of these, Lr correction comprised a large proportion of the atmospheric correction. The atmosphere-corrected remote sensing reflectance data of the hyperspectral images closely matched the in-situ measurements. The data were assessed for red tide events using ratio analysis and the fluorescence line height technique; the ratio analysis more effectively detected regions with suspected red tides.

Derivation of Red Tide Index and Density Using Geostationary Ocean Color Imager (GOCI) Data

Red tide causes significant damage to marine resources such as aquaculture and fisheries in coastal regions. Such red tide events occur globally, across latitudes and ocean ecoregions. Satellite observations can be an effective tool for tracking and investigating red tides and have great potential for informing strategies to minimize their impacts on coastal fisheries. However, previous satellite-based red tide detection algorithms have been mostly conducted over short time scales and within relatively small areas, and have shown significant differences from actual field data, highlighting a need for new, more accurate algorithms to be developed. In this study, we present the newly developed normalized red tide index (NRTI). The NRTI uses Geostationary Ocean Color Imager (GOCI) data to detect red tides by observing in situ spectral characteristics of red tides and sea water using spectroradiometer in the coastal region of Korean Peninsula during severe red tide events. The bimodality of peaks in spectral reflectance with respect to wavelengths has become the basis for developing NRTI, by multiplying the heights of both spectral peaks. Based on the high correlation between the NRTI and the red tide density, we propose an estimation formulation to calculate the red tide density using GOCI data. The formulation and methodology of NRTI and density estimation in this study is anticipated to be applicable to other ocean color satellite data and other regions around the world, thereby increasing capacity to quantify and track red tides at large spatial scales and in real time.

Generating Hard Examples for Pixel-Wise Classification

Pixel-wise classification in remote sensing identifies entities in large-scale satellite-based images at the pixel level. Few fully annotated large-scale datasets for pixel-wise classification exist due to the challenges of annotating individual pixels. Training data scarcity inevitably ensues from the annotation challenge, leading to overfitting classifiers and degraded classification performance. The lack of annotated pixels also necessarily results in few hard examples of various entities critical for generating a robust classification hyperplane. To overcome the problem of the data scarcity and lack of hard examples in training, we introduce a two-step hard example generation (HEG) approach that first generates hard example candidates and then mines actual hard examples. In the first step, a generator that creates hard example candidates is learned via the adversarial learning framework by fooling a discriminator and a pixel-wise classification model at the same time. In the second step, mining is performed to build a fixed number of hard examples from a large pool of real and artificially generated examples. To evaluate the effectiveness of the proposed HEG approach, we design a 9-layer fully convolutional network suitable for pixel-wise classification. Experiments show that using generated hard examples from the proposed HEG approach improves the pixel-wise classification model's accuracy on red tide detection and hyperspectral image classification tasks.

Red tide detection using deep learning and high-spatial resolution optical satellite imagery

ABSTRACT Red tide is one of the most devastating phenomena that have impacted coastal environments and fishery on a local scale in the worldwide seas. Satellite imagery can provide a synoptic view of the red tides over the wide region. Previous methods to detect the red tides have not sufficiently performed and revealed limitations in the study region. This study developed a red tide detection scheme based on the deep-learning method by using Landsat-8 OLI data during unprecedented explosive red tide events in the southern coastal region of the Korean Peninsula in 2013. To develop and validate the red tide detection of this study, we conducted cruise campaigns to obtain in-situ water sampling for red tide species and its density, chlorophyll-a concentration, suspended particulate matter (SPM), and spectrum data of red tides as a target object and other reference data using a spectroradiometer in the coastal regions from 2013 to 2015. The seawater shows different spectral shape by its components such as red tide, chlorophyll-a concentration, and SPM. Spectral characteristics of the red tides demonstrated bimodal peaks over visible wavelengths regardless of the species of the red tide. Considering such spectral characteristics, the red tide detection algorithm was constructed by the deep-learning method with Landsat-8 OLI level-2 reflectance values and in-situ red tide observations. The validation results of the algorithm as compared with the map of in-situ red tide measurements showed a high probability of detection values greater than 0.7. These works have made it possible to monitor the red tides with high-spatial resolution satellite data and provide a tool to minimize a lot of socioecological impacts from red tide.

