Machine Learning-Based Wetland Vulnerability Assessment in the Sindh Province Ramsar Site Using Remote Sensing Data

Abstract

Wetlands provide vital ecological and socioeconomic services but face escalating pressures worldwide. This study undertakes an integrated spatiotemporal assessment of the multifaceted vulnerabilities shaping Khinjhir Lake, an ecologically significant wetland ecosystem in Pakistan, using advanced geospatial and machine learning techniques. Multi-temporal optical remote sensing data from 2000 to 2020 was analyzed through spectral water indices, land cover classification, change detection and risk mapping to examine moisture variability, land cover modifications, area changes and proximity-based threats over two decades. The random forest algorithm attained the highest accuracy (89.5%) for land cover classification based on rigorous k-fold cross-validation, with a training accuracy of 91.2% and a testing accuracy of 87.3%. This demonstrates the model’s effectiveness and robustness for wetland vulnerability modeling in the study area, showing 11% shrinkage in open water bodies since 2000. Inventory risk zoning revealed 30% of present-day wetland areas under moderate to high vulnerability. The cellular automata–Markov (CA–Markov) model predicted continued long-term declines driven by swelling anthropogenic pressures like the 29 million population growth surrounding Khinjhir Lake. The research demonstrates the effectiveness of integrating satellite data analytics, machine learning algorithms and spatial modeling to generate actionable insights into wetland vulnerability to guide conservation planning. The findings provide a robust baseline to inform policies aimed at ensuring the health and sustainable management and conservation of Khinjhir Lake wetlands in the face of escalating human and climatic pressures that threaten the ecological health and functioning of these vital ecosystems.

Land Cover Dynamics in the Northwestern Virunga Landscape: An Analysis of the Past Two Decades in a Dynamic Economic and Security Context

“…The random forest classification algorithm was chosen for its robustness and high classification accuracy compared to other classification methods, such as maximum likelihood [20]. Random forest classification operates through multiple decision trees during classification training to offer a final result based on several decision trees [10]. Google Earth's high-resolution images are considered suitable as reference data [15,16].…”

“…The development of remote sensing has facilitated the monitoring of land use at the local, national, and global scales. Remote sensing is used to monitor various types of land cover and use, including forest, savannah, wetland, agricultural areas, and urbanized regions [9][10][11]. Particularly in the context of armed conflict, when data are often scarce, remote sensing is a powerful tool for monitoring land cover and land use, enabling the anticipation of post-conflict management strategies [12,13].…”