Risk identification of mangroves facing Spartina alterniflora invasion using data-driven approaches with UAV and machine learning models

Abstract

The rapid and large-scale invasion of Spartina alterniflora has led to extensive biodiversity loss and the degradation of essential ecosystem services, particularly in mangroves. Recent studies have shown that the landscape pattern of mangroves is a key indicator of whether Spartina alterniflora can successfully invade. Therefore, assessing the risk of S. alterniflora invasion from the perspective of mangrove landscape patterns is crucial. This study utilizes drone imagery to extract the spatial distribution of mangroves and S. alterniflora in the Jiulong Estuary. Using an interpretable machine learning model, the relationship between mangrove landscape patterns and S. alterniflora coverage was studied at three plot sizes (10 m, 20 m, 30 m). The results show that: (1) The interpretable machine learning model constructed based on UAV (Unmanned Aerial Vehicle) big data can assess S. alterniflora coverage through mangrove landscape patterns. The validation set achieved good results with Adjusted R2 (>0.974), MAE (Mean Absolute Error) (<4.8), and RMSE (Root Mean Square Error) (<7) across the three plot sizes, though the SMAPE (Symmetric Mean Absolute Percentage Error) indicator was relatively poor (>20 %). (2) At all three plot sizes, mangrove coverage, mangrove tree height, average patch perimeter, patch density, landscape shape index, and edge density significantly impacted the suppression of S. alterniflora coverage by mangroves. However, the relative importance of these indicators changes with increasing spatial granularity. (3) The SHAP (SHapley Additive exPlanations) Value of the model revealed the nonlinear response of S. alterniflora coverage to changes in mangrove coverage: mangrove coverage inhibits S. alterniflora growth between 41 %–64 %, and completely suppresses it above 65 %. This study effectively assesses the extent of mangrove invasion by S. alterniflora and provides clear spatial evidence of the threshold for mangrove coverage to suppress S. alterniflora growth. It emphasizes that rationally regulating mangrove distribution through landscape indices will more effectively resist the invasion of S. alterniflora.