Coastal dissolved oxygen (DO) concentrations have a profound impact on nearshore ecosystems and, in recent years, there has been an increased prevalance of low DO hypoxic events that negatively impact nearshore organisms. Even with advanced numerical models, accurate prediction of coastal DO variability is challenging and computationally expensive. Here, we apply machine learning techniques in order to reconstruct and predict nearshore DO concentrations in a small coastal embayment while using a comprehensive set of nearshore and offshore measurements and easily measured input (training) parameters. We show that both random forest regression (RFR) and support vector regression (SVR) models accurately reproduce both the offshore DO and nearshore DO with extremely high accuracy. In general, RFR consistently peformed slightly better than SVR, the latter of which was more difficult to tune and took longer to train. Although each of the nearshore datasets were able to accurately predict DO values using training data from the same site, the model only had moderate success when using training data from one site to predict DO at another site, which was likely due to the the complexities in the underlying dynamics across the sites. We also show that high accuracy can be achieved with relatively little training data, highlighting a potential application for correcting time series with missing DO data due to quality control or sensor issues. This work establishes the ability of machine learning models to accurately reproduce DO concentrations in both offshore and nearshore coastal waters, with important implications for the ability to detect and indirectly measure coastal hypoxic events in near real-time. Future work should explore the ability of machine learning models in order to accurately forecast hypoxic events.
1 January 2015 in Journal of Computational and Applied Mathematics
Glaucoma is one of the leading causes of irreversible blindness in people over 40 years old. Previously, it was developed acomputational tool for automatic glaucoma detection, which implements anovel method that has shown improvement in the accuracy of the detection compared to other classical methods. However, this method is sensitive to the quality of the acquired image. For this reason, automatic image restoration of the source images is needed to improve the quality of glaucoma suspect detection. We propose to use the Perona–Malik anisotropic diffusion filter as part of the pre-processing step because apart from attenuating noise and brilliance in the images, it preserves essential information such as the borders of the optic disc and the cup boundaries, which are of particular interest in this work. We solve numerically the problem in partial differential equations, which represent the Perona–Malik diffusion filter, using explicit finite mimetic differences methods, which have the advantage of preserving the continuum properties of the mathematical operators often encountered in image processing and analysis equations, ensuring better orders of convergence. By guaranteeing these mathematical properties, the original structure of the source image is maintained, improving the diagnosis of the patient.