Self-Organizing Multichannel Deep Learning System for River Turbidity Monitoring

Abstract

This paper focuses on proposing a new framework for self-organizing multi-channel deep learning system (SMDLS) to solve the problem of river turbidity monitoring, which is one of the most critical indicators of water contamination. First, the basic architecture of our proposed SMDLS is established based on newly designed fractal modules, each of which is composed of one fixed block and one nested block. The nested block in the higher-level fractal module is essentially the lower-level fractal module. Second, we develop a novel riverway-like generalized regression loss function to improve the robustness of the proposed SMDLS to distorted labels, which is caused by small noise (e.g., the temperature drift noise and wet drift noise of turbidity sensors) in most cases and big noise (e.g., the outlier noise due to solar radiation shielded by mountains) on rare occasions. Finally, we further introduce an ensemble-induced multi-channel fusion to modify the proposed SMDLS for strengthening its performance and generalization ability. Experiment conducted on large-size river turbidity monitoring database demonstrates that our system considerably outperforms existing state-of-the-art learning systems.