Multi-temporal satellite imagery provides critical insights into mangrove cover dynamics and supports coastal management. This study examined changes in mangrove cover (1990–2023) and mid-century projections across six Indonesian regions: Pariaman (West Sumatra) and Indramayu, Brebes, Pemalang, Surabaya, and Madura Island (Northern Java). Landsat and Sentinel-2 imagery were processed using Google Earth Engine (GEE) to derive historical mangrove maps. Future projections were generated using a cellular automata–artificial neural network (CA–ANN) approach implemented in the MOLUSCE plugin for five sites, while mangrove dynamics on Madura Island were projected using a Random Forest (RF) probability-based model in GEE. Results show clear spatial and temporal variability in mangrove cover. Mangrove cover declined slightly in Pariaman (–1.77 ha; − 0.006 ha yr⁻¹) but may increase by 2055 (+ 0.002 ha yr⁻¹). Indramayu experienced a net gain of 23.32 ha (+ 0.017 ha yr⁻¹) but is projected to lose 6.63 ha (–0.006 ha yr⁻¹). Brebes expanded substantially by 627.86 ha (+ 0.022 ha yr⁻¹) and is expected to remain stable, whereas Pemalang showed only minor historical gain (+ 1.16 ha) yet could decline by 54.8 ha (–0.042 ha yr⁻¹). Surabaya increased by 829.09 ha (+ 0.022 ha yr⁻¹) but may lose 113.35 ha by 2052 (–0.003 ha yr⁻¹). Madura recorded the largest gain (+ 2,209.73 ha; +0.024 ha yr⁻¹) with a slight projected decline (–0.001 ha yr⁻¹). These projections are scenario-based representations of likely directional change and should not be interpreted as deterministic forecasts.
No takes yet. Share an insight, caveat, or question.
Rahim et al. (2026) studied this question.
Synapse has enriched 2 closely related papers on similar clinical questions. Consider them for comparative context: