Remote sensing provides a new idea and an advanced method for lithology identification, but lithology identification by remote sensing is quite difficult because 1. the disciplines of lithology identification in a concrete region are often quite different from the experts' experience; 2. in the regions with flourishing vegetation, lithology information is poor, so it is very difficult to identify the lithologies by remote sensing images. At present, the studies on lithology identification by remote sensing are primarily conducted on the regions with low vegetation coverage and high rock bareness. And there is no mature method of lithology identification in the regions with flourishing vegetation. Traditional methods lacking in the mining and extraction of the various complicated lithology information from a remote sensing image, often need much manual intervention and possess poor intelligence and accuracy. An intelligent method proposed in this paper for lithology identification based on support vector machine (SVM) and adaptive cellular automata (ACA) is expected to solve the above problems. The method adopted Landsat-7 ETM+ images and 1: 50000 geological map as the data origins. It first derived the lithology identification factors on three aspects: 1. spectra, 2. texture and 3. vegetation cover. Second, it plied the remote sensing images with the geological map and established the SVM to obtain the transition rules according to the factor values of the samples. Finally, it established an ACA model to intelligently identify the lithologies according to the transition and neighborhood rules. In this paper an ACA model is proposed and compared with the traditional one. Results of 2 real-world examples show that: 1. The SVM-ACA method obtains a good result of lithology identification in the regions with flourishing vegetation; 2. it possesses high accuracies of lithology identification (with the overall accuracies of 92.29% and 85.54%, respectively, in the two typical regions of the Three Gorges) and is more accurate than the other six methods [such as the supervised methods of minimum distance, maximum likelihood, and parallelpiped, the intelligent methods of SVM and decision tree (DT), and the combined method of decision tree with cellular automata (CA) (DT-CA)]; 3. compared with the traditional CA, the ACA model needs less iteration times and possesses a faster convergent speed and a lower algorithm complexity. At present, there is still no report on applying CA into the area of lithology identification, and the results of the real-world examples verify the effectiveness of the SVM-ACA model, so the method proposed in this paper provides a new idea for the intelligent and accurate identification of lithology in the regions with flourishing vegetation. (C) 2011 Society of Photo-Optical Instrumentation Engineers (SPIE). [DOI: 10.1117/1.3598315]