Leishmaniasis, a climate-sensitive zoonotic neglected tropical disease, is transmitted by Phlebotomine sand flies and closely linked to socio-economic inequities. Understanding its spatio-temporal dynamics under environmental and social change is critical for effective control. A machine learning framework (XGBoost) was developed to map the global and European distribution of leishmaniasis, incorporating climatic indicators, land cover, elevation, and socio-economic indices (Human Development Index, AROPE). For Europe, five proven vector species (Phlebotomus perniciosus, P. ariasi, P. perfiliewi, P. neglectus, and P. tobbi) were modelled alongside cutaneous and visceral leishmaniasis. Across both analyses, land use features, particularly shrubland and forest cover, had the greatest explanatory power, reflecting their role in providing microclimates and vertebrate hosts for sand flies. Climatic factors, notably mean temperature of the coldest quarter and humidity of the warmest/driest quarters, were also influential, as these facilitate sand fly survival. Socio-economic predictors consistently improved model performance, confirming the role of poverty and inequity as determinants of disease distribution. Globally, leishmaniasis risk increased by ~17% since the 1990s, with Africa, Asia, and the Americas experiencing the greatest rise. In Europe, modest continental-scale increases (CL +1.28%; VL +2.47%) masked strong sub-national heterogeneity, including northward expansion of visceral leishmaniasis and increases in cutaneous leishmaniasis in southern and eastern regions. Sand fly projections indicated expansion of warm-adapted species (P. ariasi, P. perniciosus, P. neglectus) and contraction of species preferring cooler, more humid niches (P. perfiliewi, P. tobbi). These findings highlight climate change, land use, and inequity as interacting drivers of leishmaniasis, emphasising the need for enhanced surveillance, integrated vector management, and targeted support for vulnerable populations, including refugees and migrants.