Geo-AI to aid disaster response by memory-augmented deep reservoir computing
Issue title: Selection of papers from the 21st EANN (Engineering Applications of Neural Networks) and 16th AIAI (Artificial Intelligence Applications and Innovations) Joint International Conference
Affiliations: [a] Faculty of Mathematics Programming and General Courses, School of Civil Engineering, Democritus University of Thrace, Kimmeria, Xanthi, Greece | [b] Faculty of Environment and Technology, Department of Computer Science and Creative Technologies, University of the West of England, Bristol, UK
Correspondence:
[*]
Corresponding author: Konstantinos Demertzis, Faculty of Mathematics Programming and General Courses, School of Civil Engineering, Democritus University of Thrace, Kimmeria, Xanthi, Greece. E-mail: [email protected],Website:https://utopia.duth.gr/∼kdemertz.
Abstract: It is a fact that natural disasters often cause severe damage both to ecosystems and humans. Moreover, man-made disasters can have enormous moral and economic consequences for people. A typical example is the large deadly and catastrophic explosion in Beirut on 4 August 2020, which destroyed a very large area of the city. This research paper introduces a Geo-AI disaster response computer vision system, capable to map an area using material from Synthetic Aperture Radar (SAR). SAR is a unique form of radar that can penetrate the clouds and collect data day and night under any weather conditions. Specifically, the Memory-Augmented Deep Convolutional Echo State Network (MA/DCESN) is introduced for the first time in the literature, as an advanced Machine Vision (MAV) architecture. It uses a meta-learning technique, which is based on a memory-augmented approach. The target is the employment of Deep Reservoir Computing (DRC) for domain adaptation. The developed Deep Convolutional Echo State Network (DCESN) combines a classic Convolutional Neural Network (CNN), with a Deep Echo State Network (DESN), and analog neurons with sparse random connections. Its training is performed following the Recursive Least Square (RLS) method. In addition, the integration of external memory allows the storage of useful data from past processes, while facilitating the rapid integration of new information, without the need for retraining. The proposed DCESN implements a set of original modifications regarding training setting, memory retrieval mechanisms, addressing techniques, and ways of assigning attention weights to memory vectors. As it is experimentally shown, the whole approach produces remarkable stability, high generalization efficiency and significant classification accuracy, significantly extending the state-of-the-art Machine Vision methods.
Keywords: Geo-AI, disaster response, domain adaptation, meta-learning, synthetic aperture radar, echo state network, deep reservoir computing, memory-augmented architecture
