Search

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]

Improving the operational effectiveness of hydropower systems is becoming more relevant considering the shift to renewable energy sources and the rising social, financial, and environmental costs associated with the construction of new hydropower facilities. This challenge is interdisciplinary as it involves technical, managerial, and institutional aspects. This paper focuses on a technical aspect, more specifically on the relationship between the quality of short-term ensemble streamflow forecasts and the energy produced by a hydropower system. A secondary objective is to measure the contribution of both the meteorological and structural uncertainties on the energy output. To achieve this, a numerical experiment comprising multiple sets of hydrologic ensemble forecasts of different quality and a suite of reservoir optimization models is developed for a case study in Canada (the hydropower system of the Gatineau River basin). These ensemble forecasts are processed by the short-term reservoir operation model in rolling-horizon mode over a planning period of 6 years. Each day, the short-term optimization model seeks to maximize the energy output over the 14-day forecast lead time considering the expected future value of the system derived from a midterm optimization model. The relationship between hydropower generation and common statistical scores characterizing the ensemble forecasts indicates that although there is a link between the quality of the forecasts and the energy production, it is not a one-to-one causal relationship. Our results also show that the diversity of hydrological models is beneficial to the production of energy, indicating that the diversity of model structures compensates the deficiencies of individuals models and adds value to the forecast. [ABSTRACT FROM AUTHOR]

"Short-term load forecasting (STLF)" is increasingly significant because of the extensive use of distributed energy resources, the incorporation of intermitted RES, and the implementation of DSM. This paper provides a novel ensemble forecasting model with wavelet transform for the STLF depending on the decomposition principle of load profiles. The model can effectively capture the portion of daily load profiles caused by seasonal variations. The results indicate that it is possible to improve STLF accuracy with the proposed method. The proposed approach is tested with the data taken from Ontario's electricity market in Canada. The results show that the proposed technique performs well in-terms of prediction when compared to existing traditional and cutting-edge methods. The performance of the model was validated with different datasets. Moreover, this approach can provide accurate load forecasting using ensemble models. Therefore, utilities and smart grid operators can use this approach as an additional decision-making tool to improve their real-time decisions. [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]

The Canadian Earth System Model version 5 (CanESM5) developed at Environment and Climate Change Canada's Canadian Centre for Climate Modelling and Analysis (CCCma) is participating in phase 6 of the Coupled Model Intercomparison Project (CMIP6). A 40-member ensemble of CanESM5 historical decadal forecasts (or hindcasts) is integrated for ten years from realistic initial states during 1961 to present using prescribed external forcing. The results are part of CCCma's contribution to the Decadal Climate Prediction Project (DCPP) component of CMIP6. This paper evaluates CanESM5 large ensemble decadal hindcasts against observational benchmarks and against historical climate simulations initialized from preindustrial control run states. The focus is on the evaluation of the potential predictability and actual skill of annual and multi-year averages of key oceanic and atmospheric fields at regional and global scales. The impact of initialization on prediction skill is quantified from the hindcasts decomposition into uninitialized and initialized components. The dependence of potential and actual skill on ensemble size is examined. CanESM5 decadal hindcasts skilfully predict upper-ocean states and surface climate with a significant impact from initialization that depend on climate variable, forecast range, and geographic location. Deficiencies in the skill of North Atlantic surface climate are identified and potential causes discussed. The inclusion of biogeochemical modules in CanESM5 enables the prediction of carbon cycle variables which are shown to be skilful on decadal time scales, with a strong long-lasting impact from initialization on skill in the ocean and a moderate short-lived impact on land. [ABSTRACT FROM AUTHOR]

• Column height is the parameter with more impact on longitudinal displacements. • Deck skew is the parameter with lesser influence on the seismic response. • Minimum required support lengths by actual codes are found to be very conservative. • The period is a more accurate parameter to predict longitudinal displacements. • An equation is proposed to estimate the required support length from the period. Loss of bridge deck supports is one of the major failures observed during past earthquakes. Deck collapse due to loss of support has been observed mainly on simply supported bridge structures with insufficient support length at expansion bearings. To accommodate the large displacements induced by seismic movements and to avoid bridge collapse, modern seismic standards and regulations require a minimum support length at expansion deck bearings. This paper presents the state of knowledge on the empirical support length equation and the main geometric parameters influencing the required support length at deck expansion bearings. It also presents the results of the parametric study performed on typical existing single and multi-span simply supported bridges subjected to seismic loads typical of Eastern Canada. The results allowed to identify and describe the key geometric parameters influencing the nonlinear responses of existing bridges, evaluate their relative influence in terms of displacements and ductility associated with the loss of deck supports. It also compares the current empirical equation with predicted displacements and proposes an equation more suitable for predicting expected displacements (lower than code values) in an evaluation framework for judging the seismic vulnerability of existing such as the bridge models considered in this study. [ABSTRACT FROM AUTHOR]

