Green tide disaster monitoring system based on multi-source data

Shang, Weitao; Gao, Zhiqiang; Jiang, Xiaoxu; Liu, Chaoshun; Gao, Wei

doi:10.1117/12.2235897

Cited by 3 publications

(7 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The surveillance ship data could provide accurate information of U. prolifera for a small area ( Fig. 2c) and can verify the results from RS images [7], [8]. However, because of the limitations in staffing and financial resources, surveillance ship data cannot provide continuous monitoring over a wide area, but is only an auxiliary means for U. prolifera detection.…”

Section: B Datamentioning

confidence: 99%

“…The compatibility matrix represents all mutual compatibility ratios in Source about A i , namely, U. prolifera(i = 1) or sea water (i = 2). The compatibility matrix can be calculated using (8) and (9).…”

Section: ) Improved Approach For U Prolifera Detectionmentioning

confidence: 99%

“…SOA also uses ocean surveillance ships to detect U. prolifera blooms close to the shore and planes to detect blooms further out to sea. The surveillance ships and planes can help to direct the attention of decision makers to the most important U. prolifera bloom areas, check the U. prolifera growth conditions, and verify the results from RS images [7], [8]. Among these three methods, remote sensing plays an essential role in the detection and prevention of U. prolifera [8], [10] owing to its wide coverage and low cost.…”

Section: Introductionmentioning

confidence: 99%

“…The surveillance ships and planes can help to direct the attention of decision makers to the most important U. prolifera bloom areas, check the U. prolifera growth conditions, and verify the results from RS images [7], [8]. Among these three methods, remote sensing plays an essential role in the detection and prevention of U. prolifera [8], [10] owing to its wide coverage and low cost. Surveillance airplanes or unmanned aerial vehicles (UAVs) can detect U. prolifera along their flight paths at a relatively higher speed, but these approaches are costly and heavily depend on weather conditions.…”

Section: Introductionmentioning

confidence: 99%

“…However, navigation of these ships is closely related to sea surface conditions, and detection over large areas is expensive. Therefore, data from surveillance ships, airplanes, and UAVs are used as auxiliary data in U. prolifera monitoring, because of their limited scope or high cost [2], [1], [8].…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Multi-Source Evidence Data Fusion Approach to Detect Daily Distribution and Coverage of Ulva Prolifera in the Yellow Sea, China

Wang

Fang²,

et al. 2019

IEEE Access

View full text Add to dashboard Cite

Ulva prolifera (U. prolifera), a seaweed species in the family Ulvaceae, has been causing green tides in the Yellow Sea, China, every year since 2008. This has attracted the attention of the government and the scientific community because of its influence on the region's marine economy and coastal zone environment. Remote sensing, surveillance ships, and airplanes are three common surveillance approaches used by the State Oceanic Administration (SOA) for U. prolifera detection in the Yellow Sea. However, improving the accuracy and convenience of daily U. prolifera detection by fusing the data from these sources, and obtaining the coverage area and distribution of U. prolifera without human intervention, are two challenges that need to be addressed. To this end, this study proposes an improved multi-source evidence fusion method based on Dempster-Shafer evidence theory to detect the distribution and coverage area of U. prolifera using data from multiple sources (MODIS images, Sentinel-2A images, and surveillance ship data). This improved approach can handle the conflicts caused by differences in image characteristics and spatial resolutions as well as differences between surveillance ship data and remote sensing data. The capability of the improved method to extract the distribution and coverage area of U. prolifera was tested experimentally. The results agree with the reference data supplied by SOA in terms of spatial position and geometry. The fusion of multi-source data demonstrates better results in the detection of U. prolifera coverage area and spatial distribution compared with those from individual data sources. The improved approach can be applied to daily and emergent monitoring tasks for U. prolifera detection.

show abstract

Section: B Datamentioning

confidence: 99%

Section: ) Improved Approach For U Prolifera Detectionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Multi-Source Evidence Data Fusion Approach to Detect Daily Distribution and Coverage of Ulva Prolifera in the Yellow Sea, China

