Search

The application of big data, radiomics, machine learning, and artificial intelligence (AI) algorithms in radiology requires access to large data sets containing personal health information. Because machine learning projects often require collaboration between different sites or data transfer to a third party, precautions are required to safeguard patient privacy. Safety measures are required to prevent inadvertent access to and transfer of identifiable information. The Canadian Association of Radiologists (CAR) is the national voice of radiology committed to promoting the highest standards in patient-centered imaging, lifelong learning, and research. The CAR has created an AI Ethical and Legal standing committee with the mandate to guide the medical imaging community in terms of best practices in data management, access to health care data, de-identification, and accountability practices. Part 2 of this article will inform CAR members on the practical aspects of medical imaging de-identification, strengths and limitations of de-identification approaches, list of de-identification software and tools available, and perspectives on future directions. [ABSTRACT FROM AUTHOR]

Artificial intelligence (AI) software that analyzes medical images is becoming increasingly prevalent. Unlike earlier generations of AI software, which relied on expert knowledge to identify imaging features, machine learning approaches automatically learn to recognize these features. However, the promise of accurate personalized medicine can only be fulfilled with access to large quantities of medical data from patients. This data could be used for purposes such as predicting disease, diagnosis, treatment optimization, and prognostication. Radiology is positioned to lead development and implementation of AI algorithms and to manage the associated ethical and legal challenges. This white paper from the Canadian Association of Radiologists provides a framework for study of the legal and ethical issues related to AI in medical imaging, related to patient data (privacy, confidentiality, ownership, and sharing); algorithms (levels of autonomy, liability, and jurisprudence); practice (best practices and current legal framework); and finally, opportunities in AI from the perspective of a universal health care system. [ABSTRACT FROM AUTHOR]

Abstract Artificial intelligence (AI) is rapidly moving from an experimental phase to an implementation phase in many fields, including medicine. The combination of improved availability of large datasets, increasing computing power, and advances in learning algorithms has created major performance breakthroughs in the development of AI applications. In the last 5 years, AI techniques known as deep learning have delivered rapidly improving performance in image recognition, caption generation, and speech recognition. Radiology, in particular, is a prime candidate for early adoption of these techniques. It is anticipated that the implementation of AI in radiology over the next decade will significantly improve the quality, value, and depth of radiology's contribution to patient care and population health, and will revolutionize radiologists' workflows. The Canadian Association of Radiologists (CAR) is the national voice of radiology committed to promoting the highest standards in patient-centered imaging, lifelong learning, and research. The CAR has created an AI working group with the mandate to discuss and deliberate on practice, policy, and patient care issues related to the introduction and implementation of AI in imaging. This white paper provides recommendations for the CAR derived from deliberations between members of the AI working group. This white paper on AI in radiology will inform CAR members and policymakers on key terminology, educational needs of members, research and development, partnerships, potential clinical applications, implementation, structure and governance, role of radiologists, and potential impact of AI on radiology in Canada. [ABSTRACT FROM AUTHOR]

Artificial Intelligence (AI) carries the potential for unprecedented disruption in radiology, with possible positive and negative consequences. The integration of AI in radiology holds the potential to revolutionize healthcare practices by advancing diagnosis, quantification, and management of multiple medical conditions. Nevertheless, the ever‑growing availability of AI tools in radiology highlights an increasing need to critically evaluate claims for its utility and to differentiate safe product offerings from potentially harmful, or fundamentally unhelpful ones. This multi‑society paper, presenting the views of Radiology Societies in the USA, Canada, Europe, Australia, and New Zealand, defines the potential practical problems and ethical issues surrounding the incorporation of AI into radiological practice. In addition to delineating the main points of concern that developers, regulators, and purchasers of AI tools should consider prior to their introduction into clinical practice, this statement also suggests methods to monitor their stability and safety in clinical use, and their suitability for possible autonomous function. This statement is intended to serve as a useful summary of the practical issues which should be considered by all parties involved in the development of radiology AI resources, and their implementation as clinical tools. [ABSTRACT FROM AUTHOR]

With the continuous improvement of shale oil and gas recovery technologies and achievements, a large amount of geological information and data have been accumulated for the description of shale reservoirs, and it has become possible to use machine learning methods for "sweet spots" prediction in shale oil and gas areas. Taking the Duvernay shale oil and gas field in Canada as an example, this paper attempts to build recoverable shale oil and gas reserve prediction models using machine learning methods and geological and development big data, to predict the distribution of recoverable shale oil and gas reserves and provide a basis for well location deployment and engineering modifications. The research results of the machine learning model in this study are as follows: ① Three machine learning methods were applied to build a prediction model and random forest showed the best performance. The R2 values of the built recoverable shale oil and gas reserves prediction models are 0.7894 and 0.8210, respectively, with an accuracy that meets the requirements of production applications; ② The geological main controlling factors for recoverable shale oil and gas reserves in this area are organic matter maturity and total organic carbon (TOC), followed by porosity and effective thickness; the main controlling factor for engineering modifications is the total proppant volume, followed by total stages and horizontal lateral length; ③ The abundance of recoverable shale oil and gas reserves in the central part of the study area is predicted to be relatively high, which makes it a favorable area for future well location deployment. [ABSTRACT FROM AUTHOR]

Although road surface friction is considered the most effective performance measure for maintenance operations, it is not commonly used due to the high cost of collection. As a result, most jurisdictions use subjective visual indicators that qualitatively describe the state of the road surface, even though they create measurement inconsistencies and offer less detailed maintenance tracking. For maintenance personnel to transition into using friction, the collection cost must be reduced. This paper attempts to do so by proposing a low-cost, machine learning-based method for predicting road surface friction using dash camera imagery and demonstrates its feasibility through a case study. The dataset used for this project was collected in the City of Edmonton, AB, Canada during its 2021/2022 winter season. Three models were developed using tree-based algorithms, where all three displayed high performance with an average root mean squared error of 0.0796 or 79.3% accuracy based on RMSPE. [ABSTRACT FROM AUTHOR]

