Using machine learning to examine street green space types at a high spatial resolution: Application in Los Angeles County on socioeconomic disparities in exposure

Exploring climate change discourse on social media and blogs using a topic modeling analysis

Climate change is one of the most pressing global issues of our time, and understanding public perception and awareness of the topic is crucial for developing effective policies to mitigate its effects. While traditional survey methods have been used to gauge public opinion, advances in natural language processing (NLP) and data visualization techniques offer new opportunities to analyze user-generated content from social media and blog posts. In this study, a new dataset of climate change-related texts was collected from social media sources and various blogs. The dataset was analyzed using BERTopic and LDA to identify and visualize the most important topics related to climate change. The study also used sentence similarity to determine the similarities in the comments written and which topic categories they belonged to. The performance of different techniques for keyword extraction and text representation, including OpenAI, Maximal Marginal Relevance (MMR), and KeyBERT, was compared for topic modeling with BERTopic. It was seen that the best coherence score and topic diversity metric were obtained with OpenAI-based BERTopic. The results provide insights into the public's attitudes and perceptions towards climate change, which can inform policy development and contribute to efforts to reduce activities that cause climate change.

Assessing and forecasting collective urban heat exposure with smart city digital twins

Due to population growth, climate change, and the urban heat island effect, heat exposure is becoming an important issue faced by urban built environments. Heat exposure assessment is a prerequisite for mitigation measures to reduce the impact of heat exposure. However, there is limited research on urban heat exposure assessment approaches that provides fine-scale spatiotemporal heat exposure information, integrated with meteorological status and human collective exposure as they move about in cities, to enable proactive heat exposure mitigation measures. Smart city digital twins (SCDTs) provide a new potential avenue for addressing this gap, enabling fine spatiotemporal scales, human-infrastructure interaction modeling, and predictive and decision support capabilities. This study aims to develop and test an SCDT for collective urban heat exposure assessment and forecasting. Meteorological sensors and computer vision techniques were implemented in Columbus, Georgia, to acquire temperature, humidity, and passersby count data. These data were then integrated into a collective temperature humidity index. A time-series prediction model and a crowd simulation were employed to predict future short-term heat exposures based on the data accumulated by this SCDT and to support heat exposure mitigation efforts. The results demonstrate the potential of SCDT to enhance public safety by providing city officials with a tool for discovering, predicting, and, ultimately, mitigating community exposure to extreme heat.

Temporal and spatial characteristics of high temperatures, heat waves, and population distribution risk in China from 1951 to 2019

Understanding the relationships between high temperatures (HT) and heat waves (HW) is vital for enhancing human health, especially in areas with dense population. This paper analyzes the temporal and spatial characteristics of different HT and HW intensities, their spatial influence, and the population distribution risk at different HW intensities for 844 meteorological stations between 1951 and 2019. The results indicate that (1) HT and extreme temperature (ET) days are symmetrically distributed along the Huhuanyong Line, from southeast to northwest China. The times, days, and accumulated temperatures of HW, the times, days, and accumulated temperature of strong heat waves (SHW), and the times, days, and accumulated temperature of extreme heat waves (EHW) were distributed similarly; (2) with the increase in high temperatures or heat waves from HT to ET or from HW to SHW, the proportion of stations with an upward trend was always greater in China, while stations with a downward trend were mainly located in the North China Plain and Huai River Basin. For HW, SHW, and EHW, the increasing range of times and days were less than the accumulated temperatures; (3) between 1990 and 2019, there was an expansion of the HW and SHW distribution area with an annual average of more than 10 days, and the EHW distribution area with an annual average of more than 3 days. Moreover, the number of people exposed to HW, SHW, and EHW also increased during this period; and (4) considering the population distribution characteristics and the regional HT and HW characteristics, society needs to form regional adaptation actions for different HT and HW intensities.

