<![CDATA[Coastal wetlands have an important function, namely as an economic function and an ecological function, therefore the mapping and classification of wetlands is very important. However, remote sensing has limitations, namely high variability and spectral similarity between kleas. This makes the development of image fusion of SAR and optical images in classification, the combination of SAR and optical can provide better information. Over time, the CNN method of performing image fusion developed, which is a good method used to perform classification. In this study, Sentinel-2 fusion and VV polarization were used to identify the shrub classes that dominate Segara Anakan. The results of the application of CNN1D in the classification of wetlands in Segara Anakan resulted in an overall accuracy of 79.37% and a kappa of 0.76, so that CNN1D is very good at recognizing wetland classes but has limitations in recognizing Nypa which has spectral similarities with other classes. The benefit of using CNN1D that has been trained is that the model can be applied to a variety of other images. In its application, we used the image of Segara Anakan from 2019-2025 so as to gain knowledge, namely that Segara Anakan is controlled by the sedimentation process so that wetland classes increase dynamically. The massive sedimentation process in Segara Anakan was then overgrown by mangrove vegetation, besides that another trend is the change of vegetation from mangroves to nypa vegetation. This is because nypa vegetation is a vegetation that can adapt to medium to low salinity. Despite conducting a multitemporal study with a narrow gap of 6 years, the CNN1D that we have trained can classify wetlands in Segara Anakan well from 2019 to 2025. In addition, CNN1D with a light computing load can be an option if you need deep learning applications in other research.]]>
