Qing Zhu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Qing Zhu has a total of 24 co-authors. Here are the top co-authors by number of shared publications:
- Fang Shen
State Key Laboratory of Estuarine and Coastal Research, East China Normal University, Shanghai, China
3 shared publications Gong Lin
Xiamen University
2 shared publications- Jing Liu
Institute of Marine Science and Technology Shandong University Qingdao China
2 shared publications - Mengyu Li
State Key Laboratory of Estuarine and Coastal Research, East China Normal University, Shanghai, China
2 shared publications - Pei Shang
State Key Laboratory of Estuarine and Coastal Research, East China Normal University, Shanghai 200241, China
2 shared publications - Richard Garth James Bellerby
Norwegian Institute for Water Research, Bergen, Norway
2 shared publications
Latest Publications
- 17 August 2025
- Published by American Geophysical Union (AGU) in Journal of Geophysical Research: Oceans
- Vol. 130  (8)
Remote Estimations of Total Alkalinity and Total Dissolved Inorganic Carbon in the Yellow and East China Seas Using Machine Learning Approach
The sea surface total alkalinity (AT) and total dissolved inorganic carbon (CT) are two essential carbonate variables to understand the marine carbon cycle, yet it has been a big challenge to retrieve AT and CT from space for the Yellow and East China Seas (YECS) owing to they are affected coupling by physical and biogeochemical processes and the heterogeneous coastal environments. To address these challenges, we developed multilayer perceptron neural network (MPNN)âbased AT and CT models with the field measured environmental variables as the model predictors, and obtained a root mean square difference (RMSD) of 27.05 Îĵmol/kg and coefficient of determination (R2) of 0.91 for AT (N = 1,520) and a RMSD was 28.31 Îĵmol/kg and R2 was 0.88 for CT (N = 513). Further, the MPNNâbased model showed much promise in remotely retrieving surface AT and CT with the spatial resolution of âĵ1 km in the YECS with a RMSD of 26.59 Îĵmol/kg, R2 of 0.76 for AT and a RMSD of 37.14 Îĵmol/kg, R2 of 0.79 for CT. Applying the MPNNâbased model to the Moderate Resolution Imaging Spectroradiometer (MODIS) products, retrieved the monthly distributions of AT and CT over the past 20 years for the first time, demonstrated strong linkages to water masses circulations, upwelling and biological processes with seasonal cycles. Also, the interannual variations of AT and CT had significant relationships with the environmental proxies, as well as climate indices (North Pacific Gyre Oscillation). This work advances understanding of coastal carbon cycling and offers a valuable tool for largeâscale, high spatialâtemporal resolution monitoring of carbon dynamics.
- 17 August 2025
- Published by American Geophysical Union (AGU) in Journal of Geophysical Research: Oceans
- Vol. 130  (8)
Remote Estimations of Total Alkalinity and Total Dissolved Inorganic Carbon in the Yellow and East China Seas Using Machine Learning Approach
The sea surface total alkalinity (AT) and total dissolved inorganic carbon (CT) are two essential carbonate variables to understand the marine carbon cycle, yet it has been a big challenge to retrieve AT and CT from space for the Yellow and East China Seas (YECS) owing to they are affected coupling by physical and biogeochemical processes and the heterogeneous coastal environments. To address these challenges, we developed multilayer perceptron neural network (MPNN)âbased AT and CT models with the field measured environmental variables as the model predictors, and obtained a root mean square difference (RMSD) of 27.05 Îĵmol/kg and coefficient of determination (R2) of 0.91 for AT (N = 1,520) and a RMSD was 28.31 Îĵmol/kg and R2 was 0.88 for CT (N = 513). Further, the MPNNâbased model showed much promise in remotely retrieving surface AT and CT with the spatial resolution of âĵ1 km in the YECS with a RMSD of 26.59 Îĵmol/kg, R2 of 0.76 for AT and a RMSD of 37.14 Îĵmol/kg, R2 of 0.79 for CT. Applying the MPNNâbased model to the Moderate Resolution Imaging Spectroradiometer (MODIS) products, retrieved the monthly distributions of AT and CT over the past 20 years for the first time, demonstrated strong linkages to water masses circulations, upwelling and biological processes with seasonal cycles. Also, the interannual variations of AT and CT had significant relationships with the environmental proxies, as well as climate indices (North Pacific Gyre Oscillation). This work advances understanding of coastal carbon cycling and offers a valuable tool for largeâscale, high spatialâtemporal resolution monitoring of carbon dynamics.
