Jonatan Gonzalez-Monsalvo

The purpose of this research is to establish whether there are factors that contribute to the predatory activation of serial homicide offenders (SHOs) in relation to the lunar cycles. In order to move the discussion away from the media fascination with SHOs and the perpetuation of myths regarding the lunar cycle, we used a quasi-Poisson log-linear regression model based on 9976 homicides that occurred between 1 January 1960 and 30 November 2016. The results indicate that lunar phase does not influence the frequency of homicides (p = 0.997), with rate ratios across Moon phases ranging narrowly around 1.00 (e.g., full moon RR = 1.03; 95% CI: 0.66-1.63). Likewise, other variables related to the lunar cycle, such as the Moon´s distance from Earth, seasonal variation, and the percentage of the Moon´s illuminated surface, were not statistically significant predictors of homicide. In contrast, the age of the victims showed a strong and significant relationship, with persons aged 15-64 being 8.71 times more likely to be homicide victims than others (p < 2e-16). In general, these findings, obtained over a 56-year observation period, provide no statistical evidence of a relationship between the lunar cycle and SHO criminal activity. The large sample size and extended temporal coverage enhance the generalizability of these conclusions.

Climate change poses significant risks to Mediterranean aquaculture, with sea surface temperature (SST) identified as a critical stressor affecting cultivated species. This study aims to assess climate-related risks for coastal aquaculture in the Valencian Community (Spain) by analyzing SST spatiotemporal variability and predicting future trends. A multi-method approach was employed, combining ARIMA models for 10-year predictions at eight coastal locations, Bayesian hierarchical models (BHM) fitted via INLA for spatiotemporal analysis of maximum SST and temperature range (2000–2024), and Generalized Additive Models (GAM) to evaluate relationships with climate indices (NAO, AMO, ENSO). Results revealed a consistent warming trend since the 1990s, with ARIMA predictions indicating maximum SST values of 27.2±0.1 °C in September over the next decade. The spatiotemporal model showed effective spatial correlation ranges of 246 km for maximum SST and 207 km for SST range. Anomalous warming years (2003, 2006, 2018, 2023–2024) coincided with documented marine heatwave events. The GAM explained 98.2% of deviance, with AMO showing significant influence (>0.001) while ENSO was not statistically significant. Notably, the area north of San Antonio Cape exhibited lower warming trends, suggesting potential climate refuge characteristics. Southern locations (Altea, Campello) currently experience the highest temperatures, but projections indicate Valencia and Sagunto will become the warmest areas. These findings provide essential information for marine spatial planning and recommend a precautionary approach when considering aquaculture relocation towards northern coastal areas.

We introduce a novel nonparametric method for testing the hypothesis of independence between a marked point process with functional marks and a covariate. In a special case, when the functional marks are constructed using the local indicator of spatial association (LISA) functions, it results in testing the second-order intensity reweighted stationarity (SOIRS) hypothesis against a specific alternative that is determined by a chosen covariate. SOIRS is often used as a convenient assumption in analysing point patterns, but a general formal test of the SOIRS hypothesis is not available in the literature. Our simulation experiments indicate that the proposed test performs well both in size and power. The practical application of the proposed methodology is demonstrated using a point pattern of fish locations in a water reservoir, accompanied by four covariates.

This study introduces a novel method specifically designed to detect clusters of points within linear networks. This method extends a classification approach used for point processes in spatial contexts. Unlike traditional methods that operate on planar spaces, our approach adapts to the unique geometric challenges of linear networks, where classical properties of point processes are altered, and intuitive data visualisation becomes more complex. Our method utilises the distribution of the Kth nearest neighbour volumes, extending planar-based clustering techniques to identify regions of increased point density within a network. This approach is particularly effective for distinguishing overlapping Poisson processes within the same linear network. We demonstrate the practical utility of our method through applications to road traffic accident data from two Colombian cities, Bogota and Medellin. Our results reveal distinct clusters of high-density points in road segments where severe traffic accidents (resulting in injuries or fatalities) are most likely to occur, highlighting areas of increased risk. These clusters were primarily located on major arterial roads with high traffic volumes. In contrast, low-density points corresponded to areas with fewer accidents, likely due to lower traffic flow or other mitigating factors. Our findings provide valuable insights for urban planning and road safety management.

We consider the feature detection problem in the presence of clutter in point processes on linear networks. We extend the classification method developed in previous studies to this more complex geometric context, where the classical properties of a point process change and data visualization are not intuitive. We use the K-th nearest neighbour volumes distribution in linear networks for this approach. As a result, our method is suitable for analysing point patterns consisting of features and clutter as two superimposed Poisson processes on the same linear network. To illustrate the method, we present simulations and examples of road traffic accidents that resulted in injuries or deaths in two cities in Colombia.

Infectious disease modeling plays an important role in understanding disease spreading dynamics and can be used for prevention and control. The well-known SIR (Susceptible, Infected, and Recovered) compartment model and spatial and spatio-temporal statistical models are common choices for studying problems of this kind. This paper proposes a spatio-temporal modeling framework to characterize infectious disease dynamics by integrating the SIR compartment and log-Gaussian Cox process (LGCP) models. The method’s performance is assessed via simulation using a combination of real and synthetic data for a region in São Paulo, Brazil. We also apply our modeling approach to analyze COVID-19 dynamics in Cali, Colombia. The results show that our modified LGCP model, which takes advantage of information obtained from the previous SIR modeling step, leads to a better forecasting performance than equivalent models that do not do that. Finally, the proposed method also allows the incorporation of age-stratified contact information, which provides valuable decision-making insights.

Crime data analysis is an essential source of information to aid social and political decisions makers regarding the allocation of public security resources. Computer-aided dispatch systems and technological advances in geographic information systems have made analysing and visualising historical spatial and temporal records of crimes a vital part of police operations and strategy. We look at our motivating crime problem as a spatio-temporal point pattern. Using a conditional approach based on properties of Poisson point processes, we transform the spatio-temporal point process prediction problem into a classification problem. We create spatio-temporal handcrafted features to link future and past events and use machine learning algorithms to learn behavioural patterns from the data. The fitted model is then used to carry out the reverse transformation, i.e. to perform spatio-temporal risk predictions based on the outcomes of the classification problem. Our procedure has theoretical formalism from point process theory and gains flexibility and computational efficiency inherited from the machine learning field. We show its performance under some simulated scenarios and a real application to spatio-temporal prediction and risk assessment of homicides in Bogota, Colombia.