| The research of regional farming system's priority sequence is the main basis of regional agricultural structural adjustment. This
study is based on the investigation of the status quo of agricultural natural resources, agro-ecological environment and the level of economic development in rural areas of dryland farming areas in Northwest China, and summs up seven kinds of major farming systems of dryland area in northwest China. BP neural network model and network training is applied in evaluation index generated by sequence of random technology and evaluation of their own level of value. After the network training, different evaluation of farming systems are input. By calculating, we can get the evaluation of grade value of farming system priority. The results show that: the farming system priority of dryland farming area in Northwest China is a complex farming system of animal food fruit >cotton (oil) rotation farming system > farming system of industry characteristics(apple)-type > drought water-saving farming system > small grains, grass-animal based farming system > two grains and a pasture farming system > farming system of grain and oil beans grass fertilizer. As long as given values of the corresponding evaluation indexes, by the calculation of BP neural network model, the grade value of evaluation of farming system priority can be directly got. This model can be used for the evaluation of farming system priority. |