Analysis of coastline changes and influencing factors for the Macao Special Administrative Region based on Neural Network Algorithms

The Macao Special Administrative Region is located in the southeastern coastal area of China. The region of Macao was narrow in the history, so land reclamation has become a main means of expanding its geographical scope. Exploring the significance of land reclamation for the planning and urban construction of the Macao region provides valuable references. (1) The google earth engine (GEE) cloud processing platform is used in this study to calculate the modified normalized difference water index (MNDWI) based on Landsat data from 1986 to 2021; (2) the Jenks natural index classification method is used to extract the water body range, and the water body boundary as well as area at different periods is calculated combined with the neural network classification method in ENVI; (3) this study then combines the patch-generating land use simulation (PLUS) model to predict the future trend of shoreline changes in the study area in 2036. The result indicates that the MNDWI and neural net classification method lead to a high classification accuracy with both the overall accuracy (OA) and Kappa coefficient being higher than 87%. Land reclamation activities in Macao were gradually intense from 1986 to 2021, with social and economic conditions such as transportation being main influencing factors, which provides valuable references and inspiration for the regional planning of the Macao Special Administrative Region.