Chlorophyll-a (Chl-a) concentration, a crucial indicator of phytoplankton
biomass across inland waters, is sensitive to seasonality. The variations
in trophic states regarding seasonality may cause changes of the spectral
properties of Chl-a, posing uncertainty to the accuracy of remote sensing
semi-empirical models. In particular, lakes in subtropical regions regularly
experience different trophic states in dry and wet seasons. In the first
study, a season-insensitive Chl-a retrieval model using multi-task convolution
neural wetwork with multiple output layers (MCNN) is proposed. A layer-
sharing network combines with data augmentation is adopted to alleviate
the issue of insufficient quantity of in situ samples. In addition, a
hyperparameter optimization method is executed to automatically refine the
MCNN architecture. To evaluate the accuracy of proposed method, Laguna
Lake, one of the largest lakes in Southeast Asia, is selected as the validation
target. The lake is characterized by light oligotrophic and mesotrophic
states in wet season, whereas the states change to mesotrophication and light
eutrophication in dry season. A collection of Sentinel-3 Ocean and Land
Colour Instrument (OLCI) Level-2 images and synchronous in situ Chl-a
measurements in two seasons was used for model calibration and evaluation.
In experiments, the MCNN model outperformed other semi-empirical models
in k-fold cross-validation procedure, in terms of the average coefficient of
determination and root mean square error. The slope of regressed line closes
to 1, which is generated between estimated and in situ Chl-a measurements,
also demonstrate the predictive robustness of the MCNN model to properly
capture seasonal patterns of Chl-a concentrations.

In the second study, I consider to use convolution neural network for
atmospheric correction of Landsat-8 OLI satellite imagery. The retrieval of
water remote-sensing reflectance is a crucial step prior to the estimation of
optically active biogeochemical parameters in inland waters using remote-
sensing technologies with optical satellite imagery. The atmospheric effects
are generally considerable and complex, which make atmospheric corrections
(ACs) difficult to accurately derive the bottom-of-atmosphere reflectance.
The radiative transfer model is considered to be a promising approach
for atmospheric correction. This approach requires inferencing a set of
parameters using complicated models and tables, including the aerosol
model, atmospheric conditions, and sensor geometric information. This
mechanism leads to uncertainty in the removal of atmospheric effects and
sometimes produces negative remote-sensing reflectance. In this study, a
learning-based atmospheric correction model, called ConvNet-AC, based on
convolutional and fully-connected neural networks is proposed to retrieve
remote-sensing reflectance over inland waters in tropical regions for Landsat
8 imagery. Considering the model usability and data simplicity, the inputs
to the model consist of top-of-atmosphere reflectance, sun-sensor geometric
angles, water vapor, and aerosol optical thickness. In ConvNet-AC, the
convolutional subnetwork extracts spectral features of the top-of-atmosphere
reflectance while the fully-connected subnetwork integrates the spectral
features with sun-sensor geometric angles and aerosol optical thickness to
derive the remote-sensing reflectance. To overcome model overfitting and
geographical sensitivity problems caused by insufficient quantity of in-situ
training samples, a large set of satellite-derived remote-sensing reflectance
samples in various trophic states are generated by using an existing AC model.
The satellite-derived samples along with a small set of in-situ spectral samples
are used to optimize thousands of unknown parameters in ConvNet-AC. To
improve the model generalization, the training data imbalance problem is
alleviated by using down-sampling strategy for satellite-derived samples and
splitting strategy for in-situ samples. In addition, sigmoid function is selected
as the activation function in the output layer, which avoids the output of
negative reflectance. In experiments, parts of in-situ reflectance samples
with Landsat 8 OLI images were used to train the model. The trained model
was validated with the remaining in-situ reflectance samples, and the model
was further tested by using data in other lakes for feasible, effective, and
model over-fitting assessments. The ConvNet-AC was compared with related
atmospheric correction models using in-situ measurements, showing that the
ConvNet-AC has better performance than the compared models.

Once the remote sensing reflectance has been produced by the
ConvNet-AC, this product will continue be used as inputs in the development
of ConvNet-CHL model. The ConvNet-CHL is built to estimate the
chlorophyll-a concentration over Lake Ho Tay, Vietnam. The results has
shown that the retrieval accuracy of the ConvNet-CHL is higher than that
of green-to-blue band ratio. The ratio is specific developed for quantifying
chlorophyll-a concentration in Lake Ho Tay.

