Objective: This study aimed to predict the spatial and temporal distribution pattern of Oncomelania hupensis (O. hupensis) on a fine scale based on ecological niche models, so as to provide insights into O. hupensis surveillance.Methods: Geographic distribution and environmental variables of O. hupensis in Suzhou City were collected from 2016 to 2020. Five machine learning algorithms were used, including eXtreme gradient boosting (XGB), support vector machine (SVM), random forest (RF), generalized boosted (GBM), and C5.0 algorithms, to predict the distribution of O. hupensis and investigate the relative contribution of each environmental variable. The accuracy of the five ecological niche models was evaluated using the area under the receiver operating characteristic (ROC) curve (AUC) with ten-fold cross-validation.Results: Five models predicted that the potential distribution of O. hupensis was in southwestern areas of Wuzhong, Wujiang, Taichang, and Xiangcheng counties. The AUC of RF, XGB, GBM, SVM, and C5.0 algorithms were 0.8233, 0.8051, 0.7938, 0.7897, and 0.7282, respectively. Comparing the predictive results and the truth of O. hupensis distribution in 2021, XGB and GBM models were shown to be more effective. The six greatest contributors to predicting potential O. hupensis distribution included silt content (13.13%), clay content (10.21%), population density (8.16%), annual accumulated temperatures of ≥0°C (8.12%), night-time lights (7.67%), and average annual precipitation (7.23%).Conclusions: Environmental factors play a key role in the spatial and temporal distribution pattern of O. hupensis. The XGB and GBM machine learning algorithms are effective and highly accurate for fine-scale prediction of potential O. hupensis distribution, which provides insights into the surveillance of O. hupensis.

With global warming and socioeconomic developments, there is a tendency toward the emergence and spread of mountain-type zoonotic visceral leishmaniasis (MT-ZVL) in China. Timely identification of the transmission risk and spread of MT-ZVL is, therefore, of great significance for effectively interrupting the spread of MT-ZVL and eliminating the disease. In this study, 26 environmental variables—namely, climatic, geographical, and 2 socioeconomic indicators were collected from regions where MT-ZVL patients were detected during the period from 2019 to 2021, to create 10 ecological niche models. The performance of these ecological niche models was evaluated using the area under the receiver-operating characteristic curve (AUC) and true skill statistic (TSS), and ensemble models were created to predict the transmission risk of MT-ZVL in China. All ten ecological niche models were effective at predicting the transmission risk of MT-ZVL in China, and there were significant differences in the mean AUC (H = 33.311, p < 0.05) and TSS values among these ten models (H = 26.344, p < 0.05). The random forest, maximum entropy, generalized boosted, and multivariate adaptive regression splines showed high performance at predicting the transmission risk of MT-ZVL (AUC > 0.95, TSS > 0.85). Ensemble models predicted a transmission risk of MT-ZVL in the provinces of Shanxi, Shaanxi, Henan, Gansu, Sichuan, and Hebei, which was centered in Shanxi Province and presented high spatial clustering characteristics. Multiple ensemble ecological niche models created based on climatic and environmental variables are effective at predicting the transmission risk of MT-ZVL in China. This risk is centered in Shanxi Province and tends towards gradual radiation dispersion to surrounding regions. Our results provide insights into MT-ZVL surveillance in regions at high risk of MT-ZVL.