Duro D.C.,University of Saskatchewan |
Franklin S.E.,Trent University |
Dube M.G.,Total EandP Canada Ltd. |
Dube M.G.,Canadian Rivers Institute
International Journal of Remote Sensing | Year: 2012
The random forest (RF) classifier is a relatively new machine learning algorithm that can handle data sets with large numbers and types of variables. Multi-scale object-based image analysis (MOBIA) can generate dozens, and sometimes hundreds, of variables used to classify earth observation (EO) imagery. In this study, a MOBIA approach is used to classify the land cover in an area undergoing intensive agricultural development. The information derived from the elevation data and imagery from two EO satellites are classified using the RF algorithm. Using a wrapper feature selection algorithm based on the RF, a large initial data set consisting of 418 variables was reduced by ~60%, with relatively little loss in the overall classification accuracy. With this feature-reduced data set, the RF classifier produced a useable depiction of the land cover in the selected study area and achieved an overall classification accuracy of greater than 90%. Variable importance measures produced by the RF algorithm provided an insight into which object features were relatively more important for classifying the individual land-cover types. The MOBIA approach outlined in this study achieved the following: (i) consistently high overall classification accuracies (>85%) using the RF algorithm in all models examined, both before and after feature reduction; (ii) feature selection of a large data set with little expense to the overall classification accuracy; and (iii) increased interpretability of classification models due to the feature selection process and the use of variable importance scores generated by the RF algorithm. © 2012 Copyright Taylor and Francis Group, LLC.
Squires A.J.,University of Saskatchewan |
Dube M.G.,Canadian Rivers Institute |
Rozon-Ramilo L.D.,Stantec Inc.
Environmental Toxicology and Chemistry | Year: 2013
The Athabasca River basin, located in Alberta, Canada, covers 157, 000km2 and holds significant cultural and economic importance. Recent research assessed changes in several water quality and quantity parameters that have changed both spatially (along the river continuum) and temporally (pre-development and present day) in the Athabasca River Basin. In particular, parameters such as salinity and dissolved sulphate have changed significantly across the Athabasca River mainstem over the past five decades. Further laboratory testing has linked concentrations of these parameters to changes in fathead minnow reproduction. Research is required to determine whether these changes observed in the laboratory can be applied to actual in-river conditions. The objectives of the present study were to twofold: assess changes in fathead minnow response metrics (i.e., condition, liver and gonad size, egg production, and gill histology) associated with increasing concentrations of salinity and dissolved sulphate and determine whether sublethal effect thresholds established in laboratory experiments correspond to actual in-river concentrations using water from the mouth and headwaters of the Athabasca River. Three dose-response experiments (NaCl, SO4, and water sampled from the mouth of the Athabasca River) were conducted at Jasper National Park, Alberta, Canada. Significant increases in mean eggs per female per day occurred at the 50% treatment for the mouth experiment and thresholds previously developed in the laboratory were verified. Environ. Toxicol. Chem. 2013;32:662-672. © 2012 SETAC.
St-Hilaire A.,INRS ETE |
St-Hilaire A.,Canadian Rivers Institute |
Duchesne S.,INRS ETE |
Rousseau A.N.,INRS ETE
Canadian Water Resources Journal | Year: 2015
Water quality remains a major issue in Canada. This paper reviews recent research on the impacts of urbanization, agriculture and forestry on water quality in Canada. Specific water quality issues such as mining, sewage treatment and waste treatment are not included in this paper. For each land use, a brief summary of the dominant processes linking runoff to water quality is provided and recent findings are summarized. With respect to urbanized watersheds, the relatively large proportion of impervious areas, lower vegetation cover and the presence of high-density drainage systems alter surface water routing and timing of peak flows. High concentrations of heavy metals are considered to be the most important water quality problem in urban runoff, but nutrients, pathogens, concentration of pharmaceuticals and water temperature also often contribute. In watersheds dominated by agricultural activities, overland flow is an important vector of pollutants, but subsurface flow such as macropore and tile-drain flows also play a role in the alteration of water quality during or after high runoff events. Nutrients, pesticides, pathogens and sediments remain important topics of research in agricultural watersheds, and the modelling effort has significantly increased in the last few decades. Beneficial management practices (BMPs) are being tested and applied at a local scale, mostly on experimental watersheds. Forestry-related activities also affect water quality. In forested watersheds, studies have been ongoing for many decades, but have decreased in intensity in the last 15 years. Sediment delivery and water temperature can be strongly affected in watersheds with significant clear-cut logging and riparian buffer strips and sylviculture remain the main mitigation BMPs. There is a need for an increase in the monitoring effort for most water quality variables in Canada. The authors recommend that flow-dependent monitoring frameworks should be further developed and implemented in the future. © 2015 Canadian Water Resources Association
Mendoza-Morales A.J.,Av. Gomez Farias No. |
Mendoza-Morales A.J.,University of Guadalajara |
Gonzalez-Sanson G.,Av. Gomez Farias No. |
Gonzalez-Sanson G.,Canadian Rivers Institute |
And 2 more authors.
