Based On The Combination Of The ECM Model Application In Farming、forestry、Animal Husbandry And Fishery

Many articles research and discuss the relationship between the ecological economic and their influence on total output, but usually they only use two variables of these as research object and the prediction effect is not very ideal. Therefore, to provide reference and guidance for the real life, high precision of prediction is very important. This article selects a set of data, and forecast the data by two kinds of time series model and two kinds of intelligent algorithm which are selected according to the characteristics of the data themselves.Ecological-economic plays an important role in real life. Thus predicting the ecological-economic output accurately can provide guidance for the government policy makers and ecological-economic participants and reduce the blindness of ecological-economic market development so that the interests of the various aspects are maximized. In this paper, the first model is error correction model (ECM). This model will take five gross outputs of farming, forestry, animal husbandry, fishery into account, and as a consequence, the prediction’s results show that the model prediction effect is good. In order to determine whether this model is the best predicting model, this article choose the autoregressive moving average model (ARIMA) and the BP neural network model for the selected data to forecast, and contrast forecasting results, the comparison results show that the predicted effect of ECM is best; In general, the combined model prediction effect than a single model prediction effect is good, so this paper uses particle swarm optimization (PSO) to find the optimal weights, basing on the optimal weight the new prediction model is putted forward:ECM-ARIMA-BP model, BP model and ECM-ARIMA-BP for the selected data to forecast, the consequence show that the ECM-ARIMA-BP prediction model improves the prediction accuracy, prediction effect is best.