This paper describes a multidimensional spatial scan statistics approach to comparing spatial movement patterns based on origin–destination (OD) representation. This approach aims to evaluate differences and similarities between the spatial distributions of a pair of OD movement datasets, and detect areas where the two spatial distributions differ the most. Specifically, two OD datasets being compared are modeled as a bivariate marked spatial point process in a multidimensional space, consisting of points representing individual OD movement records. Such multidimensional space is formed by the Cartesian product of the origins’ and the destinations’ geographic spaces. With this spatial data model, one can evaluate how two movement distributions differ from each other by testing against a random labeling null hypothesis. A multidimensional Bernoulli spatial scan statistics method is developed to detect OD region pairs with abnormally high concentrations of one movement dataset over the other. The existence and the spatial extents of these OD region pairs indicate whether and where the two movement distributions differ. Two case studies were conducted to evaluate the approach by comparing morning and afternoon taxi trips (individual movements), and county-to-county migration flows between age groups (aggregated movement flows), and demonstrated that areas with the most significant spatial distribution differences could be detected from large movement datasets.

Movement analytics and mobility insights play a crucial role in urban planning and transportation management. The plethora of mobility data sources, such as GPS trajectories, poses new challenges and opportunities for understanding and predicting movement patterns. In this study, we predict highway speed using a gated recurrent unit (GRU) neural network. Based on statistical models, previous approaches suffer from the inherited features of traffic data, such as nonlinear problems. The proposed method predicts highway speed based on the GRU method after training on digital tachograph data (DTG). The DTG data were recorded in one month, giving approximately 300 million records. These data included the velocity and locations of vehicles on the highway. Experimental results demonstrate that the GRU-based deep learning approach outperformed the state-of-the-art alternatives, the autoregressive integrated moving average model, and the long short-term neural network (LSTM) model, in terms of prediction accuracy. Further, the computational cost of the GRU model was lower than that of the LSTM. The proposed method can be applied to traffic prediction and intelligent transportation systems.

Environmental monitoring using satellite remote sensing is challenging because of data gaps in eddy-covariance (EC)-based in situ flux tower observations. In this study, we obtain the latent heat flux (LE) from an EC station and perform gap filling using two deep learning methods (two-dimensional convolutional neural network (CNN) and long short-term memory (LSTM) neural networks) and two machine learning (ML) models (support vector machine (SVM), and random forest (RF)), and we investigate their accuracies and uncertainties. The average model performance based on ~25 input and hysteresis combinations show that the mean absolute error is in an acceptable range (34.9 to 38.5 Wm⁻²), which indicates a marginal difference among the performances of the four models. In fact, the model performance is ranked in the following order: SVM > CNN > RF > LSTM. We conduct a robust analysis of variance and post-hoc tests, which yielded statistically insignificant results (p-value ranging from 0.28 to 0.76). This indicates that the distribution of means is equal within groups and among pairs, thereby implying similar performances among the four models. The time-series analysis and Taylor diagram indicate that the improved two-dimensional CNN captures the temporal trend of LE the best, i.e., with a Pearson’s correlation of >0.87 and a normalized standard deviation of ~0.86, which are similar to those of in situ datasets, thereby demonstrating its superiority over other models. The factor elimination analysis reveals that the CNN performs better when specific meteorological factors are removed from the training stage. Additionally, a strong coupling between the hysteresis time factor and the accuracy of the ML models is observed.

The rapid expansion of large urban areas underscores the critical importance of road infrastructure. An accurate understanding of traffic flow on road networks is essential for enhancing civil services and reducing fuel consumption. However, traffic flow is influenced by a complex array of factors and perpetually changing conditions, making comprehensive prediction of road network behavior challenging. Recent research has leveraged deep learning techniques to identify and forecast traffic flow and road network conditions, enhancing prediction accuracy by extracting key features from diverse factors. In this study, we performed short-term traffic speed predictions for road networks using data from Mobileye sensors mounted on taxis in Daegu City, Republic of Korea. These sensors capture the road network flow environment and the driver’s intentions. Utilizing these data, we integrated convolutional neural networks (CNNs) with spatio-temporal graph convolutional networks (STGCNs). Our experimental results demonstrated that the combined STGCN and CNN model outperformed the standalone STGCN and CNN models. The findings of this study contribute to the advancement of short-term traffic speed prediction models, thereby improving road network flow management.

Forest fires are severe disasters that cause significant damage in the Republic of Korea and the entire world, and an effort is being made to prevent forest fires internationally. The Republic of Korea budgets 3.38 million USD every year to prevent forest fires. However, an average of 430 wildfires occur nationwide annually. Thirty-eight percent of the forest fire budget is used for forest restoration. Restoring afforestation in the affected areas is a top priority. This study aimed to estimate the degree of vegetative regeneration using the Normalized Difference Vegetation Index (NDVI), Enhanced Vegetation Index (EVI), Soil-Adjustment Vegetation Index (SAVI), and Normalized Burn Ratio (NBR). Although many studies have used NBR with NDVI to extract plant regeneration regions, they suffer from atmospheric effects and soil brightness. Thus, this study utilizes NBR with NDVI, EVI, and SAVI to accurately select areas for targeted forest restoration. Furthermore, this study applies clustering analysis to extract the spatial boundary of vegetative regenerative regions. The proposed method suggests a pixel range of vegetation indices. These ranges can be used as an indicator, such as the NBR’s Fire Severity Level, which reflects the mountain’s local characteristics, meaning that it can be useful after forest fires. Using the three vegetation indices can extract more accurate vegetation areas than using NBR with NDVI and can help determine a forest restoration target area.

This article provides a decentralized and coordinate-free algorithm, called decentralized gradient field (DGraF), to identify critical points (peaks, pits, and passes) and the topological structure of the surface network connecting those critical points. Algorithms that can operate in the network without centralized control and without coordinates are important in emerging resource-constrained spatial computing environments, in particular geosensor networks. Our approach accounts for the discrepancies between finite granularity sensor data and the underlying continuous field, ignored by previous work. Empirical evaluation shows that our DGraF algorithm can improve the accuracy of critical points identification when compared with the current state-of-the-art decentralized algorithm and matches the accuracy of a centralized algorithm for peaks and pits. The DGraF algorithm is efficient, requiring O(n) overall communication complexity, where n is the number of nodes in the geosensor network. Further, empirical investigations of our algorithm across a range of simulations demonstrate improved load balance of DGraF when compared with an existing decentralized algorithm. Our investigation highlights a number of important issues for future research on the detection of holes and the monitoring of dynamic events in a field.