Spatiotemporal processes, such as floods, rainfall-runoff, and land-use changes, continuously evolve over space and time with high dynamism and complex nonlinearity. Accurate and efficient spatiotemporal process prediction is crucial for understanding their underlying patterns. Recently, deep learning has effectively addressed spatiotemporal prediction issues in Earth science. However, most existing studies address either short-term or long-term dependencies, but ignore the multiscale characteristics and spatial heterogeneity inherent to spatiotemporal processes and critical for practical applicability. This study develops a Spatiotemporal Adaptive Multiscale Transformer (SAMT) model for spatiotemporal process prediction. First, we design an enhanced multiscale spatial heterogeneity module to extract multiscale spatial heterogeneity. Then, we introduce the adaptive scale selection that assigns weights to features at different scales based on their contributions. In addition, we incorporate a spatiotemporal transformer block to simultaneously capture short-term and long-term dependencies. We conduct extensive experiments on three representative spatiotemporal datasets of rainfall, temperature, and flood. Compared to state-of-the-art models, the SAMT model achieves significant improvements across all evaluation metrics. The developed SAMT model critically improves the performance of spatiotemporal process prediction for more accurate and effective modelling of spatiotemporal evolution patterns in the field of Earth sciences.

Geographically weighted regression (GWR) is a classic local linear method for modeling spatial non-stationarity that is applied in various geographical scenarios. The modeling of spatial proximity in traditional GWR and its variants is usually based on various forms of spatial distances to construct spatial weights, overlooking the potential effect of multidimensional attribute similarity of physical entities. Therefore, we proposed the geographically spatial-attribute weighted regression (GSAWR) method with convolutional neural networks to account for spatial non-stationarity based on spatial proximity and attribute similarity. An attribute fusion convolutional neural network (AFCNN) considers the differential effects of attribute variables by assessing similarities among multiple variables. A spatial-attribute joint proximity neural network (SAJPNN) combines attribute similarity and spatial proximity to generate a proximity measure adaptive to both spatial proximity and attribute similarity. A spatial-attribute weighted convolutional neural network (SAWCNN) and ordinary linear regression (OLR) use the spatial-attribute joint proximity to make final predictions. We validated the GSAWR approach on simulated dataset and two real-world datasets: the PM2.5 and HIV datasets. The results revealed that the GSAWR model outperformed the other baseline models in terms of fitting and prediction performance. Ablation experiments and coefficient visualization further determined the effectiveness and interpretability of GSAWR model.

Location prediction based on social media information is highly valuable in human mobility research and has multiple real-life applications. However, existing research methods often ignore social influences, largely ignoring implicit information regarding interactions between users and geographical locations. Additionally, they generally employ single modeling structures, which restricts the effective integration of complex spatiotemporal characteristics and factors influencing user mobility. In this context, we propose a novel network with physical and social awareness that expresses both physical and social influences of user mobility from a global perspective based on a heterogeneous graph constructed using users and spatial locations as nodes and relationships between them as edges. This graph enables the model to leverage information from connected nodes and edges to infer missing or unobserved data. The model predicts future locations of users by effectively integrating the temporal and spatial features of user trajectory series. The proposed model is validated using three social media datasets. The experimental results demonstrate that the proposed method outperforms the state-of-the-art baseline models. This indicates the importance of considering complex interactions between users and locations, as well as the various influences of physical and social spaces.

From a process perspective, a flood includes several phases with distinguishable features. Fine-grained multisource data for different flood phases can be used to inform decision-making as flooding progresses. Therefore, the aim of this study was to develop an integrated framework based on human perceptions to progressively profile floods, including flood process segmentation rules (FPSR), flood severity index (FSI) and flood process perception ontology (FPPO). FPSR identifies flood phases based on specific signals in multisource data and provides spatiotemporal process information to FPPO consistent with flood perception. FSI follows FPSR to evaluate flooding throughout its evolution process. The comparison between FPSR and the flood monitoring index (IF) demonstrates that FPSR can detect flood events and segment the flooding process into latency, onset, development and recovery phases. The correlations between the standardized antecedent precipitation index (SAPI) and FSI show that FSI can assess flood severity with both natural and social effects in every flooding phase (R2 = 0.726 and 0.673 for the 2016 and 2020 floods, respectively). An experiment finds that flood events in Wuhan, China, usually begin in mid-to-late June and are the most severe in July, when more caution is needed for flood prevention and mitigation.

