Rapid urbanization in the recent decades has quickly fuelled up the process of global warming. Many mitigation measures have been formulated and implemented in order to tackle the effect of global warming. Green roofs (roof with vegetated cover) have been proposed and implemented by various countries as one of the new environmentally friendly innovation. This paper evaluates the qualitative and quantitative performances of an extensive green roof system under tropical climate. Simulations showed that the peak discharge of stormwater run-off was reduced up to 26% in relation to concrete tile roof. Its reduction ability was decreased for storms with intense rainfall. Increment of pH was observed for the green roof run-off, and the run-off quality ranged between class I and II under Malaysia National Water Quality Index (WQI). High concentrations of phosphate were observed in the run-off samples, which showed that substrates (fertilized planting soil) might be the potential contributor. Findings indicated that there was a reduction up to around 5% for indoor temperature of the building after installation of the extensive green roof system.

The process of implementing neural networks in a computer system is known as deep learning. In this study, a deep learning model, namely long short-term memory (LSTM), was established to predict and forecast water levels for stations located at the Nam Ngum River Basin in Lao PDR. Water levels are predicted and forecasted based on the rainfall and water level data observed at previous time steps. It is proposed that the optimal sequence length for modeling should be determined based on the threshold of the correlation coefficient obtained from the water level and rainfall time series. The trained LSTM models in this study can be considered fair and adequate for water level prediction, as NSE values from 0.5 to 0.7 were mostly obtained from the model validations in the testing periods. The results showed that the autocorrelation and cross-correlation analysis did help in determining the optimal sequence length in an LSTM model. The performance levels of the LSTM model in forecasting future water levels in the Nam Ngum River Basin varied; the forecasted water level hydrographs for the Pakkayoung station generally corresponded with the observed ones, while the forecasted water level hydrographs for the other stations deviated significantly from the observed hydrographs.

This study explores the application of a Long Short-Term Memory (LSTM) model for river water level forecasting, emphasizing the critical role of hyper-parameters optimization. Similar to physical and numerical rainfall-runoff models, LSTM relies on parameters to drive its data-driven modeling process. The performance of such models is highly sensitive to the chosen hyper-parameters, making their optimization essential. To address this, three algorithms—Grid Search, Random Search, and Bayesian Search—were applied to identify the most effective hyper-parameter combinations. Cross-correlation analysis revealed that average rainfall had a stronger influence on river water levels than upstream point rainfall, leading to its selection as the model input. The optimization focused on five key hyper-parameters: neuron units, learning rate, dropout rate, number of epochs, and batch size. Results showed that, while Grid Search required the most computational time, both Random and Bayesian Search were more efficient. Notably, Bayesian Search yielded the best predictive performance with minimal time cost, making it the preferred optimization method. Additionally, reproducible LSTM simulations were conducted to ensure the consistency and practical applicability of the forecasting in real-world scenarios. Overall, Bayesian Search is recommended for optimizing LSTM models due to its balance of accuracy and computational efficiency in hydrological forecasting.

Ensuring the quality of hydrological data is critical for effective flood forecasting, water resource management, and disaster risk reduction, especially in regions vulnerable to typhoons and extreme weather. This study presents a framework for quality control and outlier detection in rainfall and water level time series data using both supervised and unsupervised machine learning algorithms. The proposed approach is capable of detecting outliers arising from sensor malfunctions, missing values, and extreme measurements that may otherwise compromise the reliability of hydrological datasets. Supervised learning using XGBoost was trained on labeled historical data to detect known outlier patterns, while the unsupervised Isolation Forest algorithm was employed to identify unknown or rare outliers without the need for prior labels. This established framework was evaluated using hydrological datasets collected from Lao PDR, one of the member countries of the Typhoon Committee. The results demonstrate that the adopted machine learning algorithms effectively detected real-world outliers, thereby enhancing real-time monitoring and supporting data-driven decision-making. The Isolation Forest model yielded 1.21 and 12 times more false positives and false negatives, respectively, than the XGBoost model, demonstrating that XGBoost achieved superior outlier detection performance when labeled data were available. The proposed framework is designed to assist member countries in shifting from manual, human-dependent processes to AI-enabled, data-driven hydrological data management.

The main purpose of this study is to propose a methodology for identifying vulnerable regions in the Cameron Highlands that are susceptible to soil loss, based on runoff aggregation structure and the energy expenditure pattern of the natural river basin, within the framework of power law distribution. To this end, three geomorphologic factors, namely shear stress and stream power, as well as the drainage area of every point in the basin of interest, have been extracted using GIS, and then their complementary cumulative distributions are graphically analyzed by fitting them to power law distribution, with the purpose of identifying the sensitive points within the basin that are susceptible to soil loss with respect to scaling regimes of shear stress and stream power. It is observed that the range of vulnerable regions by the scaling regime of shear stress is much narrower than by the scaling regime of stream power. This result seems to suggest that shear stress is a scale-dependent factor, which does not follow power law distribution and does not adequately reflect the energy expenditure pattern of a river basin. Therefore, stream power is preferred as a more reasonable factor for the evaluation of soil loss. The methodology proposed in this study can be validated by visualizing the path of soil loss, which is generated from the hillslope process (characterized by the local slope) to the valley through a fluvial process (characterized by the drainage area as well as the local slope).

This study presents the reviews and derivations of ARF for storm design applications in Malaysia. Considering that present rainfall characteristics may change due to climate change, rainfall time series data of the selected rainfall interval of nine rainfall stations in Kuala Lumpur were examined by several homogeneity tests and trend test to determine the existence of trends. Average-Point rainfall tracking method was adopted to compute the Maximum Areal Average Rainfall (MAAR). Increasing trends were observed both in the point rainfalls and areal rainfalls especially for short rainfall interval which cause increment of ARF derived in this study. However, the increasing trend diminished as the rainfall interval increased. The increment also implies that ARF is a non-stationary factor. Thus the ARF derived several decades ago is not appropriate for present storm design applications. Spatial autocorrelation results indicated that the study area is characterized with localized rainfall pattern with threshold radius of about 11km which corresponding to circular area of 400 km². The reviewed ARF complies with the localized rainfall pattern and comparison revealed that ARF is not a universal factor. In conclusion, the ARF estimations has been improved for storm design applications of local concerns with response to changing climate.