In this paper we propose a machine learning-based approach to predict a multitude of insurance claim categories related to canine diseases. We introduce several machine learning approaches that are evaluated on a pet insurance dataset consisting of 785,565 dogs from the US and Canada whose insurance claims have been recorded over 17 years. 270,203 dogs with a long insurance tenure were used to train a model while the inference is applicable to all dogs in the dataset. Through this analysis we demonstrate that with this richness of data, supported by the right feature engineering, and machine learning approaches, 45 disease categories can be predicted with high accuracy. [ABSTRACT FROM AUTHOR]

Annual turnover of home care workers represents a huge loss of revenue and is a key source of inefficiency in the home health care industry. In this article, we propose a data-driven approach to monitor employee churn and to capture the evolution of employee intent to leave. Unlike most papers in the literature, we use machine learning techniques to analyze over 2 million visits in the US, Canada, and Australia between 2016 and 2019. Results show that the gap between the number of hours worked and in the contract is the most important factor to predict employee intent to leave, which means an employee should be given as many hours as requested in the contract to improve retention. Secondary results show that having diverse shift lengths and continuity in services and patients seem to be associated with less turnover. [ABSTRACT FROM AUTHOR]

There is a large amount of drilling core data in the Mackay River oil sands block in Canada, and the accurate identification of facies from the cores is important and necessary for the understanding of the subsurface reservoir. The traditional recognition method of facies from cores is by human work and is very time consuming. Furthermore, the results are different according to different geologists because of the subjective judgment criterion. An efficient and objective method is important to solve the above problem. In this paper, the deep learning image-recognition algorithm is used to automatically and intelligently recognize the facies type from the core image. Through a series of high-reliability preprocessing operations, such as cropping, segmentation, rotation transformation, and noise removal of the original core image, that have been manually identified, the key feature information in the images is extracted based on the ResNet50 convolutional neural network. On the dataset of about 200 core images from 13 facies, an intelligent identification system of facies from core images is constructed, which realizes automatic facies identification from core images. Comparing this method with traditional convolutional neural networks and support vector machines (SVM), the results show that the recognition accuracy of this model is as high as 91.12%, which is higher than the other two models. It is also shown that for a relatively special dataset, such as core images, it is necessary to rely on their global features in order to classify them, and, with a large similarity between some of the categories, it is extremely difficult to classify them. The selection of a suitable neural network model can have a great impact on the accuracy of recognition results. Then, the recognized facies are input as hard data to construct the three-dimensional facies model, which reveals the complex heterogeneity and distribution of the subsurface reservoir for further exploration and development. [ABSTRACT FROM AUTHOR]

This paper investigates the relationships among the important process parameters that impact Post-combustion Carbon Capture (PCC) carbon dioxide (C O 2) separation. A better understanding of the complex relationships among those parameters can support optimization and performance enhancement of the separation process. Being able to precisely predict the process parameters will enable the operator to determine the current state of the process, forecast any potential changes or events, and adjust process parameters to enhance the plant's performance. With the objective of studying the process parameters' correlations in the amine-based PCC process, we modeled the multi-year historical production data of the Clean Energy Technologies Research Institute (CETRi) (formerly known as the International Test Center for PCC or ITC) in Regina, Saskatchewan, Canada, using a Decision Forest approach. The model validation process revealed that the Decision Forest model produced higher predictive accuracy than previous efforts. The Decision Forest models we developed also represent knowledge about the importance of parameters involved in the capture process, and such knowledge is useful for further optimization of the capture process in the future. • Modeling the parameters of the Carbon Capture process with machine learning (ML). • The ML models used Decision Forest with Gradient Boosting and Oblique Split. • The ML models achieved superior predictive accuracy compared to past efforts. • The ML models support interpretability by visualizing weights and prediction paths. [ABSTRACT FROM AUTHOR]

This paper investigates how to best compare algorithms for predicting chronic homelessness for the purpose of identifying good candidates for housing programs. Predictive methods can rapidly refer potentially chronic shelter users to housing but also sometimes incorrectly identify individuals who will not become chronic (false positives). We use shelter access histories to demonstrate that these false positives are often still good candidates for housing. Using this approach, we compare a simple threshold method for predicting chronic homelessness to the more complex logistic regression and neural network algorithms. While traditional binary classification performance metrics show that the machine learning algorithms perform better than the threshold technique, an examination of the shelter access histories of the cohorts identified by the three algorithms show that they select groups with very similar characteristics. This has important implications for resource constrained not-for-profit organizations since the threshold technique can be implemented using much simpler information technology infrastructure than the machine learning algorithms. [ABSTRACT FROM AUTHOR]

Accurate wind speed forecasting ensures the controllability for the wind power system. In this paper, a structure with density-weighted active learning (DWAL)-based model selection strategy from the perspective of meteorological factors is proposed to improve the accuracy and stability for wind speed deterministic and probabilistic forecasting. To improve training efficiency and accelerate the sample selection process, DWAL is employed. The multi-objective flower pollination algorithm is used to combine best models selected from model space with optimal weights for higher accuracy and stability. Except deterministic forecasts, as large-scale wind power generation integrated into power grid, the wind direction should also be forecasted and the estimation of the wind speed and direction uncertainty is vital, offering various aspects of forecasts for risk management. Thus, both deterministic and probabilistic forecasting for the wind speed vector are included in this paper. Eight datasets from Ontario Province, Canada, are utilized to evaluate forecasting performance of the model selection and the proposed structure. Results demonstrated: (a) the proposed structure is suitable for wind speed vector forecasting; (b) the proposed structure obtains more precise and stable forecasting performance; (c) the proposed structure improves the accuracy of deterministic forecasting and provides probabilistic information for wind speed vector forecasting. • Propose a novel forecasting structure based on meteorological analysis. • The model selection is employed. • The multi-objective flower pollination algorithm is used. • Density-weighted active learning algorithm is applied. • Both deterministic forecasting and probabilistic forecasting are applied. [ABSTRACT FROM AUTHOR]

