Wetland classification in Newfoundland and Labrador using multi-source SAR and optical data integration

A vast portion of Newfoundland and Labrador (NL) is covered by wetland areas. Notably, it is the only province in Atlantic Canada that does not have a wetland inventory system. Wetlands are important areas of research because they play a pivotal role in ecological conservation and impact human activities in the province. Therefore, classifying wetland types and monitoring their changes are crucial tasks recommended for the province. In this study, wetlands in five pilot sites, distributed across NL, were classified using the integration of aerial imagery, Synthetic Aperture Radar, and optical satellite data. First, each study area was segmented using the object-based method, and then various spectral and polarimetric features were evaluated to select the best features for identifying wetland classes using the Random Forest algorithm. The accuracies of the classifications were assessed by the parameters obtained from confusion matrices, and the overall accuracies varied between 81% and 91%. Moreover, the average producer and user accuracies for wetland classes, considering all pilot sites, were 71% and 72%, respectively. Since the proposed methodology demonstrated high accuracies for wetland classification in different study areas with various ecological characteristics, the application of future classifications in other areas of interest is promising.     

Leveling geochemical data between map sheets

Geochemical surveys are frequently assembled into larger, regional compilations. In some cases a boundary shift in the values for one or more elements may be observed at the join of adjacent surveys. This indicates that data for the affected elements are not consistent between the surveys. Where the same sampling medium has been used, the shift may be due to different crews/organizations, who varied in their sampling techniques. However, most commonly the shift is due to imperfect calibration of the analytical method used for samples from the different surveys. For example, there may have been a lack of proper analytical standardization between survey programs. To carry out leveling, bands are established on either side of the boundary between two surveys that show a shift. It is desirable that the bands have a close match in terms of geology and physiography. A quantitative method is presented to estimate the optimum width for these bands. Quantiles of the data within each band are calculated. The quantile pairs are plotted in X–Y space and a line fitted to express the relationship between the pairs of quantiles. The equation of this line is used to correct the shift between the two surveys. This method is tested on data for Mo in stream sediments, and pH of stream water, from two National Geochemical Reconnaissance Surveys in British Columbia.     

Identification of homogenous regions in Gorganrood basin (Iran) for the purpose of regionalization

Estimation of flood in basins with poor condition of hydrometric stations as in quantity and quality is a dominant problem around the world, mainly in developing country where lack of funds and human resources cause more limitation in number of gauging stations. One of the areas that experience frequent floods and also suffer from small number of stations in Iran is Gorganrood basin. So there is a great need for the estimation and prediction of runoff in this area to prevent any future floods. Due to insufficient station in this area, direct prediction of flood is not applicable. Regional flood frequency analysis is a practical and widely used solution for these situations, which involves the identification of homogenous regions. Gorganrood region was hydrologically homogenized according to the extracted parameters that influence the floods. One of these parameters was Normalized Difference Vegetation Index (NDVI) driven from MODIS images. Curvature is another parameter that relates to topographic attributes. From factor analysis, the most appropriate variables were selected. According to these parameters (NDVI, curvature, area, slope…), the regions were classified into homogenous regions. For the purpose of homogenization, hierarchical (wards) clustering, fuzzy clustering and Kohonen method were applied. L-moment technique was used for the investigation of the results. The heterogeneity measure for one of the groups (Group 1) was more than two; therefore some modifications were applied. The region was grouped into two homogenous subregions. All of the clustering methods showed same results. The models showed that class 4 of NDVI is influential on flood in some return periods. The resulted models can be applied in future studies in different aspects of practical hydrology.     

Site selection for managed aquifer recharge using fuzzy rules: integrating geographical information system (GIS) tools and multi-criteria decision making

One of the most important water-resources management strategies for arid lands is managed aquifer recharge (MAR). In establishing a MAR scheme, site selection is the prime prerequisite that can be assisted by geographic information system (GIS) tools. One of the most important uncertainties in the site-selection process using GIS is finite ranges or intervals resulting from data classification. In order to reduce these uncertainties, a novel method has been developed involving the integration of multi-criteria decision making (MCDM), GIS, and a fuzzy inference system (FIS). The Shemil-Ashkara plain in the Hormozgan Province of Iran was selected as the case study; slope, geology, groundwater depth, potential for runoff, land use, and groundwater electrical conductivity have been considered as site-selection factors. By defining fuzzy membership functions for the input layers and the output layer, and by constructing fuzzy rules, a FIS has been developed. Comparison of the results produced by the proposed method and the traditional simple additive weighted (SAW) method shows that the proposed method yields more precise results. In conclusion, fuzzy-set theory can be an effective method to overcome associated uncertainties in classification of geographic information data.     