Wang

Fang²,

et al. 2019

IEEE Access

View full text Add to dashboard Cite

show abstract

Bidirectional Spatio-Temporal Association Between the Observed Results of Ulva Prolifera Green Tides in the Yellow Sea and the Social Response in Sina Weibo

Wang

Fang

Song

2021

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Massive green tides caused by Ulva prolifera have annually occurred in the Yellow Sea since 2007, which has attracted much attention from the government and society. There are associations between the green tides in the Yellow Sea and social response in the social media (i.e. Sina Weibo), which are bidirectional and could be captured by the bidirectional neural network. For instance, how to detect daily U.prolifera green tides by fusing remote sensing data with social media data, and how to use the observed U.prolifera green tides to infer the social response are two challenges of State-Oceanic Administration, China. This paper first illustrated that there are bidirectional associations between green tides and Sina Weibo data. Then, this paper introduced a bidirectional spatiotemporal associative memory neural network model (BSAMNN) for modeling this bidirectional association from the spatiotemporal perspective. BSAMNN first extracted six characteristics from green tides and nine characteristics from the social responses in 2016-2019. Secondly, these characteristics were split by year and the characteristics in 2016-2018 were respectively put into the bidirectional associative memory neural network (BAM) which is a two-layer artificial neural network. Based on the BAM results and the observed data, the residual network was constructed. Thirdly, BSAMNN extracted the spatiotemporal rules from the characteristics in 2016-2018 as the constraints through the mining rule algorithm and modify the results via sea surface wind and ocean surface current. Last, BSAMNN put the characteristics in 2019 into BAM and used the residual network to modify the results, which was constrained by the spatiotemporal rules.The feasibility and reliability of our approach were demonstrated by using the U.prolifera green tides in 2019. The average accuracy, false alarm rate, and missing alarm rate of BSAMNN results were 0.69, 0.25, and 0.31 respectively which was 0.11 higher, 0.10 lower, and 0.11 lower than that of the traditional bidirectional associative memory neural network. The results indicated that our method is an effective alternative of linking the U.prolifera green tides and its public sentiments on social media.

show abstract

Remote Sensing Monitoring of Green Tide Disaster Using MODIS and GF-1 Data: A Case Study in the Yellow Sea

Men,

Liu,

et al. 2023

JMSE

View full text Add to dashboard Cite

Satellites with low-to-medium spatial resolution face challenges in monitoring the early and receding stages of green tides, while those with high spatial resolution tend to reduce the monitoring frequency of such phenomena. This study aimed to observe the emergence, evolution, and migratory patterns of green tides. We integrated GF-1 and MODIS imagery to collaboratively monitor the green tide disaster in the Yellow Sea during 2021. Initially, a linear regression model was employed to adjust the green tide coverage area as captured using MODIS imagery. We jointly observed the distribution range, drift path, and coverage area of the green tide and analyzed the drift path in coordination with offshore wind field and flow field data. Furthermore, we investigated the influence of SST, SSS, and rainfall on the 2021 green tide outbreak. The correlations calculated between SST, SSS, and precipitation with the changes in the area of the green tide were 0.43, 0.76, and 0.48, respectively. Our findings indicate that the large-scale green tide outbreak in 2021 may be associated with several factors. An increase in SST and SSS during the initial phase of the green tide established the essential conditions, while substantial rainfall during its developmental stage provided favorable conditions. Notably, the SSS exhibited a close association with the outbreak of the green tide.

show abstract

Green tide disaster monitoring system based on multi-source data

Cited by 3 publications

References 6 publications

Multi-Source Evidence Data Fusion Approach to Detect Daily Distribution and Coverage of Ulva Prolifera in the Yellow Sea, China

Multi-Source Evidence Data Fusion Approach to Detect Daily Distribution and Coverage of Ulva Prolifera in the Yellow Sea, China

Bidirectional Spatio-Temporal Association Between the Observed Results of Ulva Prolifera Green Tides in the Yellow Sea and the Social Response in Sina Weibo

Remote Sensing Monitoring of Green Tide Disaster Using MODIS and GF-1 Data: A Case Study in the Yellow Sea

Contact Info

Product

Resources

About