Search

Liu, C.; Qian, B.; Wang, L., and Miao, Q., 2019. Application of GIS and remote sensing in spatial distribution of nitrogen and phosphorus pollutant in urban rivers: A case study of Linyi Economic Development Zone, China. In: Guido-Aldana, P.A. and Mulahasan, S. (eds.), Advances in Water Resources and Exploration. Journal of Coastal Research, Special Issue No. 93, pp. 250–256. Coconut Creek (Florida), ISSN 0749-0208. The objectives of this paper were to develop, evaluate and apply the remote sensing based on models of ammonia nitrogen (NH3-N) and total phosphorus (TP) for the Yi and Shu River in Linyi Economic Development Zone, Shandong Province, China. The scenes of Landsat-8 OLI satellite data were used to establish the relationship between the planetary reflectance and the measured data for five years (i.e., 2014-2017). The five spectral bands (i.e., Coastal, Blue, Green, Red, NIR) were used to obtain the most suitable modeling factor from the different band combinations. The liner regression analysis showed that red band both had highest correlation with NH3-N and TP in Yi and Shu River. For the Yi River, the co-efficient of determination (R2) of red band was 0.541 for the NH3-N model and 0.498 for the TP model. For the Shu River, the co-efficient of determination (R2) of red band was 0.643 for the NH3-N model and 0.565 for the TP model. The best-fit Models were validated with measured data and found that the errors of the NH3-N and TP models of the Yi River were 34.93% and 29.33%, respectively, and while 33.66% and 32.48% for the Shu River. With the models, the distribution diagrams of NH3-N and TP were generated, which can be assisted analysis of spatial and temporal for Yi and Shu River. The results showed that the established models could indicate the trend of NH3-N and TP in rivers that was validated by field visit. The proposed approach in this paper has satisfactory validity and practicability, thus could be reference for study on NH3-N and TP in water based on remote sensing. [ABSTRACT FROM AUTHOR]

The objectives of this paper were to develop, evaluate and apply the remote sensing based on models of ammonia nitrogen (NH3-N) and total phosphorus (TP) for the Yi and Shu River in Linyi Economic Development Zone, Shandong Province, China. The scenes of Landsat-8 OLI satellite data were used to establish the relationship between the planetary reflectance and the measured data for five years (i.e., 2014-2017). The five spectral bands (i.e., Coastal, Blue, Green, Red, NIR) were used to obtain the most suitable modeling factor from the different band combinations. The liner regression analysis showed that red band both had highest correlation with NH3-N and TP in Yi and Shu River. For the Yi River, the co-efficient of determination (R2) of red band was 0.541 for the NH3-N model and 0.498 for the TP model. For the Shu River, the co-efficient of determination (R2) of red band was 0.643 for the NH3-N model and 0.565 for the TP model. The best-fit Models were validated with measured data and found that the errors of the NH3-N and TP models of the Yi River were 34.93% and 29.33%, respectively, and while 33.66% and 32.48% for the Shu River. With the models, the distribution diagrams of NH3-N and TP were generated, which can be assisted analysis of spatial and temporal for Yi and Shu River. The results showed that the established models could indicate the trend of NH3-N and TP in rivers that was validated by field visit. The proposed approach in this paper has satisfactory validity and practicability, thus could be reference for study on NH3-N and TP in water based on remote sensing. [ABSTRACT FROM AUTHOR]

Liu, C.; Qian, B.; Wang, L., and Miao, Q., 2019. Application of GIS and remote sensing in spatial distribution of nitrogen and phosphorus pollutant in urban rivers: A case study of Linyi Economic Development Zone, China. In: Guido-Aldana, P.A. and Mulahasan, S. (eds.), Advances in Water Resources and Exploration. Journal of Coastal Research, Special Issue No. 93, pp. 250–256. Coconut Creek (Florida), ISSN 0749-0208. The objectives of this paper were to develop, evaluate and apply the remote sensing based on models of ammonia nitrogen (NH3-N) and total phosphorus (TP) for the Yi and Shu River in Linyi Economic Development Zone, Shandong Province, China. The scenes of Landsat-8 OLI satellite data were used to establish the relationship between the planetary reflectance and the measured data for five years (i.e., 2014-2017). The five spectral bands (i.e., Coastal, Blue, Green, Red, NIR) were used to obtain the most suitable modeling factor from the different band combinations. The liner regression analysis showed that red band both had highest correlation with NH3-N and TP in Yi and Shu River. For the Yi River, the co-efficient of determination (R2) of red band was 0.541 for the NH3-N model and 0.498 for the TP model. For the Shu River, the co-efficient of determination (R2) of red band was 0.643 for the NH3-N model and 0.565 for the TP model. The best-fit Models were validated with measured data and found that the errors of the NH3-N and TP models of the Yi River were 34.93% and 29.33%, respectively, and while 33.66% and 32.48% for the Shu River. With the models, the distribution diagrams of NH3-N and TP were generated, which can be assisted analysis of spatial and temporal for Yi and Shu River. The results showed that the established models could indicate the trend of NH3-N and TP in rivers that was validated by field visit. The proposed approach in this paper has satisfactory validity and practicability, thus could be reference for study on NH3-N and TP in water based on remote sensing. [ABSTRACT FROM AUTHOR]

