Figure - available from: Frontiers in Environmental Science
This content is subject to copyright.
Source publication
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 2...
Similar publications
![Accuracies obtained by different researchers [20, 26, 39, 80]](publication/369622899/figure/fig3/AS:11431281189274863@1695001922057/Accuracies-obtained-by-different-researchers-20-26-39-80_Q320.jpg)
The prediction of incompetent rock masses susceptible to tunnel wall collapse is a common concern in any construction project using a tunnel boring machine (TBM). In China, to identify these weak locations, field geological surveys are traditionally conducted in accordance with the rock mass rating system specified by the national classification st...
Citations
... There was a strong correlation between Bio3 and Bio4, and Bio4 was retained for model construction due to its significant contribution to predicting the potential habitats of snails [41]. For socioeconomic factors, DP, which demonstrates a powerful predictive capability for the distribution of snails [42], was correlated with GDP, and hence DP was retained as a predictive variable. Finally, 16 variables were employed in the model development process, including 10 climatic variables (Bio2, Bio4, Bio7, Bio9, Bio14, Bio15, Bio19, AR, AAP, and IM), three geographical variables (slope, NDVI, and DST), and three socioeconomic variables (HFP, DP, and NLI) ( Table 1). ...
... In this study, we employed eight presence/absence-based machine learning models, and the RF model showed the best predictability. Similarly, in previous studies on the distribution of snails, the RF model outperformed other models based on AUC evaluation metrics [39,42]. The RF model is an ensemble learning method based on the automatic combination of a set of tree-like predictors and is able to resist overfitting its training set to a certain extent [45]. ...
Background
Oncomelania hupensis is the sole intermediate host of Schistosoma japonicum. Its emergence and recurrence pose a constant challenge to the elimination of schistosomiasis in China. It is important to accurately predict the snail distribution for schistosomiasis prevention and control.
Methods
Data describing the distribution of O. hupensis in 2016 was obtained from the Yunnan Institute of Endemic Disease Control and Prevention. Eight machine learning algorithms, including eXtreme Gradient Boosting (XGB), support vector machine (SVM), random forest (RF), generalized boosting model (GBM), neural network (NN), classification and regression trees (CART), k-nearest neighbors (KNN), and generalized additive model (GAM), were employed to explore the impacts of climatic, geographical, and socioeconomic variables on the distribution of suitable areas for O. hupensis. Predictions of the distribution of suitable areas for O. hupensis were made for various periods (2030s, 2050s, and 2070s) under different climate scenarios (SSP126, SSP245, SSP370, and SSP585).
Results
The RF model exhibited the best performance (AUC: 0.991, sensitivity: 0.982, specificity: 0.995, kappa: 0.942) and the CART model performed the worst (AUC: 0.884, sensitivity: 0.922, specificity: 0.943, kappa: 0.829). Based on the RF model, the top six important variables were as follows: Bio15 (precipitation seasonality) (33.6%), average annual precipitation (25.2%), Bio2 (mean diurnal temperature range) (21.7%), Bio19 (precipitation of the coldest quarter) (14.5%), population density (13.5%), and night light index (11.1%). The results demonstrated that the overall suitable habitats for O. hupensis were predominantly distributed in the schistosomiasis-endemic areas located in northwestern Yunnan Province under the current climate situation and were predicted to expand north- and westward due to climate change.
Conclusions
This study showed that the prediction of the current distribution of O. hupensis corresponded well with the actual records. Furthermore, our study provided compelling evidence that the geographical distribution of snails was projected to expand toward the north and west of Yunnan Province in the coming decades, indicating that the distribution of snails is driven by climate factors. Our findings will be of great significance for formulating effective strategies for snail control.
Graphical Abstract
... Shi [44] developed a niche model using machine learning algorithms to predict the probability of suitable snail habitats for the S. japonicum vector Oncomelania hupensis in China. 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%). ...
... An example of a coupled e-flow-habitat model for use in hydraulic schistosomiasis control could combine the ecological niche model as described by Shi [44], with a new model for predicting the terminal settling velocity and drag coefficient of Oncomelania [62]. That model could then be integrated with observations from the PBCM and current e-flow studies and habitat models [63,64,65]. ...
In 1971, scientists from Mahidol University in Thailand and the Smithsonian Institution in the USA formed a research team to study a new species of Schistosoma in the Mekong River in Thailand and Laos. The studies, completed during 1971–1973, prior to the construction of any dams or restrictions to the natural flow regime of the Mekong River, provide a unique description of the natural ecological state of the river that can serve as a baseline for current research. The natural transmission of Schistosoma japonicum , Mekong Strain, was first reported on Khong Island, Laos in 1973 using sentinel mice. The first detailed description of the habitat ecology of the snail vector Neotricula aperta was done on-site in 1971 simultaneously with that research and is unique in providing the only description of the river shoreline habitat before any dams were built and any alteration of the natural flow regime was in place. Aggregating current information in a Place-Based Conceptual Model (PBCM) as an organizing template, along with current habitat models that combine ecological data with e-flows, can be developed and used as a tool to predict suitable habitats for snails. The natural flow regime of the Mekong River prior to any impoundments is described with current updates on the potential impacts of climate change and dams with flow-related snail habitat characteristics, including sediment drift and water quality. The application of the PBCM to describe and compare descriptive information on current and potential future N . aperta/S . mekongi habitat is discussed.
... Transmission of schistosomiasis is associated with variations in climate environments, and climate changes will affect the spatial distribution and transmission intensity of infection [14]. Transmission is also indirectly affected by population movement and socioeconomic development. ...
Schistosomiasis caused by Schistosoma japonicum is one of the major neglected tropical diseases worldwide. The snail Oncomelania hupensis is the only intermediate host of S. japonicum, which is recognized as an indicator of the schistosomias occurrence. In order to evaluate the risk of schistosomiasis in China, this work investigate the potential geographical distribution of host snail habitus by developing an ensemble ecological niche model with reference to the suitable environmental factors. The historical records of snail habitus were collected form the national schistosomiasis surveillance program from the year of 2005 to 2014. A total of 25 environmental factors in terms of the climate, geographic, and socioeconomic determinants of snail habitats were collected and geographically coded with reference to the snail data. Based on the correlations among snail habitats and the geographically associated environmental factors, an ensemble ecological niche model was developed by integrating ten standard models, aiming for improving the predictive accuracy. Three indexes are used for model performance evaluation, including receiver operating characteristic curves, kappa statistics, and true skill statistics. The model was used for mapping the risk of schistosomiasis in the middle and lower reaches of the Yangtze River. The results have shown that the predicted risk areas were classified into low risk (4.55%), medium risk (2.01%), and high risk areas (4.40%), accounting for 10.96% of the land area of China. This study demonstrated that the developed ensemble ecological niche models was an effective tool for evaluating the risk of schistosomiasis, particularly for the endemic regions, which were not covered by the national schistosomiasis control program.
