Predicting chronic wasting disease in white-tailed deer at the county scale using machine learning.

Continued spread of chronic wasting disease (CWD) through wild cervid herds negatively impacts populations, erodes wildlife conservation, drains resource dollars, and challenges wildlife management agencies. Risk factors for CWD have been investigated at state scales, but a regional model to predict locations of new infections can guide increasingly efficient surveillance efforts. We predicted CWD incidence by county using CWD surveillance data depicting white-tailed deer (Odocoileus virginianus) in 16 eastern and midwestern US states. We predicted the binary outcome of CWD-status using four machine learning models, utilized five-fold cross-validation and grid search to pinpoint the best model, then compared model predictions against the subsequent year of surveillance data. Cross validation revealed that the Light Boosting Gradient model was the most reliable predictor given the regional data. The predictive model could be helpful for surveillance planning. Predictions of false positives emphasize areas that warrant targeted CWD surveillance because of similar conditions with counties known to harbor CWD. However, disagreements in positives and negatives between the CWD Prediction Web App predictions and the on-the-ground surveillance data one year later underscore the need for state wildlife agency professionals to use a layered modeling approach to ensure robust surveillance planning. The CWD Prediction Web App is at https://cwd-predict.streamlit.app/ .

How can we augment the few that remain? Using stable population dynamics to aid reintroduction planning of an iteroparous species.

Restoration of depleted populations is an important method in biological conservation. Reintroduction strategies frequently aim to restore stable, increasing, self-sustaining populations. Knowledge of asymptotic system dynamics may provide advantage in selecting reintroduction strategies. We introduce interactive software that is designed to identify strategies for release of females that are immediately aligned with stable population dynamics from species represented by 2-, 3-, 4-, and 5-stage life history strategies. The software allows managers to input a matrix of interest, the desired number of breeding females, and the desired management timeline, and calls upon stable population theory to give release strategies that are in concert with both stable population status and the management goals. We demonstrate how the software can aid in assessing various strategies ahead of a hypothetical restoration. For the purpose of demonstration of the tool only, we use published vital rates of an ungulate species, but remark that the selection of species for demonstration is not central to the use of this tool. Adaption of this tool to real-life restorations of any 2-, 3-, 4-, or 5-stage iteroparous species may aid in understanding how to minimize undesirable recovery complications that may naturally arise from transient population dynamics. The software is freely available at: https//cwhl.vet.cornell.edu/tools/stapopd.