Mapping wetlands and monitoring spatiotemporal variabilities in wetland regions are useful for providing basic ecosystem-monitoring data that are necessary for the protection and management of wetlands. The main objective of this work was to propose a new approach for monitoring the spatiotemporal patterns and reclamation of coastal wetlands in the Liaohe Delta region from 1987 to 2017. With the proposed approach, we aimed to improve the classification accuracy by using integrated classification and a preferred features method. First, after preprocessing the remote sensing data representing the four years of 1987, 1997, 2007 and 2017, we extracted the first component of the principal component analysis (PCA1), normalized difference vegetation index (NDVI), modified normalized difference water index (MNDWI), soil index (SI), index-based build-up index (IBI), and tasseled cap transformation (TCT) values of the characteristic parameters, such as the brightness component, and then used the maximum likelihood classifier (MLC) and decision tree (DT) methods to classify the preprocessed image landscapes. Finally, we combined the results of the two classification methods with the optimal characteristic parameter band to form new data images and applied the MLC method to perform landscape classification. The analytical results showed that the proposed method can obtain a high average accuracy of 87.71% and a kappa coefficient of 0.85, reflecting a 16.50% higher average accuracy and a 20.72% higher kappa coefficient than the MLC results (average accuracy of 75.29% and kappa coefficient of 0.71). These results indicate that the proposed method is effective and feasible for long-term landscape dynamics research. By using this method, the landscape distributions of the Liaohe Delta wetlands in 4 periods were obtained. We found that although the area of reed wetlands in the Liaohe Delta region was reduced from 1987–1997 (from 1284.44 km² in 1987 to 1006.70 km² in 1997), the results were very good in the later periods, indicating optimized wetland protection (from 1040.20 km² in 2007 to 1275.53 km² in 2017). The coastal zone changed significantly throughout the study period, especially from 2007–2017; during this period, the coastline was significantly affected by human activities, and large areas of tidal flats and coastal suaeda were converted into salt pans and aquaculture areas, while ports, piers, and urban construction areas also continued to extend to the shallow-sea areas (resulting in the coastline land area increasing by 263.24 km²).

Wetland landscape classification is fundamental to monitoring changes in ecosystem patterns. This study proposes an ensemble classification approach that integrates Maximum Likelihood Classification (MLC) and Decision Tree (DT) methods with optimized feature selection for long-term wetland monitoring in the Liaohe Delta, China. Based on four periods of Landsat remote sensing images from 1987, 1997, 2007, and 2017, multi-dimensional features including PCA1, TCT, NDVI, and MNDWI were extracted to construct a hierarchical classification system comprising 13 landscape types. The results show that the integrated method achieved an overall classification accuracy of 87.71% and a Kappa coefficient of 0.85, improving by 16.50% and 19.72%, respectively, compared with the single MLC approach. The classification results reveal significant spatiotemporal variations in landscape patterns. Reed wetlands decreased from 1284.44 km² in 1987 to 1006.70 km² in 1997, followed by a recovery to 1275.53 km² in 2017. In contrast, Suaeda communities experienced severe degradation, declining sharply from 227.48 km² in 1987 to 30.52 km² in 2017. Meanwhile, the coastline advanced landward by 263.24 km², with the proportion of artificial shoreline increasing from 12.4% to 38.7%. The changes in wetland landscape types in the Liaohe Delta from 1987 to 2017 were mainly influenced by urbanization processes and ecological restoration policies. These findings indicate that the proposed method can effectively support long-term wetland landscape dynamics analysis and provide a useful reference for coastal wetland management.