In the three last decades, continental Ecuador biosphere reserves (CEBRs) have undergone important land cover transformations because of human‐managed systems such as agriculture, livestock, forestry, and urbanization. Thus, the native landscape structure has been altered, exhibiting a mosaic of patches with varying sizes and shapes. The resulting landscape could shape some patterns over time, reflecting the complex interactions between human activities and biotic‐abiotic factors, such as soil, climate, and water availability. Quantifying the landscape patterns and their dynamics is essential for the monitoring and assessment of the ecological consequences of land‐cover change in time. Based on the soil maps and raster land‐cover maps from 1990 to 2016 of two CEBRs, the spatial deforestation patterns were quantified through lacunarity and multifractal analysis. To conduct these analyses, the deforested areas were identified and overlapped to predominant soil types. The results showed that the deforestation process pattern and soil types interact through complex relations due to specific site characteristics. Thereby, both soil and land cover interacted in fractal structures. The patch area distribution of deforestation patterns linked to soil types reveals a power‐law relationship in which, as the area of the deforested patches increased, their frequency decreased. Also, this relation presents self‐similarity and multifractal behaviour over a wide range of scales from 46–2,674 pixels, with a pixel size of 30 m × 30 m. However, each CEBR showed varying degrees of heterogeneity and complexity, which were reflected through lacunarity and multifractal parameters. The dynamics of deforestation patterns linked to soil types can be spatially dependent on the initial patchiness state, the distance to the adjacent patches, and the suitability of the soil for agrarian activities. Altogether, these were the spatial underlying factors of the deforestation evolution in the two CEBRs. Highlights Deforestation patterns show spatial self‐similarity Deforestation patterns are linked to soil types Landscape ecology, lacunarity, and multifractal analyses are useful to understand deforestation patterns Initial patch location, distance to the nearest neighbour and soil suitability boost the deforestation expansion