Software-defined traffic light preemption for faster emergency medical service response in smart cities.

Proper management of rescue operations following an accident is one of the most fundamental challenges faced by today's smart cities. Taking advantage of vehicular communications, in this paper we propose novel mechanisms for the acceleration of the rescue operation resulting in a reduction in fatalities in accidents. We propose a Software-Defined Traffic Light Preemption (SD-TLP) mechanism that enables Emergency Medical Vehicles (EMVs) to travel along the rescue route with minimal interruptions. The SD-TLP makes preemption decisions based on global knowledge of the traffic conditions in the city. We also propose mechanisms for the selection of the nearest emergency center and fast discharge of the route of EMVs. Furthermore, depending on the dynamic traffic conditions on the streets at the time of the accident, an appropriate rescue route is selected for the EMV before its departure. The proposed approach is evaluated using the OMNET++ and SUMO tools over part of the Megacity of Tabriz, Iran. The simulation results demonstrate that the method can reduce the average rescue time significantly. The proposed approach keeps the resulting disruption in city traffic acceptably low while trying to shorten the rescue time as much as possible.

Geomorphological evolution along international riverine borders: The flow of the Aras River through Iran, Azerbaijan, and Armenia.

International rivers are one of the most politicized natural resources. Their dynamism, whether driven by the influence of natural processes or artificial drivers, can generate political issues between countries where de river is the common boundary. The present study has tried to discern the role of international riverine borders as a limiting factor of their dynamics from a geomorphological point of view. In this context, the main objective of this research is to assess how land cover in the floodplain has been affected by river dynamics along a border by analysing a 160-km-long reach of the Aras River, which is the natural frontier between Iran, Azerbaijan, and Armenia, over the last 35 years (i.e., 1984-2019). Landsat images from 1984 to 2019 have been used to assess land cover changes in a floodplain buffer using Support Vector Machine algorithms and geomorphological changes through indexes such as the River Network Change Index, Channel Mobility Index, Sinuosity index, and Bank retreat index. The results show that active channel has mainly experienced a narrowing process during the study period, with a narrowing rate of 2.05 m/year. In addition, the average value of the River Network Channel Index (-2.45 m/year) reveals that lateral deposition and narrowing were the main processes occurring within the study reach. Channel displacement toward the non-Iranian part was more prominent, being around 27 m on average along the whole study reach which may cause new problems and conflicts that conditions the border situation. In the whole study period, the succession category showed a higher rate of increase in comparison with rejuvenation. Stabilization of surfaces prevailed, with most of the area maintaining the same type during the study period. Regarding land cover types, artificialization appears to be the most prominent transition that express the Aras River, and specifically the floodplain buffer zone, has been strongly affected by human pressure, with farmland activities, urbanization, and damming being the most important types. The key to this habitat degradation comes from the management with irrigation purposes of large reservoirs that directly or indirectly would cause most of the changes detected.

Spatial and temporal analysis of urban heat island using Landsat satellite images.

The average land surface temperature (LST) of Earth has increased since the late nineteenth century due to the warming of the Earth's atmosphere. Increased surface temperatures, especially in cities, are a significant environmental problem that intensifies urban heat islands (UHIs). In this study, land surface temperature, urban thermal field variance index (UTFVI), and UHI index were mapped using Landsat 4, 5, 7, and 8 satellite images to identify the distribution and determine the intensities of the UHI. Maps of land use at multi-year intervals between 1995 and 2016 were created using the support vector machine (SVM) method. These were used to compare LST variations to land-use changes and to determine the linkages between the two. The results showed that the highest recorded temperatures in Ahvaz, the capital of Khozestan Province, Iran, occurred in areas of bare land (42.93°C) and residential development (40.06°C) in 2017. Land use classification showed that the highest classification accuracy (in 2016) was 93%. The most varying extents of land use in Ahvaz were bare lands, residential lands, and green spaces. Green spaces in the study area in 1995 and 2016 covered 14% and 7% of the area, respectively, which showed a 50% reduction in green space over 21 years. A composite map of UTFVI and UHI showed that the locations classified as very hot had the worst UTFVI. The results of this study of Ahvaz, Iran's heat islands, can inform and guide urban planners in locational matters and in efforts to mitigate and adapt changing land uses in order to limit the intensification of the UHI.

Assessing the susceptibility of schools to flood events in Iran.

