Agricultural suitability modeled using water and bioclimatic variables for climate change

Keywords: Suitability; sustainability; climate; water; specialty crop; machine-learning
Session Type: Virtual Paper Abstract
Day: Friday
Session Start / End Time: 2/25/2022 11:20 AM (Eastern Time (US & Canada)) - 2/25/2022 12:40 PM (Eastern Time (US & Canada))
Room: Virtual 38

Abstract

California’s agricultural production is always improving the crop choice and technology to enhance yield and efficiency of resources. In the last ten years, specialty crops grew by more than 20% in area to 3 million acres in 2018, and almost doubled in revenue to $21.7 billion in 2018. However, California’s agriculture is facing a crucial challenge in water management. Crops demand for water tends to increase with hotter, drier years. These conditions are expected to be more frequent in California due to climate change. The goal of this research is to estimate current and future agricultural suitability using machine-learning for the selected specialty crops in California. The Dynamic Water Surface Extent (DSWE) method supplies long-term, high-temporal resolution data on surface water. The contribution will be in both the use of new datasets, such as the DSWE, and the use of CMIP6 global circulation models climate data. The main method of estimation is the species distribution model using machine-learning algorithm such as maxent and random forest. Preliminary results using CMIP6 GCMs downscaled bioclimatic variables estimate severe loss of agricultural suitability (>95% area reduction) for almonds, walnuts, and strawberries, severe loss of suitable area for grapes and citrus, and gain of suitability area for pistachio production. Understanding the relationship between surface water and specialty crop is a necessary step to improve our ability to inform future pathways for agriculture adaptation to climate change.