From pixels to objects: Integrated indicators for balancing sustainable management in protected areas

Abstract

Balancing human activities with environmental protection is a critical challenge in managing Protected Areas (PAs). Spatial zoning serves as the cornerstone of PA management and plays a crucial role in harmonizing conservation with development. This study introduces an integrated land-use management strategy that supports conservation, rehabilitation, tourism, and multilateral objectives. The approach combines pixel-based optimization with AI-enhanced object-based evaluation. Using GIS, we compiled and mapped a comprehensive set of biological, physical, infrastructural, and socio-economic criteria. Two pixel-based methods, Weighted Linear Combination (WLC) and Ordered Weighted Averaging (OWA), were applied to assess land-use suitability. A decision space was established using the Multi-Objective Land Allocation (MOLA) method. Object-based land allocation was subsequently performed using a suite of artificial intelligence models, including Boosted Regression Trees (BRT), Artificial Neural Networks (ANN), Classification and Regression Trees (CART), eXtreme Gradient Boosting (XGBoost), and Random Forest (RF). The results showed that the OWA method outperformed WLC in land suitability analysis. When integrated into the object-based approach, the RF model demonstrated the highest allocation performance, followed by ANN. Notably, RF and MOLA models showed the highest spatial agreement. This integrative framework underscores the potential of combining advanced AI-driven object-based methods with conventional pixel-based techniques to strengthen land management in PAs. The findings offer actionable insights for sustainable spatial planning in protected areas where land-use goals may be diverse and competing.