Structural Health Monitoring has the potential to enhance the safety and serviceability of our aging infrastructures by detecting anomalies at an early stage. Bayesian Dynamic Linear Models (BDLM) have been shown to be effective at detecting anomalies by extracting structural patterns and latent variables from complex and noisy time series. However, the autoregressive component modelling the stationary prediction errors in most BDLM has a tendency to wrongfully capture patterns that should be attributed to anomalies, and thus hinders their detectability. This paper proposes a new bounded autoregressive (B A R) component, which imposes constraints on the autoregressive latent process with a new mixture Rectified Linear activation Unit. The B A R component is probabilistically verified on synthetic data using a new F1t metric, and is validated using real observations collected on a bridge and on a dam located in Canada. The experimental results demonstrate that the B A R model surpasses the performance of the existing autoregressive component with (1) an improved accuracy at estimating hidden states, (2) an early detection of anomalies, (3) a capacity to detect smaller anomaly magnitudes, and (4) the ability to control the tradeoff between the anomaly detectability and the false alarm rate. [ABSTRACT FROM AUTHOR]

In response to calls for greater interdisciplinary involvement from the social sciences and humanities in the development, governance, and study of artificial intelligence systems, this paper presents one sociologist's view on the problem of algorithmic bias and the reproduction of societal bias. Discussions of bias in AI cover much of the same conceptual terrain that sociologists studying inequality have long understood using more specific terms and theories. Concerns over reproducing societal bias should be informed by an understanding of the ways that inequality is continually reproduced in society—processes that AI systems are either complicit in, or can be designed to disrupt and counter. The contrast presented here is between conservative and radical approaches to AI, with conservatism referring to dominant tendencies that reproduce and strengthen the status quo, while radical approaches work to disrupt systemic forms of inequality. The limitations of a conservative approach to racial bias are discussed through the specific example of biased criminal risk assessments and Indigenous overrepresentation in Canada's criminal justice system. This illustrates the dangers of treating racial bias as a generalizable problem and equality as a generalizable solution, emphasizing the importance of considering inequality in context. Societal issues can no longer be out of scope for AI and machine learning, given the impact of these systems on human lives. This requires engagement with a growing body of critical AI scholarship that goes beyond biased data to analyze structured ways of perpetuating inequality, opening up the possibility for interdisciplinary engagement and radical alternatives. [ABSTRACT FROM AUTHOR]

Due to the advent of powerful parallel processing tools, including modern Graphics Processing Units (GPU), new deep learning algorithms, such as Convolutional Neural Networks (CNNs), have significantly altered the state-of-the-art algorithms in satellite classification of complex environments. Recent studies have demonstrated that the generic feature maps extracted from CNNs are incredibly effective in wetland classification. The main drawback of very deep CNNs is described as structurally complex, causing the need for extensive training data. To address deep Convolutional Neural Network's limitations, a timely and computationally efficient CNN architecture is proposed in this paper. The results of the proposed model were compared to other well-known CNNs (i.e., GoogleNet and SqueezeNet) and several machine learning algorithms, including Random Forest, Gaussian Naïve Bayes, and the Bayesian Optimized Tree. Results showed while significantly reduced the training time, the proposed deep learning method outperformed GoogleNet and SqueezeNet by about 12.71% and 12.2% in terms of mean overall accuracy, respectively. The classification results shown that the accuracy of wetland classes (fen, marsh, swamp, and shallow water) were significantly improved by applying the proposed CNN method. [ABSTRACT FROM AUTHOR]

Injuries have become devastating and often under-recognized public health concerns. In Canada, injuries are the leading cause of potential years of life lost before the age of 65. The geographical patterns of injury, however, are evident both over space and time, suggesting the possibility of spatial optimization of policies at the neighborhood scale to mitigate injury risk, foster prevention, and control within metropolitan regions. In this paper, Canada's National Ambulatory Care Reporting System is used to assess unintentional and intentional injuries for Toronto between 2004 and 2010, exploring the spatial relations of injury throughout the city, together with Wellbeing Toronto data. Corroborating with these findings, spatial autocorrelations at global and local levels are performed for the reported over 1.7 million injuries. The sub-categorization for Toronto's neighborhood further distills the most vulnerable communities throughout the city, registering a robust spatial profile throughout. Individual neighborhoods pave the need for distinct policy profiles for injury prevention. This brings one of the main novelties of this contribution. A comparison of the three regression models is carried out. The findings suggest that the performance of spatial regression models is significantly stronger, showing evidence that spatial regressions should be used for injury research. Wellbeing Toronto data performs reasonably well in assessing unintentional injuries, morbidity, and falls. Less so to understand the dynamics of intentional injuries. The results enable a framework to allow tailor-made injury prevention initiatives at the neighborhood level as a vital source for planning and participatory decision making in the medical field in developed cities such as Toronto. [ABSTRACT FROM AUTHOR]

