PhD Projects

Multi-source multimodal deep learning to improve situation awareness:

An application of emergency traffic management

​

Nilani's PhD research project focuses on using deep learning to fuse multiple modalities of data, including text, visual and audio, in real-time to provide structured information for disaster response. The research aims to improve situation awareness for emergency responders by leveraging the increasing amount of data generated by people during disasters, including data sharing through social media applications. The project is implementing a multimodal deep learning framework in the specific application area of Emergency Traffic Management, using traffic-related CCTV footage obtained through a data sharing agreement with Christchurch City Council.

​

Papers and presentations

• DEES: a real-time system for event extraction from disaster-related web text

• Multi-source Multimodal Data and Deep Learning for Disaster Response: A Systematic Review

• Towards Real-time Traffic Flow Estimation using YOLO and SORT from Surveillance Video Footage

• Identifying Disaster-related Tweets: A Large-Scale Detection Model Comparison

• Traffic Flow Estimation based on Deep Learning for Emergency Traffic Management using CCTV Images

An eco-system of low-cost ground motion sensors toward Earthquake Early Warning System using P-waves

​

This PhD research project addresses knowledge gaps in earthquake early warning systems (EEWS), particularly in implementing decentralised processing, ground motion-based algorithms, and using different types of low-cost micro-electro-mechanical systems (MEMS)-based sensors. The project aims to develop a P-wave-based decentralised low-cost EEWS using a ground motion-based algorithm and an EEWS that can work with different types of MEMS-based sensors. The research will be conducted in New Zealand, where there is a lack of a nationwide EEWS.

​

Papers and presentations

• Earthquake early warning systems based on low-cost ground motion sensors: A systematic literature review 

• Algorithms for detecting P-waves and earthquake magnitude estimation: Initial literature review findings

Using citizen science data as an approach to make low-cost and safe monitoring programmes in landslide zones: Cape Kidnappers and Taranaki North Cliffs case studies

 

This PhD research project explores the potential of citizen science data to enhance traditional landslide monitoring techniques that can be costly and pose safety risks to personnel. By studying alternative data sources, the project will develop a framework to integrate citizen science initiatives for effective landslide monitoring. The study will focus on two case sites with active rockfall hazards, Cape Kidnappers and Taranaki North, to reduce risks and improve safety for the community and

​

Reducing false alerts - Dynamic range estimation using machine learning techniques for earthquake early warning

​

The proposed study aims to reduce false alerts of earthquake early warning (EEW) by developing a machine learning-based method that dynamically adjusts the alerting area based on predicted ground shaking intensity. The study will collect earthquake data, explore different ML techniques and Ground Motion Prediction Equations (GMPEs), and model an EEW system. By incorporating historical seismic data and ML, the study aims to improve real-time predictions and increase the robustness of future EEW systems. The proposed system offers benefits such as decreased warning time and adaptability to different ground conditions.

​