This paper reviews the estimation methods of wetland carbon sinks and the factors influencing the wetland carbon cycle. Wetlands are crucial carbon sinks, playing a vital role in absorbing greenhouse gases and mitigating global warming. However, the carbon cycle in wetlands is complex, influenced by various factors such as climate, topography, water levels, vegetation types, and soil types. These factors interact with each other, making it challenging to accurately estimate wetland carbon sinks. The paper highlights the limitations of current measurement methods, including direct measurement, model estimation, and remote sensing, and discusses the advantages and disadvantages of each method. It also explores the potential of integrating machine learning into wetland carbon measurement to address the complexities and uncertainties in current methods. The paper emphasizes the importance of long-term monitoring and interdisciplinary cooperation to improve the accuracy and reliability of wetland carbon measurements. Finally, it suggests that machine learning can be a promising approach to enhance the estimation of wetland carbon sinks and improve wetland management.This paper reviews the estimation methods of wetland carbon sinks and the factors influencing the wetland carbon cycle. Wetlands are crucial carbon sinks, playing a vital role in absorbing greenhouse gases and mitigating global warming. However, the carbon cycle in wetlands is complex, influenced by various factors such as climate, topography, water levels, vegetation types, and soil types. These factors interact with each other, making it challenging to accurately estimate wetland carbon sinks. The paper highlights the limitations of current measurement methods, including direct measurement, model estimation, and remote sensing, and discusses the advantages and disadvantages of each method. It also explores the potential of integrating machine learning into wetland carbon measurement to address the complexities and uncertainties in current methods. The paper emphasizes the importance of long-term monitoring and interdisciplinary cooperation to improve the accuracy and reliability of wetland carbon measurements. Finally, it suggests that machine learning can be a promising approach to enhance the estimation of wetland carbon sinks and improve wetland management.