The purpose of this paper was to propose a method to predict shear-wave velocities in the process of AVO (amplitude variation with offset) inversion, to interpret seismic converted-wave data, and to match reservoir engineering information with seismic data in regions without shear-wave velocities. During CO2 flooding and sequestration, the shear-wave velocity varies with the pressure that is caused by fluid injection. Predictions of how the shear-wave velocity changes with pressure can be used to interpret 4D seismic monitoring data during different stages of CO2 injection. To verify the calculations, the authors used the characteristic parameters of the Marly dolomite and Vuggy limestone units of the Weyburn Oilfield reservoir in Canada. The Digby's model and Gassmann's equation were used to evaluate the dependence of the shear-wave velocity on the pressure in the carbonate rock formation. The authors have developed a new method for calculating the coordination number of the model and supplement the results with a shale correction, enabling the prediction to match the measured shear-wave velocities more closely. Our method is verified by dipole sonic logging data and petrophysical test data from the Weyburn Oilfield. When applied to petrophysical test data, the average error is below 5%. When the method is applied to well log data, the average error in the porous media is 3.014% in the Marly unit and 6.288% in the Vuggy unit. [ABSTRACT FROM AUTHOR]

Purpose: The EQ-5D-5L is a commonly used instrument for assessing the utility of different health states. Health state utility values are a key component of health technology evaluations. Such evaluations are used to support evidence-based decisions surrounding health resource allocations and therefore rely on the accuracy of the valuation set used. This paper takes an alternative approach to developing an EQ-5D-5L value set for Canada. The aim is to introduce a robust method that is likely to generate a value set with improved accuracy and that can be used to generate value sets for other populations without the need for modification. Methods: The common approach to developing a valuation set for preference-based instruments is to ask a population sample to value a subset of the health states using an established preference elicitation technique. The relationship between the elicited health states and the preferences is used to inform a model to predict the utility values for the unsampled health states described by the instrument. The true relationship is unknown and the functional forms chosen in the modelling process vary across valuation studies. We use nonparametric local constant regression to estimate an EQ-5D-5L value set for Canada and propose this method as an alternative for value set development because it does not require the specification of a functional form at the outset. Results: Compared to the existing valuation model for Canada, the nonparametric method improves in-sample fit, reducing the average squared prediction error by 94.46% and the mean absolute error by 79.37%. In four of five sets of out-of-sample studies, this new approach performs significantly better than 9 comparison models. Despite lacking any restriction on the functional form of the resulting valuations, the valuation set generated by this new approach is logically consistent. 100% of the pairs of health states in which one state is dominant have health state values which respect this ordering. The value set also appears to differ substantially from the comparators. Conclusions: Overall, the results suggest that nonparametric regression is a promising tool for the estimation of EQ-5D-5L valuation sets and may be a good option in a standardised methodology for value set development. [ABSTRACT FROM AUTHOR]

The second version of the Canadian Seasonal to Interannual Prediction System (CanSIPSv2) was implemented operationally at Environment and Climate Change Canada (ECCC) in July 2019. Like its predecessors, CanSIPSv2 applies a multimodel ensemble approach with two coupled atmosphere–ocean models, CanCM4i and GEM-NEMO. While CanCM4i is a climate model, which is upgraded from CanCM4 of the previous CanSIPSv1 with improved sea ice initialization, GEM-NEMO is a newly developed numerical weather prediction (NWP)-based global atmosphere–ocean coupled model. In this paper, CanSIPSv2 is introduced, and its performance is assessed based on the reforecast of 30 years from 1981 to 2010, with 10 ensemble members of 12-month integrations for each model. Ensemble seasonal forecast skill of 2-m air temperature, 500-hPa geopotential height, precipitation rate, sea surface temperature, and sea ice concentration is assessed. Verification is also performed for the Niño-3.4, the Pacific–North American pattern (PNA), the North Atlantic Oscillation (NAO), and the Madden–Julian oscillation (MJO) indices. It is found that CanSIPSv2 outperforms the previous CanSIPSv1 system in many aspects. Atmospheric teleconnections associated with the El Niño–Southern Oscillation (ENSO) are reasonably well captured by the two CanSIPSv2 models, and a large part of the seasonal forecast skill in boreal winter can be attributed to the ENSO impact. The two models are also able to simulate the Northern Hemisphere teleconnection associated with the tropical MJO, which likely provides another source of skill on the subseasonal to seasonal time scale. [ABSTRACT FROM AUTHOR]