The fate of the carbon stored in frozen peatlands in Canada's Hudson Bay Lowlands (HBL) depends strongly on water, with wetter conditions favoring long-term storage. Dynamic surface water products generated from historical Landsat data exist to inform surface water trends in the HBL based on binary classifications of land vs water at 30 m spatial resolution. However, the HBL contains many water features smaller than 30 m, including streams and patterned fens that require a sub-pixel mapping approach to fully capture their dynamics. In this paper, we leverage an existing binary dynamic surface water product to generate a spatially and temporally comprehensive Landsat sub-pixel surface water time-series over the HBL. We first generate Landsat Red, NIR and SWIR composites from 1985 to 2021 and evaluate data-driven machine learning and physical models to derive sub-30 m water fractions across the entire mapping domain. Data-driven models were calibrated on 30 m water fractions obtained from 16 of 17 WorldView scene water fraction maps and assessed on the 17th held-out scene in a jackknife validation. Data-driven models were also calibrated by relating scaled Landsat reflectance to water fractions obtained from binary water masks at corresponding scales from 90 to 270 m. Physical models involved simple linear unmixing using a new approach that samples land endmembers in the vicinity of each pixel to represent land reflectance, and a global water endmember sampled beneath permanent water in each image. The assumption of linear scaling was verified at sub-30 m to 270 m resolution for NIR, SWIR and NDVI, which were all highly correlated with water fraction and had no significant differences among water fraction – spectral feature relationships across the full range of scales. Each of 11 different methods and input spectral features were evaluated against WorldView water fractions and ranked based on nine criteria. We found that machine learning using all spectral features including local NIR land endmembers performed best among data-driven approaches, and linear unmixing of the NIR band using local land endmembers performed best among physical. Both best-performing methods were applied to the entire time-series and surface water area trends were calculated and compared with trends obtained from binary water masks. All three methods agree on the direction of surface water change towards wetting, with sub-pixel inter-annual variation agreeing with stream discharge noted in other studies. • Physical and data-driven Landsat water fraction methods tested in the Hudson Bay Lowlands. • Physical methods perform linear unmixing between local land and global water endmembers. • Data-driven methods consist of machine learning calibrated using high-resolution water. • Best methods applied to 1985–2021 Landsat time-series reveal overall wetting trends. • Spatial trends generally suggest drying in bogs and wetting in fens. [ABSTRACT FROM AUTHOR]

Offsite construction shifts construction work to the factory environment, enabling automation of traditionally manual operations. While this approach has proven to be advantageous for the construction industry in Canada, changes in the process of manufacturing panelized walls have brought new challenges and opportunities. With the aim of providing alternatives to current manual quality control activities, an automated vision-based online inspection system for screw-fastening operations in light-gauge steel frame manufacturing is proposed in this paper. Targeting two common defects in the framing process, squareness and the quality of the screw-fastening operation itself, real-time quality assessment of the frame is achieved. The proposed system uses novel machine vision algorithms to generate the inspection data: a squareness estimation algorithm is developed, based on edge detection and the Hough transform, that can determine the squareness of a steel connection with a margin of error less than two degrees, whereas a R-CNN is designed based on a pre-trained ResNet-50 for detection and classification of screw-fastening operations, achieving an overall accuracy of 91.67%. All the inspection results are made accessible through a Python-based interface in order to direct operators towards either identifying potential quality issues or confirming the quality of the product leaving the station. The inspection system is validated over a real frame in a semi-automated machine environment. In future work, the inspection system will be deployed in continuous production setups in order to further test its accuracy and applicability. [ABSTRACT FROM AUTHOR]

Background: National ranking from the triennial Programme of International Student Assessment (PISA) often serves as a barometer of national performance and human capital. Though excessive student‐ and school‐level covariates (n > 700) may prove intractable for traditional least‐squares estimate procedures, shrinkage methods may be more suitable for subset selection. Aims: With a focus on the United States, this paper proposes sparse regression for PISA 2012 to discover salient student‐ and school‐level predictor variables for mathematical literacy achievement. Sample: The sparse regression analysis was conducted on 10 top‐tiered OECD countries/economies, Canada, and the United States in mathematical literacy on the 2012 PISA. Two‐ and three‐level hierarchical regression analyses were performed on Canadian and US students (N = 26,522) along with five of the ten top‐tiered countries/economies (N = 58,385). Methods: Using the 'least absolute shrinkage and selection operator' (LASSO) technique, the study (1) identified salient predictor variables of mathematical literacy performance for the top‐tiered countries/economies, Canada, and the United States and (2) used these salient variables to perform two‐ and three‐level hierarchical regression on data from Canada and the United States along with five top‐tiered countries/economies. Weights and replicates were used to account for complex sample design. A weighted, two‐level confirmatory factor analysis was performed to identify latent constructs. Missing data were handled through multiple imputation. Results: Separate two‐level hierarchical models accounted for 32–35% student‐level and 58–70% school‐level variance in Canada and the United States, respectively; three‐level models accounted for 33% of level‐one variance, 62–65% level‐two variance, and 13–44% of level‐three variance for the US/Canada and US/Canada/top‐tiered students, respectively. Following top‐tiered countries/economies, Canadian students had high levels of self‐efficacy, were more likely to encounter advanced concepts in class, were less activity/small group‐centred, and were more likely to consider truancy a learning hindrance. Factor analyses revealed a positive relation with rigour and class organization (teacher‐centred) for top‐tiered countries and Canada, though not for the United States. For all countries, there was a strong relation between rigour and self‐beliefs. Conclusion: Compared to top performers, a less rigorous curriculum, coupled with class and school factors, may explain lag in US performance. [ABSTRACT FROM AUTHOR]

As the importance of eco-friendly transportation increases, providing an efficient approach for marine vessel operation is essential. Methods for status monitoring with consideration to the weather condition and forecasting with the use of in-service data from ships requires accurate and complete models for predicting the energy efficiency of a ship. The models need to effectively process all the operational data in real-time. This paper presents models that can predict fuel consumption using in-service data collected from a passenger ship. Statistical and domain-knowledge methods were used to select the proper input variables for the models. These methods prevent over-fitting, missing data, and multicollinearity while providing practical applicability. Prediction models that were investigated include multiple linear regression (MLR), decision tree approach (DT), an artificial neural network (ANN), and ensemble methods. The best predictive performance was from a model developed using the XGboost technique which is a boosting ensemble approach. Our code is available on GitHub at https://github.com/pagand/model%5foptimze%5fvessel/tree/OE for future research. • Comparison of fuel consumption models for west coast Canada vessel • Feature engineering utilized domain knowledge to identify key variables • Parametric and non-parametric models used for prediction model development • Evaluation included running time, mean error, and future step prediction error. [ABSTRACT FROM AUTHOR]

