Landslides often cause significant casualties and economic losses, and therefore landslide susceptibility mapping (LSM) has become increasingly urgent and important. The potential of deep learning (DL) like convolutional neural networks (CNN) based on landslide causative factors has not been fully explored yet. The main target of this study is the investigation of a GIS-based LSM in Zanjan, Iran and to explore the most important causative factor of landslides in the case study area. Different machine learning (ML) methods have been employed and compared to select the best results in the case study area. The CNN is compared with four ML algorithms, including random forest (RF), artificial neural network (ANN), support vector machine (SVM), and logistic regression (LR). To do so, sixteen landslide causative factors have been extracted and their related spatial layers have been prepared. Then, the algorithms were trained with related landslide and non-landslide points. The results illustrate that the five ML algorithms performed suitably (precision = 82.43–85.6%, AUC = 0.934–0.967). The RF algorithm achieves the best result, while the CNN, SVM, the ANN, and the LR have the best results after RF, respectively, in this case study. Moreover, variable importance analysis results indicate that slope and topographic curvature contribute more to the prediction. The results would be beneficial to planning strategies for landslide risk management.

Traffic flow information is of great importance for transport planning and related research. The conventional methods of automated data collection, such as annual average daily traffic (AADT) data, are often restricted by limited installation, while the state-of-the-art sensing technologies (e.g., GPS) only reflect some types of traffic flow (e.g., taxi and bus). Complete coverage of traffic flow is still lacking, thus demanding a rigorous estimation model. Most studies dedicated to estimating the traffic flow of the entire road network rely on single to only a few properties of the road network and the results may not be promising. This paper presents an idea of integrating five topological measures and road length to estimate traffic flow based on a multiple regression approach. An empirical study in Hong Kong has been conducted with three types of traffic datasets, namely floating car, public transport route, and AADT. Six measures, namely degree, betweenness, closeness, page rank, clustering coefficient, and road length, are used for traffic flow estimation. It is found that each measure correlates differently for the three types of traffic data. Multiple regression approach is then conducted, including multiple linear regression and random forest. The results show that a combination of various topological and geometrical measures has proved to have a better performance in estimating traffic flow than that of a single measure. This paper is especially helpful for transport planners to estimate traffic flow based on correlation available but limited flow data with road network characteristics.

Land use allocation (LUA) is of prime importance for the development of urban sustainability and resilience. Since the process of planning and managing land use requires balancing different conflicting social, economic, and environmental factors, it has become a complex and significant issue in urban planning worldwide. LUA is usually regarded as a spatial multi-objective optimization (MOO) problem in previous studies. In this paper, we develop an MOO approach for tackling the LUA problem, in which maximum economy, minimum carbon emissions, maximum accessibility, maximum integration, and maximum compactness are formulated as optimal objectives. To solve the MOO problem, an improved non-dominated sorting genetic algorithm III (NSGA-III) is proposed in terms of mutation and crossover operations by preserving the constraints on the sizes for each land use type. The proposed approach was applied to KaMavota district, Maputo City, Mozambique, to generate a proper land use plan. The results showed that the improved NSGA-III yielded better performance than the standard NSGA-III. The optimal solutions produced by the MOO approach provide good trade-offs between the conflicting objectives. This research is beneficial for policymakers and city planners by providing alternative land use allocation plans for urban sustainability and resilience.

Background: Taxi drivers in a Chinese megacity are frequently exposed to traffic-related particulate matter (PM_2.5) due to their job nature, busy road traffic, and urban density. A robust method to quantify dynamic population exposure to PM_2.5 among taxi drivers is important for occupational risk prevention, however, it is limited by data availability. Methods: This study proposed a rapid assessment of dynamic exposure to PM_2.5 among drivers based on satellite-derived information, air quality data from monitoring stations, and GPS-based taxi trajectory data. An empirical study was conducted in Wuhan, China, to examine spatial and temporal variability of dynamic exposure and compare whether drivers’ exposure exceeded the World Health Organization (WHO) and China air quality guideline thresholds. Kernel density estimation was conducted to further explore the relationship between dynamic exposure and taxi drivers’ activities. Results: The taxi drivers’ weekday and weekend 24-h PM_2.5 exposure was 83.60 μg/m³ and 55.62 μg/m³ respectively, 3.4 and 2.2 times than the WHO’s recommended level of 25 µg/m³. Specifically, drivers with high PM_2.5 exposure had a higher average trip distance and smaller activity areas. Although major transportation interchanges/terminals were the common activity hotspots for both taxi drivers with high and low exposure, activity hotspots of drivers with high exposure were mainly located in busy riverside commercial areas within historic and central districts bounded by the “Inner Ring Road”, while hotspots of drivers with low exposure were new commercial areas in the extended urbanized area bounded by the “Third Ring Road”. Conclusion: These findings emphasized the need for air quality management and community planning to mitigate the potential health risks of taxi drivers.