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.

As edge devices grow smarter and application scenarios become more diverse, users' demands for lower latency and higher efficiency in data storage and processing have risen sharply. Individual edge devices and nodes are no longer sufficient to meet these expanding storage requirements. Consequently, developing efficient, low-latency, and cost-effective solutions for collaborative storage across edge devices and nodes has become a critical challenge. In this paper, we present a framework for the transaction and pricing of storage resources in an edge computing environment involving multiple edge service providers, to address trust and incentive issues in storage resource collaboration. Firstly, we propose a secure and decentralized storage resource trading mechanism by leveraging blockchain technology and smart contracts. We introduce Proof of Transaction Expectation (PoTE), an efficient, reliable, and lightweight consensus mechanism, to ensure transaction transparency, openness, and non-repudiation. Secondly, we introduce a game theory-based storage resource pricing model, where a leader interacts with multiple followers to optimize profits while maintaining service quality. To address dynamic pricing and storage resource allocation problems under incomplete information, we propose the Stackelberg Game Approach based on Multi-Agent Reinforcement Learning (SGA-MARL), which formulates the optimal pricing and trading share decisions in the two-stage Stackelberg game as a stochastic Markov Decision Process (MDP). Simulations and prototype testing validate the effectiveness of the proposed system, with results showing that the PoTE consensus achieves up to 40% higher throughput than Proof-of-Work while reducing latency by over 50% compared to PBFT, and the SGA-MARL algorithm improves leader profit by approximately 30% and resource satisfaction rates by over 80% compared to baseline methods like MA-PPO and DQN.

Presents corrections to the paper, (Corrections to “Accelerating Cross-Scene Co-Seismic Landslide Detection Through Progressive Transfer Learning and Lightweight Deep Learning Strategies”).

Accurate and spatiotemporal seamless soil moisture (SM) products are important for hydrological drought monitoring and agricultural water management. Currently, physically-based process models with data assimilation are widely used for global seamless SM generation, such as Soil Moisture Active Passive level 4 (SMAP L4), the land component of the fifth generation of European Reanalysis (ERA5-land) and Global Land Data Assimilation System Noah (GLDAS-Noah). These datasets are usually produced using high-performance computation platforms and may subject to potential uncertainties from model structure and parameters, limiting their practical application capacity in a flexible way in local or global areas. Here, we proposed a data-driven artificial intelligence (AI)-based method to generate spatiotemporal seamless daily soil moisture data using triple collocation, machine learning and data assimilation. Specifically, the triple collocation correlation coefficients (TCR) method is employed to combine different SM datasets in order to obtain high-accuracy label data for model training first. A LightGBM machine learning (ML) model is constructed to simulate global daily soil moisture at 0.25◦ in an autoregressive way, using ERA5 meteorological forcings and MSWEP precipitation data as inputs. In addition, the satellite-based soil moisture SMAP level 3 (SMAP L3) is assimilated into the developed machine learning model using the simple Newtonian nudging technique to update the soil moisture simulation states. The incorporation of data assimilation into machine learning mimics the idea of physical models and brings much room for adaptable soil moisture simulations. The developed data-driven model is examined over global land areas from March 31, 2015 to May 31, 2023 with a ten-fold cross validation scheme, evaluated using 1094 in-situ soil moisture stations from International Soil Moisture Network (ISMN). The results indicate that the ML-based assimilated soil moisture dataset (MLDA) demonstrates a median correlation (R) of 0.741 and an unbiased root mean square error (ubRMSE) of 0.0437 m3/m3, better than SMAP L4 (R=0.717, ubRMSE=0.0452 m3/m3, ERA5-land (R=0.706, ubRMSE=0.0452 m3/m3) and GLDAS (R=0.633, ubRMSE=0.0501 m3/m3). Compared to the three model-based soil moisture products, the ML-DA dataset exhibits superior performance in time and space and also in dry-wet zones. Therefore, the developed ML-DA framework offers significant potential for accurate, spatiotemporal soil moisture simulations globally.

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.

Sudden co-seismic landslides strike, causing widespread devastation and demanding a rapid response. The swift and accurate acquisition of landslide information is essential for effective disaster relief. Deep learning (DL)-based computer-aided interpretation methods have emerged as cutting-edge tools for landslide detection. Nevertheless, traditional DL approaches face limitations, such as high annotation costs, slow processing speeds, and low generalizability, rendering them unsuitable for rapid co-seismic landslide recognition tasks. This study presents a progressive approach for co-seismic landslide detection. First, we develop a Multi-scale Feature Fusion Lightweight Neural Network (MFFLnet), achieving exceptional generalizability and speed while maintaining precision. Second, we employ the deep transfer learning (TL) strategy, enabling MFFLnet to leverage prior landslide knowledge from a source domain and a refined data augmentation algorithm to combat overfitting. The proposed methodology is implemented in two co-seismic landslide scenes in Hokkaido, Japan, and Luding, China. Experimental results demonstrate that the proposed method exhibits outstanding performance in regional landslide recognition and robust performance across different co-seismic landslide detection scenarios. Our approach proves competitive in efficient co-seismic landslide disaster recognition and cross-scene identification, showcasing significant applicability in the face of rapid response demands.

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.

