GLOBE Projects

GLOBE Side Navigation

Autonomous Mosquito Habitat Detection using Satellite Imagery and Convolutional Neural Networks for Disease Risk Mapping

Student(s):Sriram Elango and Nandini Ramachandran
Grade Level:Secondary School (grades 9-12, ages 14-18)
GLOBE Teacher:Cassie Soeffing
Contributors:Dr. Rusty Low, scientist, IGES Peder Nelson, scientist, OSU Dr. Erika Podest, scientist, NASA JPL Dr. Becky Boger, scientist
Report Type(s):International Virtual Science Symposium Report, Mission Mosquito Report
Protocols:Land Cover Classification, Mosquitoes
Presentation Video: View Video
Presentation Poster: View Document
Optional Badges:Be a Data Scientist, Make An Impact, Be a STEM Professional
Date Submitted:02/23/2022
Mosquitoes are known vectors for disease transmission that cause over one million deaths globally each year. The majority of natural mosquito habitats are areas containing standing water such as ponds, lakes, and marshes. These habitats are challenging to detect using conventional ground-based technology on a macro scale. Contemporary approaches, such as drones, UAVs, and other aerial imaging technology are costly when implemented. Multispectral imaging technology such as Lidar is most accurate on a finer spatial scale whereas the proposed convolutional neural network(CNN) approach can be applied for disease risk mapping and further guide preventative efforts on a more global scale. By assessing the performance of autonomous mosquito habitat detection technology, the transmission of mosquito borne diseases can be prevented in a cost-effective manner. This approach aims to identify the spatiotemporal distribution of mosquito habitats in extensive areas that are difficult to survey using ground-based technology by employing computer vision on satellite imagery for proof of concept. The research presents an evaluation and the results of 3 different CNN models to determine their accuracy of predicting large-scale mosquito habitats. For this approach, a dataset was constructed utilizing Google Earth satellite imagery containing a variety of geographical features in residential neighborhoods as well as cities across the world. Larger land cover variables such as ponds/lakes, inlets, and rivers were utilized to classify mosquito habitats while minute sites such as puddles, footprints, and additional human-produced mosquito habitats were omitted for higher accuracy on a larger scale. Using the dataset, multiple CNN networks were trained and evaluated for accuracy of habitat prediction. Utilizing a CNN-based approach on readily available satellite imagery is cost-effective and scalable, unlike most aerial imaging technology. Testing revealed that YOLOv4 obtained greater accuracy in mosquito habitat detection than YOLOR or YOLOv5 for identifying large-scale mosquito habitats. YOLOv4 is found to be a viable method for global mosquito habitat detection and surveillance.