- 25 March 2025
- Published by Optica Publishing Group in Optics Express
- Vol. 33  (7) , 14910-14942
Evaluation of two semi-analytical algorithms for retrieving absorption properties in the marginal seas of China: a perspective from water types and trophic levels
Based on a relatively large dataset having concurrent measurements of remote sensing reflectance (R rs) and absorption coefficients collected in the marginal seas of China (MSC) over the past two decades (2003-2021), we evaluated two widely used semi-analytical algorithms (SAAs) for retrieving the absorption properties in the MSC from both field-measured and satellite data. The SAAs are the quasi-analytical algorithm version 6 (QAA_v6) and the generalized inherent optical properties model (GIOP), while the satellite data are from the moderate resolution imaging spectroradiometer on the aqua satellite. The water body was classified following a proposed system, also separated via the trophic level (oligotrophic, mesotrophic, and eutrophic) based on chlorophyll-a concentration, so the performance of these two SAAs was evaluated for the different water types. For the water types we evaluated, both QAA_v6 and GIOP are found to have different applicable water types in retrieving absorption properties, and the relatively reliable retrieval results of absorption properties are mainly in the water types 3-13, and at the wavebands shorter than 500 nm. In addition, the retrieval performance of these two SAAs for a dg (the sum of colored dissolved organic matter and non-pigmented particulate matter) and a ph (phytoplankton pigment) in the eutrophic waters in the MSC still needs to be improved. Before 500 nm, MODIS-Aqua data can provide reliable a nw (non-water absorption), a dg, and a ph with QAA_v6; and can provide reliable a nw and a ph with GIOP. This study provides what we believe to be a new and more detailed perspective for evaluating the retrieval of absorption properties using these two SAAs in the MSC, and our results suggest that water types should be considered in improving the estimation of intermediate variables in these SAAs.
- 25 March 2025
- Published by Optica Publishing Group in Optics Express
- Vol. 33  (7) , 14910-14942
Evaluation of two semi-analytical algorithms for retrieving absorption properties in the marginal seas of China: a perspective from water types and trophic levels
Based on a relatively large dataset having concurrent measurements of remote sensing reflectance (R rs) and absorption coefficients collected in the marginal seas of China (MSC) over the past two decades (2003-2021), we evaluated two widely used semi-analytical algorithms (SAAs) for retrieving the absorption properties in the MSC from both field-measured and satellite data. The SAAs are the quasi-analytical algorithm version 6 (QAA_v6) and the generalized inherent optical properties model (GIOP), while the satellite data are from the moderate resolution imaging spectroradiometer on the aqua satellite. The water body was classified following a proposed system, also separated via the trophic level (oligotrophic, mesotrophic, and eutrophic) based on chlorophyll-a concentration, so the performance of these two SAAs was evaluated for the different water types. For the water types we evaluated, both QAA_v6 and GIOP are found to have different applicable water types in retrieving absorption properties, and the relatively reliable retrieval results of absorption properties are mainly in the water types 3-13, and at the wavebands shorter than 500 nm. In addition, the retrieval performance of these two SAAs for a dg (the sum of colored dissolved organic matter and non-pigmented particulate matter) and a ph (phytoplankton pigment) in the eutrophic waters in the MSC still needs to be improved. Before 500 nm, MODIS-Aqua data can provide reliable a nw (non-water absorption), a dg, and a ph with QAA_v6; and can provide reliable a nw and a ph with GIOP. This study provides what we believe to be a new and more detailed perspective for evaluating the retrieval of absorption properties using these two SAAs in the MSC, and our results suggest that water types should be considered in improving the estimation of intermediate variables in these SAAs.
