Content area
Full Text
ABSTRACT
Rainfall is a climate element with high variations in space and time scales, so it is not easy to predict. One way to predict rainfall is statistical downscaling (SD). SD can predict local rainfall based on Global Circulation Model (GCM) data. The Decadal Climate Prediction Project (DCPP), one of the GCMs, originates from adjacent grids and experiences multicollinearity problems. Rainfall as a response variable is Tweedie Compound Poisson Gamma (TCPG) distribution data because it has a discrete component (rainfall events) and a continuous component (rainfall intensity), so SD modelling will be carried out using Tweedie-LASSO. This research aims to compare the performance of bias correction and ensemble methods in SD in predicting rainfall in West Java, Indonesia. Bias correction uses Empirical Quantile Mapping (EQM) with CHIRPS data, and the ensemble method uses a stacking technique with Random Forest (Stacking-RF) due to the varied characteristics of DCPP model sources. Evaluation results using Root Mean Square Error Prediction (RMSEP) and correlation coefficient show that bias correction improves single-model performance but not ensemble models. Besides that, ensemble models outperform single models both before and after bias correction. The combination of bias correction and ensemble modelling can be recommended when conducting SD to enhance the prediction capability of rainfall at stations and other areas.
Keyword: Bias Correction, Empirical Quantile Mapping, Ensemble, Rainfall, Statistical Downscaling, Tweedie-LASSO
(ProQuest: ... denotes formulae omitted.)
Rainfall is a climatic factor that exhibits significant variations across different locations and times, making it challenging to predict, but it has a vital role in tropical regions such as Indonesia (Swarinoto et al., 2012). The fundamental role of rainfall cannot be understated, as it significantly impacts a wide range of domains, including agriculture, forestry, plantations, irrigation, marine activities, infrastructure, and beyond. Information related to rainfall can be obtained through the Global Circulation Model (GCM), which results from numerical simulation forecasts. These GCMs were designed by various world climate institutions, which have variations in spatial resolution and the equations used to produce atmospheric parameters. Despite the usefulness of GCM output data, it presents challenges when linking it with local-scale rainfall data due to its global scope and large dimensions. Therefore, specific techniques are required to facilitate this process. According to Dar et al. (2018), Statistical Downscaling (SD)...