[Display omitted] • Six feature selection methods were evaluated for wind speed quantiles estimation at ungauged locations. • Feature selection enabled the identification of the most important predictors for various wind speed quantiles. • The most parsimonious features selection methods led to the lowest generalization error. • The location distance from the coast and the surface roughness were the most significant wind speed quantiles predictors. Wind speed estimation at ungauged locations is one of the preliminary steps for wind resource assessment. With the availability of high-resolution Digital Elevation Models (DEM) and remote sensing data, the number of potential wind speed predictors has grown substantially. The adequate spatial scale of these predictors is unknown a priori, leading to the use of multiple spatial scales of predictors in wind speed estimation models. Implementing a feature selection method as a pre-processing step of the analysis is necessary to avoid overfitting and the resulting potential model underperformance. This paper evaluated six feature selection methods (forward stepwise regression, Least Absolute Shrinkage and Selection Operator (LASSO), Elastic Net, maximum relevance minimum redundancy (MRMR), Genetic algorithm, and recursive feature elimination using support vector regression) for the estimation of different wind speed quantiles across Canada. The selected features were used to fit a regression-kriging model, and the importance of the predictors was evaluated with their associated regression coefficients. The results of the study showed that LASSO and MRMR are the most efficient algorithms with the least number of parameters to tune and good generalization performance. The study found that some predictors were more important for specific exceedance probabilities. The most important predictors were the distance from the coast and surface roughness length, regardless of exceedance probability. [ABSTRACT FROM AUTHOR]

• Groundwater level prediction for a long period of time is considered in this paper. • We proposed a graph-based machine learning using which the spatial relationships are taken into account. • Our results indicate that spatial correlations are helpful when one deals with geospatial data. • The proposed method is compared with standard techniques. Accurate prediction of groundwater level (GWL) over a period of time is of great importance for groundwater resources management. Machine learning techniques due to their great performance have recently been used for this problem. Previous methods, however, did not consider the spatial relationships between wells due to the difficulty to handle unstructured well location data. In this paper, a graph neural network (GNN) is used to forecast groundwater dynamics where it can represent each well as a node in the graph. The spatial information is, thus, extracted from an interconnected network using graph convolution layers with a self-adaptive adjacency matrix. The temporal features of the sequence are obtained by gated temporal convolutional networks. The model was applied and evaluated for wells in the southwest area of British Colombia in Canada using data about 11 years (2010–2020). The proposed model performs better in terms of all the defined evaluation metrics, when compared with two baseline models: long short-term memory (LSTM) and gated recurrent units (GRU). Moreover, when the spatial dependencies are completely unknown, the model can still learn them from the data and obtain comparable performance. Furthermore, the proposed model has a high efficiency since it can simultaneously model GWL change for all monitoring wells in the system. We also demonstrated that the spatial dependencies between each well could be intuitively interpreted from the learned adjacency matrix. [ABSTRACT FROM AUTHOR]

The pulp and paper industry is a fundamental sector of the economy of many countries. However, this sector requires real collaboration and initiatives from stakeholders to reduce its significant consumption of energy and emission of greenhouse gases. Heat exchangers are examples of equipment in pulp mills that are subjected to undesirable and complex phenomena such as evolution of fouling over time, which leads to inefficiency in terms of energy consumption and unplanned shutdowns, resulting in ineffective maintenance strategies and production costs. Therefore, there is a clear need to develop an accurate predictive maintenance tool that helps mill operators avoid such situations. It is necessary for that tool to effectively track the fouling evolution level and, based on it, deploy a reliable prognostics approach to estimate more accurately the time-to-clean of this equipment. This study presents a new hybrid prognostics approach for fouling prediction in heat exchangers. The proposed approach relies on the fusion of information of different prediction horizons to estimate the time-to-clean. Employing long short-term memory, it allows adaptation of long-term predictions by accurate short-term predictions using multiple non-linear auto-regressive exogenous models. This fusion not only captures the changes in degradation trend over time, but also ensures a good accuracy of prognostics results in both the short- and long-term horizons for planning maintenance actions. The effectiveness of the proposed approach was successfully proven on real industrial data collected from a pulp mill heat exchanger located in Canada. • New adaptive prognostic approach based on fusion of short and long-term predictors. • Selection of relevant physical parameters for monitoring of fouling evolution. • Accurate long-term fouling prediction by using short-term predictors. • High accuracy of fouling time-to-clean in a real heat exchanger plant. [ABSTRACT FROM AUTHOR]

Freely-available satellite data streams and the ability to process these data on cloud-computing platforms such as Google Earth Engine have made frequent, large-scale landcover mapping at high resolution a real possibility. In this paper we apply these technologies, along with machine learning, to the mapping of peatlands–a landcover class that is critical for preserving biodiversity, helping to address climate change impacts, and providing ecosystem services, e.g., carbon storage–in the Boreal Forest Natural Region of Alberta, Canada. We outline a data-driven, scientific framework that: compiles large amounts of Earth observation data sets (radar, optical, and LiDAR); examines the extracted variables for suitability in peatland modelling; optimizes model parameterization; and finally, predicts peatland occurrence across a large boreal area (397, 958 km2) of Alberta at 10 m spatial resolution (equalling 3.9 billion pixels across Alberta). The resulting peatland occurrence model shows an accuracy of 87% and a kappa statistic of 0.57 when compared to our validation data set. Differentiating peatlands from mineral wetlands achieved an accuracy of 69% and kappa statistic of 0.37. This data-driven approach is applicable at large geopolitical scales (e.g., provincial, national) for wetland and landcover inventories that support long-term, responsible resource management. [ABSTRACT FROM AUTHOR]

