Recent advances in species distribution models (SDMs) associated with artificial intelligence (AI) and increased volumes of available data for model variables have allowed reliable evaluation of the potential distribution of any species. A reliable SDM requires suitable occurrence records and variables with optimal model structures. In this study, we developed three different machine learning-based SDMs [MaxEnt, random forest (RF), and multi-layer perceptron (MLP)] to predict the global potential distribution of two invasive ants under current and future climates. These SDMs showed that the potential distribution of Solenopsis invicta would be expanded by climatic change, whereas it would not significantly change for Anoplolepis gracilipes. The models were compared using model performance metrics, and the optimal model structure and spatial projection were selected. The MaxEnt exhibited high performance, while the MLP model exhibited low performance, with the largest variation by climate change. Random forest showed the smallest potential distribution area, but it was robust considering the number of occurrence records and changes in model variables. All the models showed reliable performance, but the difference in performance and projection size suggested that optimal model selection based on data availability, model variables, study objectives, or an ensemble approach was necessary to develop a comprehensive SDM to minimize modeling uncertainty. We expect that this study will help with the use of AI-based SDMs for the evaluation and risk assessment of invasive ant species.

This study evaluated the potential distribution of the potato tuber moth. This species severely impacts global potato production, especially in China and India, which have the world’s largest potato production. We developed two indices considering host plant availability and production in addition to climatic suitability, which was simulated using the CLIMEX model. Thus, three different indices were used to project potential distribution of the potato tuber moth under a climate change scenario: (1) climatic suitability (ecoclimatic index (EI)) (EI_M), (2) climatic suitability combined with host plant availability (EI_N1), and (3) climatic suitability combined with host plant production (EI_N2). Under the current climate, EI_M was high in southern India and central to southern China, while EI_N1 and EI_N2 were approximately 38% and 20% lower than EI_M, respectively. Under the Special Report on Emissions Scenario A1B, the potato tuber moth would probably not occur in India, but its distribution could be extended to the north, reaching N47°. The areas with the highest climatic suitability by potato tuber moth based on three indices were Sichuan and Karnataka in response to climate change. These areas require adequate pest control, such as prevention of spread through transport of potato seed or by using cold storage facilities.

The spongy moth (Lymantria dispar) is a forest pest that damages a variety of trees in North America and Eurasia. A spongy moth outbreak occurred in part of South Korea in 2020 and caused severe damage to domestic forests and human society. Since the occurrence of spongy moths is influenced by climatic factors, this study examines the causes of spongy moth outbreaks by analyzing the temporal and spatial differences in climatic factors, influencing spongy moth occurrence using specimens collected during field surveys. Climatic factors were identified using global occurrence coordinates to compare the weather characteristics of spongy moth occurrence in domestic regions, using the kernel density function. Spatial and temporal comparisons were performed for monthly weather factors obtained from field surveys in 2020 and 2021 in areas with high and low spongy moth larvae densities. Spongy moth outbreaks may result from particular combinations of variable seasonality in temperature and precipitation, including high temperatures during cold periods and low precipitation during developmental periods.

According to the concept of smart postharvest management, an information and communication technology sensor–based monitoring system is required in the juicing process to reduce losses and improve process efficiency. Such technologies are considered economically burdensome and technically challenging for small-scale enterprises to adopt. From this perspective, this study aimed to develop a smart monitoring system for the juicing processes in small-scale enterprises and to identify the optimal operating conditions based on the monitoring data. The system developed is equipped with two weight sensors attached to the twin-screw juice extractor, allowing for the automatic measurement of the weight of the raw material and the resulting juice product. The measured data are automatically transmitted and stored on a computer. Additionally, the system was designed to remotely control the speeds of the juicing and feeding screws, which are the primary controlling factors of the twin-screw juicer. Juice yield and processing time were optimized using carrots and pears. The optimal juicing and feeding speeds for pear yield were found to be 167.4 rpm and 1557 rpm, respectively; carrots achieved an optimal yield at a juicing speed of 502.2 rpm and feeding speed of 1211 rpm. In contrast, the processing time was minimized at juicing–feeding speeds of 6–6 and 7–5 for pears and carrots, respectively. Consequently, it was challenging to determine the optimal conditions for simultaneously optimizing the yield and processing time. This also suggests that the juicing process is affected by the properties of the fruits and vegetables being processed. By developing a system capable of accumulating the data necessary for the digitization of postharvest management and food processing, this research offers a valuable platform for the smart monitoring and optimization of the juicing process.