Bernardo, N., Watanabe, F., Rodrigues, T., & Alcantara, E. (2017). Atmospheric correction issues for retrieving total suspended matter concentrations in inland waters using oli/landsat-8 image. ADVANCES IN SPACE RESEARCH, 59(9), 2335-2348.

Bernstein, L. S., Adler-Golden, S. M., Sundberg, R. L., Levine, R. Y., Perkins, T. C., Berk, A.,... Hoke, M. L. (2005). Validation of the quick atmospheric correction (quac) algorithm for vnir-swir multi-and hyperspectral imagery. In Algorithms and technologies for multispectral, hyperspectral, and ultraspectral imagery xi (Vol. 5806, pp. 668–678).

Blix, K., Li, J., Massicotte, P., & Matsuoka, A. (2019). Developing a new machine-learning algorithm for estimating chlorophyll-a concentration in optically complex waters: A case study for high northern latitude waters by using sentinel 3 olci. Remote Sensing, 11(18), 2076.

Bongco, I. G., Santos-Borja, A. C., & Nauta, T. A. (2003). Application of habitat evaluation procedure for impact assessment studies in laguna de bay, philippines. Hydrobiologia, 506(1-3), 811-817.

Brezonik, P. L., Olmanson, L. G., Finlay, J. C., & Bauer, M. E. (2015). Factors affecting the measurement of cdom by remote sensing of optically complex inland waters. Remote Sensing of Environment, 157, 199–215.

Callieco, F., & Dell Acqua, F. (2011). A comparison between two radiative transfer models for atmospheric correction over a wide range of wavelengths. International journal of remote sensing, 32(5), 1357–1370.

Cao, Z., Ma, R., Duan, H., Pahlevan, N., Melack, J., Shen, M., & Xue, K. (2020). A
machine learning approach to estimate chlorophyll-a from landsat-8 measurements in inland lakes. Remote Sensing of Environment, 248, 111974.

Chavez, P. (1988). An improved dark-object subtraction technique for atmospheric scattering correction of multispectral data. Remote Sensing of Environment, 24(3), 459-479.

Chen, Q., Yu, R., Hao, Y., Wu, L., Zhang, W., Zhang, Q., & Bu, X. (2018). A new method for mapping aquatic vegetation especially underwater vegetation in lake ulansuhai using gf-1 satellite data. Remote Sensing, 10(8), 1279.

Cui, L., Li, G., Ren, H., He, L., Liao, H., Ouyang, N., & Zhang, Y. (2014). Assessment of
atmospheric correction methods for historical landsat tm images in the coastal zone: A case study in jiangsu, china. EUROPEAN JOURNAL OF REMOTE SENSING, 47, 701-716.

Dall＇Olmo, G., & Gitelson, A. A. (2005). Effect of bio-optical parameter variability
on the remote estimation of chlorophyll-a concentration in turbid productive waters: experimental results. Applied optics, 44(3), 412–422.

De Keukelaere, L., Sterckx, S., Adriaensen, S., Knaeps, E., Reusen, I., Giardino, C., ...
others (2018). Atmospheric correction of landsat-8/oli and sentinel-2/msi data using icor algorithm: validation for coastal and inland waters. European Journal of Remote Sensing, 51(1), 525–542.

Diederik, & Ba, J. (2017). Adam: A method for stochastic optimization. arXiv pre-print server.

Ding, H., Shi, J., Wang, Y., & Wei, L. (2015). An improved dark-object subtraction
technique for atmospheric correction of landsat 8. In Mippr 2015: Remote sensing
image processing, geographic information systems, and other applications (Vol. 9815, pp. 128–135).

Duffy, K., Vandal, T., Wang, W., Nemani, R., & Ganguly, A. R. (2019). Deep learning
emulation of multi-angle implementation of atmospheric correction (maiac). arXiv
preprint arXiv:1910.13408.

Fairus, T., Balakrishnan, S., & Ramazan, A. (2022). Improving the saline water evaporation rates using highly conductive carbonaceous materials under infrared light for improved freshwater production. Desalination, 531, 115710.

Fan, Y., Li, W., Chen, N., Ahn, J.-H., Park, Y.-J., Kratzer, S., ... Stamnes, K. (2021).
Oc-smart: A machine learning based data analysis platform for satellite ocean color sensors. Remote Sensing of Environment, 253, 112236.

