Automatic Detection of Algal Blooms Using Sentinel-2 MSI and Landsat OLI Images

Xu, Dandan; Pu, Yihan; Zhu, Mengyuan; Zhang, Luan; Shi, Kun

doi:10.1109/jstars.2021.3105746

Cited by 13 publications

(8 citation statements)

References 82 publications

(178 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These techniques involve the use of sensors to collect data remotely, often from satellites, aircraft or drones [21][22][23]. By using artificial intelligence algorithms to analyze the collected data, researchers can gain insights into environmental patterns and make predictions about future trends [24,25]. With the help of machine learning models, scientists can develop early warning systems to detect harmful algal blooms, helping to mitigate the negative effects of eutrophication on lake ecosystems [26][27][28].…”

Section: Introductionmentioning

confidence: 99%

Estimation of Water Quality Parameters through a Combination of Deep Learning and Remote Sensing Techniques in a Lake in Southern Chile

Rodríguez-López,

Usta,

Duran-Llacer

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

In this study, we combined machine learning and remote sensing techniques to estimate the value of chlorophyll-a concentration in a freshwater ecosystem in the South American continent (lake in Southern Chile). In a previous study, nine artificial intelligence (AI) algorithms were tested to predict water quality data from measurements during monitoring campaigns. In this study, in addition to field data (Case A), meteorological variables (Case B) and satellite data (Case C) were used to predict chlorophyll-a in Lake Llanquihue. The models used were SARIMAX, LSTM, and RNN, all of which showed generally good statistics for the prediction of the chlorophyll-a variable. Model validation metrics showed that all three models effectively predicted chlorophyll as an indicator of the presence of algae in water bodies. Coefficient of determination values ranging from 0.64 to 0.93 were obtained, with the LSTM model showing the best statistics in any of the cases tested. The LSTM model generally performed well across most stations, with lower values for MSE (<0.260 (μg/L)2), RMSE (<0.510 ug/L), MaxError (<0.730 μg/L), and MAE (<0.442 μg/L). This model, which combines machine learning and remote sensing techniques, is applicable to other Chilean and world lakes that have similar characteristics. In addition, it is a starting point for decision-makers in the protection and conservation of water resource quality.

show abstract

Section: Introductionmentioning

confidence: 99%

Estimation of Water Quality Parameters through a Combination of Deep Learning and Remote Sensing Techniques in a Lake in Southern Chile

Rodríguez-López,

Usta,

Duran-Llacer

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Landsat images were used in [18] to calculate NDVI for water hyacinth detection. Other works used spectral indices and spatial autocorrelation analysis to detect algal blooms in Sentinel-2 and Landsat images [19], and also used MODIS images to calculate the floating algae index (FAI).…”

Section: A Using Spectral Indices To Detect Invasive Aquatic Plantsmentioning

confidence: 99%

Mapping Invasive Aquatic Plants in Sentinel-2 Images Using Convolutional Neural Networks Trained With Spectral Indices

Rodriguez-Garlito

Paz

2023

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

View full text Add to dashboard Cite

Multispectral images collected by the European Space Agency (ESA)'s Sentinel-2 satellite offer a powerful resource for accurately and efficiently mapping areas affected by the distribution of invasive aquatic plants. In this work, we use different spectral indices to detect invasive aquatic plants in the Guadiana river, Spain. Our methodology uses a convolutional neural network (CNN) as the baseline classifier and trains it using spectral indices calculated using different Sentinel-2 band combinations. Specifically, we consider the following spectral indices: with two bands, we calculate the normalized difference vegetation index (NDVI), normalized difference water index (NDWI), and normalized difference infrared index (NDII). With three bands, we calculate the red-green-blue (RGB) composite and the floating algae index (FAI). Finally, we also use four bands to calculate the bare soil index (BSI). In our results, we observed that CNNs can better map invasive aquatic plants in the considered case study when trained intelligently (using spectral indices) as compared to using all spectral bands provided by the Sentinel-2 instrument.

show abstract

“…Automatic shoreline extraction is based on the concept of the LISA method, which captures spatial clustering based on the spatial correlation between variables and surrounding variables [28]. In Landsat imagery, the texture of water is smooth compared with that of land, establishing an autocorrelation between each pixel of water bodies and its neighbors.…”

Section: Automatic Shoreline Extraction From Remote Sensing Imagesmentioning

confidence: 99%

“…The local indicator of spatial autocorrelation (LISA) method captures spatial clusters based on the spatial correlation between a variable and its surrounding variables. The LISA method has great potential in eliminating illogical results, due to its emphasis on the autocorrelation between each pixel and its neighbors [28]. It has been shown to be an effective method, with high accuracy for distinguishing between land and water bodies for ecological research [29][30][31].…”

Section: Introductionmentioning

confidence: 99%

Shoreline Dynamics of Chongming Island and Driving Factor Analysis Based on Landsat Images

Wang

Zhang

et al. 2022

Remote Sensing

Self Cite

View full text Add to dashboard Cite

Chongming Island, the third largest island in China, has experienced dramatic shoreline changes due to erosion, river deposits, and human activities. While previous studies have shown the capacity of Landsat series images to extract shoreline dynamics, the spatial variation of shoreline dynamics and their corresponding driving factors remain unclear. Therefore, we established a method to monitor the shoreline dynamics of Chongming Island from 1984 to 2020 and to evaluate the driving factors of shoreline changes using a novel approach to Landsat image analysis. The method, based on the LISA (local indicator of spatial autocorrelation) concept, automatically extracted the shoreline from Landsat imagery. The results show that the LISA method, based on the SWIR1 band, has a high capacity for shoreline extraction in Chongming Island. By distinguishing the responses of the eastern and northern shorelines to upstream sediment loads and comprehensively analyzing the driving factors of eastern and northern dynamics, we found that: (i) although upstream sediment loads decreased dramatically, the shoreline of Chongming Island is still expanding due to human activities (i.e., reclamation and an estuary project) and sediment re-suspension from near-shore or cross-shore currents; (ii) the expansion of Chongming Island was initially due to the dynamics at the eastern shoreline, but the expansion of the eastern shoreline slowed after 2008 as upstream sedimentation slowed, less construction of cofferdams took place, and the Qingcaosha Reservoir was constructed; (iii) the northern shoreline of Chongming Island expanded rapidly after 1999, due to the merger of Xinlongsha, Xincunsha, and Chongming Island, and the transport of coastal and offshore sediments by hydrodynamic processes; and (iv) the main driving factors of eastern shoreline movement on Chongming Island are cofferdam reclamation and coastal engineering, and the changes at the northern shoreline are mainly affected by reclamation projects, offshore sediment supplies, and upstream sediment inflow. The results of this study provide theoretical fundamentals for land reclamation and future urban planning for Chongming Island.

show abstract

Automatic Detection of Algal Blooms Using Sentinel-2 MSI and Landsat OLI Images

Cited by 13 publications

References 82 publications

Estimation of Water Quality Parameters through a Combination of Deep Learning and Remote Sensing Techniques in a Lake in Southern Chile

Estimation of Water Quality Parameters through a Combination of Deep Learning and Remote Sensing Techniques in a Lake in Southern Chile

Mapping Invasive Aquatic Plants in Sentinel-2 Images Using Convolutional Neural Networks Trained With Spectral Indices

Shoreline Dynamics of Chongming Island and Driving Factor Analysis Based on Landsat Images

Contact Info

Product

Resources

About