Data science for sustainable global food systems

点击翻译按钮获取中文摘要

Transitioning to a sustainable global food system is a major challenge for the 21st century. We need to reduce existing hunger and malnutrition, while feeding an additional 2 billion people expected by 2050, at the same time as reducing agriculture's environmental footprint, and making agriculture more climate resilient. Many, competing, solutions have been proposed to address this challenge, and a contentious debate ranges between those in favor of increasing food production through sustainable intensification, and the use of precision agriculture and genetic engineering versus those favoring food sovereignty and agroecological production methods. I propose that a potential reason for this debate is because the conversations remain global and abstract, bereft of local contexts, and looking for panaceas. To overcome these issues, I propose to develop data and analytical tools to explore food system sustainability solutions that are context-dependent, system integrated, and embrace a diversity of options. I plan to do this by: 1) developing critical new global and regional agricultural land use data sets using previously developed data fusion methods: 2) using systematic reviews and meta-analyses to examine the effectiveness of alternate farming systems; 3) exploring locally-effective and context-dependent farming system interventions by further developing a purposely-built web-based tool, and 4) develop regional-scale scenario models to explore integrated food system solutions. Through this research, I hope to identify pathways toward sustainable and climate-resilient food systems that explicitly consider local and regional contexts, embrace a diversity of farming and food system solutions, and examine integrated solutions.