Fan, Y., Li, W., Gatebe, C. K., Jamet, C., Zibordi, G., Schroeder, T., & Stamnes, K. (2017). Atmospheric correction over coastal waters using multilayer neural networks. Remote Sensing of Environment, 199, 218–240.

Gholizadeh, M. H., Melesse, A. M., & Reddi, L. (2016). A comprehensive review on water quality parameters estimation using remote sensing techniques. Sensors, 16(8)

Gitelson, A. A., Dall’Olmo, G., Moses, W., Rundquist, D. C., Barrow, T., Fisher, T. R., ...
Holz, J. (2008). A simple semi-analytical model for remote estimation of chlorophyll-a in turbid waters: Validation. Remote Sensing of Environment, 112(9), 3582-3593.

Gons, H. J. (1999). Optical teledetection of chlorophyll a in turbid inland waters.
Environmental science & technology, 33(7), 1127–1132.

Gons, H. J., Rijkeboer, M., & Ruddick, K. G. (2002). A chlorophyll-retrieval algorithm
for satellite imagery (medium resolution imaging spectrometer) of inland and coastal waters. Journal of Plankton Research, 24(9), 947–951.

Guanter, L., Alonso, L., & Moreno, J. (2005). First results from the proba/chris
hyperspectral/multiangular satellite system over land and water targets. IEEE
Geoscience and Remote Sensing Letters, 2(3), 250–254

Ha, N. T. T., Koike, K., & Nhuan, M. T. (2013). Improved accuracy of chlorophyll-a
concentration estimates from modis imagery using a two-band ratio algorithm and geostatistics: As applied to the monitoring of eutrophication processes over tien yen bay (northern vietnam). Remote Sensing, 6(1), 421–442.

Ha, N. T. T., Koike, K., Nhuan, M. T., Canh, B. D., Thao, N. T. P., & Parsons, M. (2017).
Landsat 8/oli two bands ratio algorithm for chlorophyll-a concentration mapping in hypertrophic waters: An application to west lake in hanoi (vietnam). IEEE Journal
of Selected Topics in Applied Earth Observations and Remote Sensing, 10(11), 4919-4929

Hafeez, S., Wong, M., Ho, H., Nazeer, M., Nichol, J., Abbas, S., ... Pun, L. (2019).
Comparison of machine learning algorithms for retrieval of water quality indicators
in case-ii waters: A case study of hong kong. Remote Sensing, 11(6), 617.

Hallare, A., Kosmehl, T., Schulze, T., Hollert, H., Kohler, H., & Triebskorn, R. (2005).
Assessing contamination levels of laguna lake sediments (philippines) using a contact assay with zebrafish (danio rerio) embryos. Science of the Total Environment, 347(1-3), 254-271

Han, L., & Rundquist, D. C. (1997). Comparison of nir/red ratio and first derivative of reflectance in estimating algal-chlorophyll concentration: A case study in a turbid
reservoir. Remote sensing of Environment, 62(3), 253–261.

Imran, K., & Minjuan, Z. (2019). Water resource management and public preferences for water ecosystem services: A choice experiment approach for inland river basin management. Science of The Total Environment, 646, 821-831.

Jalbuena, R. L., Blanco, A. C., Manuel, A., Sta. Ana, R. R., & Santos, J. A. (2019). Bio optical modelling of laguna lake using bomber tool and wasi-derived inverted parameters. ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, XLII-4/W16, 277-282.

Jiang, L., Nielsen, K., Andersen, O. B., & B., P. (2017). Cryosat-2 radar altimetry for
monitoring freshwater resources of china. REMOTE SENSING OF ENVIRONMENT,
200, 125-139.

Keith, D., Rover, J., Green, J., Zalewsky, B., Charpentier, M., Thursby, G., & Bishop, J.
(2018). Monitoring algal blooms in drinking water reservoirs using the landsat-8
operational land imager. International journal of remote sensing, 39(9), 2818–2846.

Kim, Y. H., Im, J., Ha, H. K., Choi, J.-K., & Ha, S. (2014). Machine learning approaches
to coastal water quality monitoring using goci satellite data. GIScience & Remote
Sensing, 51(2), 158-174

Knaeps, E., Raymaekers, D., Sterckx, S., & Odermatt, D. (2010). An intercomparison of analytical inversion approaches to retrieve water quality for two distinct inland waters.

