Assessing Detectability of Global Flood Occurrences using Daily and Monthly GRACE/GRACE-FO

 

Floods pose a threat to the lives of millions of people globally each year, with economic losses exceeding those of any other natural hazard. Improving flood forecasting with longer lead times can support enhanced risk management strategies and reduce associated socioeconomic losses. The objective of this study was to assess the detectability of floods using newly developed GRACE daily and regular monthly total water storage data. 

We compared total water storage (TWS) maxima from GRACE and GRACE-FO with flood occurrences from 2002 to 2020. GRACE daily TWS maxima were based on three daily GRACE solutions (UTCSR-RSWM, GFZ-RBF, and ITSG-2018) derived using statistical learning and geophysical models for the GRACE period (2002-2017). Monthly GRACE and GRACE-FO data were based on mascons solutions from UT-CSR and NASA-JPL for 2002-2020. A flood susceptibility index was developed based on the climate signal portion in the TWSA and compared with other flood indices (e.g., standardized precipitation index and streamflow). We evaluated the spatiotemporal coincidence rate of change of the 90th percentile of the daily and monthly precipitation based on the GPM-Imerg and GPCP rainfall data and the corresponding 90th percentile of the daily and monthly TWSA. The coincidence rate between GRACE TWSA maxima and precipitation were also compared relative to actual flood data (~3000 events) from the Dartmouth flood Observatory (DFO) catalog. 

Preliminary results using precipitation data from GPCP reveal that monthly GRACE/GRACE-FO data have a high predication rate for the monthly maxima precipitation > 90th percentile with a lead time of ~ two months across the tropical rain belt. Assessment against the real flood events shows that the three daily GRACE data perform well for flood events resulting from heavy and monsoonal rain and slightly differ for the events triggered by snowmelt and storm surges. The duration of flood events from GRACE data is generally shorter than the periods reported by DFO. An empirical relationship was derived between floods' duration based on the cause and the expected precursor coincidence rate from daily GRACE data. Further analysis is necessary to evaluate the GRACE precursor rate using different lead times and tolerance windows, quantify the change in rate relative to climate, topography, and soil types, and interpret the different performance GRACE products. This preliminary analysis suggests the high potential for GRACE/GRACE-FO data to extend flood forecast lead times and potentially improve the mitigation strategies