Downscaling & super-resolution
Assessment of Drought Disasters (EDI) Based on ENSO and NOAA Climate Data Using ANN in Bondowoso Regency
In one sentence. Backpropagation ANN statistically downscales ENSO and NOAA indices to monthly rainfall in Bondowoso, Indonesia, to drive EDI drought assessment with R2 of 0.97.
Abstract
Bondowoso Regency is declared to be at high risk for the threat of drought based on the IRBI map of the National Disaster Management Agency in 2020. This study aims to assess drought disasters based on ENSO and NOAA data. The proposed method for rainfall modeling was Statistical Downscaling (SD) using the Backpropagation Neural Network (BPNN), for which the output models were used for drought assessment using the EDI. The reliability test of the rainfall model is to compare the rainfall model with the observed rainfall. The reliability test of the EDI is to compare the results of the EDI analysis from the input rain model data with the observed rainfall data. ANN modeling results showed that monthly rainfall predictions are better. This is indicated by the R2 monthly, and 10-day base values of 0.97 and 0.83, respectively, with RMSE values of 0.05 and 0.07, and the best modeling in EDI analysis was R2 0.88 and 0.63 with RMSE 0.35 and 0.65. Based on the results of this study, it is shown that drought disaster assessment based on ENSO and NOAA climate data can be used as an alternative to support the decision-making system for drought mitigation.
Labels
- Topic
- Downscaling & super-resolution, Extremes & hazards
- Type
- Application study
- Method
- Classical ML (trees, GP, linear, kernels)
- Domain
- Local / station, Regional
- Data
- Station / in-situ, Other
- Status
- Research
- Identifiers
- DOI:10.21776/ub.pengairan.2023.014.01.3 OpenAlex:W4386640874
- Added
- 2026-10-22
Labels and summary are generated by Claude and reviewed weekly. Wrong? Edit this entry.