Characterizing Differences Across Time Series Datasets
Characterize the specific differences in characteristics across various time series datasets.
References
We left the specific differences in characteristics across various time series datasets for future work.
One plausible source of the difference is traffic composition: the Danish corpus's ferry-dominated straits carry more strongly time-of-day and day-of-week structured routines than a port and waterway dominated by tug, tow and tanker transits (Section~\ref{sec:data}), so a chronological split has less regular short-term structure to leak across than a vessel-sharing one does on this corpus; we did not test this explanation directly.
Superior wind-regression performance in the AU dataset may reflect differences in data definitions and quality between hemispheres, driven by different operational procedures in regional meteorological agencies . But it is unclear how this affects model performance. This paper does not study the cause of performance gaps between hemispheres, so we leave this problem for future work.