- 3 March 2025
- Published by Wiley in Limnology and Oceanography: Methods
Retrieving vertical phytoplankton functional types in the South China Sea and adjacent Taiwan Strait based on phytoplankton absorption spectra and machine learning
Phytoplankton functional types (PFTs) found in natural aquatic environments play different roles in the biogeochemical cycles of different elements. However, commonly used methods for identifying PFTs have inherent limitations. In this study, based on a large dataset (1747 samples) collected from 2004 to 2019 in the South China Sea and adjacent Taiwan Strait, which had concurrent measurements of the spectral absorption coefficient of phytoplankton and chlorophyll a concentration of nine PFTs (PFTsChla), along with depth and time information, a reliable support vector regression (SVR) model was developed to retrieve these nine PFTsChla in the water column. These PFTs included diatoms, dinoflagellates, haptophytes_8, haptophytes_6, chlorophytes, cryptophytes, Prochlorococcus, Synechococcus, and prasinophytes. The independent validation results indicated that the SVR model outperformed the traditional PFTsChla retrieval algorithms, with an average mean bias of â14.2%, an average mean absolute unbiased relative difference of 60.3%, and an average coefficient of determination of 0.56. The predicted PFTsChla values and their error distributions in the water column were subsequently analyzed. Finally, the SVR model was found to be applicable to most PFTsChla retrieval in the East China Sea.
- 3 March 2025
- Published by Wiley in Limnology and Oceanography: Methods
Retrieving vertical phytoplankton functional types in the South China Sea and adjacent Taiwan Strait based on phytoplankton absorption spectra and machine learning
Phytoplankton functional types (PFTs) found in natural aquatic environments play different roles in the biogeochemical cycles of different elements. However, commonly used methods for identifying PFTs have inherent limitations. In this study, based on a large dataset (1747 samples) collected from 2004 to 2019 in the South China Sea and adjacent Taiwan Strait, which had concurrent measurements of the spectral absorption coefficient of phytoplankton and chlorophyll a concentration of nine PFTs (PFTsChla), along with depth and time information, a reliable support vector regression (SVR) model was developed to retrieve these nine PFTsChla in the water column. These PFTs included diatoms, dinoflagellates, haptophytes_8, haptophytes_6, chlorophytes, cryptophytes, Prochlorococcus, Synechococcus, and prasinophytes. The independent validation results indicated that the SVR model outperformed the traditional PFTsChla retrieval algorithms, with an average mean bias of â14.2%, an average mean absolute unbiased relative difference of 60.3%, and an average coefficient of determination of 0.56. The predicted PFTsChla values and their error distributions in the water column were subsequently analyzed. Finally, the SVR model was found to be applicable to most PFTsChla retrieval in the East China Sea.
- 7 April 2024
- Published by Elsevier in Progress in Oceanography
- Vol. 224
Intraseasonal response of marine planktonic ecosystem to summertime Madden-Julian Oscillation in the South China Sea: A model study
- 7 April 2024
- Published by Elsevier in Progress in Oceanography
- Vol. 224
Intraseasonal response of marine planktonic ecosystem to summertime Madden-Julian Oscillation in the South China Sea: A model study
- 27 February 2024
- Published by Elsevier in Progress in Oceanography
- Vol. 223
Offshore high chlorophyll eddies: Separating upwelling from nearshore migration from ocean color remote sensing
- 27 February 2024
- Published by Elsevier in Progress in Oceanography
- Vol. 223
Offshore high chlorophyll eddies: Separating upwelling from nearshore migration from ocean color remote sensing
- Open Access
- 26 October 2023
- Published by American Geophysical Union (AGU) in Earth and Space Science
- Vol. 10  (11)
Estimating Sea Surface Salinity in the East China Sea Using Satellite Remote Sensing and Machine Learning
Sea surface salinity (SSS) is a master variable in oceanography and important to understand marine biogeochemical and physical processes. In the East China Sea (ECS), a random forest based regression ensemble model (RF) was developed to estimate the SSS with a spatial resolution of âĵ1 km based on a large synchronous data set of in situ SSS observations, MODISâderived remote sensing reflectance (Rrs) and sea surface temperature (SST). The model showed the best performance when the Rrs(412), Rrs(488), Rrs(555), Rrs(667), SST and Julian day (JD) were used as inputs, with a root mean square error (RMSE) of 0.84, mean absolute error (MAE) of 0.31 and coefficient of determination (R2) of 0.81 for model training (N = 4,504), and a RMSE of 0.77, MAE of 0.30 and R2 of 0.86 for the model test (N = 1,153). The accuracy of the SSS model was examined using an independent data set during the period of 2020â2022 with a RMSE of 0.66 and MAE of 0.39 (N = 2,151). The interannual and seasonal signal of modeled SSS of the ECS, showed that important drivers of variability are the Changjiang discharge and the EastâAsian monsoon. Applications of the model to other Chinese marginal seas (Yellow and Bohai seas) showed good agreement in distribution patterns when compared with the estimated SSS from NASA Soil Moisture Active Passive. Once more empirical oceanographic data is made available, this robust model can be applied to other regions retraining the model with informed local data sets.
