Orietta Nicolis

Earthquake prediction remains one of the most challenging tasks in natural hazard research due to the complexity and heterogeneity of seismic processes in space and time. To address this, we propose a deep learning (DL) framework based on graph convolutional and recurrent neural networks (RNNs) to forecast the maximum seismic magnitude in different regions of Chile. Using a cleaned and spatially segmented catalog of seismic events, we construct a graph where each node represents a seismic cluster derived from K‐means clustering, with edges reflecting spatial proximity. Two models are evaluated: a standard Long Short‐Term Memory (LSTM) network and a hybrid Graph Convolutional Network‐LSTM (GCN‐LSTM), which incorporates both temporal dynamics and spatial dependencies. Our results show that the GCN‐LSTM model significantly outperforms the simple LSTM in terms of F1‐score and recall, especially in regions with complex seismic activity. This demonstrates the advantage of graph‐based neural models in capturing spatial correlations and improving earthquake magnitude prediction at a regional scale.

(1) Understanding and characterizing the spatial and temporal variability of agricultural data is a key aspect of precision agriculture, particularly in soil management. Modeling the spatiotemporal dependency structure through geostatistical methods is essential for accurately estimating the parameters that define this structure and for performing Kriging-based interpolation. This study aimed to analyze the spatiotemporal variability of the soybean yield over ten crop years (2012–2013 to 2021–2022) in an agricultural area located in Cascavel, Paraná, Brazil. (2) Spatial analyses were conducted using two approaches: the Gaussian linear spatial model with independent multiple repetitions and the spatiotemporal model with a separable covariance structure. (3) The results showed that the maps generated using the Gaussian linear spatial model with multiple independent repetitions exhibited similar patterns to the individual soybean yield maps for each crop year. However, when comparing the kriged soybean yield maps based on independent multiple repetitions with those derived from the spatiotemporal model with a separable covariance structure, the accuracy indices indicated that the maps were dissimilar. (4) This suggests that incorporating the spatiotemporal structure provides additional information, making it a more comprehensive approach for analyzing soybean yield variability. The best model was chosen through cross-validation and a trace. Thus, incorporating a spatiotemporal model with a separable covariance structure increases the accuracy and interpretability of soybean yield analyses, making it a more effective tool for decision-making in precision agriculture.

In this study, we analyze the seismic activity of Chile, a region known for its diverse seismic characteristics, to validate and strengthen our findings on the identification of indicators of precursory phases. We employ Bayesian inference, processing data through sliding time windows. Each window contains a fixed number of events and shifts with each new event. Regarding the temporal variations in magnitude distribution, we observe similar patterns in seismic sequences in both Italy and Chile. The estimated q-index significantly decreases before strong earthquakes and increases sharply afterward, indicating its potential as a marker of the activation state of these systems. In addition, in analyzing the spatial distances between successive earthquakes we consider various distributions, such as tapered Pareto and generalized gamma. The optimal distribution for each time window is selected by comparing the estimated values of the posterior marginal likelihood. We discover that the best-fitting distribution changes over time, serving as an additional indicator of the activation state of the systems.

A critical aspect of modeling binomial response data is selecting an appropriate link function, as an improper choice can significantly affect model precision. This paper introduces the skew–t link model, an extension of the skew–probit model, offering increased flexibility by incorporating both asymmetry and heavy tails, making it suitable for asymmetric and complex data structures. A penalized likelihood-based estimation method is proposed to stabilize parameter estimation, particularly for the asymmetry parameter. Extensive simulation studies demonstrate the model’s superior performance in terms of lower bias, root mean squared error (RMSE), and robustness compared to traditional symmetric models like probit and logit. Furthermore, the model is applied to two real-world datasets: one concerning women’s labor participation and another related to cardiovascular disease outcomes, both showing superior fitting capabilities compared to more traditional models (with probit and the skew–probit links). These findings highlight the model’s applicability to socioeconomic and medical research, characterized by skew and asymmetric data. Moreover, the proposed model could be applied in various domains where data exhibit asymmetry and complex structures.

Thin-Plate Spline Generalized Linear Models (TPS-GLMs) are an extension of Semiparametric Generalized Linear Models (SGLMs), because they allow a smoothing spline to be extended to two or more dimensions. This class of models allows modeling a set of data in which it is desired to incorporate the non-linear joint effects of some covariates to explain the variability of a certain variable of interest. In the spatial context, these models are quite useful, since they allow the effects of locations to be included, both in trend and dispersion, using a smooth surface. In this work, we extend the local influence technique for the TPS-GLM model in order to evaluate the sensitivity of the maximum penalized likelihood estimators against small perturbations in the model and data. We fit our model through a joint iterative process based on Fisher Scoring and weighted backfitting algorithms. In addition, we obtained the normal curvature for the case-weight perturbation and response variable additive perturbation schemes, in order to detect influential observations on the model fit. Finally, two data sets from different areas (agronomy and environment) were used to illustrate the methodology proposed here.