Simple methods for satellite identification of algal blooms and species using 10-year time series data from the East China Sea

Long-term ocean color satellite missions have the ability to help monitor algal blooms. However, satellite identification of algal blooms and species in turbid coastal waters has been challenging. There is an urgent need for simple and effective methods to identify locations, areas, durations, and species present in algal blooms through satellite observation, to aid in the operational and emergency monitoring of the marine environment. In this study, based on a three-band blended model, we propose an indicator (Red tide Detection Index, RDI) that is suitable for the purpose of detecting algal blooms in turbid coastal waters using multi-source ocean color data. MERIS, MODIS, and GOCI data used for the detection of algal blooms demonstrate consistent results using the RDI indicator, and these results correlate with in situ investigations. Furthermore, based on a green-red spectral slope, we propose a method that uses MERIS data to identify dominant species of diatoms and dinoflagellates in algal blooms in the East China Sea (ECS). The 10-year time series MERIS data collected between 2003 and 2012 indicates that algal bloom occurrences are mainly distributed in the nearshore areas of the ECS, and possess a distinct climatological cycle. The 10-year time series MERIS data help discriminate diatom and dinoflagellate blooms in the ECS, and show the dissimilarity in the seasonal timing of their life cycles. We find that these two dominant species in algal blooms are usually distributed in different spatial locations in the ECS. Additionally, by defining a divergence index (DI), the limitations of spectral resolutions of satellite data used for algal bloom species differentiation are quantitatively assessed.

U-Net Convolutional Neural Network Model for Deep Red Tide Learning Using GOCI

Kim, S.M.; Shin, J.; Baek, S., and Ryu, J.-H., 2019. U-Net convolutional neural network model for deep red tide learning using GOCI. In: Jung, H.-S.; Lee, S.; Ryu, J.-H., and Cui, T. (eds.), Advances in Remote Sensing and Geoscience Information Systems of Coastal Environments. Journal of Coastal Research, Special Issue No. 90, pp. 302-309. Coconut Creek (Florida), ISSN 0749-0208.GOCI launched in 2010 is a geostationary satellite image sensor that monitors ocean color. It captures 8-band spectral satellite images of northeast Asian regions hourly, eight times a day. The spatial resolution of GOCI is about 500 m. GOCI is capable of monitoring a large ocean area for sensing various events such as red tide occurrences, tidal movement changes and ocean disasters. In this study, we propose a deep convolutional neural network model, U-Net, for automatic pixel-based detection of red tide occurrence from the spectral images captured by GOCI. We construct two training datasets with GOCI images and the corresponding red-tide index maps (RI maps) accumulated through 2011 to 2018. The RI maps indicate where red tides occurred and what kind of red tide species were there. U-Net consists of five U-shaped encoder and decoder layers to extract spectral features relating to red-tide species from GOCI images. We compared the performances of U-Nets trained from two datasets (i) consisting of only four spectral bands and (ii) consisting of all six spectral bands. The RI maps predicted by the trained U-Nets showed considerably matching spatial occurrence tendencies of three red tide species to the ground truths for validation images. The mean target accuracy with the four-band dataset was 13 % lower than that with the six-band dataset. The trained U-Net for pixel-wise red tide detection would be able to effectively inspect red tide occurrences in the huge area of water surrounding the Korean peninsula.

Red Tide Detection Based on High Spatial Resolution Broad Band Satellite Data: A Case Study of GF-1

