Flash Floods Prediction Using Precipitable Water Vapor Derived From GPS Tropospheric Path Delays Over the Eastern Mediterranean

Abstract

A flash flood is a rapid and intense response of a drainage area to heavy rainfall events. In the arid and semi arid parts of the Eastern Mediterranean (EM) region, the spatiotemporal distribution of rainfall is the most important factor for flash flood generation. A possible precursor to heavy rainfall events is the rise in tropospheric water vapor amount, which can be remotely sensed using ground based Global Navigation Satellite Systems (GNSS) stations. Here, we use the Precipitable Water Vapor (PWV) derived from 9 GNSS ground based stations in the arid part of the EM region in order to predict flash floods. Our approach includes using three types of Machine Learning (ML) models in a binary classification task which predicts whether a flash flood will occur given 24 hours of PWV data. We train our models with 107 unique flash flood events and vigorously test them using a nested cross validation technique. The results indicate a good agreement between all three types of models and across various score metrics. In addition, the models are further improved by adding more features such as surface pressure measurements. Finally, a feature importance analysis shows that the most important features are the PWV values from 2 to 6 hours prior a flash flood. These promising results indicate that it is possible to augment the current flash flood warning systems with a near real-time GNSS ground based data driven approach as demonstrated in this work.

Estimating daily potential evapotranspiration using GNSS-based precipitable water vapor

“…The study on agricultural drought indices can be performed based on the proposed model for improving the accuracy and spatial-temporal resolutions of drought monitoring. Furthermore, more datasets of GNSS-PWV and meteorological data are required to develop near real-time applications for flood and drought monitoring [ 53 , 84 ]. Therefore, the developed model is a potential alternative approach to estimate the daily PET and beneficial to climate and agricultural research works for alleviating the adverse impacts by global warming and extreme weather events.…”

“…In addition, it is an alternative technology that is efficiently utilized to obtain water vapor with continuous data and high temporal resolutions in all-weather. Furthermore, it has been applied in various research works such as hydrological application [ 48 ], forecasting precipitation [ [49] , [50] , [51] ], monitoring and estimating snow evaporation [ 52 ], predicting flash floods [ 53 ], assessing the PET [ 54 , 55 ] and evaluating the drought index [ 56 ]. In Thailand, the previous studies found the study of spatial and temporal variability and the validation of PWV value from GNSS observations [ [57] , [58] , [59] ].…”

Investigating the ERA5-Based PWV Products and Identifying the Monsoon Active and Break Spells with Dense GNSS Sites in Guangxi, China

“…Water vapor is paramount in climate change [1], the hydrological cycle, heat exchange and transfer due to spatiotemporal variability, the natural greenhouse effect and latent heat released by condensation [2]. Therefore, an accurate representation of water vapor concentration is crucial for numerical weather prediction [3], extreme weather monitoring [4] and global and regional scale climate models.…”

Machine Learning-Based Calibrated Model for Forecast Vienna Mapping Function 3 Zenith Wet Delay

“…PWV is strongly associated with precipitation, extreme weather events (typhoons, hurricanes, etc. ), and climate [11][12][13][14][15]. High-accuracy ZWD enhances GNSS application performance in extreme weather monitoring and early warning.…”