Satellite yield estimation: how good is it, and what can we learn?
With today’s computing power and free satellite imagery, generating a crop yield map from satellite data is relatively easy. Knowing if that map is accurate or not, however, can be surprisingly difficult. Just how good are satellite yield maps? Are we justified in using them to assess agricultural trends or yield impacts of management practices at field and sub-field scales?
High-Resolution Soybean Yield Mapping
Soybean is the United States’ most lucrative agricultural export, driven by increasing demand for animal feeds associated with rising meat consumption around the world. With such an important agricultural commodity, understanding spatial and temporal patterns in yield is of widespread interest. Where ground-truth data on yields are not available, leveraging remote sensing and machine learning to accurately estimate farm yields can help provide these insights.
Is drought becoming more or less important for agriculture?
As the world continues to warm, many agricultural regions are seeing an increased frequency and severity of conditions that lead to drought. We know from decades of work that the ongoing climate trends are overwhelmingly negative for crops in many systems. In a recent study published in Nature Food, we look at the last two decades in the United States, and whether there is any evidence that new technologies have helped adapt to climate trends.
Mapping Crops with Smartphone Crowdsourcing, Satellite Imagery, and Deep Learning
Smallholder farms — holdings of less than 2 hectares — produce one-third of global food consumed, employ 2 billion people, and make up 84% of the world’s farms. Yet our collective knowledge of their food production remains limited: questions like what crop types smallholders are growing and where they grow them remain unanswered, making it hard to track yield progress, study farming practices, and design agricultural policies. The data gap exists because most smallholders are located in countries where the ability to conduct surveys — the traditional way of obtaining farm-level information — is still nascent or under development.