This paper describes the results of runoff modelling for nine catchments of the Upper Murray Basin (Basin 401) of the Murray-Darling Drainage Division (MDDD), Australia. The work aimed firstly to provide adequate mode...
详细信息
This paper describes the results of runoff modelling for nine catchments of the Upper Murray Basin (Basin 401) of the Murray-Darling Drainage Division (MDDD), Australia. The work aimed firstly to provide adequate models for long-term streamflow prediction in nine catchments of this Basin feeding the Hume and Dartmouth reservoirs. The development and testing of flow forecasting algorithms for operational management by the Murray-Darling Basin Commission was another purpose of the work reported here. The conceptual lumped parameter rainfall-runoff model IHACRES (Jakeman et al., 1990, 1993;Jakeman and Hornberger, 1993) was selected as the modelling tool for streamflow prediction in the catchments. The conceptual rainfall-runoff model IHACRES (with a snow melt/formation module in snow-affected catchments) and a self-adaptive linear filtering approach for the IHACRES residuals were combined and applied for forecasting daily streamflow in the Upper Murray Basin catchments. Different orders of AutoRegressive Integrated Moving Average (arima) models for the residuals were considered in order to select the most appropriate forecasting algorithm. Linear filtering of the conceptual model residuals provides considerable improvement in forecasting for both low and high values of streamflow for developing the operational streamflow forecast system. (C) 1997 Elsevier Science Ltd.
The financial markets are unpredictable, with high profits and low risk being the primary goal. Gold and Bitcoin are currently the most sought after currencies due to their importance and specificity. The search for a...
详细信息
The financial markets are unpredictable, with high profits and low risk being the primary goal. Gold and Bitcoin are currently the most sought after currencies due to their importance and specificity. The search for an effective and flexible quantitative trading strategy is particularly important in order to predict the direction of trading and the value of gold and bitcoin. For problem one: firstly data processing was carried out to fill in the missing values and descriptive statistics were performed on the data provided. Secondly, an arima model is built to predict the price series of gold and bitcoin. This is followed by an investment optimisation model based on a dynamic programming algorithm to select the best portfolio strategy. The final prediction was that there were 20 transactions, 16 in bitcoin and 4 in gold, with the last transaction resulting in a total cash amount of US$346,263.1. To address Question 2: Firstly, a convolutional neural network prediction model and a random forest model were developed to predict the price series of gold and bitcoin, and the comprehensive comparison of the accuracy found that the arima model was more accurate, which proved the correctness of the arima model selection. Afterwards, the investment planning model was tested to give the optimal investment strategy and compared with other investment strategies, and it was found that the optimal strategy in this paper reasonably takes into account the investment risk and disturbance terms. Finally, the rationality of the trading strategies given by the model is analysed and justified, which proves that the decisions made by the model established in this paper are very effective and have high significance. To address Question 3: Firstly, a sensitivity analysis was conducted, which demonstrated the strong robustness of the model in this paper to key parameters such as transaction costs. By adjusting the bitcoin and gold commission payment rates, it is found that the transaction co
暂无评论