The prediction of Aedes mosquito abundance using remote sensing and machine learning in Harris County, Texas
8 affiliations
- 1University of South Carolina Epidemiology and Biostatistics, 915 Greene Street, Columbia, SC 29208 USA
- 2Research Computing, University of South Carolina, 1430 Senate Street, Columbia, SC 29208 USA
- 3Mosquito and Vector Control Division, Harris County Public Health, Houston, TX USA
- 4Department of Biological Sciences, Florida International University, Miami, FL 33199 USA
- 5Biomolecular Sciences Institute, Florida International University, Miami, FL 33199 USA
- 6Department of Pediatric Tropical Medicine, Baylor College of Medicine, National School of Tropical Medicine, 1102 Bates Avenue, Houston, TX 77030 USA
- 7William T. Shearer Center for Human Immunobiology, Texas Children’s Hospital, Houston, TX 77030 USA
- 8Section of Epidemiology and Population Sciences, Department of Medicine, Baylor College of Medicine, 1 Baylor Plaza, Houston, TX 77030 USA
Abstract
Vector-borne diseases, particularly those transmitted by Aedes mosquitoes, remain a major public health challenge globally, with species like Aedes aegypti and Aedes albopictus as primary vectors of dengue, chikungunya, and Zika viruses. The management of these mosquitoes is complicated by their adaptability to urban environments and the resource limitations of mosquito control programs. This study presents a proof-of-concept approach to improve Aedes surveillance and control by integrating remote sensing data and machine learning techniques. We used Sentinel-2 satellite imagery and environmental data to predict Aedes abundance across Harris County, Texas, incorporating both weather and socioeconomic features into predictive models. Using XGBoost, a machine learning algorithm, we identified high-risk areas for mosquito abundance with increased accuracy over traditional methods. This study demonstrates the potential of combining remote sensing with machine learning for enhancing mosquito surveillance programs, offering an innovative new strategy to improve vector control and mitigate the spread of mosquito-borne diseases. Future research should explore broader geographic applications and additional environmental variables to further refine predictive models.
Supplementary Information: The online version contains supplementary material available at https://doi.org/10.1038/s41598-026-64249-6.
Related
- Biomechanical and movement-quality predictors of lower-limb load-related injury in collegiate athletes: a prospective cohort study using functional movement screening, wearable inertial sensing, and explainable machine learning
- Human Skin Permeability Prediction by Machine Learning for Transdermal Drug Delivery
- Machine learning-based prediction of clinical pregnancy in infertile women undergoing in vitro fertilization
- Explainable machine learning for preoperative prediction of acute kidney injury after intertrochanteric fracture surgery in older adults
- Mechanism-informed machine learning for interpretable drug release prediction and virtual formulation intervention in polymeric long-acting injectables
BibTeX
@article{li2026prediction,
title = {{The prediction of Aedes mosquito abundance using remote sensing and machine learning in Harris County, Texas}},
author = {Huixuan Li and Jun Zhou and Kyndall Dye-Braumuller and Max Vigilant and Matthew DeGennaro and Morgan H. Sekou and Abiodun O. Oluyomi and Melissa S. Nolan and Sarah M. Gunter},
journal = {Scientific Reports},
year = {2026},
month = jul,
doi = {10.1038/s41598-026-64249-6},
url = {https://doi.org/10.1038/s41598-026-64249-6},
note = {CC BY-NC-ND 4.0},
}
RIS
TY - JOUR
TI - The prediction of Aedes mosquito abundance using remote sensing and machine learning in Harris County, Texas
AU - Huixuan Li
AU - Jun Zhou
AU - Kyndall Dye-Braumuller
AU - Max Vigilant
AU - Matthew DeGennaro
AU - Morgan H. Sekou
AU - Abiodun O. Oluyomi
AU - Melissa S. Nolan
AU - Sarah M. Gunter
PY - 2026
DA - 2026/07/29
JO - Scientific Reports
DO - 10.1038/s41598-026-64249-6
UR - https://doi.org/10.1038/s41598-026-64249-6
AB - Vector-borne diseases, particularly those transmitted by Aedes mosquitoes, remain a major public health challenge globally, with species like Aedes aegypti and Aedes albopictus as primary vectors of dengue, chikungunya, and Zika viruses. The management of these mosquitoes is complicated by their adaptability to urban environments and the resource limitations of mosquito control programs. This study presents a proof-of-concept approach to improve Aedes surveillance and control by integrating remote sensing data and machine learning techniques. We used Sentinel-2 satellite imagery and environmental data to predict Aedes abundance across Harris County, Texas, incorporating both weather and socioeconomic features into predictive models. Using XGBoost, a machine learning algorithm, we identified high-risk areas for mosquito abundance with increased accuracy over traditional methods. This study demonstrates the potential of combining remote sensing with machine learning for enhancing mosquito surveillance programs, offering an innovative new strategy to improve vector control and mitigate the spread of mosquito-borne diseases. Future research should explore broader geographic applications and additional environmental variables to further refine predictive models. Supplementary Information: The online version contains supplementary material available at https://doi.org/10.1038/s41598-026-64249-6.
SN - 2045-2322
ER -