Cocoa cultivation serves as a cornerstone of agricultural economies across the pan-tropical regions, supporting millions of livelihoods and contributing significantly to global cocoa production. However, accurately mapping cocoa farm locations remains a challenging endeavor due to the complex and heterogeneous nature of tropical landscapes. Traditional mapping techniques often fall short in capturing the intricate spatial patterns of cocoa farming amidst dense vegetation, varying land cover types, farming practices and growing stages. In addition, the current mapping efforts only focus on two major producing countries (Ivory Coast, Ghana). Thus, little information on location of farms in other cocoa producing regions. To address this challenge, our research aims to employ deep learning methodologies to unveil the locations of cocoa farms across the pan-tropics. By leveraging the rich spatiotemporal information provided by Sentinel-1 and Sentinel-2 satellite data, complemented by location encodings, Robert and his team aim to develop a robust and accurate mapping framework. Through this research effort, Robert and his team aspire to provide valuable insights into cocoa farm locations, facilitating sustainable cocoa production practices, land management strategies, and conservation efforts across the pan-tropical forests. Their findings hold significant implications for cocoa farmers, agricultural policymakers, and environmental stakeholders, paving the way for informed decision-making and targeted interventions to support the resilience and sustainability and traceability of cocoa farming systems worldwide.