Revista de Biologia Tropical | Year: 2016
Barra de Navidad lagoon is a coastal wetland of international importance (Ramsar site) and it is included among the 81 Mexican mangrove priority sites. One of the most valued characteristics of this lagoon is the presence of mangrove forest in a good conservation state. The goal of our research was the measurement of mangrove litter production and environmental factors influencing its dynamics. The mangrove area was divided into seven zones and litterfall was monthly sampled from November 2011 to October 2012 using 0.25 m2 square collectors made with mosquito mesh (1 mm) and positioned at 1.3 m above the ground. Abiotic variables of the interstitial water were measured simultaneously at each zone in permanent plots using a multi-parameter probe, YSI-556-M. Total mean value of litterfall production, weighted by zone surface, was 19.12 ± 1.23 gPS/m2.mo (2.29 t/ha.year). This low productivity is a consequence of the region’s dry climate and low tide range. The species Avicennia germinans and Laguncularia racemosa produced more than 80 % of total litterfall, while Rhizophora mangle contributed only 16 % and Conocarpus erectus < 4 %. A significant correlation between litterfall production and abiotic variables was found (e.g. salinity and interstitial water depth). We concluded that there are significant spatial variations in soil abiotic variables which are correlated with differences in mangrove species composition, and produce, together with the life cycles stages of those species, significant variations in the quantity and composition of litterfall. Future research will be focused on quantifying spatial variations in forest structure and their relationship with litterfall production. © 2016, Universidad de Costa Rica. All rights reserved.
Spatial and temporal variations of juvenile fish abundance in barra de navidad coastal lagoon, jalisco, méxico: Effects of hurricane jova [Variaciones espaciales y temporales de la abundancia de peces juveniles en la laguna costera Barra de Navidad, Jalisco, México: Efectos del huracán Jova]
Gonzalez-Sanson G.,University of Guadalajara |
Gonzalez-Sanson G.,Canadian Rivers Institute |
Aguilar-Betancourt C.,University of Guadalajara |
Aguilar-Betancourt C.,Canadian Rivers Institute |
And 5 more authors.
Revista de Biologia Marina y Oceanografia | Year: 2016
Seasonal and spatial variations of nearshore juvenile fish assemblages were assessed inside the coastal lagoon of Barra de Navidad, Jalisco, Mexico. Sampling was carried out during 2 different periods: March 2011 to February 2012 in site 1 and October 2012 to November 2013 in sites 1 and 2. During the first sampling period, the hurricane Jova (October 2011) hits the study area and introduced an unpredicted environmental impact. Samples of fish assemblages were taken using a beach purse seine. Water salinity, temperature and sediment granulometry were measured. A total of 36,897 individuals of 61 species were collected and their total lengths were measured. 90% of the species and 96% of the individuals were classified as juvenile. Four taxa (Anchoa spp., Eucinostomus currani, Diapterus peruvianus and Mugil spp.) made more than 80 percent of catches in number. Significant differences were found in fish assemblage composition between sampling periods and between seasons for site 1, while significant differences were found between sites and between seasons for the second sampling period. A significant difference was found in the composition of fish assemblages before and after the hurricane Jova at site 1 during the first sampling period. Strong seasonal changes in salinity are most probably the cause of changes found in fish assemblages along the year, while differences in sediment granulometry and organic matter percentages could explain differences between sampling sites. © 2016, Universidad de Valparaiso. All Rights Reserved.