Estimate how pollination service affect soybean yield in the Brazilian Cerrado using remote sensing and multidisciplinary approaches

Authors: Dong Luo*, , Marcellus M. Caldas, Kansas State University, Paulo De Marco Junior, Federal University of Goias
Topics: Human-Environment Geography, Remote Sensing, South America
Keywords: : ecological niche model, machine learning, WOFOST, remote sensing, soybean, Cerrado
Session Type: Paper
Day: 4/5/2019
Start / End Time: 9:55 AM / 11:35 AM
Room: Washington 6, Marriott, Exhibition Level
Presentation File: No File Uploaded

The balance between agriculture expansion and biodiversity conservation is a big challenge. Among the regions facing this challenge is the Brazilian Cerrado, a hotspots for biodiversity and a world breadbasket. Soybean as a main cultivated crop in this area has expanded for decades, and its yield strongly depends on the pollination provided by insects. Among these insects, bees are the most common ones with ~20% food production depending on them as pollinator. However, soybean expansion has been pointed out a threat to biodiversity. This paper sought to analyze soybean yield change associated with biodiversity. More specifically, we wanted to: 1) estimate soybean potential yield using satellite dataset and crop simulation model (WOFOST) for selected years (2002, 2007, and 2013); 2) develop a model to map patterns of bees occurrences combining ecological niche model (ENM) and machine learning technique; 3) examine how soybean yield was affected by bee’s occurrences. These findings will shed lights in the biodiversity conservation, and also improved the understanding of the process of interaction between land use response and biodiversity in Cerrado.

Abstract Information

This abstract is already part of a session. View the session here.

To access contact information login