The Need
Climate change disproportionately affects people in low-and middle-income contexts who have done the least to contribute to it. Yet often these communities do not have the information they need to make informed decisions about how to mitigate or prepare for climate change. Machine learning holds great promise to advance efforts across a variety of sectors to understand, mitigate, and adapt to climate change. However, particularly in low- and middle-income contexts globally, the effective use of machine learning is hampered by a lack of ground truth data accessible to all.
For example, global models of the impact of rising precipitation on malaria incidence are incorrect in some parts of the world because they are missing local data.
A lack of data about how extreme heat events are affecting human health is preventing policymakers from preparing their communities to respond to these events. AI and remote sensing could help map energy infrastructure needs and enable us to effectively deploy renewable energy globally, but many parts of the world that would benefit the most from such technologies do not currently have the data to power them.
Forests in many low- and middle-income contexts globally provide essential ecosystem services such as carbon sequestration but are vulnerable to deforestation due to agriculture, mining, logging, and urban development, contributing to global greenhouse gas emissions. ML with local ground truth data could help unlock the potential for forests to serve as natural climate solutions by improving deforestation estimates and targeting strategic afforestation efforts.
Lacuna Funding
Lacuna Fund supports dataset creation, aggregation, and maintenance for the training and evaluation of machine learning models by and for local communities most affected by climate change in three tracks:
- Understanding climate harms to health and livelihoods
- Improving energy systems and infrastructure for climate change mitigation and adaptation
- Exploring the relationship between climate change and forests
With a geographic focus on low- and middle-income countries in Africa, Asia, and Latin America, the calls put resources directly into the hands of actors in affected areas and ensure solutions are developed locally and centered on community needs and priorities.