• We concentrated on the stability prediction of underground entry-type excavations. • Three RF-based hybrid models are present to predict entry-type excavation stability. • MVO, GWO and MFO can assist the hyper-parameters tuning of RF. • The accuracy of the proposed models is better than the models in previous studies. • The models based on RF can update the critical span graph scientifically. The stability evaluation of underground entry-type excavations is a prerequisite of the entry-type mining method, which directly affects whether workers can be provided with a safe and reliable working environment and whether subsequent mining operations can be carried out normally. The design and stability assessment of entry-type excavations in current mining engineering largely relies on an empirical design method called the critical span graph, which has been widely applied in the initial span design of various cut and fill stopes. In recent years, with the wide application of various intelligent algorithms in the field of mine engineering, models based on intelligent algorithms provide new research methods and ideas for the assessment of rock stability in entry-type excavations. This study aims to introduce several hybrid models based on the random forest (RF) algorithm into the stability evaluation work to find new data-driven methods with higher accuracy to update the critical span graph. To pursue better classification performance, this paper selects three optimization strategies, namely multi-verse optimizer (MVO), grey wolf optimizer (GWO) and moth-flame optimization (MFO) algorithm, to optimize two core parameters of RF, and establishes three corresponding hybrid models, abbreviated as MVO-RF, GWO-RF and MFO-RF, based on the database containing 399 samples from seven Canada mines. There are two input parameters in the database, i.e., opening span and rock mass condition (expressed as RMR), and the output parameter is rock mass stability, which is specifically divided into three categories: stable, potentially unstable and unstable. In addition, five commonly used measurement indexes applicable to multiclassification problems were adopted to verify the classification ability of the models, i.e., the accuracy (ACC), precision calculated using macro-average (PRE M), recall calculated using macro-average (REC M), F1 score calculated using macro-average (F1 M) and Kappa index (Kappa). The results indicate that the three hybrid models performed well based on the test set accounting for 25 % of the original database, in which the accuracy of the MFO-RF model was the highest: ACC = 0.9300; PRE M = 0.9288; REC M = 0.8983; F1 M = 0.9116; Kappa = 0.8666. To evaluate whether the three optimization strategies can effectively improve the performance of RF and judge the degree of improvement, the performance of an unoptimized RF model was discussed in this study. In addition, two support vector machine (SVM) models with different kernel functions were selected as references for performance evaluation. The results indicated that compared with the RF and two SVM models, the classification accuracy of the three hybrid models was obviously more satisfactory. The classification accuracy of the three hybrid models reached 0.91, which was sufficient to explain the excellent classification ability of these models. After tuning the RF hyperparameters of each hybrid model, the critical span graph was further updated according to the optimized classification models, which was the focus of this research. By comparing the critical span graphs obtained by the three hybrid models with the single RF model and two kinds of SVM models, it is certain that the three hybrid models proposed in this paper, MVO-RF, GWO-RF and MFO-RF, are promising in the study of evaluating the stability of entry-type excavations and may be deemed auxiliary decision tools to define the stability region of the critical span graph. [ABSTRACT FROM AUTHOR]

• A convolutional neural network-based method to calculate the composite system reliability indices. • A data generation scheme to both train the CNN and calculate reliability indices. • Training and testing algorithm for the CNN to calculate composite system reliability indices. • Developing mathematical model to calculate composite system reliability indices. This paper proposes a machine learning-based approach in conjunction with Monte Carlo simulation (MCS) to improve the computation efficiency of composite power system reliability evaluation. Traditional composite system reliability evaluation approaches are computationally demanding and may become inapplicable to large integrated power grids due to the requirements of repetitively solving optimal power flow (OPF) for a large number of system states. Machine learning-based approaches have been used to avoid solving OPF in composite system reliability evaluation except in the training stage. However, current approaches have been derived to classify system states into success and failure states (i.e., up or down). In other words, they can be used to evaluate power system probability and frequency reliability indices, but they cannot be used to evaluate power and energy reliability indices unless OPF is solved for each failure state to determine minimum load curtailments. In this paper, a convolutional neural network (CNN)-based regression approach is proposed to determine the minimum amount of load curtailments of sampled states without solving OPF, except in the training stage. Minimum load curtailments are then used to evaluate power and energy indices (e.g., expected demand not supplied) as well as to evaluate the probability and frequency indices. The proposed approach is applied on several systems including the IEEE Reliability Test Systems (The IEEE RTS and IEEE RTS-96) and Saskatchewan Power Corporation in Canada. Results show that the proposed approach is computationally efficient (fast and accurate) in calculating the most common composite system reliability indices. The developed source code of the proposed method is available to the community for future research and development. [ABSTRACT FROM AUTHOR]

Purpose – This paper aims to analyze the relationship among measures of resource and service usage and other features of academic libraries in the USA and Canada. Design/methodology/approach – Through the use of a self-organizing map, academic library data were clustered and visualized. Analysis of the library data was conducted through the computation of a "library performance metric" that was applied to the resulting map. Findings – Two areas of high-performing academic libraries emerged on the map. One area included libraries with large numbers of resources, while another area included libraries that had low resources but gave greater numbers of presentations to groups, offered greater numbers of public service hours, and had greater numbers of staffed service points. Research limitations/implications – The metrics chosen as a measure of library performance offer only a partial picture of how libraries are being used. Future research might involve the use of a self-organizing map to cluster library data within certain parameters and the identification of high-performing libraries within these clusters. Practical implications – This study suggests that libraries can improve their performance not only by acquiring greater resources but also by putting greater emphasis on the services that they provide to their users. Originality/value – This paper demonstrates how a self-organizing map can be used in the analysis of large data sets to facilitate library comparisons. [ABSTRACT FROM AUTHOR]

The first image is a Mineral Prospectivity Map (MPM) produced using 35 input predictor variables (maps) and the Random Forest (RF) machine learning algorithm whereas the second image is the same except it was produced using the best 10 predictor variables calculated by the RF algorithm. [Display omitted] • Mineral prospectivity mapping (MPM) • Geology – Chibougamau, Quebec. • Gold (Au) model. Two mineral prospectivity maps (MPM) focusing on a general Au model for the Chibougamau region of Quebec, Canada, have been produced in this paper. The random forest algorithm has been used to integrate 35 evidence (predictor) layers which represent vectors to Au mineralization. The MPMs generated are robust as evidenced by efficiency of classification curves. The known zones of Au mineralization are well predicted; furthermore, new prospective areas with no known Au have been identified which are prime for exploration follow-up. The Chibougamau area is somewhat fertile with respect to Au and the strongest predictors are fault density and intersection density, contact density and Au anomalies in rock. [ABSTRACT FROM AUTHOR]

