Abstract: This paper presents a new model called fuzzy-Markov chain model with weights to predict the future value of cultivated land demand in land use planning. The new model ameliorates the traditional time homogeneous finite Markov chain model by adopting fuzzy logic theory. The new model applies fuzzy sequential cluster method to set up the dissimilitude fuzzy clustering sections based on land use trend coefficients. Standardized self-correlative coefficients based on the special characteristics of correlation among the historical stochastic variables are regarded as weights. And the transition probabilities matrix of the new model is obtained by using the fuzzy logic theory and statistical analysis method. The experimental results show that the ameliorative model adopted fuzzy logical theory is more scientific and practical than the traditional predictive model.