Predicting coastal erosion susceptibility in Bangladesh under climate scenario via machine learning techniques

PLOS One | https://doi.org/10.1371/journal.pone.0334347 November 5, 2025 25 / 34 align with the work of [144], who documented faster coastline retreat in high sea-level rise scenarios. However, compared to the regional-scale estimates seen in previous work, the spatially explicit outputs of this analysis provide a more detailed view of risk distribution, increasing their usefulness for local adaptation planning. By combining machine learning, climate modeling, and geospatial analysis, this study creates a solid, data-driven framework for evaluating the danger of coastal erosion. The models are useful tools for predicting erosion under present and future conditions because of their excellent predictive ability and good spatial resolution. This hybrid methodology provides more generalizability and actionable insights for resilient coastal management and governance as compared to traditional approaches used in coastal Bangladesh. Although the modeling framework employed in this study is techni- cally transferable to other geographic locations, its predictability and interpretability will necessarily be region-dependent. Geomorphological variation including coral reefs, deltas, cliffs, and climatic regimes like monsoonal versus arid regimes, and land use necessitate extensive recalibration of the model using local input variables to yield significant and credi- ble results. Not only this but also the lack of real-time erosion monitoring could compromise temporal accuracy. Future

research should focus on the transfer and calibration of this framework across different geographic and climatic settings, employing local parameters, and also real-time monitoring to enhance model robustness, generalizability, and applicability across different coastal systems. Conclusion The security of Bangladesh’s shoreline is in danger because sea levels are rising faster, climate change is getting worse, and the land is becoming less stable. Using modern machine learning methods and 20 important meteorological, geo- graphical, hydrological, tropological, and land-use factors, this study looked at how Susceptibility the coast is to erosion. The main things that affect erosion risk are the normalized difference vegetation index (NDVI). To find areas that are likely to erode, different ensemble learning methods were used, such as bagging (Random Forest, Bagging, Decision Tree, Table 5. Coastal erosion Susceptibility zones distribution among districts in the Coastal region by the best model (XGBoost). Low Moderate High Percentage Area Percentage Area Percentage Area Bagerhat 10.30% 407.78 87.14% 3449.70 2.56% 101.52 Barguna 0.48% 8.72 91.45% 1674.38 8.08% 147.90 Barisal 21.83% 607.85 74.98% 2088.11 3.20% 89.04 Bhola 2.02% 68.70 78.58% 2673.93 19.41% 660.37 Chandpur 13.14% 232.67 85.94% 1397.33 0.91% 15.00 Chittagong 0.83% 43.72 88.40% 4669.95 10.78% 569.33 Cox’s Bazar 0.24% 5.88 73.57% 1833.26 26.20% 652.86 Feni 0.10% 0.98 90.13% 892.26 9.77% 96.76 Gopalganj 52.71% 774.35 47.17% 692.89 0.12% 1.76

Jashore 86.94% 2266.41 12.96% 337.94 0.10% 2.64 Jhalokati 20.27% 143.29 77.91% 550.85 1.82% 12.85 Khulna 18.92% 831.52 78.68% 3457.38 2.39% 105.11 Lakshmipur 4.52% 65.06 85.83% 1235.99 9.65% 138.94 Narail 71.24% 689.62 28.67% 277.49 0.09% 0.88 Noakhali 0.46% 16.98 82.60% 3044.53 16.94% 624.49 Patuakhali 0.60% 19.24 77.93% 2510.19 21.47% 691.57 Pirojpur 16.54% 211.44 80.86% 1033.41 2.59% 33.15 Satkhira 21.43% 817.90 74.74% 2852.90 3.83% 146.20 Shariatpur 46.78% 549.22 52.60% 617.56 0.61% 7.22 https://doi.org/10.1371/journal.pone.0334347.t005