1-2 of 2 results
-
Fusing Satellite and Drone Data with GIS to Create New Analytical Decision Support Tools for Varying Farm Types
PI Kevin Adkins
PI Nickolas Macchiarella
CO-I Ronny Schroeder
CO-I University of Michigan School for Environment and Sustainability (SEAS) and the Department of Ecology and Evolutionary Biology
The synergy between moderate resolution satellite imagery and fine resolution drone imagery, LiDAR data, and meteorological data, along with generally available GIS data, must be identified and optimized. These data will be integrated to produce a variety of products that help identify what tools, inputs, and management strategies most effectively contribute to an increase in the productivity and resilience of an important agricultural system to a major weather or climate related disturbance.
Satellite imagery has been used in agriculture for some time and the increasing implementation of drones into agriculture and agriculture science holds unique promise. However, the synergy between moderate resolution satellite imagery, fine resolution drone imagery, fine resolution LiDAR (Light Detection And Ranging) data, fine-resolution meteorological data, and generally available GIS (Geographic Information Systems) data must be identified and optimized. To be most useful, this fusion of data should help provide estimates in the health and yield of agriculture systems as well as insight into the microclimate and ecosystem variation within a farm site. These data will be integrated to produce a variety of fine-resolution maps that can be analyzed to identify what tools, inputs, and management strategies most effectively contribute to an increase in productivity, agroecological system health, and resiliency or restoration (typically in response to weather or climatic disturbance) of a given farming operation and site. This research will apply these data science methods and tools to varying farm types in Puerto Rico. We expect new insight into how the fusing of a multitude of data can be effectively integrated into an agriculture operation and, subsequently, determine which outputs are most valuable to the varied farm types, practices, and locations. This investigation will also provide critical information on the resistance and resilience of an important agricultural system to major weather or climate-related disturbances and, subsequently, inform management decisions related to climate change adaptation.Categories: Faculty-Staff
-
GUMP: General Urban Area Microclimate Predictions Tool
PI Kevin Adkins
CO-I Nickolas Macchiarella
CO-I National Aeronautics and Space Administration NASA
Hyperlocal weather predictions are often necessary in order to determine whether a particular sUAS route will be safe to fly. The General Urban area Microclimate Predictions tool (GUMP) seeks to provide such predictions through the use of machine learning (ML) models and computational fluid dynamics (CFD) simulations. The computed wind flow field is converted into an intuitive risk map for sUAS operators through the use of appropriate thresholds on wind velocities.
Adverse weather conditions, particularly, high winds, can have a highly adverse impact on small unmanned aircraft system (sUAS) operations. These conditions can vary significantly within a small area (particularly, in an urban environment); thus, hyperlocal weather predictions are often necessary in order to determine whether a particular sUAS route will be safe to fly. The General Urban area Microclimate Predictions tool (GUMP) seeks to provide such predictions through the use of machine learning (ML) models and computational fluid dynamics (CFD) simulations. Specifically, ML models are trained to ingest mesoscale forecasts from the National Oceanic and Atmospheric Administration (NOAA) and output refined forecasts for some specific location, typically, a weather station that serves as a source of ground truth data during training. At the same time, CFD simulations over 3D models of structures (e.g., buildings) are utilized to extend the refined forecast to other points within the area of interest surrounding the location. Because it is difficult to perform such simulations in real-time, they are executed offline under a wide range of boundary conditions, generating a broad set of resulting wind flow fields. During deployment, GUMP retrieves the wind flow field that is most consistent with the ML model’s forecast. The wind flow field can be converted into an intuitive risk map for sUAS operators through the use of appropriate thresholds on wind velocities. I addition to NASA, additional partners on this project are Intelligent Automation Inc. and AvMet.Categories: Faculty-Staff
1-2 of 2 results