- 26 October 2023
- Published by American Geophysical Union (AGU) in Earth and Space Science
- Vol. 10  (11)
Open AccessEstimating Sea Surface Salinity in the East China Sea Using Satellite Remote Sensing and Machine Learning
Sea surface salinity (SSS) is a master variable in oceanography and important to understand marine biogeochemical and physical processes. In the East China Sea (ECS), a random forest based regression ensemble model (RF) was developed to estimate the SSS with a spatial resolution of âĵ1 km based on a large synchronous data set of in situ SSS observations, MODISâderived remote sensing reflectance (Rrs) and sea surface temperature (SST). The model showed the best performance when the Rrs(412), Rrs(488), Rrs(555), Rrs(667), SST and Julian day (JD) were used as inputs, with a root mean square error (RMSE) of 0.84, mean absolute error (MAE) of 0.31 and coefficient of determination (R2) of 0.81 for model training (N = 4,504), and a RMSE of 0.77, MAE of 0.30 and R2 of 0.86 for the model test (N = 1,153). The accuracy of the SSS model was examined using an independent data set during the period of 2020â2022 with a RMSE of 0.66 and MAE of 0.39 (N = 2,151). The interannual and seasonal signal of modeled SSS of the ECS, showed that important drivers of variability are the Changjiang discharge and the EastâAsian monsoon. Applications of the model to other Chinese marginal seas (Yellow and Bohai seas) showed good agreement in distribution patterns when compared with the estimated SSS from NASA Soil Moisture Active Passive. Once more empirical oceanographic data is made available, this robust model can be applied to other regions retraining the model with informed local data sets.
- 8 March 2022
- Published by Wiley in Limnology and Oceanography
- Vol. 67  (4) , 946-961
Light absorption spectra of naturally mixed phytoplankton assemblages for retrieval of phytoplankton group composition in coastal oceans
Phytoplankton group composition is complex and highly variable in coastal waters. Given that different taxonomic groups have different pigment signatures, which in turn impact the light absorption spectra of phytoplankton, the absorption spectralâbased approach has the potential for distinguishing phytoplankton groups. Using a large dataset of in situ surface observations of concurrent HPLC (highâperformance liquid chromatography) pigments and phytoplankton absorption spectra collected from 2015 to 2018 in Chinese coastal oceans, in situ phytoplankton group composition was obtained from chemotaxonomic analysis (CHEMTAX). By using the linear additive principle on phytoplankton absorption spectra and CHEMTAX results, the chlorophyllâspecific absorption spectra of eight phytoplankton groups were reconstructed, including prasinophytes, dinoflagellates, cryptophytes, chlorophytes, cyanobacteria, diatoms, chrysophytes, and prymnesiophytes. These chlorophyllâspecific absorption spectra were subsequently used as inputs to a spectralâbased inversion model for estimating phytoplankton group composition from the phytoplankton absorption coefficient. The optimal band selection and initial guesses of the phytoplankton group composition, derived from correlation and HCA (hierarchical cluster analysis) analyses, were included in the model inversion to improve the accuracy of retrievals. The performance of the proposed model was validated using an independent dataset, showing accurate estimates of chlorophyll a (Chl a) concentrations for seven phytoplankton groups (0.371 ⤠r ⤠0.721, p < 0.05), apart from chrysophytes. Our results suggest that the absorption spectralâbased approach is able to discriminate phytoplankton group composition quantitatively, which has implications for retrieving Chl a concentrations of phytoplankton groups from hyperspectral platforms and satellites.