Li, H., He, X., Bai, Y., Shanmugam, P., Park, Y.-J., Liu, J., ... Huang, H. (2020). Atmospheric correction of geostationary satellite ocean color data under high solar zenith angles in open oceans. Remote Sensing of Environment, 249, 112022.

Li, L., Jamieson, K., DeSalvo, G., Rostamizadeh, A., & Talwalkar, A. (2017). Hyperband: A novel bandit-based approach to hyperparameter optimization. The Journal of Machine Learning Research, 18(1), 6765-6816.

Lyapustin, A. I., Wang, Y., Laszlo, I., Hilker, T., Hall, F. G., Sellers, P. J., ... Korkin, S. V.
(2012). Multi-angle implementation of atmospheric correction for modis (maiac): 3. atmospheric correction. Remote Sensing of Environment, 127, 385–393.

Manh, N. V., Lin, C. H., Chu, H. J., Lalu, M. J., & Muhammad, A. S. (2020). Spectral
feature selection optimization for water quality estimation. International journal of
environmental research and public health, 17(1), 272.

Manh, N. V., Lin, C. H., Syariz, M. A., Le, T. T. H., & Blanco, A. C. (2021). Multi-task
convolution neural network for season-insensitive chlorophyll-a estimation in inland water. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 14, 10439–10449

Matthews, M. W. (2011). A current review of empirical procedures of remote sensing in inland and near-coastal transitional waters. International Journal of Remote Sensing, 32(21), 6855–6899.

McDougall, C. W., Hanley, N., Quilliam, R. S., Needham, K., & Oliver, D. M. (2020).
Valuing inland blue space: A contingent valuation study of two large freshwater lakes. SCIENCE OF THE TOTAL ENVIRONMENT, 715.

Mishra, S., & Mishra, D. R. (2012). Normalized difference chlorophyll index: A novel
model for remote estimation of chlorophyll-a concentration in turbid productive waters. Remote Sensing of Environment, 117, 394–406.

Morel, A., & Prieur, L. (1977). Analysis of variations in ocean color1. Limnology and Oceanography, 22(4), 709-722

Moses, W. J., Gitelson, A. A., Berdnikov, S., & Povazhnyy, V. (2009). Satellite estimation of chlorophyll-a concentration using the red and nir bands of meris—the azov sea case study. IEEE Geoscience and Remote Sensing Letters, 6(4), 845–849

Mushtaq, F., & Nee L., M. G. (2017). Remote estimation of water quality parameters of himalayan lake (kashmir) using landsat 8 oli imagery. Geocarto international, 32(3), 274–285.

Olmanson, L. G., Brezonik, P. L., Finlay, J. C., & Bauer, M. E. (2016). Comparison of
landsat 8 and landsat 7 for regional measurements of cdom and water clarity in lakes. Remote Sensing of Environment, 185, 119–128.

Pahlevan, N., Smith, B., Schalles, J., Binding, C., Cao, Z., Ma, R., ... Stumpf, R.
(2020). Seamless retrievals of chlorophyll-a from sentinel-2 (msi) and sentinel-3
(olci) in inland and coastal waters: A machine-learning approach. Remote Sensing
of Environment, 240, 111604.

Pallottini, M., Goretti, E., Gaino, E., Selvaggi, R., Cappelletti, D., & Céréghino, R. (2015). Invertebrate diversity in relation to chemical pollution in an umbrian stream system (italy). Comptes Rendus Biologies, 338(7), 511–520

Pyo, J., Duan, H., Baek, S., Kim, M. S., Jeon, T., Kwon, Y. S., ... Cho, K. H.
(2019). A convolutional neural network regression for quantifying cyanobacteria using hyperspectral imagery. Remote Sensing of Environment, 233, 111350.

Randolph, K., Wilson, J., Tedesco, L., Li, L., Pascual, D. L., & Soyeux, E. (2008).
Hyperspectral remote sensing of cyanobacteria in turbid productive water using
optically active pigments, chlorophyll a and phycocyanin. Remote Sensing of
Environment, 112(11), 4009-4019.

Reif, M. K. (2011). Remote sensing for inland water quality monitoring: A us army corps of engineers perspective.

Renosh, P. R., Doxaran, D., Keukelaere, L. D., & Gossn, J. I. (2020). Evaluation of
atmospheric correction algorithms for sentinel-2-msi and sentinel-3-olci in highly
turbid estuarine waters. Remote Sensing, 12(8), 1285.

