Rapid agriculture-driven deforestation poses significant challenges to achieving global climate and biodiversity targets. Establishing clear linkages between deforestation and food production is essential for guiding the development, implementation, and evaluation of forest conservation and climate change mitigation efforts. However, the limited scope and comprehensiveness of available datasets hinder the effectiveness of these initiatives. To address this gap, we developed the Deforestation Driver and Carbon Emission (DeDuCE) model, a global modeling framework that integrates the best available spatial and statistical datasets to enhance the quantification of deforestation driven by agricultural and forestry commodities. The model processes terabytes of high-resolution spatial data (e.g., crop commodities, tree cover loss, land use) alongside statistical datasets to attribute deforestation to specific commodities. DeDuCE is implemented using Python’s open-source programming ecosystem, ensuring compliance with FAIR data principles to promote accessibility, integrity, and transparency (see model code: GitHub repository). However, its computational demands are substantial. To efficiently process deforestation-emission accounting, the model requires multitasking with 30–50 parallel processing tasks, each running for 5–10 hours. Given these requirements, access to high-performance computing (HPC) resources is essential to enhance our computational capacity and storage capabilities. These resources will enable more efficient execution of our model, allowing us to process larger datasets, improve model resolution, and generate timely insights to support ongoing global efforts to curb deforestation. We seek HPC infrastructure support to ensure the scalability and robustness of DeDuCE (i.e., integrating new and emerging dataset as soon as they become available to improve deforestation estimates), ultimately strengthening its contribution to science-based decision-making for forest conservation and climate action.