Debris flow is one of the most destructive phenomena of natural hazards. Recently, major natural hazard, claiming human lives and assets, is due to debris flow in the world. Several practical methods for forecasting d...Debris flow is one of the most destructive phenomena of natural hazards. Recently, major natural hazard, claiming human lives and assets, is due to debris flow in the world. Several practical methods for forecasting debris flow have been proposed, however, the accuracy of these methods is not high enough for practical use because of the stochastic and non-linear characteristics of debris flow. Artificial neural network has proven to be feasible and useful in developing models for nonlinear systems. On the other hand, predicting the future behavior based on a time series of collected historical data is also an important tool in many scientific applications. In this study we present a three-layer feed-forward neural network model to forecast surge of debris flow according to the time series data collected in the Jiangjia Ravine, situated in north part of Yunnan Province of China. The simulation and prediction of debris flow using the proposed approach shows this model is feasible, however, further studies are needed.展开更多
The need for accurate rainfall prediction is readily apparent when considering many benefits in which such information would provide for river control, reservoir operation, forestry interests, flood mitigation, etc.. ...The need for accurate rainfall prediction is readily apparent when considering many benefits in which such information would provide for river control, reservoir operation, forestry interests, flood mitigation, etc.. Due to importance of rainfall in many aspects, studies on rainfall forecast have been conducted since a few decades ago. Although many methods have been introduced, all the researches describe the study as complex because it involves numerous variables and still need to be improved. Nowadays, there are various traditional techniques and mathematical models available, yet, there are no result on which method provide the most reliable estimation. AR （auto-regressive）, ARMA （auto-regressive moving average）, ARIMA （auto-regressive integrated moving average） and ANNs （artificial neural networks） were introduced as a useful and efficient tool for modeling and forecasting. The conventional time series provide reasonable accuracy but suffer from the assumptions of stationary and linearity. The concept of neurons was introduced first which then developed to ANNs with back propagation training algorithm. Although certain ANNs） models are equivalent to time series model, but it is limited to short term forecasting. This Paper presents a mathematical approach for rainfall forecasting for Iran on monthly basic. The model is trained for monthly rainfall forecasting and tested to evaluate the performance of the model. The result Shows reasonably good accuracy for monthly rainfall forecasting.展开更多
文摘Debris flow is one of the most destructive phenomena of natural hazards. Recently, major natural hazard, claiming human lives and assets, is due to debris flow in the world. Several practical methods for forecasting debris flow have been proposed, however, the accuracy of these methods is not high enough for practical use because of the stochastic and non-linear characteristics of debris flow. Artificial neural network has proven to be feasible and useful in developing models for nonlinear systems. On the other hand, predicting the future behavior based on a time series of collected historical data is also an important tool in many scientific applications. In this study we present a three-layer feed-forward neural network model to forecast surge of debris flow according to the time series data collected in the Jiangjia Ravine, situated in north part of Yunnan Province of China. The simulation and prediction of debris flow using the proposed approach shows this model is feasible, however, further studies are needed.
文摘The need for accurate rainfall prediction is readily apparent when considering many benefits in which such information would provide for river control, reservoir operation, forestry interests, flood mitigation, etc.. Due to importance of rainfall in many aspects, studies on rainfall forecast have been conducted since a few decades ago. Although many methods have been introduced, all the researches describe the study as complex because it involves numerous variables and still need to be improved. Nowadays, there are various traditional techniques and mathematical models available, yet, there are no result on which method provide the most reliable estimation. AR （auto-regressive）, ARMA （auto-regressive moving average）, ARIMA （auto-regressive integrated moving average） and ANNs （artificial neural networks） were introduced as a useful and efficient tool for modeling and forecasting. The conventional time series provide reasonable accuracy but suffer from the assumptions of stationary and linearity. The concept of neurons was introduced first which then developed to ANNs with back propagation training algorithm. Although certain ANNs） models are equivalent to time series model, but it is limited to short term forecasting. This Paper presents a mathematical approach for rainfall forecasting for Iran on monthly basic. The model is trained for monthly rainfall forecasting and tested to evaluate the performance of the model. The result Shows reasonably good accuracy for monthly rainfall forecasting.
