Predicting stream water quality under different urban development pattern scenarios with an interpretable machine learning approach

So-Young

et al. 2021

Water

This study evaluated watershed health (WH) change using reference values for environmental changes at various times. Land use in 1985 was defined as the reference value under the most natural conditions, and the WH for the years 1995 to 2019 was calculated in comparison to 1985. The proposed method was used to assess the WH of 78 standard subbasins in South Korea’s Geum River Basin (GRB), where complex land-use change has occurred since 1995. For evaluating hydrology and water quality (WQ) health index, Soil and Water Assessment Tool (SWAT) and four land-use maps (1985, 1995, 2008, and 2019) were used to simulate the hydrology and WQ. A multivariate normal distribution (MND) from poor (0) to good (1) was used to assess WH based on SWAT modeling results. Based on the reference value, the WQ health from 1995 to 2019 changed to within 0.1, while the range of changes in the hydrology index was analyzed over 0.18. As a result of WH changes from 1985 to 2019, hydrological health deteriorated in high-density urbanized subbasins, while WQ health deteriorated in upland-cultivation-increased subbasins. This study provides useful information for recognizing potential WH issues related to long-term environmental changes.

Section: Land-use Change Impact On Whmentioning

confidence: 94%

Evaluation of Land-Use Changes Impact on Watershed Health Using Probabilistic Approaches

So-Young

et al. 2021

Water

Environment and Planning B: Urban Analytics and City Science

“…Urban forests moderate temperatures in local microclimates, resulting in energy savings (Sawka et al, 2013) and improved air quality in adjacent neighborhoods (Nowak et al, 2006;Saebø et al, 2012). Moreover, studies show that urban forests locally control rainfall surface runoff (Inkil€ ainen et al, 2013), improve water quaity (Wang et al 2021), enhance soil stabilization (Grau et al, 2008) and support biodiversity by providing habitat to many species (Goddard et al, 2010;Nielsen et al, 2014). The multifunctionality of urban forests is also emphasized by the numerous health and recreational benefits delivered to local residents (Jorgensen and Gobster, 2010;Tzoulas et al, 2007).…”

Section: Planning Methods For Multifunctional Green Infrastructurementioning

confidence: 99%

A regional spatial planning model for multifunctional green infrastructure

Goodspeed

Liu

Gounaridis

et al. 2021

There is a growing interest in planning for green infrastructure, as well as a growing recognition of the multifunctional nature of green infrastructure, since it provides many social and environmental benefits to cities and regions. However, there is a lack of appropriate methods for prioritizing the locations for green infrastructure interventions. In response, this article proposes a spatial multi-criteria analysis for green infrastructure. We demonstrate the method at the regional scale for Southeast Michigan, as well as through two embedded case studies within this region. We show how the method can be adapted for rural parks and conservation planning, as well as for urban green infrastructure planning within the City of Detroit. Although lacking the analytical structure needed for some planning questions, and limited by data and access to appropriate technical skills, we argue the spatial planning approach strikes an appropriate balance between technical rigor and transparency required for collaborative planning practice. The described GIS-based analysis technique can be used as part of a planning process to identify locations for green infrastructure expansion or improvement in a way that acknowledges and balances their social and environmental benefits.

“…However, in practical water quality prediction, the relationships between Chl-a concentrations and impact factors are usually nonlinear and there are interactive effects among different factors. Therefore, the linear statistical models have relatively low simulation accuracy [20]. Compared with mathematical statistical models, machine learning models can identify complex nonlinear relationships to the greatest extent and have better processing capacity with imbalanced data and missing data, so they have lower data requirements, higher prediction accuracy and more robust prediction performance [20,50].…”

Section: Performance Comparisons Of Machine Learning Models and Other Modelsmentioning

confidence: 99%

“…In recent years, with the development of artificial intelligence, various machine learning models have also developed rapidly. With the advantages of high efficiency in calculating very large data collections, great ability to analyze complex nonlinear relationships and low data requirements, these models were expected to solve complex water environmental problems, such as predicting water resource availability [16], revealing hydrological phenomena of large basins [17,18], analyzing water quality variations [19,20], and so on. Some scholars used machine learning models and traditional statistical models to predict water quality variations and found that machine learning models had less data demand, higher prediction accuracy, and greater accuracy improvement with more driving factors introduced [21,22].…”

Section: Introductionmentioning

confidence: 99%

Machine Learning-Based Prediction of Chlorophyll-a Variations in Receiving Reservoir of World’s Largest Water Transfer Project—A Case Study in the Miyun Reservoir, North China

Liao

Zang

Wang

et al. 2021

Water

Although water transfer projects can alleviate the water crisis, they may cause potential risks to water quality safety in receiving areas. The Miyun Reservoir in northern China, one of the receiving reservoirs of the world’s largest water transfer project (South-to-North Water Transfer Project, SNWTP), was selected as a case study. Considering its potential eutrophication trend, two machine learning models, i.e., the support vector machine (SVM) model and the random forest (RF) model, were built to investigate the trophic state by predicting the variations of chlorophyll-a (Chl-a) concentrations, the typical reflection of eutrophication, in the reservoir after the implementation of SNWTP. The results showed that compared with the SVM model, the RF model had higher prediction accuracy and more robust prediction ability with abnormal data, and was thus more suitable for predicting Chl-a concentration variations in the receiving reservoir. Additionally, short-term water transfer would not cause significant variations of Chl-a concentrations. After the project implementation, the impact of transferred water on the water quality of the receiving reservoir would have gradually increased. After a 10-year implementation, transferred water would cause a significant decline in the receiving reservoir’s water quality, and Chl-a concentrations would increase, especially from July to August. This led to a potential risk of trophic state change in the Miyun Reservoir and required further attention from managers. This study can provide prediction techniques and advice on water quality security management associated with eutrophication risks resulting from water transfer projects.