- 8 March 2022
- Published by Wiley in Limnology and Oceanography
- Vol. 67  (4) , 946-961
Light absorption spectra of naturally mixed phytoplankton assemblages for retrieval of phytoplankton group composition in coastal oceans
Phytoplankton group composition is complex and highly variable in coastal waters. Given that different taxonomic groups have different pigment signatures, which in turn impact the light absorption spectra of phytoplankton, the absorption spectralâbased approach has the potential for distinguishing phytoplankton groups. Using a large dataset of in situ surface observations of concurrent HPLC (highâperformance liquid chromatography) pigments and phytoplankton absorption spectra collected from 2015 to 2018 in Chinese coastal oceans, in situ phytoplankton group composition was obtained from chemotaxonomic analysis (CHEMTAX). By using the linear additive principle on phytoplankton absorption spectra and CHEMTAX results, the chlorophyllâspecific absorption spectra of eight phytoplankton groups were reconstructed, including prasinophytes, dinoflagellates, cryptophytes, chlorophytes, cyanobacteria, diatoms, chrysophytes, and prymnesiophytes. These chlorophyllâspecific absorption spectra were subsequently used as inputs to a spectralâbased inversion model for estimating phytoplankton group composition from the phytoplankton absorption coefficient. The optimal band selection and initial guesses of the phytoplankton group composition, derived from correlation and HCA (hierarchical cluster analysis) analyses, were included in the model inversion to improve the accuracy of retrievals. The performance of the proposed model was validated using an independent dataset, showing accurate estimates of chlorophyll a (Chl a) concentrations for seven phytoplankton groups (0.371 ⤠r ⤠0.721, p < 0.05), apart from chrysophytes. Our results suggest that the absorption spectralâbased approach is able to discriminate phytoplankton group composition quantitatively, which has implications for retrieving Chl a concentrations of phytoplankton groups from hyperspectral platforms and satellites.
- Open Access
- 22 January 2020
- Published by MDPI AG in Remote Sensing
- Vol. 12  (3) , 364
Correction: Zhu, Q., et al. Hyperspectral Remote Sensing of Phytoplankton Species Composition Based on Transfer Learning. Remote Sensing 2019, 11, 2001
The authors wish to make the following corrections to this paper
- 22 January 2020
- Published by MDPI AG in Remote Sensing
- Vol. 12  (3) , 364
Open AccessCorrection: Zhu, Q., et al. Hyperspectral Remote Sensing of Phytoplankton Species Composition Based on Transfer Learning. Remote Sensing 2019, 11, 2001
The authors wish to make the following corrections to this paper
- Open Access
- 24 August 2019
- Published by MDPI AG in Remote Sensing
- Vol. 11  (17) , 2001
Hyperspectral Remote Sensing of Phytoplankton Species Composition Based on Transfer Learning
Phytoplankton species composition research is key to understanding phytoplankton ecological and biogeochemical functions. Hyperspectral optical sensor technology allows us to obtain detailed information about phytoplankton species composition. In the present study, a transfer learning method to inverse phytoplankton species composition using in situ hyperspectral remote sensing reflectance and hyperspectral satellite imagery was presented. By transferring the general knowledge learned from the first few layers of a deep neural network (DNN) trained by a general simulation dataset, and updating the last few layers with an in situ dataset, the requirement for large numbers of in situ samples for training the DNN to predict phytoplankton species composition in natural waters was lowered. This method was established from in situ datasets and validated with datasets collected in different ocean regions in China with considerable accuracy (R2 = 0.88, mean absolute percentage error (MAPE) = 26.08%). Application of the method to Hyperspectral Imager for the Coastal Ocean (HICO) imagery showed that spatial distributions of dominant phytoplankton species and associated compositions could be derived. These results indicated the feasibility of species composition inversion from hyperspectral remote sensing, highlighting the advantages of transfer learning algorithms, which can bring broader application prospects for phytoplankton species composition and phytoplankton functional type research.
