The Fourth International Workshop on Environmental Applications of Machine Learning EAML
نویسندگان
چکیده
Historically, management strategies in Canada’s boreal forest have focused on forestpolygons and terrestrial biodiversity to address ecological considerations in forestmanagement. However, efficient management strategies in Canada’s boreal forest mustconsider ecological processes from a watershed perspective. The Boreal Plain ecozone of theCanadian boreal forest is exemplified by low topographic relief, alkaline, phosphorus-richsoils developed from sedimentary bedrock. Thus, soil sediment during snowmelt and rainevents, when soil is more susceptible to erosion, represents the highest threat with respect tophosphorus migration to water bodies. Particulate phosphorus, being the dominantphosphorus form in the region, contributes largely to nutrient enrichment of receivingstreams. The area is currently experiencing both natural (mainly wildfires) and anthropogenic(primarily forest harvesting activities) watershed disturbance. The associated accelerated rateof watershed disturbance threatens to destabilize aquatic ecosystems of the region as a resultof possible dissolved oxygen depletion, cyanobacteria growth and toxin production. Hence, ascience-based decision support tool that can predict the impact of future forest activities onwater quantity and quality, particularly phosphorus concentration in receiving streams, iscritical to sustainable development of a forested ecosystem. This study represents a building block of the required decision support tool. It examines theapplicability of using artificial neural network (ANN) in modelling stream flow and water-phase phosphorus concentration from a watershed perspective. A three-layer feed forwardmulti layer perceptron ANN trained with error back propagation algorithm was used to modelboth the flow and the daily change in the total phosphorus concentration (∆TP) of a smallforested watershed, Northern Alberta, Canada. Flow was first modelled using EnvironmentCanada Whitecourt airport weather station data (rainfall, snowfall, and mean, minimum, andmaximum daily air temperatures). ∆TP was then modelled utilizing the produced modelledflow time series and the Environment Canada Whitecourt airport weather station data. Thecapabilities of time series analysis in quantifying autocorrelation and cross-correlationstatistics was utilized to identify possible model lagged inputs prior to model development
منابع مشابه
Machine learning algorithms in air quality modeling
Modern studies in the field of environment science and engineering show that deterministic models struggle to capture the relationship between the concentration of atmospheric pollutants and their emission sources. The recent advances in statistical modeling based on machine learning approaches have emerged as solution to tackle these issues. It is a fact that, input variable type largely affec...
متن کاملFault diagnosis in a distillation column using a support vector machine based classifier
Fault diagnosis has always been an essential aspect of control system design. This is necessary due to the growing demand for increased performance and safety of industrial systems is discussed. Support vector machine classifier is a new technique based on statistical learning theory and is designed to reduce structural bias. Support vector machine classification in many applications in v...
متن کاملInternational Workshop on Current Challenges in Kernel Methods ( CCKM 06 )
The official 2006 kernel workshop " 10 years of kernel machines " Koninklijke Vlaamse Academie van België Sponsors De Wetenschappelijke Onderzoeksgemeenschap (WOG) " Machine Learning for Data Mining and its Applications " De Koninklijke Vlaamse Academie van Belgie (KVAB) The PASCAL network of excellence
متن کاملMachine learning algorithms for time series in financial markets
This research is related to the usefulness of different machine learning methods in forecasting time series on financial markets. The main issue in this field is that economic managers and scientific society are still longing for more accurate forecasting algorithms. Fulfilling this request leads to an increase in forecasting quality and, therefore, more profitability and efficiency. In this pa...
متن کاملForecasting the Tehran Stock market by Machine Learning Methods using a New Loss Function
Stock market forecasting has attracted so many researchers and investors that many studies have been done in this field. These studies have led to the development of many predictive methods, the most widely used of which are machine learning-based methods. In machine learning-based methods, loss function has a key role in determining the model weights. In this study a new loss function is ...
متن کامل