The quality of Automatic Identification System (AIS) data is of fundamental importance for maritime situational awareness and navigation risk assessment. To improve operational efficiency, a deep learning method based on Bi-directional Long Short-Term Memory Recurrent Neural Networks (BLSTM-RNNs) is proposed and applied in AIS trajectory data restoration. Case studies have been conducted in two distinct reaches of the Yangtze River and the capability of the proposed method has been evaluated. Comparisons have been made between the BLSTM-RNNs-based method and the linear method and classic Artificial Neural Networks. Satisfactory results have been obtained by all methods in straight waterways while the BLSTM-RNNs-based method is superior in meandering waterways. Owing to the bi-directional prediction nature of the proposed method, ship trajectory restoration is favourable for complicated geometry and multiple missing points cases. The residual error of the proposed model is computed through Euclidean distance which decreases to an order of 10 m. It is considered that the present study could provide an alternative method for improving AIS data quality, thus ensuring its completeness and reliability.

Daily water level forecasting is of significant importance for the comprehensive utilization of water resources. An improved least squares support vector machine (LSSVM) model was introduced by including an extra bias error control term in the objective function. The tuning parameters were determined by the cross-validation scheme. Both conventional and improved LSSVM models were applied in the short term forecasting of the water level in the middle reaches of the Yangtze River, China. Evaluations were made with both models through metrics such as RMSE (Root Mean Squared Error), MAPE (Mean Absolute Percent Error) and index of agreement (d). More accurate forecasts were obtained although the improvement is regarded as moderate. Results indicate the capability and flexibility of LSSVM-type models in resolving time sequence problems. The improved LSSVM model is expected to provide useful water level information for the managements of hydroelectric resources in Rivers.

The dynamic processes in the tidal reaches of the Yangtze River lead to the complexity of short-term water level forecasting. Historical data of daily water level are obtained for the lower reaches (Anqing–Wuhu–Nanjing) of the Yangtze River. Stationary time series of water level is derived by making the first-order difference with the raw datasets. An artificial neural network–Kalman hybrid model is proposed for water level forecasting, in which the Kalman filtering is introduced for partial data reconstruction. The model is calibrated with the hydrologic daily water level data of years 2014–2016 for MaAnshan station. Comparing with the traditional artificial neural network model, daily water level predictions are improved by the hybrid algorithm. Discrepancies appear under the circumstance of sharp variations of water level observations. Moreover, the implementation strategy of Kalman filtering algorithm is explored, which indicates the superiority of local Kalman filtering.

With the rapid development of port construction and the shipping industry, port water quality issues are of great concern. This is always a challenging task due to the frequent human activities and dynamic processes involved. A parallel intelligent water quality monitoring system is therefore proposed to ensure the effective monitoring and intelligent control of water pollutants. The real monitoring system and the artificial monitoring system of port water quality are established by applying artificial systems, computational experiments and parallel execution (ACP method). Both systems interact with each other and execute in parallel. The artificial monitoring system simulates complex scenarios, while the real monitoring system feeds the artificial monitoring system with actual monitoring data. By means of data-driven and model-driven approaches, the two systems can compute, observe and evaluate to control, manage and train models. Through the continuous optimization between the two systems, the efficiency and accuracy of the water quality monitoring system could be improved. Technical support can be further provided for the planning of water quality monitoring sites, implementation of monitoring tasks, allocation of emergency resources, etc. As in-situ monitoring data are obtained, computational experiments and parallel executions could be conducted to achieve the ultimate goal of port water quality management.