A large portion of Canada is covered by wetlands; mapping and monitoring them is of great importance for various applications. In this regard, Remote Sensing (RS) technology has been widely employed for wetland studies in Canada over the past 45 years. This study evaluates meta-data to investigate the status and trends of wetland studies in Canada using RS technology by reviewing the scientific papers published between 1976 and the end of 2020 (300 papers in total). Initially, a meta-analysis was conducted to analyze the status of RS-based wetland studies in terms of the wetland classification systems, methods, classes, RS data usage, publication details (e.g., authors, keywords, citations, and publications time), geographic information, and level of classification accuracies. The deep systematic review of 128 peer-reviewed articles illustrated the rising trend in using multi-source RS datasets along with advanced machine learning algorithms for wetland mapping in Canada. It was also observed that most of the studies were implemented over the province of Ontario. Pixel-based supervised classifiers were the most popular wetland classification algorithms. This review summarizes different RS systems and methodologies for wetland mapping in Canada to outline how RS has been utilized for the generation of wetland inventories. The results of this review paper provide the current state-of-the-art methods and datasets for wetland studies in Canada and will provide direction for future wetland mapping research. [ABSTRACT FROM AUTHOR]

Protecting financial consumers from investment fraud has been a recurring problem in Canada. The purpose of this paper is to predict the demographic characteristics of investors who are likely to be victims of investment fraud. Data for this paper came from the Investment Industry Regulatory Organization of Canada's (IIROC) database between January of 2009 and December of 2019. In total, 4575 investors were coded as victims of investment fraud. The study employed a machine-learning algorithm to predict the probability of fraud victimization. The machine learning model deployed in this paper predicted the typical demographic profile of fraud victims as investors who classify as female, have poor financial knowledge, know the advisor from the past, and are retired. Investors who are characterized as having limited financial literacy but a long-time relationship with their advisor have reduced probabilities of being victimized. However, male investors with low or moderate-level investment knowledge were more likely to be preyed upon by their investment advisors. While not statistically significant, older adults, in general, are at greater risk of being victimized. The findings from this paper can be used by Canadian self-regulatory organizations and securities commissions to inform their investors' protection mandates. [ABSTRACT FROM AUTHOR]

The emergence of climate change (CC) is affecting and changing the development of the natural environment, biological species, and human society. In order to better understand the influence of climate change and provide convincing evidence, the need to quantify the impact of climate change is urgent. In this paper, a climate change model is constructed by using a radial basis function (RBF) neural network. To verify the relevance between climate change and extreme weather (EW), the EW model was built using a support vector machine. In the case study of Canada, its level of climate change was calculated as being 0.2241 ("normal"), and it was found that the factors of CO2 emission, average temperature, and sea surface temperature are significant to Canada's climate change. In 2025, the climate level of Canada will become "a little bad" based on the prediction results. Then, the Pearson correlation value is calculated as being 0.571, which confirmed the moderate positive correlation between climate change and extreme weather. This paper provides a strong reference for comprehensively understanding the influences brought about by climate change. [ABSTRACT FROM AUTHOR]

Many impact studies require climate change information at a finer resolution than that provided by global climate models (GCMs). This paper investigates the performances of existing state-of-the-art rule induction and tree algorithms, namely single conjunctive rule learner, decision table, M5 model tree, and REPTree, and explores the impact of climate change on maximum and minimum temperatures (i.e., predictands) of 14 meteorological stations in the Upper Thames River Basin, Ontario, Canada. The data used for evaluation were large-scale predictor variables, extracted from National Centers for Environmental Prediction/National Center for Atmospheric Research reanalysis dataset and the simulations from third generation Canadian coupled global climate model. Data for four grid points covering the study region were used for developing the downscaling model. M5 model tree algorithm was found to yield better performance among all other learning techniques explored in the present study. Hence, this technique was applied to project predictands generated from GCM using three scenarios (A1B, A2, and B1) for the periods (2046-2065 and 2081-2100). A simple multiplicative shift was used for correcting predictand values. The potential of the downscaling models in simulating predictands was evaluated, and downscaling results reveal that the proposed downscaling model can reproduce local daily predictands from large-scale weather variables. Trend of projected maximum and minimum temperatures was studied for historical as well as downscaled values using GCM and scenario uncertainty. There is likely an increasing trend for T and T for A1B, A2, and B1 scenarios while decreasing trend has been observed for B1 scenarios during 2081-2100. [ABSTRACT FROM AUTHOR]

This paper shows how machine learning can help in analyzing and understanding historical change. Using data from the Canadian census of 1901, we discover the influences on bilingualism in Canada at the beginning of the last century. The discovered theories partly agree with, and partly complement, the existing views of historians on this question. Our approach, based around a decision tree, not only infers theories directly from data, but also evaluates existing theories and revises them to improve their consistency with the data. One novel aspect of this work is the use of confidence intervals to determine which factors are both statistically and practically significant, and thus contribute appreciably to the overall accuracy of the theory. When inducing a decision tree directly from data, confidence interrvals determine when new tests should be added. If an existing theory is being evaluated, confidence intervals also determine when old tests should be replaced, or deleted, to improve the theory. Our aim is to minimize the changes made to an existing theory to accommodate the new data. To this end, we propose a semantic measure of similarity between trees and demonstrate how this can be used to limit the changes made. [ABSTRACT FROM AUTHOR]

