Harnessing urban analytics and machine learning for sustainable urban development: A multidimensional framework for modeling environmental impacts of urbanization in Saudi Arabia.

Sustainable urban development is crucial for managing natural resources and mitigating environmental impacts induced by rapid urbanization. This study demonstrates an integrated framework using machine learning-based urban analytics techniques to evaluate spatiotemporal urban expansion in Saudi Arabia (1987-2022) and quantify impacts on leading land, water, and air-related environmental parameters (EPs). Remote sensing and statistical techniques were applied to estimate vegetation health, built-up area, impervious surface, water bodies, soil characteristics, thermal comfort, air pollutants (PM2.5, CH4, CO, NO2, SO2), and nighttime light EPs. Regression assessment and Principal Component Analysis (PCA) were applied to assess the relationships between urban expansion and EPs. The findings highlight the substantial growth of urban areas (0.067%-0.14%), a decline in soil moisture (16%-14%), water bodies (60%-22%), a nationwide increase of PM2.5 (44 µg/m3 to 73 µg/m3) and night light intensity (0.166-9.670) concentrations resulting in significant impacts on land, water, and air quality parameters. PCA showed vegetation cover, soil moisture, thermal comfort, PM2.5, and NO2 are highly impacted by urban expansion compared to other EPs. The results highlight the need for effective and sustainable interventions to mitigate environmental impacts using green innovations and urban development by applying mixed-use development, green space preservation, green building technologies, and implementing renewable energy approaches. The framework recommended for environmental management in this study provides a robust foundation for evidence-based policies and adaptive management practices that balance economic progress and environmental sustainability. It will also help policymakers and urban planners in making informed decisions and promoting resilient urban growth.

Decoding seasonal variability of air pollutants with climate factors: A geostatistical approach using multimodal regression models for informed climate change mitigation.

In response to changes in climatic patterns, a profound comprehension of air pollutants (AP) variability is vital for enhancing climate models and facilitating informed decision-making in nations susceptible to climate change. Earlier research primarily depended on limited models, potentially neglecting intricate relationships and not fully encapsulating associations. This study, in contrast, probed the spatiotemporal variability of airborne particles (CO, CH4, SO2, and NO2) under varying climatic conditions within a climate-sensitive nation, utilizing multiple regression models. Spatial and seasonal AP data were acquired via the Google Earth Engine platform, which indicated elevated AP concentrations in primarily urban areas. Remarkably, the average airborne particle levels were lower in 2020 than in 2019, though they escalated during winter. The study employed linear regression, Pearson's correlation (PC), Spearman rank correlation models, and Geographically Weighted Regression (GWR) models to probe the relationship between pollutant variability and climatic elements such as rainfall, temperature, and humidity. Across all seasons, APs showed a negative correlation with rainfall while displaying positive correlations with temperature and humidity. The GWR and PC models produced the most reliable results from all the models employed, with the GWR model superseding the rest. Moreover, heightened aerosol levels were detected within a rainfall range of 600 mm/season, a temperature range of 25-30 °C, and humidity levels of 75 %-85 %. Overall, this study emphasizes the growing levels of APs in correlation with meteorological changes. By adopting a comprehensive approach and considering multiple factors, this research provides a more sophisticated understanding of the relationship between AP variability and climatic shifts.

Spatiotemporal characterization of relative humidity trends and influence of climatic factors in Bangladesh.

The frequency and intensity of climate change and resulting impacts are more prevalent in South Asian countries, particularly in Bangladesh. Relative humidity (RH) is a crucial aspect of climate, and higher RH variability has far-reaching impacts on human health, agriculture, environment, and infrastructure. While temperature and rainfall have gained much research attention, RH studies have received scant attention in the research literature. This study investigated the trends and variability of RH levels in Bangladesh and the influence of other meteorological factors over the past 40 years. Variabilities in the meteorological factors were identified by calculating descriptive statistics. Innovative trend analysis (ITA) and Mann-Kendall test (MK-test) methods were utilized to assess monthly, seasonal, and annual trends. The magnitude of temperature, rainfall, and windspeed influences on RH variability were identified using Pearson's correlation, Spearman rank correlation, and Kendall correlation model. Variability analysis showed higher spatial variations in RH levels across the country, and RH skewed negatively in all stations. Results reveal that daily, monthly, seasonal, and annual trends of RH exhibited positive trends in all stations, with an increasing rate of 0.083-0.53% per year in summer, 0.43-0.68% per year in winter, and 0.58-0.31% per year in the rainy season. Both ITA and MK-test provided consistent results, indicating no discrepancies in trend results. All three models indicate that temperature, rainfall, and windspeed have weak to moderate positive influences on changing RH levels in Bangladesh. The study will contribute to decision-making to improve crop yields, health outcomes, and infrastructure efficiency.

Estimating ground-level PM2.5 using subset regression model and machine learning algorithms in Asian megacity, Dhaka, Bangladesh.

