This paper outlines a new deep-learning algorithm that increases accuracy in estimating air pollution over large geographic scales and lengthy time periods. This can help better understand the relation between public health and long-term environmental exposures.
Read More →
This research studies biking patterns in Chicago by analyzing massive bike-sharing data. It uncovers unique travel trends during weekdays, weekends, and for different types of riders, which could help improve bike-sharing system functionality.
Read More →
This study explores how Twitter and Foursquare data can give insights into the daily activities, transportation needs, and business trends of a city, leading to a better understanding of how a city functions.
Read More →
This study automates the detection of popular tourist destinations using geotagged photos on platforms like Flickr. The findings could significantly benefit tourism management.
Read More →
The study investigates how changes in land-use can impact the temperature of the land surface. This research pertains particularly to urban growth and highlights the balance that water and vegetation play in offsetting the "urban heat island" effect.
Read More →
The study outlines a new way of revealing patterns in public health and behavior through "georeferenced word-clouds". The findings suggest this method could enhance data analysis precision and boost the effectiveness of planning and environmental management.
Read More →
This paper presents a unique travel planning tool that uses reviews, photos, and travel costs from different online platforms to make customized travel plans. These personalized plans are useful not only for travelers but also for hotel managers to make strategic decisions.
Read More →
The paper presents new methods to enhance spatiotemporal interpolation accuracy and efficiency, useful for public health applications such as studying the impact of air pollution on health.
Read More →
This study investigates different methods to estimate the exposure of the U.S. population to microscopic pollutants that can cause health problems. Their findings aid in identifying problem areas and understanding seasonal variations.
Read More →
This paper uncovers how locals and tourists in ten US cities share space by using location-based Flickr data. The findings provide useful insights for urban planning and tourism research.
Read More →
The study implies that smartphones' embedded sensors can enhance understanding of transportation patterns. It reduces the need for traditional time-consuming methods, like self-reporting and surveys, by tracking human movement more accurately.
Read More →
This research measures how green space in cities has evolved due to rapid urbanization and environmental policies in China. It sheds light on how urban growth and greening strategies are shaping sustainable development.
Read More →
This study utilizes social media data, particularly Twitter posts, to trace the development and impact of particular events in real time. The method potentially allows better understanding of city dynamics and prompt access to real-time information, benefiting various societal and decision-making applications.
Read More →
This study analyzes where children choose to play in rapidly urbanizing cities and their views on these places, revealing that children's play areas frequently overlap with public spaces and areas they perceive as 'bad'. The information can aid evidence-based city planning.
Read More →
The study aims to uncover if public bike-sharing systems (BSSs) can reduce citywide congestion in the US. The study examines this via a dataset covering urban areas over a nine-year period.
Read More →
This study introduces a system that uses smartphones to collect and analyze human activity data. The method helps understand our interaction with the environment better, identifying locations where individuals are most active.
Read More →
This study presents a new web tool that uses GPS data and user responses to visually represent people's interactions with their environment. The tool helps communities engage in planning processes and promotes environmental awareness.
Read More →
This study uses machine learning to analyze the factors influencing why people in Chicago choose bike-sharing over taxis. The study reveals interesting insights about travel patterns, which can inform sustainable transportation planning.
Read More →
The study develops models to predict housing rent prices in Atlanta, using data from rental listings and deep learning strategies. This approach could increase the accuracy of rent predictions, improving real estate understanding.
Read More →
This research paper presents an innovative method using deep learning to predict PM 2.5 pollution levels across China. The approach, which combines various kinds of data, improves the accuracy of forecasts, thereby aiding in pollution prevention and health impact assessments.
Read More →For inquiries, collaborations, or to learn more about our AI projects, feel free to contact us. We're here to discuss how AI can benefit your work and business.