Wetlands are important ecosystems that are linked to climate change mitigation. As 25% of global wetlands are located in Canada, accurate and up-to-date wetland classification is of high importance, nationally and internationally. The advent of deep learning techniques has revolutionized the current use of machine learning algorithms to classify complex environments, specifically in remote sensing. In this paper, we explore the potential and possible limitations to be overcome regarding the use of ensemble deep learning techniques for complex wetland classification and discusses the potential and limitation of various solo convolutional neural networks (CNNs), including DenseNet, GoogLeNet, ShuffleNet, MobileNet, Xception, Inception-ResNet, ResNet18, and ResNet101 in three different study areas located in Newfoundland and Labrador, Canada (i.e., Avalon, Gros Morne, and Grand Falls). Moreover, to improve the classification accuracies of wetland classes of bog, fen, marsh, swamp, and shallow water, the results of the three best CNNs in each study area is fused using three supervised classifiers of random forest (RF), bagged tree (BTree), Bayesian optimized tree (BOT), and one unsupervised majority voting classifier. The results suggest that the ensemble models, in particular BTree, have a valuable role to play in the classification of wetland classes of bog, fen, marsh, swamp, and shallow water. The ensemble CNNs show an improvement of 9.63–19.04% in terms of mean producer's accuracy compared to the solo CNNs, to recognize wetland classes in three different study areas. This research indicates a promising potential for integrating ensemble-based learning and deep learning for operational large area land cover, particularly complex wetland type classification. [ABSTRACT FROM AUTHOR]

In this paper, a machine learning algorithm based on artificial neural network architecture investigates the correlation between drainage chemistries in seepage water and ambient weather conditions around waste rock piles. The proposed neural network consists of a long short-term memory unit and a fully connected neural network which uses sequenced input to consider current and previous weather impact on the drainage chemistries. A 20-year (1998–2017) monitoring database obtained from the full-scale waste rock pile of the Equity Silver mine in BC, Canada is used for validating the proposed approach. The neural network is trained based on total precipitation and mean temperature as input and the acidity as output. The results indicate that the calculated acidity from the trained neural network matches with that measured in the field well. In addition, the accuracy of calculated acidity can be further increased by adding a time tag of acidity measurement date into the input layer. This refined approach can capture the long-term evolution and dynamics of hydrogeochemical and biochemical properties inside the waste rock piles. • Correlation between drainage chemistry and weather is studied for waste rock piles. • Long short term memory (LSTM) is proposed to correlate historical monitoring data. • Both of short-term and long-term fluctuations in drainage acidities is captured. • Drainage acidities can be predicted reasonably when weather forecast is available. [ABSTRACT FROM AUTHOR]

• Using deep temporal convolutional networks for building simulation surrogate models. • Deep network processes annual hourly weather time series data (≈ 150,000 inputs). • Accurate emulation of simulation outcomes for all locations in Canada. • 3% error in estimating annual heating demand for unseen locations and building designs. • Reasonable accuracy ( R 2 = 0.92) in estimating hourly demands given weather data. Surrogate models can emulate physics-based building energy simulation with a machine learning model trained on simulation input and output data. The trained model is extremely fast to run, allowing us to estimate simulation outcomes for thousands of different building designs in seconds. Recent studies have shown the diverse benefits for sustainable building design. Surrogates were applied to provide rapid feedback at the early design stage, to accelerate sensitivity analysis, uncertainty analysis and design optimization, or to improve building model calibration. However, the current process of surrogate modelling offers much room for improvement. In particular, a surrogate model is bound to the specific building design problem it has been trained for. This includes a specific site, requiring time-intensive retraining if the building performance at another location is to be analysed. In this paper, we develop a single surrogate model that spans arbitrarily many locations. For that purpose, we are among the first to use a deep temporal convolutional neural network to process annual multivariate weather data with hourly resolution (≈ 150,000 inputs). The network learns features relevant to estimate heating or cooling demand. We combine these location-specific weather features with building design parameters to serve as input to a single surrogate model (feed-forward neural network). In a case study with 569 weather files from locations in Canada, we show that the surrogate model deviates by less than 3% when predicting annual heating demand for new building designs at locations outside of the training data set. [ABSTRACT FROM AUTHOR]

Devastating floods occur regularly around the world. Recently, machine learning models have been used for flood susceptibility mapping. However, even when these algorithms are provided with adequate ground truth training samples, they can fail to predict flood extends reliably. On the other hand, the height above nearest drainage (HAND) model can produce flood prediction maps with limited accuracy. The objective of this research is to produce an accurate and dynamic flood modeling technique to produce flood maps as a function of water level by combining the HAND model and machine learning. In this paper, the HAND model was utilized to generate a preliminary flood map; then, the predictions of the HAND model were used to produce pseudo training samples for a R.F. model. To improve the R.F. training stage, five of the most effective flood mapping conditioning factors are used, namely, Altitude, Slope, Aspect, Distance from River and Land use/cover map. In this approach, the R.F. model is trained to dynamically estimate the flood extent with the pseudo training points acquired from the HAND model. However, due to the limited accuracy of the HAND model, a random sample consensus (RANSAC) method was used to detect outliers. The accuracy of the proposed model for flood extent prediction, was tested on different flood events in the city of Fredericton, NB, Canada in 2014, 2016, 2018, 2019. Furthermore, to ensure that the proposed model can produce accurate flood maps in other areas as well, it was also tested on the 2019 flood in Gatineau, QC, Canada. Accuracy assessment metrics, such as overall accuracy, Cohen's kappa coefficient, Matthews correlation coefficient, true positive rate (TPR), true negative rate (TNR), false positive rate (FPR) and false negative rate (FNR), were used to compare the predicted flood extent of the study areas, to the extent estimated by the HAND model and the extent imaged by Sentinel-2 and Landsat satellites. The results confirm that the proposed model can improve the flood extent prediction of the HAND model without using any ground truth training data. [ABSTRACT FROM AUTHOR]

In most cases, the benchmarking models of energy use in houses are developed based on current and past data, and they continue to be used without any update. This paper proposes the method of retraining of benchmarking models by applying machine learning techniques when new measurements are made available. The method uses as a case study the measurements of heating energy demand from two semi-detached houses of Northern Canada. The results of the prediction of heating energy demand using static or augmented window techniques are compared with measurements. The daily energy signature is used as a benchmarking model due to its simplicity and performance. However, the proposed retraining method can be applied to any form of benchmarking model. The method should be applied in all possible situations, and be an integral part of intelligent building automation and control systems (BACS) for the ongoing commissioning for building energy-related applications. [ABSTRACT FROM AUTHOR]