Massive feature extraction for explaining and foretelling hydroclimatic time series forecastability at the global scale
This work addresses the gap in quantifying forecastability for hydroclimatic data, which is important for climate and water resource management, but it is incremental as it applies existing forecasting methods to new data with systematic feature extraction.
The study tackled the problem of understanding and predicting the forecastability of hydroclimatic time series by investigating relationships between descriptive features and actual forecastability, using over 13,000 monthly temperature, precipitation, and river flow time series to provide global-scale characterizations and interpretations for 12-month ahead forecasts.
Statistical analyses and descriptive characterizations are sometimes assumed to be offering information on time series forecastability. Despite the scientific interest suggested by such assumptions, the relationships between descriptive time series features (e.g., temporal dependence, entropy, seasonality, trend and linearity features) and actual time series forecastability (quantified by issuing and assessing forecasts for the past) are scarcely studied and quantified in the literature. In this work, we aim to fill in this gap by investigating such relationships, and the way that they can be exploited for understanding hydroclimatic forecastability and its patterns. To this end, we follow a systematic framework bringing together a variety of -- mostly new for hydrology -- concepts and methods, including 57 descriptive features and nine seasonal time series forecasting methods (i.e., one simple, five exponential smoothing, two state space and one automated autoregressive fractionally integrated moving average methods). We apply this framework to three global datasets originating from the larger Global Historical Climatology Network (GHCN) and Global Streamflow Indices and Metadata (GSIM) archives. As these datasets comprise over 13 000 monthly temperature, precipitation and river flow time series from several continents and hydroclimatic regimes, they allow us to provide trustable characterizations and interpretations of 12-month ahead hydroclimatic forecastability at the global scale...