Species distribution models: A comparison of statistical approaches for livestock and disease epidemics

Ecology and geography of Cache Valley virus assessed using ecological niche modeling

BACKGROUND

Cache Valley virus (CVV) is an understudied Orthobunyavirus with a high spillover transmission potential due to its wide geographical distribution and large number of associated hosts and vectors. Although CVV is known to be widely distributed throughout North America, no studies have explored its geography or employed computational methods to explore the mammal and mosquito species likely participating in the CVV sylvatic cycle.

METHODS

We used a literature review and online databases to compile locality data for CVV and its potential vectors and hosts. We linked location data points with climatic data via ecological niche modeling to estimate the geographical range of CVV and hotspots of transmission risk. We used background similarity tests to identify likely CVV mosquito vectors and mammal hosts to detect ecological signals from CVV sylvatic transmission.

RESULTS

CVV distribution maps revealed a widespread potential viral occurrence throughout North America. Ecological niche models identified areas with climate, vectors, and hosts suitable to maintain CVV transmission. Our background similarity tests identified Aedes vexans, Culiseta inornata, and Culex tarsalis as the most likely vectors and Odocoileus virginianus (white-tailed deer) as the most likely host sustaining sylvatic transmission.

CONCLUSIONS

CVV has a continental-level, widespread transmission potential. Large areas of North America have suitable climate, vectors, and hosts for CVV emergence, establishment, and spread. We identified geographical hotspots that have no confirmed CVV reports to date and, in view of CVV misdiagnosis or underreporting, can guide future surveillance to specific localities and species.

Using Machine Learning to make nanomaterials sustainable

Sustainable development is a key challenge for contemporary human societies; failure to achieve sustainability could threaten human survival. In this review article, we illustrate how Machine Learning (ML) could support more sustainable development, covering the basics of data gathering through each step of the Environmental Risk Assessment (ERA). The literature provides several examples showing how ML can be employed in most steps of a typical ERA.A key observation is that there are currently no clear guidance for using such autonomous technologies in ERAs or which standards/checks are required. Steering thus seems to be the most important task for supporting the use of ML in the ERA of nano- and smart-materials. Resources should be devoted to developing a strategy for implementing ML in ERA with a strong emphasis on data foundations, methodologies, and the related sensitivities/uncertainties. We should recognise historical errors and biases (e.g., in data) to avoid embedding them during ML programming.

Spatial Suitability Evaluation of Livestock and Poultry Breeding: A Case Study in Wangkui County, Heilongjiang Province, China

With the development of animal husbandry, environmental pollution caused by livestock and poultry breeding (LPB) has become a major problem faced by environmental protection departments. In response to this problem, this study established a spatial suitability evaluation system for LPB. According to the particularity of the indicators, there is a nonlinear relationship after quantification and not all elements in the matrix presented by the indexes and evaluation units have an ‘order’ relationship. Therefore, this study selects a method of combining a self-organising map network. The Hasse diagram technique and geographic information system were used to evaluate the suitability of LPB. Practical application research was conducted in Wangkui County. Most regions of Wangkui County are unsuitable for LPB, accounting for 81.23% of the total area of the county. A small part of a suitable region (434.76 km2) was determined to be a potential site for LPB. According to the results of suitable breeding regions, 17 existing large-scale livestock and poultry farms (LPFs) with unreasonable distribution were optimised for space, which are located in an urban construction area. Spatial optimisation was performed using GIS buffer and overlay analyses, providing the best relocation plot for these 17 LPFs. The results provide a scientific basis for the utilisation of livestock manure and spatial layout planning for LPB.

