Ecological niche modeling based on ensemble algorithms to predicting current and future potential distribution of African swine fever virus in China

Abstract

African swine fever (ASF) is a tick-borne infectious disease initially described in Shenyang province China in 2018 but is now currently present nationwide. ASF has high infectivity and mortality rates, which often results in transportation and trade bans, and high expenses to prevent and control the, hence causing huge economic losses and a huge negative impact on the Chinese pig farming industry. Ecological niche modeling has long been adopted in the epidemiology of infectious diseases, in particular vector-borne diseases. This study aimed to establish an ecological niche model combined with data from ASF incidence rates in China from August 2018 to December 2021 in order to predict areas for African swine fever virus (ASFV) distribution in China. The model was developed in R software using the biomod2 package and ensemble modeling techniques. Environmental and topographic variables included were mean diurnal range (°C), isothermality, mean temperature of wettest quarter (°C), precipitation seasonality (cv), mean precipitation of warmest quarter(mm), mean precipitation of coldest quarter (mm), normalized difference vegetation index, wind speed (m/s), solar radiation (kJ /day), and elevation/altitude (m). Contribution rates of the variables normalized difference vegetation index, mean temperature of wettest quarter, mean precipitation of coldest quarter, and mean precipitation of warmest quarter were, respectively, 47.61%, 28.85%, 10.85%, and 7.27% (according to CA), which accounted for over 80% of contribution rates related to variables. According to model prediction, most of areas revealed as suitable for ASF distribution are located in the southeast coast or central region of China, wherein environmental conditions are suitable for soft ticks' survival. In contrast, areas unsuitable for ASFV distribution in China are associated with arid climate and poor vegetation, which are less conducive to soft ticks' survival, hence to ASFV transmission. In addition, prediction spatial suitability for future ASFV distribution suggests narrower areas for ASFV spread. Thus, the ensemble model designed herein could be used to conceive more efficient prevention and control measure against ASF according to different geographical locations in China.

Figure 1

ASF occurrence point (The map is made by ArcGIS software and uses the WG-1984 coordinate system).

Figure 2

The disease-adaptive level of the ensemble model was expressed as the mean suitable. (The map is made by ArcGIS10.2 https://www.esri.com/ and R 4.1.3 software https://mirrors.bfsu.edu.cn/CRAN/).

Figure 3

The disease-adaptive level of the ensemble model was expressed as the committee averaging (The map is made by ArcGIS10.2 https://www.esri.com/ and R 4.1.3 software https://mirrors.bfsu.edu.cn/CRAN/).

Figure 4

The disease-adaptive level of the ensemble model was expressed as the weighted mean suitable (The map is made by ArcGIS10.2 https://www.esri.com/ and R 4.1.3 software https://mirrors.bfsu.edu.cn/CRAN/).

Figure 5

Model uncertainty was represented by clamping mask value. 1 (red) represents the uncertainty of the prediction model, 0.5 means that half of the model was certain and a half was uncertain, and 0 (blue) indicates that the model prediction was deterministic (The map is made by ArcGIS10.2 https://www.esri.com/ and R 4.1.3 software https://mirrors.bfsu.edu.cn/CRAN/).

Figure 6

The model predicts areas suitable for ASF from 2020 to 2040 (The map is made by ArcGIS10.2 https://www.esri.com/ and R 4.1.3 software https://mirrors.bfsu.edu.cn/CRAN/).

Figure 7

The model predicts areas suitable for ASF from 2040 to 2060 (The map is made by ArcGIS10.2 https://www.esri.com/ and R 4.1.3 software https://mirrors.bfsu.edu.cn/CRAN/).