ABSTRACT
The occurrence and severity of extreme precipitation events have been increasing globally. Although numerous projections have been proposed and developed for evaluating the climate change impacts, most models suffer from significant bias error due to the coarse resolution of the climate datasets, which affects the accuracy of the climate change assessment. Therefore, in this study, post-processing techniques (interpolation and bias correction methods) were adopted on the database for Policy Decision Making for Future Climate Change (d4PDF) model for extreme climatic flood events simulation in the Chao Phraya River Basin, Thailand, under + 4-K future climate simulation. Due to the limited number of the rain gages, the gradient plus inverse distance squared interpolation method (combination of multiple linear regression and distance weighting methods) was applied in this study. In the bias correction methods, the additional setting of monthly and seasonal periods was adjusted. The proposed bias correction approach deployed gamma distribution combined with generalized Pareto distribution setting with the seasonal period for the rainy season datasets, whereas only the gamma setting was applied with the monthly period during the dry season. The outcomes revealed that the proposed method could react to extreme rainfall events, expand dry days during dry season, and intensify rainfall amount during rainy season. The post-processing d4PDF trends of six sea surface temperature (SST) patterns (consists of 90 ensemble members) of two periods (near future: 2051-2070 and far future: 2091-2110) recorded the highest and lowest amounts of annual rainfalls of 4,450 mm/year in mid-stream of Nan River and 710 mm/year in the lower CPRB, respectively. Notably, the significant variances noted in the rainfall patterns among ensembles, demanding further investigation in future climate change, impact studies. The findings of the study provided novel insights on the importance of proper post-processing techniques for improving the robustness of d4PDF in climate change impacts assessment.
ABSTRACT
The unprecedented outbreak of COVID-19 significantly improved the atmospheric environment for lockdown-imposed regions; however, scant evidence exists on its impacts on regions without lockdown. A novel research framework is proposed to evaluate the long-term monthly spatiotemporal impact of COVID-19 on Taiwan air quality through different statistical analyses, including geostatistical analysis, change detection analysis and identification of nonattainment pollutant occurrence between the average mean air pollutant concentrations from 2018-2019 and 2020, considering both meteorological and public transportation impacts. Contrary to lockdown-imposed regions, insignificant or worsened air quality conditions were observed at the beginning of COVID-19, but a delayed improvement occurred after April in Taiwan. The annual mean concentrations of PM10, PM2.5, SO2, NO2, CO and O3 in 2020 were reduced by 24%, 18%, 15%, 9.6%, 7.4% and 1.3%, respectively (relative to 2018-2019), and the overall occurrence frequency of nonattainment air pollutants declined by over 30%. Backward stepwise regression models for each air pollutant were successfully constructed utilizing 12 meteorological parameters (R2 > 0.8 except for SO2) to simulate the meteorological normalized business-as-usual concentration. The hybrid single-particle Lagrangian integrated trajectory (HYSPLIT) model simulated the fate of air pollutants (e.g., local emissions or transboundary pollution) for anomalous months. The changes in different public transportation usage volumes (e.g., roadway, railway, air, and waterway) moderately reduced air pollution, particularly CO and NO2. Reduced public transportation use had a more significant impact than meteorology on air quality improvement in Taiwan, highlighting the importance of proper public transportation management for air pollution control and paving a new path for sustainable air quality management even in the absence of a lockdown.
ABSTRACT
Rivers in Malaysia are classified based on water quality index (WQI) that comprises of six parameters, namely, ammoniacal nitrogen (AN), biochemical oxygen demand (BOD), chemical oxygen demand (COD), dissolved oxygen (DO), pH, and suspended solids (SS). Due to its tropical climate, the impact of seasonal monsoons on river quality is significant, with the increased occurrence of extreme precipitation events; however, there has been little discussion on the application of artificial intelligence models for monsoonal river classification. In light of these, this study had applied artificial neural network (ANN) and support vector machine (SVM) models for monsoonal (dry and wet seasons) river classification using three of the water quality parameters to minimise the cost of river monitoring and associated errors in WQI computation. A structured trial-and-error approach was applied on input parameter selection and hyperparameter optimisation for both models. Accuracy, sensitivity, and precision were selected as the performance criteria. For dry season, BOD-DO-pH was selected as the optimum input combination by both ANN and SVM models, with testing accuracy of 88.7% and 82.1%, respectively. As for wet season, the optimum input combinations of ANN and SVM models were BOD-pH-SS and BOD-DO-pH with testing accuracy of 89.5% and 88.0%, respectively. As a result, both optimised ANN and SVM models have proven their prediction capacities for river classification, which may be deployed as effective and reliable tools in tropical regions. Notably, better learning and higher capacity of the ANN model for dataset characteristics extraction generated better predictability and generalisability than SVM model under imbalanced dataset.