Wildfire is a critical process shaping the structure and composition of forest landscapes of western Canada. Spatially-explicit forest disturbance history and forest structure estimated using remotely-sensed data enables the characterization of burn probability, defined as the susceptibility of landscapes to fire hazard over time. In this research, we leveraged the Landsat archive to determine the capacity of land cover, forest structure, and forest disturbance information, together with ancillary data, to estimate burn probability. We analyzed the interactions between a number of contributing factors and identified landscapes with high probability to burn across forested ecosystems of Saskatchewan, Canada. Overall, we found that forests composed of coniferous species, with shorter trees (<3 m), low canopy height variability, an open stand structure (<10% canopy cover), and low timber volumes (<50 m3/ha), had higher burn probabilities. A 2015 burn probability map indicated that forests that did burn in 2015 (determined using independently mapped wildfires) had a median predicted burn probability of 81%, while the median burn probability for unburned forest area was 19%. This paper demonstrates the potential to generate detailed and spatially-explicit burn probability maps from time series remote sensing data to inform wildland fire risk modeling, management, and mitigation. [ABSTRACT FROM AUTHOR]

Objectives: Weather is a key source of marine risk, but relationships between fishing activity, safety, and weather remain poorly understood. Critically, the fit between available marine forecast products, fish harvesters' needs, and harvester's decision-making processes has not been rigorously assessed. This paper addresses these gaps by documenting a) weather-related decision-making by harvesters, and its relationship to forecasts across multiple regions and fisheries on Canada's East coast (Newfoundland) and b) the dynamics of forecast production priorities. Methods: A multi-disciplinary, community-engaged research approach, conducted in partnership with the Newfoundland and Labrador Fish Harvesting Safety Association (NL-FHSA). Data consist of semi-structured interviews with fish harvesters and weather forecasters, focused on marine forecast production and use. Results: Results emphasize that there is a subjective "art" to both production and use of marine forecasts. Forecasters and harvesters share several common values regarding forecasts, but different emphases: forecasters favor some combination of accuracy, consistency, and utility, while harvesters are largely concerned with utility. Finally, harvesters' decision-making is based on nuanced and contextual interpretations of a few key hazards (winds and, to a lesser extent, waves). Conclusion: This community-engaged research has triggered experimentation with forecasts tailored to fisheries utility within Environment and Climate Change Canada (ECCC). It lays the groundwork for ongoing, mutually beneficial dialogue between forecasters and harvesters, engaging harvesters with the forecasting process while familiarizing forecasters with harvester's decision-making processes. Ongoing industry partnerships (NL-FHSA) continue to sustain momentum from this study towards further enhancing the utility of future marine forecasts for small-scale harvesters. [ABSTRACT FROM AUTHOR]

This paper evaluates the forecast performance of Canadian financial institutions and forecasting firms between 1984 and 2003. The sample period is roughly double that of an earlier study. We divide the sample in two and investigate whether a particular institution has improved its relative standing over the last ten years. Results for two Quebec institutions — the Banque Nationale (National Bank) and the Mouvement Desjardins — are now included in the second part of the sample, whereas a complete dataset was not available for these two institutions during the 1980s. We look as well at the relative performance of individual forecasters compared to the consensus forecast (defined as the mean of the forecasts available during the period in question). The paper then compares the accuracy of the Canadian consensus forecast with the forecast offered by the OECD each December for a limited number of key macroeconomic variables. [ABSTRACT FROM AUTHOR]

This paper examines the importance of the unit of analysis selected for trip generation modelling when the model estimation data are collected in a household travel survey. The paper reviews the literature on the arguments made for the use of the "individual" or the "household" as the unit of analysis in trip production modelling, and then through a statistical exposition it determines what should be the appropriate unit of analysis. An empirical test of the forecast performance of household- and person-trip generation models is conducted using data collected in a household-travel-behaviour survey in the Greater Toronto Area of Canada. The paper concludes that the household is theoretically the preferable analysis unit to use in trip production modelling when the model estimation data are collected in a household travel survey in which the household is the sampling unit. The empirical test indicates that household-trip generation models yield predictions of trips at the household and traffic zone level, respectively, that are marginally more accurate than those yielded by person-trip generation models. [ABSTRACT FROM AUTHOR]