- 24 August 2019
- Published by MDPI AG in Remote Sensing
- Vol. 11  (17) , 2001
Open AccessHyperspectral Remote Sensing of Phytoplankton Species Composition Based on Transfer Learning
Phytoplankton species composition research is key to understanding phytoplankton ecological and biogeochemical functions. Hyperspectral optical sensor technology allows us to obtain detailed information about phytoplankton species composition. In the present study, a transfer learning method to inverse phytoplankton species composition using in situ hyperspectral remote sensing reflectance and hyperspectral satellite imagery was presented. By transferring the general knowledge learned from the first few layers of a deep neural network (DNN) trained by a general simulation dataset, and updating the last few layers with an in situ dataset, the requirement for large numbers of in situ samples for training the DNN to predict phytoplankton species composition in natural waters was lowered. This method was established from in situ datasets and validated with datasets collected in different ocean regions in China with considerable accuracy (R2 = 0.88, mean absolute percentage error (MAPE) = 26.08%). Application of the method to Hyperspectral Imager for the Coastal Ocean (HICO) imagery showed that spatial distributions of dominant phytoplankton species and associated compositions could be derived. These results indicated the feasibility of species composition inversion from hyperspectral remote sensing, highlighting the advantages of transfer learning algorithms, which can bring broader application prospects for phytoplankton species composition and phytoplankton functional type research.
- 13 October 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 11  (1) , 34-44
Distinguishing Cyanobacterial Bloom From Floating Leaf Vegetation in Lake Taihu Based on Medium-Resolution Imaging Spectrometer (MERIS) Data
Based on field measurements of water surface reflectance spectra in Lake Taihu, we construct a model for distinguishing between cyanobacterial bloom and floating leaf vegetation by combining a chlorophyll spectral index with a baseline of phycocyanin. In situ R rs measurements validation results show that this model performs well in distinguishing cyanobacterial bloom from floating leaf vegetation in Lake Taihu. We apply this model to 52 remote sensing images from the Medium-Resolution Imaging Spectrometer (MERIS) from 2003 to 2011. Using two different accuracy evaluation methods, we find an average recognition accuracy of more than 80% for cyanobacterial bloom and floating leaf vegetation when using optimal index thresholds. Using an average index threshold to extract cyanobacterial bloom and floating leaf vegetation from the images, the relative accuracies are 78.8% and 74.6%, respectively. If more efficiency is desired, these average thresholds can be used, which is convenient for batch processing and automated extraction of cyanobacterial bloom and floating leaf vegetation from remote sensing data. The overall distribution of cyanobacterial bloom and floating leaf vegetation in Lake Taihu from 2003 to 2011 is determined by overlapping the distribution maps from individual images, and the results of our analysis are consistent with previously published results. In addition, our analysis shows that this model is immune to perturbations from thin clouds and aerosols.
- 13 October 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 11  (1) , 34-44
Distinguishing Cyanobacterial Bloom From Floating Leaf Vegetation in Lake Taihu Based on Medium-Resolution Imaging Spectrometer (MERIS) Data
Based on field measurements of water surface reflectance spectra in Lake Taihu, we construct a model for distinguishing between cyanobacterial bloom and floating leaf vegetation by combining a chlorophyll spectral index with a baseline of phycocyanin. In situ R rs measurements validation results show that this model performs well in distinguishing cyanobacterial bloom from floating leaf vegetation in Lake Taihu. We apply this model to 52 remote sensing images from the Medium-Resolution Imaging Spectrometer (MERIS) from 2003 to 2011. Using two different accuracy evaluation methods, we find an average recognition accuracy of more than 80% for cyanobacterial bloom and floating leaf vegetation when using optimal index thresholds. Using an average index threshold to extract cyanobacterial bloom and floating leaf vegetation from the images, the relative accuracies are 78.8% and 74.6%, respectively. If more efficiency is desired, these average thresholds can be used, which is convenient for batch processing and automated extraction of cyanobacterial bloom and floating leaf vegetation from remote sensing data. The overall distribution of cyanobacterial bloom and floating leaf vegetation in Lake Taihu from 2003 to 2011 is determined by overlapping the distribution maps from individual images, and the results of our analysis are consistent with previously published results. In addition, our analysis shows that this model is immune to perturbations from thin clouds and aerosols.