Increasing global plastic usage has raised critical concerns regarding marine pollution. This study addresses the pressing issue of floating marine macro-litter (FMML) by developing a novel monitoring system using a multi-spectral sensor and drones along the southern coast of South Korea. Subsequently, a convolutional neural network (CNN) model was utilized to classify four distinct marine litter materials: film, fiber, fragment, and foam. Automatic atmospheric correction with the drone data atmospheric correction (DROACOR) method, which is specifically designed for currently available drone-based sensors, ensured consistent reflectance across altitudes in the FMML dataset. The CNN models exhibited promising performance, with precision, recall, and F1 score values of 0.9, 0.88, and 0.89, respectively. Furthermore, gradient-weighted class activation mapping (Grad-CAM), an object recognition technique, allowed us to interpret the classification performance. Overall, this study will shed light on successful FMML identification using multi-spectral observations for broader applications in diverse marine environments.

The consecutive submesoscale sea surface processes observed by an unmanned aerial vehicle (UAV) were used to decompose into spatial waves and current features. For the image decomposition, the Fast and Adaptive Multidimensional Empirical Mode Decomposition (FA-MEMD) method was employed to disintegrate multicomponent signals identified in sea surface optical images into modulated signals characterized by their amplitudes and frequencies. These signals, referred to as Bidimensional Intrinsic Mode Functions (BIMFs), represent the inherent two-dimensional oscillatory patterns within sea surface optical data. The BIMFs, separated into seven modes and a residual component, were subsequently reconstructed based on the physical frequencies. A two-dimensional Fast Fourier Transform (2D FFT) for each high-frequency mode was used for surface wave analysis to illustrate the wave characteristics. Wavenumbers (K_x, K_y) ranging between 0.01–0.1 radm⁻¹ and wave directions predominantly in the northeastward direction were identified from the spectral peak ranges. The Optical Flow (OF) algorithm was applied to the remaining consecutive low-frequency modes as the current signal under 0.1 Hz for surface current analysis and to estimate a current field with a 1 m spatial resolution. The accuracy of currents in the overall region was validated with in situ drifter measurements, showing an R-squared (R²) value of 0.80 and an average root-mean-square error (RMSE) of 0.03 ms⁻¹. This study proposes a novel framework for analyzing individual sea surface dynamical processes acquired from high-resolution UAV imagery using a multidimensional signal decomposition method specialized in nonlinear and nonstationary data analysis.

Marine environmental issues due to marine debris are worldwide phenomena. According to a press release from the Ministry of Oceans and Fisheries of Korea, marine waste collection from the coastal area increased yearly. In 2020, it collected 1.38 million tons, about 45% more than in 2018. To remove them, they were collected and monitored through field monitoring systems. However, it is very inefficient in terms of time and cost. Therefore, the remote sensing approach can be suited for classifying and investigating marine waste dumped in coastal areas. Previous studies have classified marine waste by combining remote sensing based on RGB images and artificial intelligence. However, actual marine waste is often damaged, or its shape is difficult to recognize through RGB images. This study was conducted to classify various wastes using multi-spectral camera and a convolution neural network (CNN) model. We first trained and tested CNN model using three wastes, such as a brown paper box, an orange-colored buoy, and a blue plastic basket with different spectral characteristics in the land environment. Then, we conducted the classification of marine waste using CNN model and multi-spectral images taken with Uncrewed Aerial Systems (UAS) in the marine environment around Socheongcho-Ocean Research Station (S-ORS). The CNN model were trained using 1,452 seawater and 1,319 clear plastic images around the S-ORS with 128 x 128-pixel size. We calculated precision, recall, f1-score, and accuracy, suggesting that the CNN model could be used to classify various marine wastes in the various ocean environment. Overall, these results can provide useful information for marine waste monitoring.