Search results

The present study aims to construct ensemble machine learning (EML) algorithms for groundwater potentiality mapping (GPM) in the Teesta River basin of Bangladesh, including random forest (RF) and random subspace (RSS).

The RF and RSS models have been implemented for integrating 14 selected groundwater condition parametres with groundwater inventories for generating GPMs. The GPM were then validated using the empirical and bionormal receiver operating characteristics (ROC) curve.

The very high (831–1200 km²) and high groundwater potential areas (521–680 km²) were predicted using EML algorithms. The RSS (AUC-0.892) model outperformed RF model based on ROC's area under curve (AUC).

Two new EML models have been constructed for GPM. These findings will aid in proposing sustainable water resource management plans.

Bangladesh is one of the most flood-prone countries in the world. A number of research works have identified that the flood scenario will be aggravated with climate change context in Bangladesh. In 2014, Bangladesh had prepared municipal level master plan for 222 municipalities with a view to planned urban development. But climate change-induced flood has not been considered in master plan, which poses a question toward the sustainability of the plan. Ullapara Municipality of Sirajganj district has been selected to conduct the research. This study aims to evaluate how infrastructure in proposed master plan will be exposed to climate change-induced flood.

The methodology of this study follows geographic information system (GIS)-based flood exposure analysis of selected infrastructure. These infrastructures include transport infrastructure, educational infrastructure, health infrastructure and other urban facilities. Climate change-induced flood for the year 2040 has been used for flood exposure analysis.

It is evident from the flood exposure analysis that about 33.99% roads will be exposed to 1.5 m–2 m inundation level; seven primary school, six secondary school and four colleges would be highly exposed to 2.0 m–2.50 m inundation level; four health facilities would be exposed to 1.0 m–2.0 m inundation level because of future climate change. This inundation scenario for long duration will lead to dysfunction of concerned infrastructure and, in turn, undermine the stability of a socioeconomic system of Ullapara Municipality.

As the master plan is not fully implemented till now, there is scope for intervention for considering climate change-induced flood to make the plan sustainable.

The purpose of the paper is to predict mapping of areas vulnerable to flooding in the Ourika watershed in the High Atlas of Morocco with the aim of providing a useful tool capable of helping in the mitigation and management of floods in the associated region, as well as Morocco as a whole.

Four machine learning (ML) algorithms including k-nearest neighbors (KNN), artificial neural network, random forest (RF) and x-gradient boost (XGB) are adopted for modeling. Additionally, 16 predictors divided into categorical and numerical variables are used as inputs for modeling.

The results showed that RF and XGB were the best performing algorithms, with AUC scores of 99.1 and 99.2%, respectively. Conversely, KNN had the lowest predictive power, scoring 94.4%. Overall, the algorithms predicted that over 60% of the watershed was in the very low flood risk class, while the high flood risk class accounted for less than 15% of the area.

There are limited, if not non-existent studies on modeling using AI tools including ML in the region in predictive modeling of flooding, making this study intriguing.

The purpose of this study is to evaluate the rainfall intensities and their limits for durations from 0.25 to 8 h with return periods from 2 to 100 years for Ca Mau City in Vietnam.

First, the quality of the historical rainfall data series in 44 years (1975–2018) at Ca Mau station was assessed using the standard normal homogeneity test and the Pettitt test. Second, the appraised rainfall data series are used to establish the rainfall intensity-duration-frequency curve for the study area.

Based on the findings, a two-year return period, the extreme rainfall intensities (ERIs) ranged from 9.1 mm/h for 8 h rainstorms to 91.2 mm/h for 0.25 h. At a 100-year return period, the ERIs ranged from 18.4 mm/h for 8 h rainstorms to 185.8 mm/h for 0.25 h. The results also show that the narrowest uncertainty level between the lower and upper limits recorded 1.6 mm at 8 h for the two-year return period while the widest range is at 42.5 mm at 0.25 h for the 100-year return period. In general, the possibility of high-intensity rainfall values compared to the extreme rainfall intensities is approximately 2.0% at the 100-year return period.

The results of the rainfall IDF curves can provide useful information for policymakers to make the right decisions in controlling and minimizing flooding in the study area.

The purpose of this paper is to explore perceptions of the advantages and disadvantages of green roofs for commercial real estate building owners/occupiers in a UK city and consider how these might affect the chances of their adoption.

Two sets of semi-structured interviews were conducted with purposively selected respondents, 10 with and 25 without green roofs, to compare and contrast differing perspectives. A grounded theory approach was taken to data analysis, allowing themes to emerge directly from the data.

Low awareness and understanding were observed amongst those without green roofs, which positively affected perceived costs whilst negatively affecting perceived benefits. Green roof owners gave weight to wider societal and ecosystem services benefits, whilst those without focussed much more upon building-level benefits and costs.

Because of the restricted sample size, the findings in themselves are not generalizable; rather, themes are drawn from the research for reflection.

Findings point to steps that might be required of regional and national government to increase green roof uptake. This could involve initiating conversations to raise awareness, shift discourse and perceived norms and best practice; offering incentives, education and training; and presenting high-profile exemplar projects of green roofing to begin to mainstream the technology and get it onto the radar of building owners.

Bringing together social research around cohorts with and without green roofs, the paper throws into sharp relief discussions around costs and benefits and points towards potentially more productive directions for action to encourage consideration and take-up of green roofs by building owners.

