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.

Air pollution has emerged as a significant health, environmental, economic, and social problem all over the world. In this study, geospatial technologies coupled with a LUR (Land Use Regression) approach were applied to assess the spatial-temporal distribution of fine particulate (PM_2.5). In-situ observations of air pollutants from ground monitoring stations from 2016–2018 were used as dependent variables, while the land-use/land cover, a NDVI (Normalized Difference Vegetation Index) from a MODIS sensors, and meteorology data allocations surrounding the monitoring stations from 0.25–5 km buffer ranges were collected as spatial predictors from GIS and remote sensing databases. A linear regression method was developed for the LUR model and 10-fold cross-validation was used to assess the model robustness. The R² model obtained was 56% for DKI Jakarta, Indonesia, and 83% for Taipei Metropolis, Taiwan. According to the results of the PM_2.5 model, the essential predictors for DKI Jakarta were influenced by temperature, NDVI, humidity, and residential area, while those for the Taipei Metropolis region were influenced by PM₁₀, NO₂, SO₂, UV, rainfall, spring, main road, railroad, airport, proximity to airports, mining areas, and NDVI. The validation of the results of the estimated PM_2.5 distribution use 10-cross validation with indicated R² values of 0.62 for DKI Jakarta and 0.84 for Taipei Metropolis. The results of cross-validation show the strength of the model.

Keywords: Total Suspended Solids, Chlorophyll-A, Landsat-8, Poteran Island Water The Landsat-8 satellite imagery is now highly developed compares to the former of Landsat projects. Both land and water area are possibly mapped using this satellite sensor. Considerable approaches have been made to obtain a more accurate method for extracting the information of water area from the images. It is difficult to generate an accurate water quality information from Landsat images by using some existing algorithm provided by researchers. Even though, those algorithms have been validated in some water area, but the dynamic changes and the specific characteristics of each area make it necessary to get them evaluated and validated over another water area. This paper aims to make a new algorithm by correlating the measured and estimated TSS and Chla concentration. We collected in-situ remote sensing reflectance, TSS and Chl-a concentration in 9 stations surrounding the Poteran islands as well as Landsat 8 data on the same acquisition time of April 22, 2015. The regression model for estimating TSS produced high accuracy with determination coefficient (R²), NMAE and RMSE of 0.709; 9.67 % and 1.705 g/m³ respectively. Whereas, Chla retrieval algorithm produced R² of 0.579; NMAE of 10.40% and RMSE of 51.946 mg/m³. By implementing these algorithms to Landsat 8 image, the estimated water quality parameters over Poteran island water ranged from 9.480 to 15.801 g/m³ and 238.546 to 346.627 mg/m³ for TSS and Chl-a respectively.

Estimation of Total Suspended Sediment and Chlorophyll-A Concentration from Landsat 8-Oli: The Effect of Atmospher and Retrieval Algorithm

Regional water quality mapping is the key practical issue in environmental monitoring. Global regression models transform measured spectral image data to water quality information without the consideration of spatially varying functions. However, it is extremely difficult to find a unified mapping algorithm in multiple reservoirs and lakes. The local model of water quality mapping can estimate water quality parameters effectively in multiple reservoirs using spatial regression. Experiments indicate that both models provide fine water quality mapping in low chlorophyll-a (Chla) concentration water (study area 1; root mean square error, RMSE: 0.435 and 0.413 mg m⁻³ in the best global and local models), whereas the local model provides better goodness-of-fit between the observed and derived Chla concentrations, especially in high-variance Chla concentration water (study area 2; RMSE: 20.75 and 6.49 mg m⁻³ in the best global and local models). In-situ water quality samples are collected and correlated with water surface reflectance derived from Sentinel-2 images. The blue-green band ratio and Maximum Chlorophyll Index (MCI)/Fluorescence Line Height (FLH) are feasible for estimating the Chla concentration in these waterbodies. Considering spatially-varying functions, the local model offers a robust approach for estimating the spatial patterns of Chla concentration in multiple reservoirs. The local model of water quality mapping can greatly improve the estimation accuracy in high-variance Chla concentration waters in multiple reservoirs.