Compound and successive events of extreme precipitation and extreme runoff under heatwaves based on CMIP6 models

Global warming accelerates the rate of interregional hydrological cycles, thus leading to a significant increase in the frequency and intensity of global extreme events. An extreme event that causes other extreme events within a short period of time is a successive event. Compound and successive extreme events are more harmful than single extreme events. Therefore, this study revealed the evolution characteristics of compound heatwave and extreme precipitation/runoff events (CHP/CHR), successive heatwave and extreme precipitation/runoff events (SHP/SHR). The population exposure of the four compound events was assessed in the future. The results are as follows: (1) the frequencies of CHP, CHR, SHP, and SHR have all shown a significant upward trend since the Industrial Revolution, especially at low and high latitudes. Under the future SSP585 scenario, CHP and CHR had the largest change rates from 2065 to 2099 at 2.01 events/decade and 1.86 events/decade, respectively. (2) The proportion of severe and extreme events increased significantly in various regions from 1970 to 2014. SHP and SHR have the largest proportion of severe/extreme events in 2015-2039/2065-2099. (3) The CHP and CHR changes in the historical period mainly occurred at high latitudes, while SHP and SHR had the largest change rates in low latitudes. The temperature was dominant compound and successive events in the future. The intensity of the compound event was much larger than that of its corresponding successive event under the high-emission scenario. (4) Climate effect had the most obvious impact on the change of population exposure. Compared with the SSP126 scenario, the population exposure change of the compound event increased by 3.1 times and 3.2 times under the SSP585 scenario during 2065-2099 and 2015-2039, respectively.

Historic evolution of population exposure to heatwaves in Xinjiang Uygur Autonomous Region, China

Heatwaves have pronounced impacts on human health and the environment on a global scale. Although the characteristics of heatwaves has been well documented, there still remains a lack of dynamic studies of population exposure to heatwaves (PEH), particularly in the arid regions. In this study, we analyzed the spatio-temporal evolution characteristics of heatwaves and PEH in Xinjiang using the daily maximum temperature (Tmax), relative humidity (RH), and high-resolution gridded population datasets. The results revealed that the heatwaves in Xinjiang occur more continually and intensely from 1961 to 2020. Furthermore, there is substantial spatial heterogeneity of heatwaves with eastern part of the Tarim Basin, Turpan, and Hami been the most prone areas. The PEH in Xinjiang showed an increasing trend with high areas mainly in Kashgar, Aksu, Turpan, and Hotan. The increase in PEH is mainly contributed from population growth, climate change and their interaction. From 2001 to 2020, the climate effect contribution decreased by 8.5%, the contribution rate of population and interaction effects increased by 3.3% and 5.2%, respectively. This work provides a scientific basis for the development of policies to improve the resilience against hazards in arid regions.

Mapping Heat Wave Hazard in Urban Areas: A Novel Multi-Criteria Decision Making Approach

Global population is experiencing more frequent, longer, and more severe heat waves due to global warming and urbanization. Episodic heat waves increase mortality and morbidity rates and demands for water and energy. Urban managers typically assess heat wave risk based on heat wave hazard, population exposure, and vulnerability, with a general assumption of spatial uniformity of heat wave hazard. We present a novel analysis that demonstrates an approach to determine the spatial distribution of a set of heat wave properties and hazard. The analysis is based on the Livneh dataset at a 1/16-degree resolution from 1950 to 2009 in Maricopa County, Arizona, USA. We then focused on neighborhoods with the most frequent, severe, earlier, and extended periods of heat wave occurrences. On average, the first heat wave occurs 40 days earlier in the eastern part of the county; the northeast part of this region experiences 12 days further extreme hot days and 30 days longer heat wave season than other regions of the area. Then, we applied a multi-criteria decision-making (MCDM) tool (TOPSIS) to evaluate the total hazard posed by heat wave components. We found that the northern and central parts of the metropolitan area are subject to the greatest heat wave hazard and that individual heat wave hazard components did not necessarily indicate heat hazard. This approach is intended to support local government planning for heat wave adaptation and mitigation strategies, where cooling centers, heat emergency water distribution networks, and electrical energy delivery can be targeted based on current and projected local heat wave characteristics.

Effective interventions on health effects of Chinese rural elderly under heat exposure

Due to climate change, the heatwave has become a more serious public health threat with aging as an aggravating factor in recent years. There is a pressing need to detect the most effective prevention and response measures. However, the specific health effects of interventions have not been characterized on an individual scale. In this study, an intervention experiment was designed to explore the health effects of heat exposure at the individual level and assess the effects of different interventions based on a comprehensive health sensitivity index (CHSI) in Xinyi, China. Forty-one subjects were recruited randomly, and divided into one control group and three intervention groups. Interventions included education (Educate by lecturing, offering relative materials, and communication), subsidy support (offer subsidy to offset the cost of running air conditioning), and cooling-spray (install a piece of cooling-spray equipment in the yard). Results showed that systolic blood pressure (SBP) and deep sleep duration (DSD) were significantly affected by short-term heat exposure, and the effects could be alleviated by three types of interventions. The estimated CHSI indicated that the effective days of the education group were longer than other groups, while the lower CHSI of the subsidy group showed lower sensitivity than the control group. These findings provide feasible implementation strategies to optimize Heat-health action plans and evaluate the intervention performance.