A database of difficult-to-forecast natural persistent deep slab avalanches was analyzed to determine thresholds for parameters that contribute to their release in western Canada. The database included avalanche observations and weather station data. The avalanches were grouped based on their primary cause-of-release, either precipitation loading, wind loading, solar warming or air temperature warming using a multivariate classification tree, which first split using a solar warming parameter. The precipitation group had a median 24 h snowfall of 15 cm and 3 d snowfall of 38 cm at weather stations, mostly at or below treeline. These amounts were likely closer between 20-30 and 50-80 cm at alpine start zones. The wind loading group experienced the most wind-transported snow potential. The solar warming group had predicted solar warming of 5.2°C, 10 cm into the snowpack, on the days of release. The air temperature warming group experienced the highest median maximum air temperature (5°C) on the days of release. These thresholds may be useful to forecast the likelihood of similar avalanches with experienced-based forecasting or with decision aids, although many false alarms are possible. A companion paper, Part II, relates weather model data to avalanche occurrences. [ABSTRACT FROM AUTHOR]

• This paper is focused on predicting price signals for energy arbitrage of storage systems. • A methodology is presented based on feature selection tools and classification techniques. • A Li-Ion battery in the Ontario competitive electricity market is considered as a case study. • Results indicate that the proposed methodology outperforms alternative point forecasting models. When participating in a competitive electricity market, energy storage systems could deliver various services and stack multiple revenue streams. One potential venue for gaining profit is energy arbitrage, i.e., to harvest the price differential that might exist in some markets between the peak and off-peak hours. To take advantage of price arbitrage, however, it is necessary to have an insight into the price fluctuations of upcoming hours. In this paper, we propose a method for generating predictive electricity price signals to help storage operators make arbitrage decisions. The proposed method delivers signals that are integrated into an optimization platform to schedule the arbitrage operation of a storage system. We examine a Lithium-ion battery as the choice of storage system and the Ontario's competitive electricity market in Canada is considered as the case study. We compare the performance of the proposed approach against the cases that alternative point forecasts of the electricity price are used for self-scheduling of the storage system. The results show that the obtained arbitrage profit of the storage system can be increased significantly using the proposed approach. [ABSTRACT FROM AUTHOR]

Abstract: Electricity is an important asset that influences not only the economy, but political or social security of a country. Reliable and accurate planning and prediction of electricity demand for a country are therefore vital. In this paper, electricity demand in Ontario province of Canada from the year 1976–2005 is modeled by using an (adaptive neuro fuzzy inference system) ANFIS. A neuro fuzzy structure can be defined as an ANN (artificial neural network) which is trained by experimental data to find the parameters of (fuzzy inference system) FIS. Inputs for the model include number of employment, (gross domestic product) GDP, population, dwelling count and two meteorological parameters related to annual weather temperature. The data were collected and screened using statistical methods. Then, based on the data, a neuro-fuzzy model for the electricity demand is built. It was found that electricity demand is most sensitive to employment. [Copyright &y& Elsevier]

Abstract: This paper presents an econometric model for the behaviour of carsharing users. The econometric model is developed to jointly forecast membership duration, the decision to become an active member in a particular month, and the frequency of monthly usage of active members. The model is estimated using the membership directory and monthly transaction data of a carsharing program, ‘Communauto Inc.’, based in Montréal, Canada. The model shows a high degree of fit to the observed dataset and provides many behavioural details of carsharing users. The results are instructive to carsharing planners in devising efficient policies. [Copyright &y& Elsevier]

This paper discusses the development of simple multiple linear regression (MLR) models for developing seasonal forecasts of the annual minimum sea-ice extent in the Beaufort/Chukchi Seas, the Laptev/East Siberian Seas, the Kara/Barents Seas, and the Canadian Arctic Archipelago regions. The potential predictor data are based on mean monthly weighted indices of sea-ice concentration, multiyear sea-ice concentration, surface skin temperature, surface albedo, and downwelling longwave radiation flux at the surface. Predictions are developed based on data available in March (spring forecast), to coincide with the National American Ice Service''s annual outlooks, and based on data available in June (summer forecast), which would provide a seasonal revision. The final regression equations retain one to three predictors, and each of the MLR models is superior to climatology. The r 2 for the MLR models range from a low of 0.44 (for the spring forecast in the Canadian Arctic Archipelago) to a high of 0.80 (for the summer forecast in the Beaufort/Chukchi Seas). [Copyright &y& Elsevier]

