Simulating Coastal Land Losses and Gains by Integrating Neighborhood Effects and Deep Learning with Cellular Automata

Dynamic land cover changes in coastal zones, e.g., land losses and gains, severely disrupt regional ecosystem balance and affect coastal human communities profoundly. There is an urgent need to precisely simulate future coastal land cover changes and identify areas prone to land loss or gain to inform coastal protection and restoration. Most previous studies do not consider the compounding effects of various driving factors and their neighborhood effects, leading to low simulation accuracy and limited knowledge about the mechanism of land cover change. To address this challenge, this study proposed a convolutional neural network (CNN) model to extract the high-dimensional features of landscape dynamic driving factors under different neighborhood scales. The Shapley Additive exPlanations (SHAP) method was applied to enhance the explainability of the CNN model by quantifying the relationship between land cover dynamics and potential driving variables. Two baseline algorithms (logistic regression and artificial neural network) were also adopted to verify the performance improvement of the CNN-CA model. We applied the three algorithms with the Cellular Automata (CA) to model and simulate land cover changes in coastal Louisiana from 2001 to 2019. The results show the CNN-CA with a 31*31 window size renders the highest accuracy (overall accuracy = 0.91, kappa coefficient = 0.87, and FoM = 0.32). The SHAP's result reveals that subsidence plays a vital role in land loss and land gain simulation. Besides, oil/gas well density is significant in predicting land loss, whereas elevation and distances to urban/roads significantly affect land creation. Finally, land cover change in coastal Louisiana was simulated based on the CNN-CA model and Markov chain, forecasting an area of 382.36 km2 land loss and 510.92 km2 land gain by 2037. This research offers a more applicable method for researchers and managers to investigate land change patterns in coastal regions.