Cornell University improves predictive agriculture with satellite imagery

Scientists from Cornell University and their international partners have introduced a novel method that could significantly enhance crop yield predictions by using satellite images to measure solar-induced chlorophyll fluorescence (SIF). According to their study published in Environmental Research Letters, this technique provides a cost-effective and rapid assessment tool, particularly beneficial for regions with limited data resources.

The study highlights the potential of satellite technology in addressing agricultural challenges exacerbated by climate change. Over the past four decades, a temperature increase of just 1 degree Celsius has led to a 66% decrease in net farm income, underscoring the urgent need for innovative solutions to mitigate climate impacts on agriculture.

Traditional methods for predicting crop yields often require extensive data that is not readily available in many parts of the world, especially in developing countries where food security is a critical issue. The Cornell team’s approach leverages SIF data to model photosynthesis, a key determinant of crop yield. While this method does not directly count the crops, it provides crucial insights into the photosynthetic activity of plants, which is directly linked to their productivity.

“The mechanism of using chlorophyll fluorescence is a significant step forward in our ability to predict agricultural outputs without relying on extensive historical data,” explained Ying Sun, Associate Professor of Soil and Crop Sciences at Cornell and co-author of the study. “This could be a game-changer for agricultural policy planning, crop insurance, and even poverty forecasting in rural areas dependent on farming.”

Chris Barrett, a co-author and Professor of Applied Economics and Management at Cornell, emphasized the practical applications of this research in policy-making and resource allocation. He pointed out the advantages of this approach in rapidly changing rural economies where traditional data collection methods are often impractical.

The research team, including scientists from the U.S., Israel, and India, is optimistic about the broader implications of their findings. They are exploring ways to refine the model for real-time applications, allowing farmers to make timely adjustments to enhance crop health and yield based on current conditions.

Source: Phys.org