Environment, vector, or host? Using machine learning to untangle the mechanisms driving arbovirus outbreaks

Climatic, landscape, and host features are critical components in shaping outbreaks of vector-borne diseases. However, the relationship between the outbreaks of vector-borne pathogens and their environmental drivers is typically complicated, nonlinear, and may vary by taxonomic units below the species level (e.g., strain or serotype). Here, we aim to untangle how these complex forces shape the risk of outbreaks of Bluetongue virus (BTV); a vector-borne pathogen that is continuously emerging and re-emerging across Europe, with severe economic implications. We tested if the ecological predictors of BTV outbreak risk were serotype-specific by examining the most prevalent serotypes recorded in Europe (1, 4, and 8). We used a robust machine learning (ML) pipeline and 23 relevant environmental features to fit predictive models to 24,245 outbreaks reported in 25 European countries between 2000 and 2019. Our ML models demonstrated high predictive performance for all BTV serotypes (accuracies > 0.87) and revealed strong nonlinear relationships between BTV outbreak risk and environmental and host features. Serotype-specific analysis suggests, however, that each of the major serotypes (1, 4, and 8) had a unique outbreak risk profile. For example, temperature and midge abundance were as the most important characteristics shaping serotype 1, whereas for serotype 4 goat density and temperature were more important. We were also able to identify strong interactive effects between environmental and host characteristics that were also serotype specific. Our ML pipeline was able to reveal more in-depth insights into the complex epidemiology of BTVs and can guide policymakers in intervention strategies to help reduce the economic implications and social cost of this important pathogen.

GIS-based approach for mapping the density and distribution of crossbred cattle

The current study was carried out to map the crossbred cattle density and distribution in the Thondamuthur block of Coimbatore district in Tamil Nadu. A house to house survey was carried out and information about the number of cattle per farm or household, breed, class, age, etc. were collected. The coordinates of households and farms with cattle were recorded using a GPS device and the locations were used to generate maps in QGIS software. The classes of crossbred cattle found in the study area were Holstein-Friesian crossbred (CBHF), Jersey crossbred (CBJ) and Mixed (Jersey-HF) class (CBJH). In the adult category, CBHF contributed about 28% of the total crossbred population followed by CBJ (20%) and CBJH (14%). In the calves category, including heifers, CBJ was marginally higher at 16% than CBHF (15%) followed by CBJH (7%). The cattle density and distribution were higher in the settlements and sparse in the farms located away from the settlements and least in the areas situated close to the hills. This information can aid in various policy and decision-making process regarding cattle management.

Modeling the spatial distribution of anthrax in southern Kenya

BACKGROUND

Anthrax is an important zoonotic disease in Kenya associated with high animal and public health burden and widespread socio-economic impacts. The disease occurs in sporadic outbreaks that involve livestock, wildlife, and humans, but knowledge on factors that affect the geographic distribution of these outbreaks is limited, challenging public health intervention planning.

METHODS

Anthrax surveillance data reported in southern Kenya from 2011 to 2017 were modeled using a boosted regression trees (BRT) framework. An ensemble of 100 BRT experiments was developed using a variable set of 18 environmental covariates and 69 unique anthrax locations. Model performance was evaluated using AUC (area under the curve) ROC (receiver operating characteristics) curves.

RESULTS

Cattle density, rainfall of wettest month, soil clay content, soil pH, soil organic carbon, length of longest dry season, vegetation index, temperature seasonality, in order, were identified as key variables for predicting environmental suitability for anthrax in the region. BRTs performed well with a mean AUC of 0.8. Areas highly suitable for anthrax were predicted predominantly in the southwestern region around the shared Kenya-Tanzania border and a belt through the regions and highlands in central Kenya. These suitable regions extend westwards to cover large areas in western highlands and the western regions around Lake Victoria and bordering Uganda. The entire eastern and lower-eastern regions towards the coastal region were predicted to have lower suitability for anthrax.

CONCLUSION

These modeling efforts identified areas of anthrax suitability across southern Kenya, including high and medium agricultural potential regions and wildlife parks, important for tourism and foreign exchange. These predictions are useful for policy makers in designing targeted surveillance and/or control interventions in Kenya. We thank the staff of Directorate of Veterinary Services under the Ministry of Agriculture, Livestock and Fisheries, for collecting and providing the anthrax historical occurrence data.