In mobile crowdsensing, there are generally two types of tasks, popular tasks, and unpopular tasks. For popular tasks, many people can perform that task, and the budget is overallocated. For unpopular tasks, fewer or no one is willing to complete them. How to motivate users to complete different popularity tasks during their work time is a challenging problem. In this paper, we design a task priority-aware incentive mechanism to solve this problem. First, we use hierarchical clustering to classify tasks into different priorities by considering their budgets, deadlines, and density distribution. The higher the task priority, the higher the extra rewards and credits the participating users get. To motivate more users to perform unpopular tasks, we give high priority to unpopular tasks. Then, we propose a greedy algorithm that allows more users to do high-priority tasks. However, too many budget adjustments can cause most users to do unpopular tasks as users are obsessed with their income. To prevent users from all selecting high-priority tasks, we further propose a differential privacy-based algorithm to protect task priority and reduce users’ attention to their income. This algorithm protects users’ income and allows users to focus more on task characteristics, such as task distribution and task deadline. Through many experiments in the reality Roma dataset, we evaluate two proposed algorithms compared with other solutions.

Soil moisture is an essential variable both in environmental monitoring research and application. With the requirement of high-precision soil moisture data, it is highly necessary to construct in-situ soil moisture sensors Web in high density, in which the economics, complexity, and low-power consumption of sensor Webs should be essentially considered. However, most current existing soil moisture monitoring networks have limitations due to high power consumption, complex architecture, and expensive equipment. These issues are not conducive to high-density soil moisture observation. In view of the existing problems in the current soil moisture in-situ sites, an effective resolution for high-density soil moisture observation is needed. For the first time, we are bringing Narrow-Band Internet of Things (NB-IoT), a low-power Internet-of-Things technology, into geospatial sensor Web for soil moisture observation. Moreover, we built a high-density in-situ soil moisture sensor Web via NB-IoT and compared it with ZigBee at the Baoxie experimental zone in Wuhan, China, there about 1 km2, and we acquired data for up to 12 months. We analyze the acquisition record of battery status, signals, and soil moisture. We analyzed the battery life, the impact of the signal on the battery performance, the signal quality, and data acquisition clearly and intuitively. This unprecedented study and application, we discovered and concluded that the low-power sensor Web of the NB-IoT communication protocol could be suitable for high-density soil moisture observation.

Envelope tracking (ET) is one of the important ways to increase the efficiency of power amplifier (PA). The supply modulator (SM) is critical to fulfil the ET strategy. This paper provides a ripple tracking method based on an open-loop digital controller for SM with one switching amplifier (SA) to efficiently track the envelope of PA. The digital controller combines the strong abilities of caching the envelope signals in advance and the powerful envelope shaping as well as the filtering capability to conquer the intrinsic obstacle of close-loop delay, accelerating the tracking speed and decreasing the operation frequency of SM. The performance of SM is highly enhanced based on the proposed circuit model with error correction technique. The proposed ripple tracking method realizes excellent average power tracking (APT) performance compared with that of multi-level SM structure and decreases the hardware requirements, significantly. A test SA chip is fabricated with a standard 0.18 μm CMOS technology and the test platform of whole SM system is established. The measurement results show that the proposed platform achieves very high efficiency of 88% in tracking the envelope of 10-MHz ~ 100-MHz OFDM baseband signals.

In this paper, we joint autoencoder with active learning for hyperspectral imagery classification. Specifically, we learn the classifier via autoencoder, where the most informative samples are acitvely selected through the interaction between the autoencoder and active learning. Experimental results, conducted using both the Kennedy Space Center and the Indian Pines hyperspectral images, show that driven by active learning, the performance of autoencoder can be greatly improved.

NDVI maps have been proven valuable in providing a spatially complete view of crop's vegetation condition, which manifests disastrous events such as massive flood and drought. It is virtually impossible to obtain from ground survey data. This paper uses NASA MODIS 250m resolution, daily surface reflectance data for crop condition monitoring. The NDVI provides an absolute metrics for vegetation condition. However, a relative measurement of the current vegetation condition against a reference vegetation condition is critical for understanding, interpreting and quantifying the current vegetation condition. In this paper, a new NDVI based vegetation condition index is presented to measure the vegetation condition with respect to the "normal condition", which is characterized by historical average. The proposed new vegetation condition index is empirically compared with several other vegetation indices to evaluate its effectiveness. Its advantages and utility for crop vegetation condition measurement are evidenced by the preliminary results.

Detecting motion-based video change, such as different types of motion video or applications using different change detection algorithms in a Web system, is difficult. This paper designs and implements architecture for a real-time or near real-time on-demand motion video change detection system using the Sensor Observation Service (SOS) and the Web Processing Service (WPS) in the Sensor Web environment. Real-time or near real-time includes sensors that obtain motion video data, SOS provides motion video data to WPS and WPS processes this data. Three solution methods are introduced: the GetObservation operation of SOS by transaction, dynamical interaction between SOS and WPS, and WPS real-time or near real-time processing. On-demand means that a developer can choose different motion video change detection algorithms under different applications or different conditions. For this purpose, a flexible, standards-based and service-oriented WPS architecture is designed, which consists of three layers: the WPS interface layer, the field interface layer and the implementation layer. To test the proposed approach, a video change detection case of monitoring a road situation is shown, which was a demonstration for Open Geospatial Consortium Web Service phase 7. The results demonstrate that the proposed approach is feasible.

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.

In mobile communications, power efficiency is an important factor in the design of the handset. HPSK modulation is used to transmit multiple channels in the reverse link of cdma2000. In this paper, we propose an improved scheme that includes zero phase transition and zero crossing reduction can reduce the peak-to-average power ratio (PAR) of the HPSK signals. The improved scheme is analysed. The scheme can reduce the PAR obviously. The zero crossing rate reduction can reduce the out-of-band power effectively. The simulation results are given and prove the validity of the schemes.