Transfer Learning for Assessing Heavy Metal Pollution in Seaports Sediments

2025-06-27

AI Summary

To address data scarcity, inconsistent standards, and labor-intensive procedures in heavy metal pollution assessment of port sediments, this study proposes an end-to-end PLI (Pollution Load Index) prediction method integrating transfer learning with deep neural networks. We innovatively design a cross-domain feature transfer mechanism to effectively mitigate the small-sample challenge in the water–sediment domain, enabling heterogeneous port data fusion and enhancing model generalizability. Evaluated on field-measured data from six major Australian ports, the model achieves MAE ≈ 0.5 and MAPE ≈ 3%, outperforming baseline models by nearly two orders of magnitude in predictive accuracy. The approach substantially reduces reliance on localized sediment sampling and laboratory analysis, offering a transferable, robust technical framework for rapid, cross-national screening and collaborative assessment of port sediment contamination.

Technology Category

• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Data Mining & Knowledge Management: Web
• Natural Language Processing: Language Grounding & Multi-modal NLP

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Detecting heavy metal pollution in soils and seaports is vital for regional environmental monitoring. The Pollution Load Index (PLI), an international standard, is commonly used to assess heavy metal containment. However, the conventional PLI assessment involves laborious procedures and data analysis of sediment samples. To address this challenge, we propose a deep-learning-based model that simplifies the heavy metal assessment process. Our model tackles the issue of data scarcity in the water-sediment domain, which is traditionally plagued by challenges in data collection and varying standards across nations. By leveraging transfer learning, we develop an accurate quantitative assessment method for predicting PLI. Our approach allows the transfer of learned features across domains with different sets of features. We evaluate our model using data from six major ports in New South Wales, Australia: Port Yamba, Port Newcastle, Port Jackson, Port Botany, Port Kembla, and Port Eden. The results demonstrate significantly lower Mean Absolute Error (MAE) and Mean Absolute Percentage Error (MAPE) of approximately 0.5 and 0.03, respectively, compared to other models. Our model performance is up to 2 orders of magnitude than other baseline models. Our proposed model offers an innovative, accessible, and cost-effective approach to predicting water quality, benefiting marine life conservation, aquaculture, and industrial pollution monitoring.

Problem

• Simplifies heavy metal pollution assessment in seaport sediments
• Addresses data scarcity in water-sediment domain via transfer learning
• Improves accuracy in Pollution Load Index (PLI) prediction

Innovation

• Deep-learning model simplifies heavy metal assessment
• Transfer learning enables cross-domain feature transfer
• Achieves low MAE and MAPE in PLI prediction