Dynamic changes in traffic conditions cause spatiotemporal variation in traffic monitoring demand. It is, therefore, necessary to conduct efficient road monitoring to identify dynamic abnormal situations, especially in peak traffic periods. Recently, unmanned aerial vehicles (UAVs) have become an attractive solution to this problem. However, UAV monitoring routes suffer from time limitations during peak traffic hours. To optimize UAV monitoring routes during rush hours, we develop a route planning method incorporating spatiotemporal variations in monitoring demand, in which we introduce a team orienteering arc routing problem with time-varying profits (TOARP-TP) and construct a corresponding mathematical model. The TOARP-TP is an extension of an already existing routing problem, team orienteering arc routing problem (TOARP). An iterated local search (ILS)-based algorithm is designed to solve the large instances of this problem. To verify the proposed method, we conduct sets of numerical experiments with the Sioux Falls road network in South Dakota, US, and a case study is applied using Wuhan, Hubei, PRC. The results demonstrate the efficiency and practicality of our method in optimizing UAV traffic monitoring routes during rush hours. Furthermore, we discuss a strategy for scenario determination and method selection in UAV route planning.

When facing a specific emergent geographical environment observation task (GeoTask), people need to be able to handle reliable and comprehensive disaster information in the shortest possible time. The lack of effective cognition of multi-sensor collaborated observation capability is a hindrance to performance. By adopting the GIS object field concept as the bottom framework, we propose a sensor observation capability object field (SOCO-Field) with sensor observation capability particle (SOC-Particle) as its core. SOCO-Field integrates SOC-Objects and GeoField for the discovery and association of sensors. SOC-Particle objectively exists on every location point in the geospatial environment, and SOC-Particles in space-continuous areas can further aggregate into SOC-Particle cluster to represent single- or multi-sensor-associated observation capability information. SOCO-Field includes three basic association behaviours and four further association behaviours to solve associated observation capability, in which the dynamic GeoField is the influential factor. An experiment on flood monitoring in the lower reaches of Jinsha River Basin is conducted. The sensor planner can view any sensor combination’s associated observation capability under a specific association mode and can effectively dispatch a multi-sensor for collaborated observation due to the effective modelling of associated sensor observation capability information (SOCInfo).

Precipitation stations are important components of a hydrological monitoring network. Given their critical role in rainfall forecasting and flood warnings, along with limited observation resources, determining the optimal locations to deploy precipitation stations presents an important problem. In this paper, we use a maximal covering location problem to identify the best precipitation station sites. Considering the terrain conditions and the characteristics of a rainfall network, the original maximal covering location model is modified with the introduction of a set of additional constraints. The minimum density requirement is used to determine a precipitation station’s coverage range, and three weighting schemes are used to evaluate each demand object’s covering priority. As a typical mountainous watershed with high annual precipitation, the Jinsha River Basin is selected as the study area to test the applicability of the proposed method. Results show that the proposed method is effective for precipitation station configuration optimization, and the model solution achieves higher coverage than the real-world deployment. Compared with the commercial solver CPLEX, a genetic algorithm-based heuristic can significantly reduce the computation time when the problem size is large. Several deployment strategies are also discussed for establishing the optimal configuration of precipitation stations.

Different versions of the Web Coverage Service (WCS) schemas of the Open Geospatial Consortium (OGC) reflect semantic conflict. When applying the extended FRAG-BASE schema-matching approach (a schema-matching method based on COMA++, including an improved schema decomposition algorithm and schema fragments identification algorithm, which enable COMA++-based support to OGC Web Service schema matching), the average recall of WCS schema matching is only 72%, average precision is only 82% and average overall is only 57%. To improve the quality of multi-version WCS retrieval, we propose a schema-matching method that measures node semantic similarity (NSS). The proposed method is based on WordNet, conjunctive normal form and a vector space model. A hybrid algorithm based on label meanings and annotations is designed to calculate the similarity between label concepts. We translate the semantic relationships between nodes into a propositional formula and verify the validity of this formula to confirm the semantic relationships. The algorithm first computes the label and node concepts and then calculates the conceptual relationship between the labels. Finally, the conceptual relationship between nodes is computed. We then use the NSS method in experiments on different versions of WCS. Results show that the average recall of WCS schema matching is greater than 83%; average precision reaches 92%; and average overall is 67%.

The OGC Web Service (OWS) schemas have the characteristics of a complex element structure, are distributed and large scale, have differences in element naming, and are available in different versions. Applying conventional matching approaches may lead to not only poor quality, but also bad performance. In this article, the OWS schema file decomposition, fragment presentation, fragment identification, fragment element match, and combination of match results are developed based on the extended FRAG-BASE (fragment-based) schema-matching method. Different versions of Web Feature Service (WFS) and Web Coverage Service (WCS) schema-matching experiments show that the average recall of the extended FRAG-BASE matching for the schemas is above 80%, the average precision reaches 90%, the average overall achieves 85%, and the matching efficiency increases by 50% as compared with that of the COMA and CONTEXT matcher. The multi-version WFS retrieval under the Antarctic Spatial Data Infrastructure (AntSDI) data service environment demonstrates the feasibility and superiority of the extended FRAG-BASE method.