Evaluation of rainfall spatial correlation effect on rainfall-runoff modeling uncertainty,considering 2-copula

Lack of accuracy of rainfall-runoff simulation (RRS) remains critical for some applications. Among various sources of uncertainty, precipitation plays a particular role. Rainfall rates as the main input data of RRS are of the first factors controlling the accuracy. In addition to the depth, spatial and temporal distributions of rainfall impact the flood discharge. Most of the previous studies on RRS uncertainty have ignored rainfall spatial distribution, where in large catchments, it is necessary to be modeled explicitly. Karoon III is one most important basin of the Iran because of the Karoon III dam in the outlet. In the present work, effect of spatial correlation of rainfall on HEC-HMS (SMA) continuous RRS uncertainty is evaluated using 2variate copula (2copula). Monte Carlo simulation (MCS) approach was used to consider the rainfall spatial dependence. To reduce the computational expense, sampling efficiency and convergence for MCS, Latin hypercube sampling (LHS) was used. Copula functions consider wide range of marginal probability distribution functions (PDFs), eliminating limits of regular join PDFs. For this aim, two scenarios were investigated. In the first scenario, sub-basin rainfall was considered independent, and in the second scenario, 2copula was adopted to model spatial correlation of rainfall. Dimensionless rainfall depths were calculated for each sub-basin, and the PDFs were determined. The generated random dimensionless rainfalls were reweighted and multiplied by watershed’s mean rainfall value. Stochastic Climate Library was used to generate continuous daily rainfalls. Sampling from dimensionless rainfalls using LHS algorithm, 100 runs of calibrated model-simulated 100 flows for each day following MCS, and 80 % certainty bound was calculated. Results showed that considering dependence decreased 18 % of the maximum uncertainty bound width, so the methodology could be recommended for decreasing predicted runoff error.     

Precipitation forecasting using classification and regression trees (CART) model: a comparative study of different approaches

Interest in semiarid climate forecasting has prominently grown due to risks associated with above average levels of precipitation amount. Longer-lead forecasts in semiarid watersheds are difficult to make due to short-term extremes and data scarcity. The current research is a new application of classification and regression trees (CART) model, which is rule-based algorithm, for prediction of the precipitation over a highly complex semiarid climate system using climate signals. We also aimed to compare the accuracy of the CART model with two most commonly applied models including time series modeling (ARIMA), and adaptive neuro-fuzzy inference system (ANFIS) for prediction of the precipitation. Various combinations of large-scale climate signals were considered as inputs. The results indicated that the CART model had a better results (with Nash–Sutcliffe efficiency, NSE?>?0.75) compared to the ANFIS and ARIMA in forecasting precipitation. Also, the results demonstrated that the ANFIS method can predict the precipitation values more accurately than the time series model based on various performance criteria. Further, fall forecasts ranked “very good” for the CART method, while the ANFIS and the time series model approximately indicated “satisfactory” and “unsatisfactory” performances for all stations, respectively. The forecasts from the CART approach can be helpful and critical for decision makers when precipitation forecast heralds a prolonged drought or flash flood.     

Comparison of machine learning methods for copper ore grade estimation

In this study, machine learning methods such as neural networks, random forests, and Gaussian processes are applied to the estimation of copper grade in a mineral deposit. The performance of these methods is compared to geostatistical techniques, such as ordinary kriging and indicator kriging. To ensure that these comparisons are realistic and relevant, the predictive accuracy is estimated on test instances located in drill holes that are different from the training data. The results of an extensive empirical study in the Sarcheshmeh porphyry copper deposit in Southeastern Iran illustrate that specially designed Gaussian processes with a symmetric standardization of the spatial location inputs and an anisotropic kernel yield the most accurate predictions. Furthermore, significant improvements are obtained when, besides location, information on the rock type is included in the set of predictor variables. This observation highlights the importance of carrying out detailed studies of the geological composition of the deposit to obtain more accurate ore grade predictions.