The analysis of rainfall patterns in the Indonesian region utilized the Empirical Orthogonal Function (EOF) method to identify spatial and temporal variations. The study evaluated the dynamic influence of the Tropical Indian Ocean (TIO) and the Tropical Pacific Ocean (TPO) on Indonesian rainfall using monthly data from the Southeast Asian Climate Assessment and Dataset (SACA&D) spanning from January 1981 to December 2016 and encompassing three extreme El Niño events in 1982/1983, 1997/1998 and 2015/2016. Using combined reanalysis and gridded-observation data, this study evaluates the potential impact of the two primary modes in the tropical Indo-Pacific region, namely the Indian Ocean Dipole (IOD) and the El Niño-Southern Oscillation (ENSO) on Indonesian rainfall. The analysis using the EOF method revealed two main modes with variances of 35.23% and 13.07%, respectively. Moreover, the results indicated that rainfall in Indonesia is highly sensitive to sea surface temperatures (SST) in the southeastern tropical Indian Ocean and the central Pacific Ocean (Niño3.4 and Niño3 areas), suggesting that changes in SST could significantly alter rainfall patterns in the region. This research is useful for informing government policies related to anticipating changes in rainfall variability as part of Indonesia’s preparedness for hydrometeorological disasters.

This study aims to investigate the characteristics of temperature and precipitation extremes in Indonesian Borneo both in space and time. Using daily data of 15 weather stations, a subset of 12 climate extreme indices has been calculated to clarify whether the frequency, intensity and duration of temperature and precipitation extremes have changed over the last three decades. Results show that the island has clearly warmed up for the last three decades. The annual average of maximum temperature (TXmean) and minimum temperature (TNmean) increased significantly by 0.22 (0.36) °C per 10 years during the studied period. The annual number of warm days (TX90p) and warm nights (TN90p) significantly increased while the number of cool days (TX10p) and cool nights (TN10p) decreased significantly. In contrast, the trends of precipitation extremes were not clearly observed. The changes in the extreme rainfall events are generally less consistent between the different stations. However, the tendency of the island to be wetter was observed as reflected by the frequency of heavy precipitation days (R20mm), the annual maxima of daily rainfall (RX1day) and the average intensity of daily rainfall (SDII). For SDII, the regional index shows a significant increasing trend by 0.3 mm/day per decade. This study fills information gaps of how climate extremes are changing in Indonesian Borneo.

Reliable spatio-temporal rainfall prediction is a key element in disaster mitigation and water resource management in dynamic tropical regions such as the Bengawan Solo River Watershed. However, high climate variability and data limitations often pose significant challenges to the accuracy of conventional prediction models. This study introduces an innovative approach by applying ensemble stacking, which combines machine learning models such as Random Forest (RF), Extreme Gradient Boosting (XGB), Support Vector Regression (SVR), Multi-Layer Perceptron (MLP), Light Gradient-Boosting Machine (LGBM) and deep learning models like Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), Temporal Convolutional Networks (TCN), Convolutional Neural Network (CNN), and Transformer architecture based on monthly Climate Hazards Group InfraRed Precipitation with Stations (CHIRPS) data (1981–2024). The novelty of this research lies in the systematic exploration of various model combination scenarios—both classical and deep learning and the evaluation of their performance in projecting rainfall for 2025–2030. All base models were trained on the 1981–2019 period and validated with data from the 2020–2024 period, while ensemble stacking was developed using a linear regression meta-learner. The results show that the optimal ensemble scenario reduces the MAE to 53.735 mm, the RMSE to 69.242 mm, and increases the R² to 0.795826—better than all individual models. Spatial and temporal analyses also indicate consistent model performance at most locations and times. Annual rainfall projections for 2025–2030 were then interpolated using IDW to generate a spatio-temporal rainfall distribution map. The improved accuracy provides a strong scientific basis for disaster preparedness, flood and drought management, and sustainable water planning in the Bengawan Solo River Watershed. Beyond this case, the approach demonstrates significant transferability to other climate-sensitive and data-scarce regions.

This work is aimed to identify areas in the country that are at high propensity to the impact of global climate phenomenon i.e. El-Nino. An affected area is recognized when rainfall decreases up to below normal condition which frequently leads drought event. For this purpose, two packages of gridded rainfall data at monthly basis with 0.5 spatial resolutions for 1950 2010 period were used, e.g. GPCC Full Data Reanalysis V.6 (product of Global Precipitation Climatology Centre) and CRU TS3.22 (product of Climatic Research Unit). El-Nino years were labelled based on Oceanic Nino Index, ONI. We applied frequency analysis to quantify the chance of El-Nino impact. GPCC data was found more accurate in representing rainfall observation than CRU data based on correlation test against station data. The results indicate the strong spatial and temporal dependencies of El-Nino impact. During peak of rainy and first transitional season (DJF and MAM), the probability to be affected by El-Nino is mostly less than 20% over whole country In contrast, July-October are months where areas with high and very high risk were observed over many regions such as Southern part of Sumatera, Java, Kalimantan, Sulawesi, Maluku and Papua. Further investigation at province level found that the timing of El-Nino impact starts in June. These results are potential to improve national capacity in risk management related to weather-climate hazards.