ELECTRONIC SUPPLEMENTARY MATERIAL

Supplementary material is available in the online version of this article at 10.1007/s11783-022-1545-4 and is accessible for authorized users.

Spatio-Temporal Patterns of Fitness Behavior in Beijing Based on Social Media Data

Fitness is an important way to ensure the health of the population, and it is important to actively understand fitness behavior. Although social media Weibo data (the Chinese Tweeter) can provide multidimensional information in terms of objectivity and generalizability, there is still more latent potential to tap. Based on Sina Weibo social media data in the year 2017, this study was conducted to explore the spatial and temporal patterns of urban residents’ different fitness behaviors and related influencing factors within the Fifth Ring Road of Beijing. FastAI, LDA, geodetector technology, and GIS spatial analysis methods were employed in this study. It was found that fitness behaviors in the study area could be categorized into four types. Residents can obtain better fitness experiences in sports venues. Different fitness types have different polycentric spatial distribution patterns. The residents’ fitness frequency shows an obvious periodic distribution (weekly and 24 h). The spatial distribution of the fitness behavior of residents is mainly affected by factors, such as catering services, education and culture, companies, and public facilities. This research could help to promote the development of urban residents’ fitness in Beijing.

Spatiotemporal Variation Analysis of the Fine-Scale Heat Wave Risk along the Jakarta-Bandung High-Speed Railway in Indonesia

As a highly important meteorological hazard, heat waves notably impact human health and socioeconomics, and accurate heat wave risk identification and assessment are effective ways to address this issue. The current spatial scale of heat wave risk assessment is relatively coarse, hardly meeting fine-scale heat wave risk assessment requirements. Therefore, based on multi-source fine-scale remote sensing data and socioeconomic data, this paper evaluates the heat wave risk along the Jakarta-Bandung high-speed railway, obtains the spatial distribution of heat wave risk in 2005, 2014 and 2019, and analyzes spatiotemporal risk variations over the past 15 years. The results show that most high-risk areas were affected by high-temperature hazards. Over time, the hazard, exposure, vulnerability and risk levels increased by 25.82%, 3.31%, 14.82% and 6.97%, respectively, from 2005–2019. Spatially, the higher risk in the northwest is mainly distributed in Jakarta. Additionally, a comparative analysis was conducted on the risk results, and the results showed that the 100-m scale showed more spatial differences than the kilometer scale. The research results in this paper can provide scientific advice on heat wave risk prevention considering the Jakarta-Bandung high-speed railway construction and regional economic and social development.

Exploring the Spatiotemporal Patterns of Residents’ Daily Activities Using Text-Based Social Media Data: A Case Study of Beijing, China

The use of social media data provided powerful data support to reveal the spatiotemporal characteristics and mechanisms of human activity, as it integrated rich spatiotemporal and textual semantic information. However, previous research has not fully utilized its semantic and spatiotemporal information, due to its technical and algorithmic limitations. The efficiency of the deep mining of textual semantic resources was also low. In this research, a multi-classification of text model, based on natural language processing technology and the Bidirectional Encoder Representations from Transformers (BERT) framework is constructed. The residents’ activities in Beijing were then classified using the Sina Weibo data in 2019. The results showed that the accuracy of the classifications was more than 90%. The types and distribution of residents’ activities were closely related to the characteristics of the activities and holiday arrangements. From the perspective of a short timescale, the activity rhythm on weekends was delayed by one hour as compared to that on weekdays. There was a significant agglomeration of residents’ activities that presented a spatial co-location cluster pattern, but the proportion of balanced co-location cluster areas was small. The research demonstrated that location conditions, especially the microlocation condition (the distance to the nearest subway station), were the driving factors that affected the resident activity cluster patterns. In this research, the proposed framework integrates textual semantic analysis, statistical method, and spatial techniques, broadens the application areas of social media data, especially text data, and provides a new paradigm for the research of residents’ activities and spatiotemporal behavior.