Urban spatial structures (USS) play an essential role in urbanization. Understanding the impact of USS patterns on their socioeconomic benefits is crucial to evaluating urban structure quality. Previous studies have, primarily, relied on statistical data and have significant temporal consistency and spatial accuracy limitations. Moreover, previous evaluation methods mainly determined the weight of indicators based on subjective assessments, such as the Delphi method, without integrating the actual socioeconomic benefits of complex urban systems. By measuring the two-dimensional (2D) urban functional landscape patterns and three-dimensional (3D) building forms of the city and considering the level of urban socioeconomic vitality as revealed by nighttime light intensity (NTLI), this study explores the influence of urban spatial structure on socioeconomic vitality. It provides a new perspective for evaluating the USS level. Furthermore, a comprehensive index, namely the Spatial Structure Socioeconomic Benefit Index (SSSBI), was constructed to quantify the socioeconomic benefits of USS. The results showed that (1) the impact of spatial structure on NTLI differs significantly with the distribution of urban functional landscape patterns and building forms. (2) The combined effect of any two spatial structure factors on NTLI was higher than the effect of each factor separately, indicating that multiple dimensions can improve urban spatial construction. (3) This study quantitatively extracts the characteristics of USS from multiple scales, which helps to find the optimal evaluation scale and build a scientific and objective evaluation model. The results showed that the USS assessment based on the SSSBI index is practical. This study could provide a reference for the government’s urban planning and land-use decisions.

Research on integrating statistical knowledge into deep learning models for earthquake forecasting has been limited. Traditional deep learning models require extensive parameter learning from scratch. This study proposes a Spatio-Temporal Convolutional (STC) model that incorporates spatio-temporal decay prior knowledge derived from the Epidemic-Type Aftershock Sequence (ETAS) into a convolutional kernel. This allows the STC model to have the prototype to learn the pattern of mainshocks to trigger aftershocks at the beginning of training, with only 4 neurons to fine-tune it. In California, the STC and the ETAS model are conducted for forecasting next-day earthquakes with magnitudes of M ≥3, M ≥4, and M ≥5. Both performances were assessed using the Receiver Operating Characteristic (ROC) curve, the Precision-Recall (PR) curve, and the Parimutuel Gambling Score (PGS). The evaluation results indicate that the STC model surpasses ETAS in forecasting next-day earthquakes not accidental. Furthermore, our analysis suggests that including earthquakes below the complete magnitudes can enhance the STC model’s classification performance, as small earthquakes also contain information about future earthquakes.

Earthquakes are the most dangerous natural disasters, and scholars try to predict them to protect lives and property. Recently, a long-term statistical analysis based on a “heating core” filter was applied to explore thermal anomalies related to earthquakes; however, some gaps are still present. Specifically, (1) whether there are differences in thermal anomalies generated by earthquakes of different magnitudes has not yet been discussed; and (2) thermal anomalies in high-spatial-resolution data are often distributed in spots, which is not convenient for statistics of thermal anomalies. To address these issues, in this study, we applied high-spatial-resolution thermal infrared data to explore the performance of the “heating core” for earthquake prediction at different magnitudes (i.e., 3, 3.5, 4, 4.5, and 5). The specific steps were as follows: first, the resampling and moving-window methods were applied to reduce the spatial resolution of the dataset and extract the suspected thermal anomalies; second, the “heating core” filter was used to eliminate thermal noise unrelated to the seismic activity in order to identify potential thermal anomalies; third, the time–distance–magnitude (TDM) windows were used to establish the correspondence between earthquakes and thermal anomalies; finally, the new 3D error diagram (false discovery rate, false negative rate, and space–time correlation window) and the significance test method were applied to investigate the performance under each minimum magnitude with training data, and the robustness was validated using a test dataset. The results show that the following: (1) there is no obvious difference in the thermal anomalies produced by earthquakes of different magnitudes under the conditions of a “heating core”, and (2) the best model with a “heating core” can predict earthquakes effectively within 200 km and within 20 days of thermal anomalies’ appearance. The binary prediction model with a “heating core” based on thermal infrared anomalies can provide some reference for earthquake prediction.

Neural point processes (NPPs) have recently been applied to seismicity modeling, but their theoretical connections to classical point processes models remain elusive. Moreover, two fundamental questions remain unresolved: (a) how much historical information is sufficient for NPPs to effectively model seismicity, and (b) what is the differential impact between inter‐event times and magnitudes on the model predictive performance? To answer these questions, we reinterpret a class of NPPs within the framework of neural modulated renewal processes (NMRPs), which generalize conventional modulated renewal processes by integrating deep learning architectures. We develop and analyze four variants: the unmodulated neural renewal process (NRP), the inter‐event times modulated NMRP (I‐NMRP), the magnitude modulated NMRP (M‐NMRP), and the jointly modulated NMRP (J‐NMRP). Their performance is systematically evaluated against the epidemic‐type aftershock sequence (ETAS) model using the EarthquakeNPP benchmark. Results demonstrate that I‐NMRP and J‐NMRP not only match, but in some cases surpass, ETAS in terms of log‐likelihood, while requiring substantially less historical input. Furthermore, the analysis reveals that inter‐event times play a more critical role than magnitudes in enhancing predictive performance. These findings establish NMRP as a flexible and efficient framework for seismicity modeling, with strong potential to incorporate diverse contextual information and to deepen our understanding of earthquake triggering processes.

To test whether geophysical anomalies contribute to earthquake forecasts beyond the inherent clustering effects in seismicity, we develop a self and external excitation point‐process model by incorporating anomalies into the temporal Epidemic‐Type Aftershock Sequence (ETAS) model. The model is applied to earthquakes that occurred between 2001 and 2010 around the Kakioka (KAK) station in Japan, with two types of anomalies, ultralow frequency (ULF) magnetic anomalies and carbon monoxide (CO) anomalies, as external excitations. Results indicate that 14.33% of the earthquakes can be interpreted by the external excitation of anomalies. Proposed ETAS + ULF + CO model achieves an overall probability gain of 1,013.55 in forecasting 218 earthquakes compared to the purely temporal ETAS model. Statistical significance is assessed by fitting the same model to the same earthquake catalog but with randomized anomaly occurrence times, confirming that the performance improvement is not due to overfitting. These findings highlight the potential for enhancing short‐term earthquake forecasts using non‐seismic precursors, particularly when multiple precursors are combined.