Lymphatic filariasis and onchocerciasis, two vector-borne macroparasitic diseases, together place over 1 billion people at risk for debilitating infections and represent significant causes of global morbidity, social stigmatization, and lost productivity. Large-scale control programs have resulted in impressive gains in human health after decades of targeted intervention efforts, but evidence is emerging that suggests that the prescribed standardized protocols may not be sufficiently flexible to achieve elimination everywhere. It is thus becoming clear that in order to design effective parasite management programs, there is a critical need to improve current understanding of how the complex and nonlinear characteristics of these biological systems influence transmission and elimination. However, due to the dynamic and complex nature of these diseases, empirical data alone may not be sufficient for answering these outstanding questions.In this dissertation, I aim to leverage advances in computational science and data-driven mathematical modelling approaches to discover new knowledge about transmission heterogeneities and the dynamics of disease control to ultimately guide LF and onchocerciasis elimination programs. First, a data-driven computational framework for discovering local transmission models and fill missing data gaps is developed and applied to investigate the extent and implications of ecological uncertainty and heterogeneity as it pertains to transmission and elimination. This framework is then used for modelling new and standard interventions to improve understanding of control dynamics and support policy design and decision-making. A multi-model ensemble is also developed for also addressing uncertainties in model structure and implementation. Throughout this work, key scientific and operational questions are addressed, aiming to facilitate the development of evidence-based programs to eliminate LF and onchocerciasis. A major theme underlying this work is the use of computational tools for scientific knowledge discovery, a topic which is explored in the final discussion of the dissertation.