Lima Metropolitana, the world’s second most arid megacity, has grown from ~577,000 inhabitants in 1945 to over 11 million by 2024. This rapid expansion has drastically reduced agricultural land and poses challenges for food security, poverty reduction, and sustainability.
This study integrates historical aerial photographs (1944–1984) with Landsat-based remote sensing (1984–2023) to map and quantify land transformations. Using Google Earth Engine, we preprocessed Landsat imagery (4–9) for cloud removal and spectral analysis. A Random Forest classifier, trained on annotated points for each LULC class, employed 150 decision trees, a minimum leaf population of 1, a bag fraction of 0.6, and a fixed seed. The model achieved ~95.3% accuracy, with most classes showing high precision (>0.93) and recall (>0.90).
Over eight decades, Lima lost 84% of its agricultural land (42,370 ha to 6,751 ha) while urban areas surged from 1,950 ha to 65,938 ha. Nearly half of this expansion took place on hillsides and barren lands, often inhabited by vulnerable communities. This decline in local agriculture increased reliance on external food sources, exacerbating insecurity and social inequalities. Between 2007 and 2017, the lowest socioeconomic strata grew from 344,472 to over 1.1 million (3.3-fold).
In response, community-led initiatives like “Ollas Comunes” (Community Soup Kitchens) have emerged as critical coping strategies, serving over 240,000 individuals daily, primarily from low-income households. These grassroots efforts underscore the urgent need for integrated urban planning that prioritizes social equity, food security, and environmental resilience.
By detailing the scale and implications of Lima’s land-use transformations, this research highlights the necessity of conserving remaining farmlands, promoting urban agriculture, and incorporating inclusive, community-driven solutions. Such measures are essential for forging a more equitable, sustainable, and food-secure future amidst ongoing urban growth and climatic constraints.