An Innovative Framework Integrating PCA–MDS Soil Quality Index (SQI), AI and Machine Learning Prediction with Multi-Criteria Decision Analysis (MCDA) for Site-Specific Soil Management toward Sustainability in Coastal Agroecosystems

Soil quality is central to agricultural sustainability and food security, yet coastal agroecosystems are increasingly threatened by degradation from intensive practices and seawater intrusion. This study aimed to integrate soil chemistry, statistical modeling, machine learning, and decision analysis to assess and manage soil quality in the Skhirat coastal plain of Morocco. A total of 30 topsoil samples were collected and analyzed for chemical and nutrients properties. Spatial interpolation revealed strong coast–inland gradients where EC ranged from 0.47 to 6.3 dS/m with highest salinity in the southwestern fringe, while CEC (8.4–39.7 cmol/kg) and OM (0.54–2.81%) peaked inland. Principal Component Analysis (PCA) explained 65.9% of total variance, with salinity drivers (EC, Na, Cl) loading negatively against fertility indicators (OM, CEC, micronutrients), discriminant analysis (DA) classified soils with > 85% accuracy and redundancy Analysis (RDA) biplots highlighted antagonism between salinity and fertility axes. The PCA–MDS Soil Quality Index (SQI) integrated key indicators (pH, EC, CEC, P, Mn) and ranged from 0.084 to 0.897 (mean 0.614), classifying 33% of sites as low quality. Machine learning model Linear Regression achieved the best performance (R² = 0.907, RMSE = 0.048, MAE = 0.042), closely preserving observed rankings. MCDA using TOPSIS and PROMETHEE II prioritized coastal sites with indices up to 0.882, robust under weight sensitivity (Spearman ρ = 0.992). This integrated framework demonstrates that soil chemical monitoring, AI prediction, and MCDA can jointly deliver robust, site-specific management strategies for vulnerable coastal agroecosystems.