In western Canada, decades of oil-and-gas exploration have fragmented boreal landscapes with a dense network of linear forest disturbances (seismic lines). These seismic lines are implicated in the decline in wildlife populations that are adapted to function in unfragmented forest landscapes. In particular, anthropogenic disturbances have led to a decline of woodland caribou populations due to increasing predator access to core caribou habitat. Restoration of seismic lines aims to reduce the landscape fragmentation and stop the decline of caribou populations. However, planning restoration in complex landscapes can be challenging because it must account for a multitude of diverse aspects. To assist with restoration planning, we present a spatial network optimization approach that selects restoration locations in a fragmented landscape while addressing key environmental and logistical constraints. We applied the model to develop restoration scenarios in the Redrock-Prairie Creek caribou range in northwestern Alberta, Canada, which includes a combination of caribou habitat and active oil-and-gas and timber extraction areas. Our study applies network optimization at two distinct scales to address both the broad-scale restoration policy planning and project-level constraints at the level of individual forest sites. We first delineated a contiguous set of coarse-scale regions where restoration is most cost-effective and used this solution to solve a fine-scale network optimization model that addresses environmental and logistical planning constraints at the level of forest patches. Our two-tiered approach helps address the challenges of fine-scale spatial optimization of restoration activities. An additional coarse-scale optimization step finds a feasible starting solution for the fine-scale restoration problem, which serves to reduce the time to find an optimal solution. The added coarse-scale spatial constraints also make the fine-scale restoration solution align with the coarse-scale landscape features, which helps address the broad-scale restoration policies. The approach is generalizable and applicable to assist restoration planning in other regions fragmented by oil-and-gas activities.

Large-scale delimiting surveys are critical for detecting pest invasions and often undertaken at different gover- nance levels. In this study, we consider two-level hierarchical planning of surveys of harmful invasive pests including a government agency with a mandate to report the spatial extent of an invasion, and regional gov- ernments (counties) concerned about the possible threat of an outbreak. The central agency plans delimiting pest surveys across multiple administrative subdivisions. Counties could participate in these surveys if funds become available. Our goal is to find the optimal levels of cooperation between the central agency and regional governments in the form of the central agency sharing funds with regional governments in a way that benefits both it and the other entities. We propose a Stackelberg game model that finds optimal levels of collaboration between two levels of government in large-scale pest survey campaigns. We apply the model to surveillance of hemlock woolly adelgid, a harmful pest of hemlock trees in Ontario, Canada. Our solutions help anticipate the underperformance of surveys conducted by regional governments because their goals do not fully align with the central agency survey objective. The methodology can be adapted to explore governance hierarchies in other regions and political jurisdictions.

Non‐renewable resource extraction contributes greatly to degradation of wildlife habitats in boreal landscapes. In western Canada, oil and gas exploration and extraction have left a dense network of linear disturbances (seismic lines) and abandoned well pads that have fragmented boreal forest. Among multiple ecological effects, these disturbances have increased predator access to the preferred habitat of some wildlife taxa, most notably boreal woodland caribou, resulting in population declines. Restoration of seismic lines and abandoned well pads is a critical activity to improve the recovery of woodland caribou populations. We present a linear programming model that optimally allocates restoration efforts to maximize the access of caribou to nearby undisturbed habitat in a fragmented landscape. We applied the model to examine restoration scenarios in the Cold Lake First Nations area in northeastern Alberta, Canada, which includes caribou habitat but also areas of active oil and gas extraction. The model depicts the landscape as a network of interconnected habitat patches and combines three network flow sub‐problems. The first sub‐problem enforces the spatial connectivity of the remaining network of unrestored sites. The second sub‐problem maximizes access to suitable habitat from the restored locations and the third sub‐problem ensures the allocation of restoration activities in as few spatially contiguous restoration projects as possible. The approach is generalizable and applicable to assist restoration planning in other resource extraction regions and for other taxa.

