ABSTRACT:The Sea Surface Temperature (SST) retrieval from satellites data Thus, it could provide SST data for a long time. Since, the algorithms of SST estimation by using Landsat 8 Thermal Band are sitedependence, we need to develop an applicable algorithm in Indonesian water. The aim of this research was to develop SST algorithms in the North Java Island Water. The data used are in-situ data measured on April 22, 2015 and also estimated brightness temperature data from Landsat 8 Thermal Band Image (band 10 and band 11). The algorithm was established using 45 data by assessing the relation of measured in-situ data and estimated brightness temperature. Then, the algorithm was validated by using another 40 points. The results showed that the good performance of the sea surface temperature algorithm with coefficient of determination (R 2 ) and Root Mean Square Error (RMSE) of 0.912 and 0.028, respectively.

The retrieval of chlorophyll-a (Chl-a) concentrations relies on empirical or analytical analyses, which generally experience difficulties from the diversity of inland waters in statistical analyses and the complexity of radiative transfer equations in analytical analyses, respectively. Previous studies proposed the utilization of artificial neural networks (ANNs) to alleviate these problems. However, ANNs do not consider the problem of insufficient in situ samples during model training, and they do not fully utilize the spatial and spectral information of remote sensing images in neural networks. In this study, a two-stage training is introduced to address the problem regarding sample insufficiency. The neural network is pretrained using the samples derived from an existing Chl-a concentration model in the first stage, and the pretrained model is refined with in situ samples in the second stage. A novel convolutional neural network for Chl-a concentration retrieval called WaterNet is proposed which utilizes both spectral and spatial information of remote sensing images. In addition, an end-to-end structure that integrates feature extraction, band expansion, and Chl-a estimation into the neural network leads to an efficient and effective Chl-a concentration retrieval. In experiments, Sentinel-3 images with the same acquisition days of in situ measurements over Laguna Lake in the Philippines were used to train and evaluate WaterNet. The quantitative analyses show that the two-stage training is more likely than the one-stage training to reach the global optimum in the optimization, and WaterNet with two-stage training outperforms, in terms of estimation accuracy, related ANN-based and band-combination-based Chl-a concentration models.

No abstract

The spatial heterogeneity and nonlinearity exhibited by bio-optical relationships in turbid inland waters complicate the retrieval of chlorophyll-a (Chl-a) concentration from multispectral satellite images. Most studies achieved satisfactory Chl-a estimation and focused solely on the spectral regions from near-infrared (NIR) to red spectral bands. However, the optical complexity of turbid waters may vary with locations and seasons, which renders the selection of spectral bands challenging. Accordingly, this study proposes an optimization process utilizing available spectral models to achieve optimal Chl-a retrieval. The method begins with the generation of a set of feature candidates, followed by candidate selection and optimization. Each candidate links to a Chl-a estimation model, including two-band, three-band, and normalized different chlorophyll index models. Moreover, a set of selected candidates using available spectral bands implies an optimal composition of estimation models, which results in an optimal Chl-a estimation. Remote sensing images and in situ Chl-a measurements in Lake Kasumigaura, Japan, are analyzed quantitatively and qualitatively to evaluate the proposed method. Results indicate that the model outperforms related Chl-a estimation models. The root-mean-squared errors of the Chl-a concentration obtained by the resulting model (OptiM-3) improve from 11.95 mg · m − 3 to 6.37 mg · m − 3 , and the Pearson’s correlation coefficients between the predicted and in situ Chl- a improve from 0.56 to 0.89.