A neural network model for classifying sustainable supervisors for Taiz's urban management optimization

The primary drivers of agricultural land depletion in Taiz be diagnosed quantitatively in this study, proposing for the first time a replicable conflict-sensitive urban management model. The overarching objective is to bridge the critical gap between sustainable urban expansion and the preservation of agro-ecological systems in fragile, data-scarce contexts. A combination of unplanned sprawl, crisis, and ineffective governance, Taiz City's rapid urbanization between 2000 and 2024 resulted in a 35% loss of agricultural land. This study proposes that governance reduces the primary causes of conflict escalation and the severity of sprawl. This study combines GIS spatial analysis (Landsat 8/9 and support vector machine classification), regression modeling, and global case comparisons (Medellín and Mumbai) to assess land-use trends. The findings indicate that governance diminishes the effects (β = −0.50, p < 0.01), sprawl (β = 0.85, p < 0.01), and conflict (β = 0.002, p < 0.05) explain 85% of the variance in losses. By 2024, 3.2 million residents' food security was at risk because of the urbanization of 60% of peri-urban fertile lands. Vertical expansion, tenure regularization and GIS planning will reclaim 20% of land by 2030.