Evaluating different machine learning methods to simulate runoff from extensive green roofs

Green roofs are increasingly popular measures to permanently reduce or delay storm-water runoff. The main objective of the study was to examine the potential of using machine learning (ML) to simulate runoff from green roofs to estimate their hydrological performance. Four machine learning methods, artificial neural network (ANN), M5 model tree, long short-term memory (LSTM) and k nearest neighbour (kNN), were applied to simulate storm-water runoff from 16 extensive green roofs located in four Norwegian cities across different climatic zones. The potential of these ML methods for estimating green roof retention was assessed by comparing their simulations with a proven conceptual retention model. Furthermore, the transferability of ML models between the different green roofs in the study was tested to investigate the potential of using ML models as a tool for planning and design purposes. The ML models yielded low volumetric errors that were comparable with the conceptual retention models, which indicates good performance in estimating annual retention. The ML models yielded satisfactory modelling results (NSE >0.5) in most of the roofs, which indicates an ability to estimate green roof detention. The variations in ML models' performance between the cities was larger than between the different configurations, which was attributed to the different climatic characteristics between the four cities. Transferred ML models between cities with similar rainfall events characteristics (Bergen–Sandnes, Trondheim–Oslo) could yield satisfactory modelling performance (Nash–Sutcliffe efficiency NSE >0.5 and percentage bias |PBIAS| <25 %) in most cases. However, we recommend the use of the conceptual retention model over the transferred ML models, to estimate the retention of new green roofs, as it gives more accurate volume estimates. Follow-up studies are needed to explore the potential of ML models in estimating detention from higher temporal resolution datasets.

Simulation of Urban Storm Water Runoff Control Based on Big Data

The acceleration of urbanization has brought about rapid economic development, but at the same time, it has also brought some damage to the ecological environment. The proportion of hardened area of the ground is higher and higher, and the rainwater runoff pollution caused by rainfall is more and more serious. In order to follow the sustainable development strategy, and for the more stable and high-speed economic development, the control of rainwater runoff pollution is urgent. The purpose of this paper is to simulate the urban storm water runoff control and find the most suitable scheme for storm water runoff pollution control. Because the simulation of SWMM is more accurate than other models, it can directly reflect the situation of rainwater runoff pollution, so the model selected for rainwater runoff in this paper is SWMM, and then build the model, through the collection and collation of the basic data of the study area, the generalization of the sub catchment area and drainage network is completed. Through the analysis of the characteristics of the study area, the rainwater garden and permeable pavement are determined as the scheme to control the rainwater runoff in the study area. Finally, the SWMM model is used to simulate the control effect of rainwater garden and pervious pavement on rainwater runoff pollution control. The experimental results show that the storm water garden can effectively control the impact of SS scouring effect on the environment, significantly reduce the discharge of SS, and significantly reduce the peak concentration of SS, and its ability to control SS increases with the thickness of the surface plant layer. The control ability of rain permeable brick pavement to SS increases with the increase of surface porosity, that is, the control effect of SS is the best when the porosity is 20%.

AN ANALYSIS ON THE EFFICIENCY OF GREEN ROOF IN MANAGING URBAN STORMWATER RUNOFF

Modernization has created new impervious urban landscape contributed to major catastrophe. Urban drainage system incapable to convey the excess rainwater resulting in flash flood due to heavy rainfall. The combination of green roof on building have tremendously proved to control stormwater efficiently. This study is conducted to review the efficiency of intensive and extensive green roof in reducing urban storm water runoff. This study identifies characteristic of green roof that contributes to lessening urban storm water runoff. Data was collected based on rigorous literature reviews and analyzed using meta-analysis. Overall, findings revealed intensive green roof performed better in reducing storm water runoff compared to extensive green roof. Green roof performance increases as the depth of substrate increased. Origanum and Sedum plants are both highly effective for intensive and extensive green roofs. The performance of green roof reduces as degree of roof slope increased.

Biochar as a Soil Amendment: Reduction in Mercury Transport from Hydraulic Mine Debris

Mercury mining and its use in gold mine operations left a legacy of contamination in northern California. Contaminated sediments and water continue to affect local and downstream ecosystems. To assess the efficacy of biochar-amended soils on decreasing Hg transport, biochar was used to amend rock and sediment columns and mesocosms to decrease suspended sediment and associated mercury (Hg) in storm water runoff from Sierra Nevada hydraulic mines. Mercury-contaminated storm water runoff and hydraulic mine debris were collected from two hydraulic mine sites in the Yuba River, California watershed. Mercury concentrations and turbidity were analyzed from storm water samples and hydraulic mine debris in three simulated storm runoff experiments using decomposed granite columns, sediment columns, and sediment mesocosms amended at 0%, 2%, or 5% biochar by weight. Columns containing hydraulic mine debris and mixed with 5% biochar had a significant (p < 0.05) reduction in filter-passed mercury (FHg) in the outflow as compared to control columns. To simulate saturated hydraulic mine debris runoff, mesocosms were filled with mine sediment and saturated with deionized water to generate runoff. Five percent biochar in mesocosm trays decreased FHg significantly (p < 0.001), but, because of the angle of the tray, sediment also moved out of the trays. Biochar was effective at reducing FHg from hydraulic mine discharge. Biochar in laboratory columns with decomposed granite or mine sediments was more effective at removing Hg than mesocosms.

Performance of pervious concrete under shear and bearing strengths

Pervious concrete is one of the materials with potential applications in the construction industry because it can help reduce environmental problems caused by conventional concrete, improve storm water management, and provide a low-impact development alternative. Pervious concrete has numerous advantages, including assisting with water filtering and lowering pollutants. The ability to reduce storm water runoff is the most important feature that attracts the attention of pervious concrete. The objective of the present investigation is to evaluate the properties of pervious concrete and compare them with normal concrete. On the other hand, the requirement for aggregate to produce concrete is high, while natural resources are reduced. An attempt was made to use Black Marble Stone Waste Aggregate in concrete by replacing natural aggregate at a ratio of 0, 50, and 100%.To obtain the behavior of pervious concrete, compressive, shear and bearing strength are evaluated. A total of 54 specimens were casted and tested in this experimental work to study the behavior of concrete. To assess the shear and bearing strengths, a regression model was developed.

Special Issue on Treatment Wetlands

This Special Issue is concerned with treatment wetlands, which are artificial (or constructed) wetlands usually treating municipal or industrial wastewater, greywater and storm water runoff [...]

Geopolymer binder for pervious concrete

Construction of pervious concrete (PC) pavements is an exclusive and efficient measure for solving environmental problems while also contributing to sustainability. Pervious concrete enables rainwater to percolate into soil thus reducing the storm water runoff and assisting in ground water recharge. It is used for the construction of pedestrian pathways, parking lots, and in various other applications. During the research, the content of coarse aggregate grains in geopolymer binder was varied in order to investigate pervious concrete properties. It was established that pervious concrete with geopolymer binder containing fly ash meets requirements set in regulations, and that it can be used for sustainable pavement construction.