AUTHOR=Hafezi Mohammad Hesam , Daisy Naznin Sultana , Liu Lei 

TITLE=A Cluster-Based Technique for Identifying and Grouping Oily Waste Types Generated From Marine Oil Spill Response Operations

JOURNAL=Frontiers in Environmental Science

VOLUME=Volume 10 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/environmental-science/articles/10.3389/fenvs.2022.910214

DOI=10.3389/fenvs.2022.910214

ISSN=2296-665X

ABSTRACT=In the event of a marine oil spill and its subsequent response operations, different types of oily wastes are generated in large quantities, and their management is a significant challenge oil spill responders face. The goal of this study is to develop a comprehensive pattern recognition modelling framework for deriving and grouping a set of unique clusters that separate different types of oily wastes from each other. The main idea is to group by oily wastes based on their unique characteristics such as percentage of oil, percentage of water, percentage of mineral matter, and percentage of organic matter. Each cluster has a relatively homogeneous pattern of pollution characteristics. Prior to implementing the cluster analysis technique, it is important to evaluate and transform the raw oily waste data using well-defined criteria. An advance machine-learning technique, fuzzy C-means clustering algorithm is employed to classify the oily wastes. The Kolmogorov–Smirnov tests are employed to examine statistical significance of clustered data. Results show a heterogeneous diversity in seven identified clusters in relation to different types of oily wastes. The cluster-based analysis method presented in this paper is an integral part of an integrated optimization-based model which will provide valuable inputs for adjustment of the existing management practices, enhancement of short-term pollution control strategies, and development of long-term oily waste management policies. The output of this study would provide with a better tool to waste characterization and sorting steps that are required to immediately separate recovered waste to support downstream response efforts. This result of this study also supports the overall goal of minimizing impact to the environment by ensuring the maximum amount of recovered waste can be recycled or disposed of in an environmentally friendly fashion. Moreover, properly classified, sorted and labelled waste will greatly help with downstream steps of packaging, transportation and tracking of waste and as a result, it will minimize total waste management time and costs, under the constraints involving waste storage and transport capacities, waste pre-treatment and treatment facility capacities, environmental regulatory compliance, as well as other operational and logistic constraints.