Prediction for Global Peste des Petits Ruminants Outbreaks Based on a Combination of Random Forest Algorithms and Meteorological Data

Peste des Petits Ruminants (PPR) is an acute and highly contagious transboundary disease caused by the PPR virus (PPRV). The virus infects goats, sheep and some wild relatives of small domestic ruminants, such as antelopes. PPR is listed by the World Organization for Animal Health as an animal disease that must be reported promptly. In this paper, PPR outbreak data combined with WorldClim database meteorological data were used to build a PPR prediction model. Using feature selection methods, eight sets of features were selected: bio3, bio10, bio15, bio18, prec7, prec8, prec12, and alt for modeling. Then different machine learning algorithms were used to build models, among which the random forest (RF) algorithm was found to have the best modeling effect. The ACC value of prediction accuracy for the model on the training set can reach 99.10%, while the ACC on the test sets was 99.10%. Therefore, RF algorithms and eight features were finally selected to build the model in order to build the online prediction system. In addition, we adopt single-factor modeling and correlation analysis of modeling variables to explore the impact of each variable on modeling results. It was found that bio18 (the warmest quarterly precipitation), prec7 (the precipitation in July), and prec8 (the precipitation in August) contributed significantly to the model, and the outbreak of the epidemic may have an important relationship with precipitation. Eventually, we used the final qualitative prediction model to establish a global online prediction system for the PPR epidemic.

Challenges and opportunities for using national animal datasets to support foot-and-mouth disease control

National level databases of animal numbers, locations and movements provide the essential foundations for disease preparedness, outbreak investigations and control activities. These activities are particularly important for managing and mitigating the risks of high-impact transboundary animal disease outbreaks such as foot-and-mouth disease (FMD), which can significantly affect international trade access and domestic food security. In countries where livestock production systems are heavily subsidized by the government, producers are often required to provide detailed animal movement and demographic data as a condition of business. In the remaining countries, it can be difficult to maintain these types of databases and impossible to estimate the extent of missing or inaccurate information due to the absence of gold standard datasets for comparison. Consequently, competent authorities are often required to make decisions about disease preparedness and control based on available data, which may result in suboptimal outcomes for their livestock industries. It is important to understand the limitations of poor data quality as well as the range of methods that have been developed to compensate in both disease-free and endemic situations. Using FMD as a case example, this review first discusses the different activities that competent authorities use farm-level animal population data for to support (1) preparedness activities in disease-free countries, (2) response activities during an acute outbreak in a disease-free country, and (3) eradication and control activities in an endemic country. We then discuss (4) data requirements needed to support epidemiological investigations, surveillance, and disease spread modelling both in disease-free and endemic countries.

Predictor species: Improving assessments of rare species occurrence by modeling environmental co-responses

Designing an effective conservation strategy requires understanding where rare species are located. Because rare species can be difficult to find, ecologists often identify other species called conservation surrogates that can help inform the distribution of rare species. Species distribution models typically rely on environmental data when predicting the occurrence of species, neglecting the effect of species' co-occurrences and biotic interactions. Here, we present a new approach that uses Bayesian networks to improve predictions by modeling environmental co-responses among species. For species from a European peat bog community, our approach consistently performs better than single-species models and better than conventional multi-species approaches that include the presence of nontarget species as additional independent variables in regression models. Our approach performs particularly well with rare species and when calibration data are limited. Furthermore, we identify a group of "predictor species" that are relatively common, insensitive to the presence of other species, and can be used to improve occurrence predictions of rare species. Predictor species are distinct from other categories of conservation surrogates such as umbrella or indicator species, which motivates focused data collection of predictor species to enhance conservation practices.

