Li-Chiu Chang

Reinforced Two-Step-Ahead Weight Adjustment Technique for Online Training of Recurrent Neural Networks

A reliable forecast of future events possesses great value. The main purpose of this paper is to propose an innovative learning technique for reinforcing the accuracy of two-step-ahead (2SA) forecasts. The real-time recurrent learning (RTRL) algorithm for recurrent neural networks (RNNs) can effectively model the dynamics of complex processes and has been used successfully in one-step-ahead forecasts for various time series. A reinforced RTRL algorithm for 2SA forecasts using RNNs is proposed in this paper, and its performance is investigated by two famous benchmark time series and a streamflow during flood events in Taiwan. Results demonstrate that the proposed reinforced 2SA RTRL algorithm for RNNs can adequately forecast the benchmark (theoretical) time series, significantly improve the accuracy of flood forecasts, and effectively reduce time-lag effects.

Forecasting of ozone episode days by cost-sensitive neural network methods.

Forecasting the occurrence of ozone episode days can be regarded as an imbalanced dataset classification problem. Since the standard artificial neural network (ANN) methods cannot make accurate predictions of such a problem, two cost-sensitive ANN methods, cost-penalty and moving threshold, were used in this study. The models classify each day as episode or non-episode according to the standard of daily maximum 8 h O(3) concentration. The ozone measurements from six monitoring stations in Taiwan were used for model training and performance evaluation. Two different input datasets, regional and single-site, were generated from raw air quality and meteorological observations. According to the numerical experiments, the predictions based on the regional dataset are much better than those obtained from the single-site dataset. Two cost-sensitive ANN methods were evaluated by receiver operating characteristic (ROC) curves. It was found that the results obtained by the two approaches are similar. If the misclassification costs are known, the cost-sensitive method can minimise the total costs. If the misclassification costs are unknown, the cost-sensitive ANN can obtain a better forecast than the standard ANN method when an appropriate cost ratio is used. For clean areas where episode days are very rare, the forecasts are poor for all methods.

Conservation of groundwater from over-exploitation—Scientific analyses for groundwater resources management

Groundwater over-exploitation has produced many critical problems in the southern Taiwan. The accumulated stresses and demands make groundwater management a complex issue that needs innovative scientific analyses for deriving better water management strategies. In this study, we aimed to provide scientific analyses of the groundwater systems in the Pingtung Plain through soft-computing techniques to explore its spatial-temporal and hydro-geological characteristics for the elaboration of future groundwater management plans and in decision-making process. We conducted a study to assess the essential features of the groundwater systems based on the long-term large datasets of regional groundwater levels by using the principal component analysis (PCA), and the self-organizing map (SOM) with regression analysis. The PCA results demonstrated that two leading components could well present the spatial characteristics of the groundwater systems and classify the region into eastern, western and transition zones. The SOM results could visibly explore the behavior of regional groundwater variations in various aquifers and the multi-relations among climate and hydrogeological variables. Results revealed that the potential of groundwater recharge made by precipitation or river flow was higher in the eastern zone than in the western zone. Analysis results further showed an increase of the groundwater levels in the western zone after year 2006, while there were no obvious increases of the groundwater levels in the eastern or transition zones. Based on the investigated characteristics, we suggest that a sound groundwater management plan should consider zonal difference of the groundwater systems to achieve groundwater conservation.

Estimating spatio-temporal dynamics of stream total phosphate concentration by soft computing techniques

This study attempts to model the spatio-temporal dynamics of total phosphate (TP) concentrations along a river for effective hydro-environmental management. We propose a systematical modeling scheme (SMS), which is an ingenious modeling process equipped with a dynamic neural network and three refined statistical methods, for reliably predicting the TP concentrations along a river simultaneously. Two different types of artificial neural network (BPNN-static neural network; NARX network-dynamic neural network) are constructed in modeling the dynamic system. The Dahan River in Taiwan is used as a study case, where ten-year seasonal water quality data collected at seven monitoring stations along the river are used for model training and validation. Results demonstrate that the NARX network can suitably capture the important dynamic features and remarkably outperforms the BPNN model, and the SMS can effectively identify key input factors, suitably overcome data scarcity, significantly increase model reliability, satisfactorily estimate site-specific TP concentration at seven monitoring stations simultaneously, and adequately reconstruct seasonal TP data into a monthly scale. The proposed SMS can reliably model the dynamic spatio-temporal water pollution variation in a river system for missing, hazardous or costly data of interest.

