Geo-environment-aware adversarial transfer learning method for landslide susceptibility evaluation of complex mountainous areas

Landslide susceptibility evaluation (LSE) is a critical issue for disaster prevention. Limited by labor cost and observation technology, landslide samples are extremely limited in dense vegetation-covered and remote areas, making the common supervised learning model underfit with limited samples. Therefore, the reliability of analysis results in mountainous areas is low. Transfer learning can achieve reliable assessment without the need for representative samples. However, transfer learning suffers from environmental heterogeneity in regional LSE and may transfer incorrect classification knowledge of landslide features from dissimilar environments. Aiming at these challenges, we proposed a geo-environment-aware LSE method based on unsupervised adversarial transfer learning. The key is to consider the difference in landslide features in different geo-environments. The study areas were first divided into multiple sub-environments, and the similarity between the sub-environments was calculated. Then an environment-aware adversarial transfer model was built for fine-grained aligning of the landslide feature with similar sub-environments and for reducing negative transfer between dissimilar environments. The fitted classification model was employed to predict the target regions and to generate the final LSE. The experimental results indicated that the proposed method achieves reliable LSE for sample-free regions. The accuracy of the proposed method is 7-12% better than commonly used methods such as support vector machines, random forests, and artificial neural networks. The performance of the proposed method is even close to the results of supervised learning with the presence of representative samples, and it also performs more globally and objectively in susceptibility mapping. These results reveal that the proposed method effectively transfers the knowledge of landslide susceptibility from other regions to the sample-free region.