The purpose of this study is to present the impacts of a fully interactive coupling between an atmospheric and a sea ice model over the Gulf of St. Lawrence, Canada. The impacts are assessed in terms of the atmospheric and sea ice forecasts produced by the coupled numerical system. The ocean-ice model has been developed at the Maurice Lamontagne Institute, where it runs operationally at a horizontal resolution of 5 km and is driven (one-way coupling) by atmospheric model forecasts provided by the Meteorological Service of Canada (MSC). In this paper the importance of two-way coupling is assessed by comparing the one-way coupled version with a two-way coupled version in which the atmospheric model interacts with the sea ice model during the simulation. The impacts are examined for a case in which the sea ice conditions are changing rapidly. Two atmospheric model configurations have been studied. The first one has a horizontal grid spacing of 24 km, which is the operational configuration used at the Canadian Meteorological Centre. The second one is a high-resolution configuration with a 4-km horizontal grid spacing. A 48-h forecast has been validated using satellite images for the ice and the clouds, and also using the air temperature and precipitation observations. It is shown that the two-way coupled system improves the atmospheric forecast and has a direct impact on the sea ice forecast. It is also found that forecasts are improved with a fine resolution that better resolves the physical events, fluxes, and forcing. The coupling technique is also briefly described and discussed. [ABSTRACT FROM AUTHOR]

This paper examines the broad movements of Canadian period and cohort fertility over the last hundred years or so, and compares them with corresponding trends in the United States and other industrialized countries. The main movement in Canada was a decline in fertility extending from the nineteenth century to the present time, interrupted in the 1940s and 1950s by a ‘baby boom’. The long decline in cohort fertility is largely explained by the decrease in the proportions of families of six or more children. This decrease continued during the baby boom, but in these years was more than offset, though not for Catholics, by the effects of increases in the proportions of families with three, four, and five children. [ABSTRACT FROM PUBLISHER]

Area feeder long-term load forecast (LTLF) is one of the most critical forecasting tasks in electric distribution utility companies. Cost effective system upgrades can only be planned out based on accurate feeder LTLF results. However, the commonly used top-down and bottom-up LTLF methods fail to combine area and feeder information and cannot effectively deal with component-level LTLF. The previous research effort on hybrid approach that aims to combine top-down and bottom-up approaches is very limited. The recent work only focuses on the forecast of the next one-year and uses a one-fit-all model for all area feeders. In response, this paper proposes a novel selective sequence learning method that can convert a multi-year LTLF problem to a multi-timestep sequence prediction problem. The model learns how to predict sequence values as well as the best-performing sequential configuration for each feeder. In addition, unsupervised learning is introduced to automatically group feeders based on load compositions ahead of learning to further enhance the performance. The proposed method was tested on an urban distribution system in Canada and compared with many conventional methods and the existing hybrid forecasting method. It achieves the best forecasting accuracy measured by three metrics AMAPE, RMSE and R-squared. It also proves the feasibility of applying sequence learning to multi-year component-level load forecast. • Converts a multi-year LTLF problem to a multi-timestep sequence prediction problem. • Can incorporate area and feeder level information in multiple historical years. • Can be used to forecast multiple years in the future. • Best sequential configurations can be automatically learned for different feeders. • Unsupervised learning is adopted to further enhance forecasting accuracy. [ABSTRACT FROM AUTHOR]

Artificial neural network (ANN) technology has evolved from the experimental stage into actual industrial applications. To achieve this significant transition, careful planning and adjustment are required. This paper illustrates such an example in the water treatment industry. The project objective is to upgrade the ANN models from a previous research project and install the system on-line in the Rossdale Water Treatment Plant in Edmonton, Alberta, Canada, to forecast raw water colour one day ahead. The article discusses the important issues and techniques to upgrade the neural network model to the actual application. Furthermore, sufficient communication is also required between the designers and the users to address the applicability and user friendly issues in model implementation. Failure in communication can render the whole process ineffective. Possible improvements are also recommended for the future on-line applications. [ABSTRACT FROM AUTHOR]