Investigating the interactive mechanisms between surface water and groundwater over the Jhuoshuei river basin in central Taiwan

In Taiwan, groundwater commonly becomes important water resources in dry periods, and/or areas lack of water storage facility due to its low cost, steady water supply and good water quality. However, improper groundwater development brings about serious decreases in groundwater levels and land subsidence which causes disasters, such as seawater intrusion or soil salination, accompanied with environmental and economic losses. It is critical to develop strategies for water resources conservation in mountainous areas. The complex heterogeneity of mountainous physiographic environment makes it challenging in the forecasts of groundwater level variations, particularly in mountainous areas. Artificial neural networks (ANNs) have been recognized as an effective modeling tool for complex nonlinear systems in the last two decades. This study aims to investigate the interactive mechanisms of groundwater at the mountainous areas of the Jhuoshuei river basin in central Taiwan through analyzing and modeling the groundwater level variations. Several issues are discussed in this study, which includes the correlation between groundwater level variation and rainfall as well as streamflow, the identification of groundwater recharge patterns and effective rainfall thresholds for estimating groundwater level variations. The results indicate: (1) the daily variation of groundwater level is closely correlated with river flow and one-day antecedent rainfall based on correlation analyses; (2) effective rainfall thresholds can be identified successfully; (3) groundwater level variations can be classified into four types for monitoring wells; and (4) the daily variations of groundwater level can be well estimated by constructed ANNs. The identified interactive mechanisms between surface water and groundwater can facilitate the mountainous water resource conservation strategy for better water management, especially irrigation water supply and for alleviating land subsidence in downstream areas in the future.

Multi-Step-Ahead Reservoir Inflow Forecasting by Artificial Intelligence Techniques

Taiwan is located in themonsoon zone of the North Pacific Ocean and experiences an average of 4-5 typhoons annually. The particular topography of Taiwan makes rivers short and steep, and thus rivers flow rapidly from catchments to reservoirs within a few hours during typhoon events. This study aims to construct realtime multi-step-ahead reservoir inflow forecast models by using Artificial Neural Networks (ANNs) based on radar rainfall data and reservoir inflow data. The Back PropagationNeural Network (BPNN) and the Recurrent Neural Network (RNN) are adopted for forecasting. Results indicate that the correlation coefficients in the testing phases of both models exceed 0.86 for one- to three-hour-ahead forecasts and exceed 0.69 for six-hour-head forecasts. The RNN model outperforms the BPNN model, which indicates the recurrent property of the RNN can effectively improve forecast accuracy when making several step-ahead forecasts. Results demonstrates that the constructed multi-step-ahead rainfall-runoff models can provide valuable instantaneous inflow forecasts for the coming six hours so that decision makers can implement more suitable reservoir operations in consideration of inflow forecasts, rather than just depend on historical scenarios.

Multi-output support vector machine for regional multi-step-ahead PM2.5 forecasting

Air quality deteriorates fast under urbanization in recent decades. Reliable and precise regional multi-step-ahead PM2.5 forecasts are crucial and beneficial for mitigating health risks. This work explores a novel framework (MM-SVM) that combines the Multi-output Support Vector Machine (M-SVM) and the Multi-Task Learning (MTL) algorithm for effectively increasing the accuracy of regional multi-step-ahead forecasts through tackling error accumulation and propagation that is commonly encountered in regional forecasting. The Single-output SVM (S-SVM) is implemented as a benchmark. Taipei City of Taiwan is our study area, where three types of air quality monitoring stations are selected to represent areas imposed with high traffic influences, high human activities and commercial trading influences, and less human interventions close to nature situation, respectively. We consider forecasts of PM2.5 concentrations as a function of meteorological and air quality factors based on long-term (2010-2016) observational datasets. Firstly, the Kendall tau coefficient is conducted to extract key spatiotemporal factors from regional meteorological and air quality inputs. Secondly, the M-SVM model is trained by the MTL to capture non-linear relationships and share correlation information across related tasks. Lastly, the MM-SVM model is validated using hourly time series of PM2.5 concentrations as well as meteorological and air quality datasets. Regarding the applicability of regional multi-step-ahead forecasts, the results demonstrate that the MM-SVM model is much more promising than the S-SVM model because only one forecast model (MM-SVM) is required, instead of constructing a site-specific S-SVM model for each station. Moreover, the forecasts of the MM-SVM are found better consistent with observations than those of any single S-SVM in both training and testing stages. Consequently, the results clearly demonstrate that the MM-SVM model could be recommended as a novel integrative technique for improving the spatiotemporal stability and accuracy of regional multi-step-ahead PM2.5 forecasts.