Drought is typically induced by the extreme water deficit stress that cascades through the atmosphere, hydrosphere, and biosphere. Cascading drought events could cause severe damage in multiple systems. However, identifying cascading drought connections considering the dynamic space-time progression remains challenging, which hinders further exploring the emergent patterns of drought cascades. This study proposes a novel framework for tracking drought cascades across multiple systems by utilizing dynamic space-time motion similarities. Our investigation focuses on the four primary drought types in Central Asia from 1980 to 2007, namely precipitation (PCP), evapotranspiration (ET), runoff, and root zone soil moisture (SM), representing the four systems of atmosphere, hydrosphere, biosphere, and soil layer respectively. A total of 503 cascading drought events are identified in this study, including the 261 four-system cascading drought events. Our results show a significant prevalence of the four-system cascading drought pattern in Central Asia with high systematic drought risk, mainly when seasonal PCP droughts with high severity/intensity and sizeable spatial extent are observed. As for the temporal order in the cascading drought events, ET droughts are likely to occur earlier than runoff droughts after PCP droughts, and SM droughts are more likely to occur at last, implying the integrated driven effect of the energy-limited and water-limited phases on the drought progression in Central Asia. Our proposed framework could attain precise internal spatial trajectories within each cascading drought event and enable the capture of space-time cascading connections across diverse drought systems and associated hazards. The identification of cascading drought patterns could provide a systematic understanding of the drought evolution across multiple systems under exacerbated global warming.