Liu, R.-J.; Zhang, J.; Cui, B.-G.; Ma, Y.; Song, P.J., and An, J.-B., 2019. Red tide detection based on high spatial resolution broad band satellite data: A case study of GF-1. In: Jung, H.-S.; Lee, S.; Ryu, J.-H., and Cui, T. (eds.), Advances in Remote Sensing and Geoscience Information Systems of Coastal Environments. Journal of Coastal Research, Special Issue No. 90, pp. 120-128. Coconut Creek (Florida), ISSN 0749-0208.Traditional red tide remote sensing detection methods are based on ocean color satellite data with high spectral resolution (spectral band width < 20 nm), but low spatial resolution. Clearly, fine-scale remote-sensing monitoring of red tide requires high spatial resolution satellite data. Yet, satellite data with high spatial resolution often lack high spectral resolution, with spectral band width > 50 nm. Moreover, systematic research has yet to demonstrate effective detection of red tide using high spatial resolution, but low spectral resolution, satellite data. In this paper, high spatial resolution (16 m), but low spectral resolution, data from the satellite, GF-1, are analyzed to determine if effective fine-scale detection of red tide is possible. The spectral response characteristics of red tide in GF-1 data are analyzed using a 2014 red tide event that occurred in Guangdong Province, China. It was found that, despite broad spectral band widths, GF-1 WFV imaging spectrometer data still exhibits a clear tide detection algorithm for GF-1 WFV data based on this red tide spectral signal. The detection accuracy of red tide for this algorithm is better than 92 %, and the F1-Score value is better than 87 %. Spatial analysis of the Guangdong 2014 red-tide event based on this algorithm showed that the maximum red tide area extracted from GF-1 satellite data is 10 km2, and that the red tide area decreases greatly during the extinction phase. A comparative analysis of MODIS satellite data indicates that, despite the availability of multiple ocean color bands, no ocean color anomaly is detected because of coarse spatial resolution. The developed method was also successfully used to detect red tide occurred in Rizhao, Shandong Province.

Synergistic Effect of Multi-Sensor Data on the Detection of Margalefidinium polykrikoides in the South Sea of Korea

Since 1995, Margalefidinium polykrikoides blooms have occurred frequently in the waters around the Korean peninsula. In the South Sea of Korea (SSK), large-scale M. polykrikoides blooms form offshore and are often transported to the coast, where they gradually accumulate. The objective of this study was to investigate the synergistic effect of multi-sensor data for identifying M. polykrikoides blooms in the SSK from July 2018 to August 2018. We found that the Spectral Shape values calculated from in situ spectra and M. polykrikoides cell abundances in the SSK were highly correlated. Comparing red tide spectra from near-coincident multi-sensor data, remote-sensing reflectance (Rrs) spectra were similar to the spectra of in situ measurements from blue to green wavelengths. Rrs true-color composite images and Spectral Shape images of each sensor showed a clear pattern of M. polykrikoides patches, although there were some limitations for detecting red tide patches in coastal areas. We confirmed the complementarity of red tide data extracted from each sensor using an integrated red tide map. Statistical assessment showed that the sensitivity of red tide detection increased when multi-sensor data were used rather than single-sensor data. These results provide useful information for the application of multi-sensor for red tide detection.

A Study on Red Tide Detection Technique by using Multi-Layer Perceptron

A Study on Red Tide Detection Technique by using Multi-Layer Perceptron

RESEARCH ON HIGH ACCURACY DETECTION OF RED TIDE HYPERSPECRRAL BASED ON DEEP LEARNING CNN

Abstract. Increasing frequency in red tide outbreaks has been reported around the world. It is of great concern due to not only their adverse effects on human health and marine organisms, but also their impacts on the economy of the affected areas. this paper put forward a high accuracy detection method based on a fully-connected deep CNN detection model with 8-layers to monitor red tide in hyperspectral remote sensing images, then make a discussion of the glint suppression method for improving the accuracy of red tide detection. The results show that the proposed CNN hyperspectral detection model can detect red tide accurately and effectively. The red tide detection accuracy of the proposed CNN model based on original image and filter-image is 95.58 % and 97.45 %, respectively, and compared with the SVM method, the CNN detection accuracy is increased by 7.52 % and 2.25 %. Compared with SVM method base on original image, the red tide CNN detection accuracy based on filter-image increased by 8.62 % and 6.37 %. It also indicates that the image glint affects the accuracy of red tide detection seriously.

Development and Application of an Acoustic System for Harmful Algal Blooms (HABs, Red Tide) Detection using an Ultrasonic Digital Sensor

The overgrowth of phytoplankton leads to negative effects such as harmful algal blooms (HABs, also called red tides) in marine environments. The HAB species Cochlodinium polykrikoides (C. polykrikoides) appears frequently in Korea during summer. In this study, we developed a real-time acoustic detection and remote-control system to detect red tides using an ultrasonic digital sensor. In the laboratory, the acoustic signals increased as the number of cells increased. At the same time, for field application, we deployed the system near the southern coast of Korea, where red tides frequently occurred in summer seasons 2013–2015. The system developed here detected red tides in situ, with a good correlation between the acoustic signals and C. polykrikoides populations. These results suggest that it may be useful for early detection of red tides.