This study presents the results of mosquito surveillance monitoring in Chungnam Province from 2017 to 2020. A total of 130,750 mosquitoes were collected, and we analyze variations of mosquito populations with emphasis on the most abundant species. We also provide the field survey data based on the different habitats in Chungnam Province.

In the study, a variation of Haemaphysalis longicornis, a major vector of fever-causing conditions, was statistically analyzed to identify the spatial and climatic factors affecting the time-dependent variations of its population. The survey occurred in different habitats in South Korea. In addition, we developed a predictive model by using a probability function to find the peak occurrence time annually. As a result, the numbers of adults and nymphs were found to be related to temperature and relative humidity and their population peaked at the end of May in all habitats except deciduous forests. This study is expected to provide information on habitat types, times, and climate patterns that require attention to help control H. longicornis populations.

Pine Wilt Disease (PWD) is a disease causing mass deaths of pine trees in South Korea, and the dead trees serve as breeding grounds for insect vectors responsible for spreading the disease to other host trees. Because the PWD requires early monitoring to minimize its damage on domestic forestry, this study aims to develop a species distribution model for predicting the potential distribution of PWD by using artificial neural network (ANN) with time-series data. Among the architectures, the Convolutional Neural Network exhibited the highest performance, achieving a validation accuracy of 0.854 and a cross-entropy loss of 0.401, and the InceptionTime model emerged as the second-best performer. This study identified the best-performing ANN architecture for a spatiotemporal evaluation of PWD occurrence, emphasizing the importance for determining hyperparameters with ecological characteristics and data types to apply deep learning into SDMs.

A machine learning-based algorithms have used for constructing species distribution models (SDMs), but their performances depend on the selection of backgrounds. This study attempted to develop a noble method for selecting backgrounds in machine-learning SDMs. Two machine-learning based SDMs (MaxEnt, and Random Forest) were employed with an example species (Spodoptera litura), and different background selection methods (random sampling, biased sampling, and ensemble sampling by using CLIMEX) were tested with multiple performance metrics (TSS, Kappa, F1-score). As a result, the model with ensemble sampling predicted the widest occurrence areas with the highest performance, suggesting the potential application of the developed method for enhancing a machine-learning SDM.