Fine particulate matter (PM2.5) has become a prominent pollutant due to rapid economic development, urbanization, industrialization, and transport activities, which has serious adverse effects on human health and the environment. Many studies have employed traditional statistical models and remote-sensing technologies to estimate PM2.5 concentrations. However, statistical models have shown inconsistency in PM2.5 concentration predictions, while machine learning algorithms have excellent predictive capacity, but little research has been done on the complementary advantages of diverse approaches. The present study proposed the best subset regression model and machine learning approaches, including random tree, additive regression, reduced error pruning tree, and random subspace, to estimate the ground-level PM2.5 concentrations over Dhaka. This study used advanced machine learning algorithms to measure the effects of meteorological factors and air pollutants (NOX, SO2, CO, and O3) on the dynamics of PM2.5 in Dhaka from 2012 to 2020. Results showed that the best subset regression model was well-performed for forecasting PM2.5 concentrations for all sites based on the integration of precipitation, relative humidity, temperature, wind speed, SO2, NOX, and O3. Precipitation, relative humidity, and temperature have negative correlations with PM2.5. The concentration levels of pollutants are much higher at the beginning and end of the year. Random subspace is the optimal model for estimating PM2.5 because it has the least statistical error metrics compared to other models. This study suggests ensemble learning models to estimate PM2.5 concentrations. This study will help quantify ground-level PM2.5 concentration exposure and recommend regional government actions to prevent and regulate PM2.5 air pollution. Supplementary Information: The online version contains supplementary material available at 10.1007/s11869-023-01329-w.

Environmental impact assessment of tobacco farming in northern Bangladesh.

Tobacco farming in Bangladesh has significant and far-reaching environmental impacts, affecting the land, water, and air. While the country has implemented tobacco control measures, the lack of monitoring and enforcement has resulted in environmental degradation and public health concerns. This study aims to document the environmental impact of tobacco farming in Bangladesh, adopting a qualitative approach to collect and analyze data. The study used focus group discussions, key informant interviews, and a structured questionnaire survey to gather data, assessing the impact of tobacco farming on the environment, socioeconomic conditions, and human health using a five-point impact assessment scale. Results illustrated that tobacco cultivation contributes to the ecosystem and natural resource degradation, leading to a loss of habitat diversity and domestic animal death. Soil erosion, water pollution, and air pollution from excessive plowing and pesticide usage have also been observed, causing skin diseases and other health issues. Despite some economic benefits, social conditions have worsened due to drug addiction and conflicts among tobacco workers. The study will help policymakers and environmentalists by highlighting the need to take action in reducing the environmental and social impacts of tobacco farming in Bangladesh. It also informs the public about the potential tobacco production and consumption risks. This study provides important insights into the adverse effects of tobacco farming in Bangladesh and emphasizes the importance of implementing appropriate measures to reduce environmental and public health impacts.

A GIS and remote sensing approach for measuring summer-winter variation of land use and land cover indices and surface temperature in Dhaka district, Bangladesh.

Rapid urbanization has induced land use and land cover change (LULC) that increases land surface temperature (LST). Analyzing seasonal variations of LULC and LST is a precondition for mitigating heat island effects and promoting a sustainable living environment. The objective of this study is to explore the association between the seasonal LST dynamics and LULC indices for the Dhaka district of Bangladesh. The LULC indices are comprised of the Normalized Difference Vegetation Index (NDVI), Normalized Difference Built-up Index (NDBI), Normalized Difference Bareness Index (NDBAI), and Modified Normalized Difference Water Index (MNDWI). The results show that the LULC effect on LST in Dhaka is significant, with an increase in summer season LST from 34.58 °C to 37.66 °C and in winter season LST from 24.710C to 26.24 °C. Predictably, the highest and lowest LST values were observed in the built-up and vegetation-covered areas, respectively. Secondly, the correlation values indicate a significant inverse correlation (R2 > 0.50) between NDVI and LST, as well as MNDWI and LST. On the contrary, positive correlations were observed between NDBI and LST, and between NDBAI and LST for both the summer and winter seasons. Finally, subsequent vegetation decline (-69.34%) and increasing built-up area (+11.30%) between 2000 and 2020 in Dhaka district were found to be the most significant factors for the increasing trend and spatial heterogeneity of LST in Dhaka. The methodological approach of this study offers a low-cost efficient technique for monitoring LST hotspots, which can guide land use planners and urban managers for spatial intervention to ensure a livable environment.

Environmental benefits of blue ecosystem services and residents' willingness to pay in Khulna city, Bangladesh.

Nature-based solutions for urban problems gaining popularity globally. The well-functioning ecosystem could offer a nature-based solution to many urban problems including water, drainage and flooding problems. Therefore, conservation and restoration of urban blue ecosystem components such as pond scape are crucial. This research taking Khulna city of Bangladesh as a case has examined the low-income fringe community's willingness to pay (WTP) for conservation and restoration of pond scape/blue ecosystem service (BES) in their locality from where they benefit. The various types of ecosystem services enjoyed by the local community were identified. To assess the community's WTP for conservation and restoration of pond scape, the payment card approach of the Contingent Valuation Method (CVM) was used. Three environmental attributes were considered to assess the existing condition of the blue ecosystem services in the study area. Findings show that 54% of respondents are not satisfied with the existing conditions of the ecosystem services resulting from the pond scape. Respondent's WTP for eleven types of service facilities was calculated. Results show that only 65.20% are eager to pay an amount of 38 Tk to 138 Tk per month for different service facilities. It means about one-third of the community people want to be free riders. The influences of different attributes of the respondents on their WTP were also analyzed. Education, income, and house-ownership appear to have a positive significant influence on WTP for conservation and restoration of pond scape in the study area. In line with the findings if policy measures are taken without further delay it would help conserve the remaining pond scape.