From wild harvest towards precision agriculture: Use of Ecological Niche Modelling to direct potential cultivation of wild medicinal plants in Crete

Understanding the distribution of wild medicinal plants and areas that are suitable for cultivation of these plants is important for both conservation and agriculture. Here, we study ten taxa with known ethnopharmacological uses, which have been used extensively in traditional medicine and as culinary supplements. We aim to (1) predict and map the potential habitat suitability for these taxa across the study area, (2) investigate spatial patterns that could have management implications, such as niche similarities among the taxa and suitability "hotspots" with the use of novel indices, and (3) develop a platform where parts of this information can be accessed and utilized by all interested groups, from the policy-maker level to the individual practitioner level. Ecological Niche Models developed for each study taxon, based on topographic, bioclimatic, soil, and land use variables had high predictive power and were used as the basis for suitability visualization. A series of informative indices were also calculated and mapped, revealing spatial patterns not readily observable from the single-taxon predictions, and providing valuable information to managers. Finally, a web-based, easy-to-use application was also created, where the predicted suitability scores for the study area can be made accessible to anyone interested. The application can provide information both in a visual form (i.e. maps of predicted suitability) and in a numerical form (i.e. estimated suitability scores for all taxa in a given geographical location). This study provides the scientific tools to make a step towards cultivating a group of economically important wild medicinal plants in Crete, as well as the tools to disseminate this information to decision makers and practitioners, and eventually integrate the research findings in local agricultural practices.

Evaluating the utility of national-scale data to estimate the local risk of foot-and-mouth disease in endemic regions

Knowledge of the distribution of foot-and-mouth disease (FMD) is required if control programmes are to be successful. However, data on the seroprevalence and incidence of affected villages in developing countries with endemic disease are scarce. This is partly due to resource constraints as well as the logistical challenges of conducting intensive surveys and diagnostic testing in remote locations. In this study, we evaluated the performance of low resolution national-scale data against high resolution local survey data to predict the FMD serological status of 168 villages in the Mandalay and Sagaing Regions of central Myanmar using both logistic regression and random forest modelling approaches. Blood samples for ELISA testing were collected from approximately 30 cattle per village in both the 6 to 18 month age range and in the over 18 month age range to distinguish between recent and historical exposure, respectively. The results of the animal level tests were aggregated to the village level to provide the outcome of interest (village positive or not positive for FMD), and three explanatory data sets were constructed: using only nationally available data, using only data collected by survey and using the combined survey and nationally available data. The true seroprevalence of FMD at the village level was 61% when only young animals were included, but increased to 87% when all animals were included. The best performing model was a logistic regression model using the combined national and survey data to predict recent infection in villages. However, this still incorrectly classified 40% of villages, which suggests that using national-level data were not reliable enough for extrapolating seroprevalence in regions where conducting detailed surveys is impractical. Other methods for collected data on FMD such as the use of local reporting should be explored.

How to make more from exposure data? An integrated machine learning pipeline to predict pathogen exposure

Predicting infectious disease dynamics is a central challenge in disease ecology. Models that can assess which individuals are most at risk of being exposed to a pathogen not only provide valuable insights into disease transmission and dynamics but can also guide management interventions. Constructing such models for wild animal populations, however, is particularly challenging; often only serological data are available on a subset of individuals and nonlinear relationships between variables are common. Here we provide a guide to the latest advances in statistical machine learning to construct pathogen-risk models that automatically incorporate complex nonlinear relationships with minimal statistical assumptions from ecological data with missing data. Our approach compares multiple machine learning algorithms in a unified environment to find the model with the best predictive performance and uses game theory to better interpret results. We apply this framework on two major pathogens that infect African lions: canine distemper virus (CDV) and feline parvovirus. Our modelling approach provided enhanced predictive performance compared to more traditional approaches, as well as new insights into disease risks in a wild population. We were able to efficiently capture and visualize strong nonlinear patterns, as well as model complex interactions between variables in shaping exposure risk from CDV and feline parvovirus. For example, we found that lions were more likely to be exposed to CDV at a young age but only in low rainfall years. When combined with our data calibration approach, our framework helped us to answer questions about risk of pathogen exposure that are difficult to address with previous methods. Our framework not only has the potential to aid in predicting disease risk in animal populations, but also can be used to build robust predictive models suitable for other ecological applications such as modelling species distribution or diversity patterns.