Application of newly developed ensemble machine learning models for daily suspended sediment load prediction and related uncertainty analysis

ABSTRACT

Ensemble machine learning models have been widely used in hydro-systems modeling as robust prediction tools that combine multiple decision trees. In this study, three newly developed ensemble machine learning models, namely gradient boost regression (GBR), AdaBoost regression (ABR) and random forest regression (RFR) are proposed for prediction of suspended sediment load (SSL), and their prediction performance and related uncertainty are assessed. The SSL of the Mississippi River, which is one of the major world rivers and is significantly affected by sedimentation, is predicted based on daily values of river discharge (Q) and suspended sediment concentration (SSC). Based on performance metrics and visualization, the RFR model shows a slight lead in prediction performance. The uncertainty analysis also indicates that the input variable combination has more impact on the obtained predictions than the model structure selection.     

Collocated Cokriging Based on Merged Secondary Attributes

There exist many secondary data that must be considered in in reservoir characterization for resource assessment and performance forecasting. These include multiple seismic attributes, geological trends and structural controls. It is essential that all secondary data be accounted for with the precision warranted by that data type. Cokriging is the standard technique in geostatistics to account for multiple data types. The most common variant of cokriging in petroleum geostatistics is collocated cokriging. Implementations of collocated cokriging are often limited to a single secondary variable. Practitioners often choose the most correlated or most relevant secondary variable. Improved models would be constructed if multiple variables were accounted for simultaneously. This paper presents a novel approach to (1) merge all secondary data into a single super secondary variable, then (2) implement collocated cokriging with the single variable. The preprocessing step is straightforward and no major changes are required in the standard implementation of collocated cokriging. The theoretical validity of this approach is proven, that is, the results are proven to be identical to a “full” approach using all multiple secondary variables simultaneously.     

Exploring Spatial Non‐Stationarity and Varying Relationships between Crash Data and Related Factors Using Geographically Weighted Poisson Regression

The spatial nature of crash data highlights the importance of employing Geographical Information Systems (GIS) in different fields of safety research. Recently, numerous studies have been carried out in safety analysis to investigate the relationships between crashes and related factors. Trip generation as a function of land use, socio‐economic, and demographic characteristics might be appropriate variables along with network characteristics and traffic volume to develop safety models. Generalized Linear Models (GLMs) describe the relationships between crashes and the explanatory variables by estimating the global and fixed coefficients. Since crash occurrences are almost certainly influenced by many spatial factors; the main objective of this study is to employ Geographically Weighted Poisson Regression (GWPR) on 253 traffic analysis zones (TAZs) in Mashhad, Iran, using traffic volume, network characteristics and trip generation variables to investigate the aspects of relationships which do not emerge when using conventional global specifications. GWPR showed an improvement in model performance as indicated by goodness‐of‐fit criteria. The results also indicated the non‐stationary state in the relationships between the number of crashes and all independent variables.