Abstract: An automatic recognition method for a dry quasi-stationary front in Kunming, Yunnan, China is provided. The automatic recognition method includes: reading data; calculating, by a differential method, a temperature lapse rate between each layer of each point from a ground surface to 650 hPa, and acquiring a maximum inversion trend value; acquiring an initially selected inversion distribution based on the maximum inversion trend value; removing a nighttime clear sky radiation inversion, retaining only a frontal inversion, and binarizing (0, 1); finding a boundary between inversion and non-inversion; removing the abnormal candidate frontal points, and acquiring frontal nodes; removing meso- and micro-scale systems; and performing one-dimensional Gaussian filtering on longitude data of the frontal nodes, and connecting the filtered frontal nodes to acquire a quasi-stationary front in Kunming, Yunnan, China.