Deep Learning for High-Quality Spatiotemporal Data Prediction

PhD Thesis Proposal Defence


Title: "Deep Learning for High-Quality Spatiotemporal Data Prediction"

by

Mr. Jiachuan WANG


Abstract:

Spatiotemporal data prediction has garnered significant attention for many
years. In recent years, deep learning methods have emerged as effective models
for spatiotemporal data, surpassing traditional methods in tasks such as data
enhancement and prediction. While considerable effort has been dedicated to
developing deep learning methods for spatiotemporal data mining, its popularity
has soared due to the increasing need for high accuracy in managing vast
amounts of data in the big data era. Besides, complex application scenarios
call for robust method designs that balance professionalism and versatility.

This thesis aims to propose a pipeline for high-quality spatiotemporal data
prediction. The pipeline includes data enhancement as preprocessing and the
design of effective tools for data modeling and prediction. In the first
problem, our aim is to denoise noisy input frames such as radar images in
situations where clean reference samples are not available, which is a common
issue in spatiotemporal data collection. Constructing it as an image denoising
problem, we use a self-supervised deep learning method that optimizes models
based solely on noisy images. The performance of this method heavily depends on
the scale of the noise, which is often unknown. To address this issue, we
closely estimate an upper bound for the noise scale without relying on clean
images. Additionally, we design a framework for iterative model updates and
scale estimation. For the second problem, we introduce meta operators to
capture complex and abstract high-order dynamics. This is particularly
important for spatiotemporal data, such as rainfall systems, compared to simple
image processing. Existing methods utilize activation functions to model
non-linearity, but these functions have bounded first-order derivatives. Taking
inspiration from classical dynamic system simulation, we apply polynomial
activation functions as a powerful tool for modeling high-order non-linearity.
To further improve training robustness, we propose a Range Norm and apply it
before the activation functions. Finally, extensive experiments on real and
synthetic datasets demonstrate that our proposed solutions outperform the
state-of-the-art algorithms.


Date:                   Monday, 6 November 2023

Time:                   4:00pm - 6:00pm

Venue:                  Room 3598
                        lifts 27/28

Committee Members:      Prof. Lei Chen (Supervisor)
                        Prof. Bo Li (Chairperson)
                        Dr. Dan Xu
                        Prof. Xiaofang Zhou


**** ALL are Welcome ****