It is necessary to predict dam inflow in advance for flood prevention and stable dam operations. Although predictive models using deep learning are increasingly studied, these existing studies have merely applied the models or adapted the model structure. In this study, data preprocessing and machine learning algorithms were improved to increase the accuracy of the predictive model. Data preprocessing was divided into two types: The learning method, which distinguishes between peak and off seasons, and the data normalization method. To search for a global solution, the model algorithm was improved by adding a random search algorithm to the gradient descent of the Multi-Layer Perceptron (MLP) method. This revised model was applied to the Soyang Dam Basin in South Korea, and deep learning-based discharge prediction was performed using historical data from 2004 to 2021. Data preprocessing improved the accuracy by up to 61.5%, and the revised model improved the accuracy by up to 40.3%. With the improved algorithm, the accuracy of dam inflow predictions increased to 89.4%. Based on these results, stable dam operation is possible through more accurate inflow predictions.

The purpose of this study is to identify the relationship between drainage density and climate, as represented by the climate aridity index, and to understand the relationship between drainage density and drainage area. A total of 121 study sites with low human impact, and a wide range of climate aridity index 0.3 (humid)–10.4 (arid), were selected based on the availability of light detection and ranging (LiDAR) data, producing a digital elevation model (DEM) with a spatial resolution of 1 m. A curvature-based method, incorporating both positive and negative curvature information, was used to extract the valley (drainage) network from the LiDAR-based DEMs. Drainage density and climate aridity index exhibited a monotonically increasing trend, contrary to the previous results that have shown a U-shaped relationship. This discrepancy was caused by the selection of watersheds with extensive human activity in the previous study. One-meter resolution DEM produced greater drainage density than the previous studies with a coarse spatial resolution of 30 m as small valleys are not detectable in low-resolution topography datasets. The discrepancy between the previous study and the current study results encouraged further investigation of the impact of the drainage area (watershed size). A negative correlation between drainage density and drainage area was reconfirmed, while a stronger decreasing trend was observed in arid regions than in humid regions.

This study analyzed the sensitivity of rainfall patterns in South China and the Indochina Peninsula (ICP) using statistical simulations of observational data. Quantitative changes in rainfall patterns over the ICP were examined for both wet and dry seasons to identify hotspots sensitive to ocean warming in the Indo-Pacific sector. The rainfall variability was amplified by combined and/or independent effects of the El Niño–Southern Oscillation and the Indian Ocean Dipole (IOD). During the years of El Niño and a positive phase of the IOD, rainfall is less than usual in Thailand, Cambodia, southern Laos, and Vietnam. Conversely, during the years of La Niña and a negative phase of the IOD, rainfall throughout the ICP is above normal, except in parts of central Laos, northern Vietnam, and South China. This study also simulated the change of ICP rainfall in the wet and dry seasons with intentional IOD changes and verified IOD-sensitive hotspots through quantitative analysis. The results of this study provide a clear understanding both of the sensitivity of regional precipitation to the IOD and of the potential future impact of statistical changes regarding the IOD in terms of understanding regional impacts associated with precipitation in changing climates.

This study analyzed temporal and regional responses of precipitation to the Indian Ocean Dipole (IOD) over southern China and the differences between IOD-only and El Niño–southern oscillation–IOD cases. The Mann–Kendall test and intentionally biased bootstrapping were used. The results revealed three main phases (development and peak, decay, and aftermath) of percentage changes in seasonal total rainfall and showed the most positive sensitivity to positive IOD events in southern China. Moreover, El Niño played an essential role in intensifying the positive response to positive IOD events in the first and second phases while contributing little to the third. In terms of precipitation variability (frequency, intensity, and magnitude), seasonal maximum 1-day precipitation and maximum number of consecutive dry days were more sensitive to positive IOD events than the maximum number of consecutive wet days and simple daily precipitation intensity index. This study enhances knowledge of the temporal and spatial sensitivity of precipitation features to positive IOD events over southern China.

This study investigated the effects of El Niño events on tropical cyclone (TC) characteristics over the western North Pacific (WNP) region. First, TC characteristics associated with large-scale atmospheric phenomena (i.e., genesis position, frequency, track, intensity, and duration) were investigated in the WNP in relation to various types of El Niño events—moderate central Pacific (MCP), moderate eastern Pacific (MEP), and strong basin-wide (SBW). Subsequently, the seasonal and regional variability of TC-induced rainfall across China was analyzed to compare precipitation patterns under the three El Niño types. When extreme El Niño events of varying degrees occurred, the local rainfall varied during the developmental and decaying years. The development of MEP and SBW was associated with a distinct change in TC-induced rainfall. During MEP development, TC-induced rainfall occurred in eastern and northeastern China, whereas in SBW, TC-induced heavy rainfall occurred in southwest China. During SBW development, the southwestern region was affected by TCs over a long period, with the eastern and northeastern regions being affected significantly fewer days. During El Niño decay, coastal areas were relatively more affected by TCs during MCP events, and the Pearl River basin was more affected during SBW events. This study’s results could help mitigate TC-related disasters and improve water-supply management.