Expert-assisted statistical learning techniques for assessing wetland conditions in urban landscapes

Abstract

Wetlands are essential components within the socio-ecological framework of urban areas, providing a wide range of ecosystem services. However, increasing natural and anthropogenic stressors place significant pressure on these wetlands, threatening their ability to sustain these vital services. To effectively assess wetland condition and develop appropriate management strategies, robust monitoring tools are needed. Statistical learning techniques, such as machine learning, have been proposed as a promising approach to enhance the development of these wetland monitoring tools. In this study, we evaluated the performance of the pre-existing wetland assessment tool used in the City of Calgary—the Aquatic Condition Index (ACI). We compared ACI performance using three different approaches for selecting indicators: machine-only selection, expert-only selection, and a hybrid approach where humans selected the indicators, but the machine determined the relationships between the indicators and wetland conditions. Our results showed that hybrid approaches, combining human expertise with statistical learning, outperformed both machine-only and expert-only methods. We then examined whether the ACI could be transitioned from field- and computer-based indicators to fully computer-based indicators using the hybrid method of selecting indicators. Our findings revealed comparable results between the two methods, suggesting that a computer-based monitoring system could help overcome the time and budgetary constraints associated with field-based monitoring while also enabling the examination of larger geographical areas. This study underscores the importance of human expertise in guiding the statistical learning process, particularly in the selection of indicators that accurately represent wetland processes.

Keywords

• Machine learning
• Neural networks
• Wetland management
• Wetland assessment