Abstract
Drought forecasting is essential for effectively managing drought-related damage and providing relevant drought information to decision-makers so they can make appropriate decisions in response to drought. Although there have been great efforts in drought-forecasting research, drought forecasting on a short-term scale (up to two weeks) is still difficult. In this research, drought-forecasting models on a short-term scale (8 days) were developed considering the temporal patterns of satellite-based drought indices and numerical model outputs through the synergistic use of convolutional long short term memory (ConvLSTM) and random forest (RF) approaches over a part of East Asia. Two widely used drought indices—Scaled Drought Condition Index (SDCI) and Standardized Precipitation Index (SPI)—were used as target variables. Through the combination of temporal patterns and the upcoming weather conditions (numerical model outputs), the overall performances of drought-forecasting models (ConvLSTM and RF combined) produced competitive results in terms of r (0.90 and 0.93 for validation SDCI and SPI, respectively) and nRMSE (0.11 and 0.08 for validation of SDCI and SPI, respectively). Furthermore, our short-term drought-forecasting model can be effective regardless of drought intensification or alleviation. The proposed drought-forecasting model can be operationally used, providing useful information on upcoming drought conditions with high resolution (0.05°).
Highlights
Drought, one of the more extreme natural disasters observed in the world, is caused by complex mechanisms between the land surface, ocean, and atmosphere [1,2,3,4]
We aimed to propose a drought-forecasting model on a short-term scale through the integration of numerical model outputs, topographic characteristics (i.e., climate zone, digital elevation model (DEM), and landcover), and satellite-based drought indices (i.e., Scaled Drought Condition Index (SDCI) and Standardized Precipitation Index (SPI)) using convolutional long short term memory (ConvLSTM) and random forest (RF) approaches
Despite the generally high accuracy, some dates had low r and high normalized root mean square error (nRMSE) due to sudden changes in drought conditions based on SDCI
Summary
One of the more extreme natural disasters observed in the world, is caused by complex mechanisms between the land surface, ocean, and atmosphere [1,2,3,4]. According to Emergency Events Database (EM-DAT) provided by Centre for Research on the Epidemiology of Disasters [11], there were 33 drought events worldwide between 2008 and 2018, creating an economic loss of $18 billion. For these reasons, drought monitoring and forecasting are essential for appropriately managing drought-related damage and providing relevant drought information to decision-makers [10,12]. Drought forecasting plays a vital role in risk management as a comprehensive preparation and mitigation of potential drought-caused damage in a timely manner [5,13,14]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