Santos-Borja, A. C. (1994). The control of saltwater intrusion into laguna de bay:
Socioeconomic and ecological significance. Lake and Reservoir Management, 10(2), 213-219.

Schindler, D. W. (2006). Recent advances in the understanding and management of
eutrophication. Limnology and Oceanography, 51, 356-363

Schroeder, T., Behnert, I., Schaale, M., Fischer, J., & Doerffer, R. (2007). Atmospheric
correction algorithm for meris above case-2 waters. International Journal of Remote Sensing, 28(7), 1469–1486.

Schroeder, T., Fischer, J., Schaale, M., & Fell, F. (2003). Artificial-neural-network-based atmospheric correction algorithm: application to meris data. In Ocean remote sensing and applications (Vol. 4892, pp. 124–132).

Spyrakos, E., O’donnell, R., Hunter, P. D., Miller, C., Scott, M., Simis, S. G., ... others
(2018). Optical types of inland and coastal waters. Limnology and Oceanography,
63(2), 846–870.

Sterckx, S., Knaeps, S., Kratzer, S., & Ruddick, K. (2015). Similarity environment correction (simec) applied to meris data over inland and coastal waters. Remote Sensing of Environment, 157, 96–110

Su, H., Lu, X., Chen, Z., Zhang, H., Lu, W., & Wu, W. (2021). Estimating coastal chlorophyll-a concentration from time-series olci data based on machine learning. Remote Sensing, 13(4), 576.

Syariz, M. A., Lin, C.-H., Nguyen, M. V., Jaelani, L. M., & Blanco, A. C. (2020). Waternet: A convolutional neural network for chlorophyll-a concentration retrieval. Remote Sensing, 12(12), 1966

Themistocleous, K., Hadjimitsis, D. G., Retalis, A., & Chrysoulakis, N. (2012). Development of a new image based atmospheric correction algorithm for aerosol optical thickness retrieval using the darkest pixel method. Journal of Applied Remote Sensing, 6(1), 063538.

Trinh, C. (2019). Hanoi strives to preserve its lakes. https://hanoitimes.vn/hanoi-makes-efforts-in-preserving-its-lakes-300584.html/. (Accessed: 2022-11-30)

Vietnamnet, V. (2022). Hanoi tries to improve West Lake water to save
fish. https://vietnamnet.vn/en/hanoi-tries-to-improve-west-lake-water-to-save-fish-2083205.html. (Accessed: 2022-12-09)

Vilas, L. G., Spyrakos, E., & Palenzuela, J. M. T. (2011). Neural network estimation of
chlorophyll a from meris full resolution data for the coastal waters of galician rias (nwspain). Remote Sensing of Environment, 115(2), 524-535.

VNA, V. (2010). Hanoi lakes reflect the city unique beauty. https://en.vietnamplus.vn/hanois-lakes-reflect-the-citys-unique-beauty/21052.vnp/. (Accessed: 2022-12-09)

Warren, M. A., Simis, S. G., Martinez-Vicente, V., Poser, K., Bresciani, M., Alikas, K., ...
Ansper, A. (2019). Assessment of atmospheric correction algorithms for the sentinel-2a multispectral imager over coastal and inland waters. Remote sensing of environment,225, 267–289

Xuan, T. (2018). Numerous dead fish float in Hanoi＇s largest lake. https://tuoitrenews.vn/
news/society/20180709/numerous-dead-fish-float-in-hanois-largest-lake/46613.html. (Accessed: 2022-12-09)

Yang, H., Kong, J., Hu, H., Du, Y., Gao, M., & Chen, F. (2022). A review of remote sensing for water quality retrieval: Progress and challenges. REMOTE SENSING, 14(8).

Zhang, T., Huang, M., & Wang, Z. (2020). Estimation of chlorophyll-a concentration of lakes based on svm algorithm and landsat 8 oli images. Environmental Science and Pollution Research, 27(13), 14977–14990.

Zhang, Z., He, G., & Wang, X. (2010). A practical dos model-based atmospheric correction algorithm. INTERNATIONAL JOURNAL OF REMOTE SENSING, 31(11), 2837-2852

Zheng, G., & Digiacomo, P. M. (2017). Remote sensing of chlorophyll-a in coastal
waters based on the light absorption coefficient of phytoplankton. Remote Sensing of Environment, 201, 331-341.