Due to climate change and the rise in international transportation, there is an emerging potential for outbreaks of mosquito-borne diseases such as malaria, dengue, and chikungunya. Consequently, the rapid detection of vector mosquito species, including those in the Aedes, Anopheles, and Culex genera, is crucial for effective vector control. Currently, mosquito population monitoring is manually conducted by experts, consuming significant time and labor, especially during peak seasons where it can take at least seven days. To address this challenge, we introduce an automated mosquito monitoring system designed for wild environments. Our method is threefold: It includes an imaging trap device for the automatic collection of mosquito data, the training of deep-learning models for mosquito identification, and an integrated management system to oversee multiple trap devices situated in various locations. Using the well-known Faster-RCNN detector with a ResNet50 backbone, we’ve achieved mAP (@IoU=0.50) of up to 81.63% in detecting Aedes albopictus, Anopheles spp., and Culex pipiens. As we continue our research, our goal is to gather more data from diverse regions. This not only aims to improve our model’s ability to detect different species but also to enhance environmental monitoring capabilities by incorporating gas sensors.

• Junyoung Park(Department of Life Sciences, Incheon National University, Convergence Research Center for Insect Vectors, Incheon National University)
• Dong In Kim(Department of Life Sciences, Incheon National University)
• Hyung Wook Kwon(Department of Life Sciences, Incheon National University, Convergence Research Center for Insect Vectors, Incheon National University, Insensory Incorporation, Incheon, Korea) Corresponding author