Investigating Temporal Convolutional Neural Networks for Satellite Image Time Series Classification: A survey
This work addresses the need for efficient and accurate land cover mapping from satellite data, which is crucial for applications like ecosystem monitoring, but it is incremental as it surveys and validates existing TCN methods rather than introducing new ones.
This survey investigates Temporal Convolutional Neural Networks (TCNs) for classifying Satellite Image Time Series (SITS) to produce accurate land cover maps, finding that TCNs outperform other benchmark methods with accuracies of 95.0% and 87.3% on two datasets.
Satellite Image Time Series (SITS) of the Earth's surface provide detailed land cover maps, with their quality in the spatial and temporal dimensions consistently improving. These image time series are integral for developing systems that aim to produce accurate, up-to-date land cover maps of the Earth's surface. Applications are wide-ranging, with notable examples including ecosystem mapping, vegetation process monitoring and anthropogenic land-use change tracking. Recently proposed methods for SITS classification have demonstrated respectable merit, but these methods tend to lack native mechanisms that exploit the temporal dimension of the data; commonly resulting in extensive data pre-processing contributing to prohibitively long training times. To overcome these shortcomings, Temporal CNNs have recently been employed for SITS classification tasks with encouraging results. This paper seeks to survey this method against a plethora of other contemporary methods for SITS classification to validate the existing findings in recent literature. Comprehensive experiments are carried out on two benchmark SITS datasets with the results demonstrating that Temporal CNNs display a superior performance to the comparative benchmark algorithms across both studied datasets, achieving accuracies of 95.0\% and 87.3\% respectively. Investigations into the Temporal CNN architecture also highlighted the non-trivial task of optimising the model for a new dataset.