Catastrophic floods cause deaths, injuries, and property damages in communities around the world. The losses can be worse among those who are more vulnerable to exposure and this can be enhanced by communities' vulnerabilities. People in undeveloped and developing countries, like Iran, are more vulnerable and may be more exposed to flood hazards. In this study we investigate the vulnerabilities of 1622 schools to flood hazard in Chaharmahal and Bakhtiari Province, Iran. We used four machine learning models to produce flood susceptibility maps. The analytic hierarchy process method was enhanced with distance from schools to create a school-focused flood-risk map. The results indicate that 492 rural schools and 147 urban schools are in very high-risk locations. Furthermore, 54% of rural students and 8% of urban students study schools in locations of very high flood risk. The situation should be examined very closely and mitigating actions are urgently needed.

A machine learning framework for multi-hazards modeling and mapping in a mountainous area.

This study sought to produce an accurate multi-hazard risk map for a mountainous region of Iran. The study area is in southwestern Iran. The region has experienced numerous extreme natural events in recent decades. This study models the probabilities of snow avalanches, landslides, wildfires, land subsidence, and floods using machine learning models that include support vector machine (SVM), boosted regression tree (BRT), and generalized linear model (GLM). Climatic, topographic, geological, social, and morphological factors were the main input variables used. The data were obtained from several sources. The accuracies of GLM, SVM, and functional discriminant analysis (FDA) models indicate that SVM is the most accurate for predicting landslides, land subsidence, and flood hazards in the study area. GLM is the best algorithm for wildfire mapping, and FDA is the most accurate model for predicting snow avalanche risk. The values of AUC (area under curve) for all five hazards using the best models are greater than 0.8, demonstrating that the model's predictive abilities are acceptable. A machine learning approach can prove to be very useful tool for hazard management and disaster mitigation, particularly for multi-hazard modeling. The predictive maps produce valuable baselines for risk management in the study area, providing evidence to manage future human interaction with hazards.

Assessing, mapping, and optimizing the locations of sediment control check dams construction.

Check dams are considered to be one of the most effective measures for conservation of the soil and water resources. However, identifying the most suitable sites for the installation of check dams remain quite demanding. This research investigates and compares five machine learning algorithms (MLAs) - boosted regression trees (BRT), multivariate adaptive regression spline (MARS), mixture discriminant analysis (MDA), random forest (RF), and support vector machine (SVM) - for generating check-dam site-suitability maps (CDSSMs) and assessing them in Firuzkuh County, Iran. First, the locations of 475 existing check dams were monitored, registered, and divided into calibration (70%) and testing datasets (30%) for training and validation of the models. Fourteen check-dam conditioning factors (CDCFs) were selected and checked for multicollinearity. The relative importance of the CDCFs assessed using the elastic net (ENET) algorithm. Results demonstrated that distance from river (DFR) and drainage density (DD) to be the most significant factors for mapping the suitable sites for the erection of check dams. This research revealed that all of five MLAs had excellent accuracy for predicting the check-dam site-suitability with high AUC values: RF (0.966), SVM (0.878), MARS (0.878), MDA (0.844), and BRT (0.843). The most accurate model (RF) showed that 16.95%, 35.55%, 31.08%, and 16.42% of study area comes under low, moderate, high, and very high suitability classes. The outcome achieved by this research will be helpful to sustainability planners and managers in constructing check dams at suitable sites for better conservation of soil and water resources.

Using machine learning algorithms to map the groundwater recharge potential zones.

Groundwater recharge is indispensable for the sustainable management of freshwater resources, especially in the arid regions. Here we address some of the important aspects of groundwater recharge through machine learning algorithms (MLAs). Three MLAs including, SVM, MARS, and RF were validated for higher prediction accuracies in generating groundwater recharge potential maps (GRPMs). Accordingly, soil permeability samples were prepared and are arbitrarily grouped into training (70%) and validation (30%) samples. The GRPMs are generated using sixteen effective factors, such as elevation (denoted using a digital elevation model; DEM), aspect, slope angle, TWI (topographic wetness index), fault density, MRVBF (multiresolution index of valley bottom flatness), rainfall, lithology, land use, drainage density, distance from rivers, distance from faults, annual ETP (evapo-transpiration), minimum temperature, maximum temperature, and rainfall 24-hr. Subsequently, the VI (variables importance) is assessed based on the LASSO algorithm. The GRPMs of three MLAs were validated using the ROC-AUC (receiver operating characteristic-area under curve) and various techniques including true positive rate (TPR), false positive rate (FPR), F-measures, fallout, sensitivity, specificity, true skill statistics (TSS), and corrected classified instances (CCI). Based on the validation, the RF algorithm performed better (AUC = 0.987) than the SVM (AUC = 0.963) and the MARS algorithm (AUC = 0.962). Furthermore, the accuracy of these MLAs are included in excellent class, based on the ROC curve threshold. Our case study shows that the GRPMs are potential guidelines for decision-makers in drafting policies related to the sustainable management of the groundwater resources.

