Imputation methods for addressing missing data of monthly rainfall in Yogyakarta, Indonesia

Abstract

Rainfall data are the most significant values in hydrology and climatology modelling. However, the datasets are prone to missing values due to various issues. This study aspires to impute the rainfall missing values by using various imputation methods such as Replacing by Mmean (RM), Nearest Neighbor (NN), Random Forest (RF), Nonlinear Interactive Partial Least-Square (NIPALS) and Markov Chain Monte Carlo (MCMC). Monthly rainfall datasets from 24 rainfall stations in Yogyakarta, Indonesia were used in this study. The datasets were then used for bootstrapping to obtain an estimate of the withinimputation standard errors for each imputed dataset. The performances of five methods were evaluated using root mean square method (RMSE). The experimental results showed that the RF-Bootstrap (RF-B) approach was attained as the most satisfying fitting for missing rainfall data in Yogyakarta, Indonesia.

Anti-Aging Potential of Plants of the Anak Dalam Tribe, Jambi, Indonesia

“…For example, chokeberry exhibits high levels of phenolic and flavonoid compounds, ranging from 9,710 mg/L to 11,093 mg/L, along with strong antioxidant activity of 12.9–14.6 mmol/L, classified as highly potent. These levels are observed when the plant is cultivated under conditions of high rainfall and temperatures, surpassing those grown under less favorable conditions [ 19 , 34 ]. This potent antioxidant activity works synergistically to counteract Reactive Oxygen Species (ROS) involved in the photoaging process, commonly known as anti-aging activity [ 25 ].…”

“…These include its poor bioavailability, rapid metabolism and elimination, low solubility, instability in gastric pH, presystemic metabolism in the liver, and absorption issues that lead to subtherapeutic plasma concentrations and reduced therapeutic effectiveness [ 30 , 31 , 32 ]. Currently, the latest development is nanodelivery systems for herbal anti-aging products as an approach to address the challenges associated with the direct use of pure phytochemicals in therapy [ 31 , 34 , 35 , 71 ]. There are still very few nanocosmetic preparations of natural origin such as curcumin as anti-aging agents.…”

Regionalization of Rainfall Regimes Using Hybrid RF-Bs Couple with Multivariate Approaches

“…However, current implementations are typically confined to the implementation of Breiman's initial regression and classification algorithm, although various advances may also help to solve a number of functional problems in the water field [25]. According to [26], Random Forest-Bootstrap (RF-B) was the strongest single-imputation approach when calculating an incredibly large number of missing values.…”

“…In addition, the framework gives an insight into the ability of the random forest to predict in terms of strength of the individual predictors and their correlations. The random forest can be applied for classification, regression, and unsupervised learning [25,26]. By assuming that X = (X 1 , X 2 , .…”

“…It is common that the performance of the imputation method is evaluated by using a root mean square root (RMSE) and a mean absolute error (MAE). According to Shaharudin et al [26], the hybrid Random Forest Bootstrap (RF-Bs) was the best method for single imputation when estimating extremely large amounts of missing values.…”