We present an applied model that helps restoration practitioners select an ideal mix of species to plant in order to meet their restoration objectives. The model generates virtual plant communities designed to optimize the delivery of multiple ecosystem functions. We used an optimization approach to find the most cost-effective combinations of species to plant to optimize the delivery of four ecosystem functions: rapid establishment of vegetation cover, soil building, biological soil health and resistance to invasion. We used trait-function relationships to characterize species' effects on ecosystem functions. This model accounts for key operational constraints selected by the user, including budget, the number of species to plant, and which functions to consider. The user can also decide whether or not to maximize the functional diversity of the species mix to increase its resilience to global environmental change. To demonstrate the practicality of this approach, we derived optimal species mixtures for the restoration of forests damaged by Cu-Ni smelters in the City of Greater Sudbury (Ontario, Canada). The species mixtures generated by the model varied according to which functions and operational constraints were selected. Results show that the species mixtures that were the most effective at delivering multiple functions were also cost-effective, but were less functionally diverse. This tool provides restoration practitioners with cost-effective restoration strategies for managing the recovery of multi-faceted socio-economic and environmental values in disturbed landscapes.

Emergency department (ED) overcrowding is a growing problem in Canada. Many interventions have been proposed to increase patient flow. The objective of this study was to predict patient admission early in the visit with the goal of reducing waiting time in ED for admitted patients. ED data for a one-year period from Thunder Bay, Canada was obtained. Initial logistic regression models were developed using age, sex, mode of arrival, and patient acuity as explanatory variables and admission yes or no as the outcome. A second stage prediction was made using the diagnostic tests ordered to further refine the predictive models. Predictive accuracy of the logistic regression model was adequate. The AUC was approximately 81%. By summing the probabilities of patients in the ED, the hourly prediction improved. This study has shown that the number of hospital beds required on an hourly basis can be predicted using triage administrative data.

The collection and examination of social media has become a useful mechanism for studying the mental activity and behavior tendencies of users. Through the analysis of collected Twitter data, models were developed for classifying drug-related tweets. Using topic pertaining keywords, such as slang and methods of drug consumption, a set of tweets was generated. Potential candidates were then preprocessed resulting in a dataset of 3,696,150 rows. The classification power of multiple methods was compared including support vector machines (SVM), XGBoost, and convolutional neural network (CNN) based classifiers. Rather than simple feature or attribute analysis, a deep learning approach was implemented to screen and analyze the tweets' semantic meaning. The two CNN-based classifiers presented the best result when compared against other methodologies. The first was trained with 2,661 manually labeled samples, while the other included synthetically generated tweets culminating in 12,142 samples. The accuracy scores were 76.35% and 82.31%, with an AUC of 0.90 and 0.91. Additionally, association rule mining showed that commonly mentioned drugs had a level of correspondence with frequently used illicit substances, proving the practical usefulness of the system. Lastly, the synthetically generated set provided increased scores, improving the classification capability and proving the worth of this methodology.

Background The collection and examination of social media has become a useful mechanism for studying the mental activity and behavior tendencies of users. Through the analysis of a collected set of Twitter data, a model will be developed for predicting positively referenced, drug-related tweets. From this, trends and correlations can be determined. Methods Social media data (tweets and attributes) were collected and processed using topic pertaining keywords, such as drug slang and use-conditions (methods of drug consumption). Potential candidates were preprocessed resulting in a dataset of 3,696,150 rows. The predictive classification power of multiple methods was compared including SVM, XGBoost, BERT and CNN-based classifiers. For the latter, a deep learning approach was implemented to screen and analyze the semantic meaning of the tweets. Results To test the predictive capability of the model, SVM and XGBoost were first employed. The results calculated from the models respectively displayed an accuracy of 59.33% and 54.90%, with AUC’s of 0.87 and 0.71. The values show a low predictive capability with little discrimination. Conversely, the CNN-based classifiers presented a significant improvement, between the two models tested. The first was trained with 2661 manually labeled samples, while the other included synthetically generated tweets culminating in 12,142 samples. The accuracy scores were 76.35% and 82.31%, with an AUC of 0.90 and 0.91. Using association rule mining in conjunction with the CNN-based classifier showed a high likelihood for keywords such as “smoke”, “cocaine”, and “marijuana” triggering a drug-positive classification. Conclusion Predictive analysis with a CNN is promising, whereas attribute-based models presented little predictive capability and were not suitable for analyzing text of data. This research found that the commonly mentioned drugs had a level of correspondence with frequently used illicit substances, proving the practical usefulness of this system. Lastly, the synthetically generated set provided increased accuracy scores and improves the predictive capability.