Scenario-Based Marine Oil Spill Emergency Response Using Hybrid Deep Reinforcement Learning and Case-Based Reasoning

Kui Huang,Wen Nie,Nianxue Luo

doi:10.3390/app10155269

Abstract

Case-based reasoning (CBR) systems often provide a basis for decision makers to make management decisions in disaster prevention and emergency response. For decades, many CBR systems have been implemented by using expert knowledge schemes to build indexes for case identification from a case library of situations and to explore the relations among cases. However, a knowledge elicitation bottleneck occurs for many knowledge-based CBR applications because expert reasoning is difficult to precisely explain. To solve these problems, this paper proposes a method using only knowledge to recognize marine oil spill cases. The proposed method combines deep reinforcement learning (DRL) with strategy selection to determine emergency responses for marine oil spill accidents by quantification of the marine oil spill scenario as the reward for the DRL agent. These accidents are described by scenarios and are considered the state inputs in the hybrid DRL/CBR framework. The challenges and opportunities of the proposed method are discussed considering different scenarios and the intentions of decision makers. This approach may be helpful in terms of developing hybrid DRL/CBR-based tools for marine oil spill emergency response.

Highlights

Oil spills have become one of the most severe marine ecological disasters worldwide
The challenges and opportunities of the proposed method are discussed considering different scenarios and the intentions of decision makers. This approach may be helpful in terms of developing hybrid deep reinforcement learning (DRL)/Case-based reasoning (CBR)-based tools for marine oil spill emergency response
We consider marine oil spill emergency response tasks in maker addresses marine oil spill accidents and makes decisions based on comparisons with historical which a decision maker addresses marine oil spill accidents and makes decisions based on data by using similarity measurements to identify a relevant past case

Summary

Introduction

Oil spills have become one of the most severe marine ecological disasters worldwide. With oil imports exceeding 420 million tons in 2017, China surpassed the United States as the world’s largest oil importer for the first time. Direct and effective methods can be used to quickly retrieve similar historical cases by using certain intelligent methods and assisting decision makers in quickly formulating emergency response plans to cope with the current emergency based on historical experience. Case-based reasoning (CBR) systems compare a new problem to a library of cases and adapt a similar library case to the problem, thereby producing a preliminary solution [1]. Since CBR systems require only a library of cases with successful solutions, such systems are often used in areas lacking a strong theoretical domain model, such as diagnosis, classification, prediction, control and action planning. CBR has been applied to help improve cost-efficiency control during infrastructure asset management in developing countries by estimating costs through retrieving and comparing the most similar instances across a case library [2]. Farmers have been provided with advice about farming operation management at a high case retrieval speed based on the associated representation method [3]

Methods

Results

Discussion

Conclusion