Yue, Y.L.; Qing, S.; Diao, R.X., and Hao, Y.L., 2020. Remote sensing of suspended particulate matter in optically complex estuarine and inland waters based on optical classification. In: Jung, H.-S.; Lee, S.; Ryu, J.-H., and Cui, T. (eds.), Advances in Geospatial Research of Coastal Environments. Journal of Coastal Research, Special Issue No. 102, pp. 303-317. Coconut Creek (Florida), ISSN 0749-0208. Accurate suspended particulate matter (SPM) concentration retrieval across complex estuarine to inland waters from ocean color remote sensing reflectance (Rrs(λ)) faces challenges. In this paper, an optical classification-based SPM retrieval algorithm in optically complex estuarine and inland waters was proposed and tested in the Yellow River Estuary and Daihai Lake, China. Firstly, the in situ measured Rrs(λ) (n = 204) were classified into two optical water types with the method defined by Matsushita et al. (2015). Secondly, we designed several mathematical models and selected the optimal algorithm according to the goodness of fit. Optimal algorithms were developed for each water type to achieve accurate SPM retrieval. Through the construction of the optimal retrieval algorithm in each water type, the uncertainty of SPM retrievals has been reduced from 95 % to about 39 % compared with the algorithm without optical classification. The retrieval algorithm based on optical water classification was further applied to the Sentinel-2 MSI L2A data over the study area and produced reliable SPM maps. Independent validation with the in situ-satellite match-ups further demonstrates the algorithm's validity (uncertainty of about 47 %). In contrast, applications of other SPM retrieval algorithms resulted in less reliable SPM results with either unsatisfactory retrieval accuracy in class1 (the lowest value of r can reach 0.02). The optical classification, together with the optimal retrieval algorithm for each optical type, is proved to be a feasible way for SPM retrieval in high accuracy over optically complex waters. [ABSTRACT FROM AUTHOR]

Wan, J.X. and Ma, Y., 2020. Multi-scale spectral-spatial remote sensing classification of coral reef habitats using CNN-SVM. In: Jung, H.-S.; Lee, S.; Ryu, J.-H., and Cui, T. (eds.), Advances in Geospatial Research of Coastal Environments. Journal of Coastal Research, Special Issue No. 102, pp. 11-20. Coconut Creek (Florida), ISSN 0749-0208. In recent years, coral reefs have undergone serious degradation globally, prompting the use of remote sensing as an effective means to monitor these reefs on a large scale. Deep learning, which is a state-of-the-art image processing technique suitable for remote-sensing applications, can be used to learn nonlinear characteristics of images and is therefore applicable to the classification of small-scale coral reefs. This paper proposes a multi-scale method based on a convolutional neural network and support vector machine (CNN-SVM) to classify the coral reef habitats of Zhaoshu Island and Zhong Island in the Xisha Archipelago, China. This method combines spectrum, texture, and bidimensional empirical mode decomposition (BEMD) based scale separation algorithm to fully learn multi-scale information of coral reefs. Remote-sensing images captured by the WorldView-2 and Gaofen-2 (GF-2) satellites are used to evaluate the performance of the proposed CNN-SVM framework. The results indicate that the proposed method performs accurately and efficiently. Compared with SVM, random forest (RF), CNN, and CNN-RF, the overall accuracy is improved by 10.57 %, and the accuracy of classifying reef-clumping areas is improved by 17.44 %. [ABSTRACT FROM AUTHOR]