There is a rapidly growing awareness of the influence of global change processes such as land-use, climate change and socioeconomic factors on the burden of mosquito-borne disease (MBD). Although individual effects of different processes on MBD risk have been studied widely, a holistic approach that considers the combined influence of different global change processes has rarely been implemented. Here, I evaluate the effects of different global change processes on MBD risk, both generally, and in a series of modelling studies using the understudied MBD, Japanese encephalitis (JE) as a case study. I integrate different data types and approaches from ecology and epidemiology, with the aim of informing public health decision-makers in the era of accelerating global change. Firstly, I synthesise current knowledge on relative and interacting effects of global change processes on MBD risk and examine how these factors have been incorporated into existing analyses, highlighting how future research could be improved. Secondly, I compile a vector surveillance database for the predominant vector of JE (Culex tritaeniorhynchus). I use a novel approach that leverages information from sparse vector surveillance data to predict seasonal vector abundance over large spatial scales, that has the potential to be used to provide guidance for the targeting of suitable interventions. I use this information in an epidemiological study of JE case surveillance data and show that human JE incidence is associated with climate, land-use and socioeconomic factors, and these factors can be used to predict JE outbreaks in north-eastern India. Thirdly, I examine possible trends in JE epidemiology by projecting into the future under various scenarios of global change to show divergence in JE risk and burden under different socioeconomic and environmental policy scenarios. Finally, I integrate the implications of these results into our understanding of the effects of global change processes on MBD, the epidemiology and control of JE, and a holistic approach to the understanding and prediction of MBD risk.