Grassland in Qinghai as the main type of ecosystem in this region is located in arid and semi-arid areas. The ecosystem is fragile and sensitive to climate change. Grassland ecosystem not only provides essential ecological and life functions for human society but also plays a vital role in mitigating and adapting to climate change. The empirical literature on grassland ecosystem services value (ESV) does not consider the impact of climate change and regional economic development level factors, which prevents policymakers from making appropriate decisions. This paper aims to analyze the influencing factors of grassland ESV assessment, and, based on the meta-prediction model, account the grassland ESV in Qinghai province.

To understand the value of grassland ecosystem services in China under climate change, this paper used 61 research literature on the evaluation of grassland ESV in China, including a total of 564 value observations to establish a value transfer database. Based on the meta-analysis method, this study has constructed a value transfer model, to evaluate the grassland ESV in Qinghai province, and an interpretation model, which can analyze if the independent variables affect the grassland ESV significantly.

The study finds that the evaluation methods, types of ecosystem service functions, climate change and grassland types can affect the grassland ESV significantly. Based on the meta-regression prediction model to evaluate the grassland ESV in Qinghai is US$1,542.67/ha/year. It indicates several targeted approaches to increase the grassland ESV, and climate change also has a specific impact on the value of grassland ecosystem services.

This study provides a scientific basis for grassland management related to the development of grasslands and ecological compensation, as well as promote the sustainable development of grassland ecosystems.

This paper contributes to the field of grassland ESV assessment in at least three aspects; first, it innovatively introduces the meta-analysis to carry out an integrated analysis of previous research results; second, it includes a broader set of influence variables in the analysis, including meteorological and economic factors; and third, it establishes a methodological basis for the field of grassland ESV accounting.

The purpose of this paper is to set out the policy guidelines and recommendations to harmonise the Serbian water legislation with European Union standards in the area of water system management as impacted by climate change.

The EU Water Framework Directive is analysed in the context of implementation of the integrated water management policy presented in the Serbian Water Law (2010), as well as the National Water Management Strategy (2016). It has been found that the water management legislation that deals with the impact of climate change on water resources is incomplete. Although there are numerous challenges related to research of climate change and water systems, water policy and legal aspects cannot be neglected. The so-called soft law instruments represented in a form of strategy documents could be a valuable response in terms of an adaptive and integrated water policy approach.

The research is applied to a case study of the Velika Morava River Basin, at Ljubicevski Most hydrological station. Long-term projections suggest a decrease in annual precipitation levels and annual flows up to the year 2100 for climatic scenarios A1B and A2, accompanied by a rapid increase in air temperatures.

This study proposes a water management policy and provides recommendations for the Velika Morava River Basin as impacted by climate change, according to the European Union legislation.

The current fire protection measures in buildings do not account for all contemporary fire hazard issues, which has made fire safety a growing concern. Therefore, this paper aims to present a critical review of current fire protection measures and their applicability to address current challenges relating to fire hazards in buildings.

To overcome fire hazards in buildings, impact of fire hazards is also reviewed to set the context for fire protection measures. Based on the review, an integrated framework for mitigation of fire hazards is proposed. The proposed framework involves enhancement of fire safety in four key areas: fire protection features in buildings, regulation and enforcement, consumer awareness and technology and resources advancement. Detailed strategies on improving fire safety in buildings in these four key areas are presented, and future research and training needs are identified.

Current fire protection measures lead to an unquantified level of fire safety in buildings, provide minimal strategies to mitigate fire hazard and do not account for contemporary fire hazard issues. Implementing key measures that include reliable fire protection systems, proper regulation and enforcement of building code provisions, enhancement of public awareness and proper use of technology and resources is key to mitigating fire hazard in buildings. Major research and training required to improve fire safety in buildings include developing cost-effective fire suppression systems and rational fire design approaches, characterizing new materials and developing performance-based codes.

The proposed framework encompasses both prevention and management of fire hazard. To demonstrate the applicability of this framework in improving fire safety in buildings, major limitations of current fire protection measures are identified, and detailed strategies are provided to address these limitations using proposed fire safety framework.

Fire represents a severe hazard in both developing and developed countries and poses significant threat to life, structure, property and environment. The proposed framework has social implications as it addresses some of the current challenges relating to fire hazard in buildings and will enhance overall fire safety.

The novelty of proposed framework lies in encompassing both prevention and management of fire hazard. This is unlike current fire safety improvement strategies, which focus only on improving fire protection features in buildings (i.e. managing impact of fire hazard) using performance-based codes. To demonstrate the applicability of this framework in improving fire safety in buildings, major limitations of current fire protection measures are identified and detailed strategies are provided to address these limitations using proposed fire safety framework. Special emphasis is given to cost-effectiveness of proposed strategies, and research and training needs for further enhancing building fire safety are identified.

This study aims to present the climate change effect on soil moisture regimes in Mexico in a global 1.5°C warming scenario.

The soil moisture regimes were determined using the Newhall simulation model with the database of mean monthly precipitation and temperature at a scale of 1: 250,000 for the current scenario and with the climate change scenarios associated with a mean global temperature increase of 1.5°C, considering two Representative Concentration Pathways, 4.5 and 8.5 W/m² and three general models of atmospheric circulation, namely, GFDL, HADGEM and MPI. The different vegetation types of the country were related to the soil moisture regimes for current conditions and for climate change.

According to the HADGEM and MPI models, almost the entire country is predicted to undergo a considerable increase in soil moisture deficit, and part of the areas of each moisture regime will shift to the next drier regime. The GFDL model also predicts this trend but at smaller proportions.

The changes in soil moisture at the regional scale that reveal the impacts of climate change and indicate where these changes will occur are important elements of the knowledge concerning the vulnerability of soils to climate change. New cartography is available in Mexico.