Performance assessment of individual and ensemble data-mining techniques for gully erosion modeling.

Gully erosion is identified as an important sediment source in a range of environments and plays a conclusive role in redistribution of eroded soils on a slope. Hence, addressing spatial occurrence pattern of this phenomenon is very important. Different ensemble models and their single counterparts, mostly data mining methods, have been used for gully erosion susceptibility mapping; however, their calibration and validation procedures need to be thoroughly addressed. The current study presents a series of individual and ensemble data mining methods including artificial neural network (ANN), support vector machine (SVM), maximum entropy (ME), ANN-SVM, ANN-ME, and SVM-ME to map gully erosion susceptibility in Aghemam watershed, Iran. To this aim, a gully inventory map along with sixteen gully conditioning factors was used. A 70:30% randomly partitioned sets were used to assess goodness-of-fit and prediction power of the models. The robustness, as the stability of models' performance in response to changes in the dataset, was assessed through three training/test replicates. As a result, conducted preliminary statistical tests showed that ANN has the highest concordance and spatial differentiation with a chi-square value of 36,656 at 95% confidence level, while the ME appeared to have the lowest concordance (1772). The ME model showed an impractical result where 45% of the study area was introduced as highly susceptible to gullying, in contrast, ANN-SVM indicated a practical result with focusing only on 34% of the study area. Through all three replicates, the ANN-SVM ensemble showed the highest goodness-of-fit and predictive power with a respective values of 0.897 (area under the success rate curve) and 0.879 (area under the prediction rate curve), on average, and correspondingly the highest robustness. This attests the important role of ensemble modeling in congruently building accurate and generalized models which emphasizes the necessity to examine different models integrations. The result of this study can prepare an outline for further biophysical designs on gullies scattered in the study area.

Interplay between river dynamics and international borders: The Hirmand River between Iran and Afghanistan.

Fluvial dynamics in riverine borders can play an important role in political relationships between countries. Rivers move and evolve under the influence of natural processes and external drivers (e.g. land use change in river catchments). The Hirmand River is an important riverine border between Iran and Afghanistan. The present study shows the evolution and lateral shifting of the Hirmand River along the international border (25.6km) over a period of 6 decades (1955-2015). Seven data series of aerial photos, topographic maps and Landsat images were used to analyze land cover and channel changes in the study reach. The land cover has changed dramatically on both sides of the border during the last 6 decades, especially in the Afghan part. Overall, 49% of all land surface changed its cover type, especially the area of agriculture and residential land contributed to that, with an increase in surface area of about 4931ha and 561ha, respectively. On the other hand, the natural cover and water bodies decreased to 38% and 63%, respectively. The impact of these land use changes on the morphological evolution of Hirmand River was investigated in 5 sub-reaches. We found an average decrease of the active channel width of 53% during 60years and the average River Network Change Index for the whole study reach during 60years was -1.25m/year. Deposition and narrowing turned out to be the main processes occurring within the study reach. Furthermore, due to natural riverine processes the Hirmand River has moved towards Afghanistan (37m on average) and lateral shifting was found to be up to 1900m in some sections.

Accuracy assessment of land cover/land use classifiers in dry and humid areas of Iran.

Land cover/land use (LCLU) maps are essential inputs for environmental analysis. Remote sensing provides an opportunity to construct LCLU maps of large geographic areas in a timely fashion. Knowing the most accurate classification method to produce LCLU maps based on site characteristics is necessary for the environment managers. The aim of this research is to examine the performance of various classification algorithms for LCLU mapping in dry and humid climates (from June to August). Testing is performed in three case studies from each of the two climates in Iran. The reference dataset of each image was randomly selected from the entire images and was randomly divided into training and validation set. Training sets included 400 pixels, and validation sets included 200 pixels of each LCLU. Results indicate that the support vector machine (SVM) and neural network methods can achieve higher overall accuracy (86.7 and 86.6%) than other examined algorithms, with a slight advantage for the SVM. Dry areas exhibit higher classification difficulty as man-made features often have overlapping spectral responses to soil. A further observation is that spatial segregation and lower mixture of LCLU classes can increase classification overall accuracy.