arXiv subjects

Raquel Menezes

Publications and source records attributed to Raquel Menezes.

8 recordsLinked to original sources

arXiv2026

Visual Spatial Learning: Single-Field Spatial Interpolation Using Convolutional Neural Networks

Predicting a complete spatially correlated field from sparse observations is a fundamental challenge in spatial statistics and environmental modelling. Classical interpolation methods such as Kriging rely on Gaussian process assumptions and variography, which can limit their effectiveness in non-stationary settings and require substantial domain expertise. In this work, we leverage an architecture based on convolutional neural networks (CNNs) for spatial interpolation that is trained and applied on a single partially observed field, without access to external data or prior fields. The model is supervised directly on the observed locations and learns to predict values at unobserved points on the user defined grid. Unlike Kriging, our method does not require explicit covariance modelling or variogram estimation, and it can flexibly capture local spatial patterns in a data-driven manner. This work demonstrates the potential of CNNs for single-instance spatial interpolation under sparse supervision, offering a practical alternative to classical geostatistical methods, and extending the use of CNNs to a new problem domain.

stat.ML↗

arXiv2026

Bitcoin's Power Law: Weak Structure, Strong Forecasts

Bitcoin's price has been described as following a power law (PL) in time, $P \sim t^{\beta}$ with $\hat\beta \approx 5.7$ over 2010-2026. We test this claim using the Clauset-Shalizi-Newman protocol applied to Bitcoin's tail-relevant distributional series, and develop three principled time-domain adaptations of the protocol. We find that (i) the distributional power law is rejected on UTXO balances and daily |returns|, with lognormal preferred decisively; (ii) the fitted time-domain exponent varies by nearly a factor of three across reasonable shifts of the time origin -- it is not specification-robust in the sense required for a shift-invariant structural reading; (iii) standard residual diagnostics and scale-invariance tests proposed in earlier work cannot distinguish a power law from a multi-component sigmoid stack fit to the same data; (iv) Bitcoin price stands apart in a cross-asset comparison spanning Bitcoin on-chain metrics and traditional asset classes: it is the only series in the nine-series in-sample test where no single-component growth curve improves on the power law, and the quarterly $K=3$ wave-stability bootstrap rejects the PL+AR(1) null on Bitcoin at $p = 0.015$ (strict 15% CV threshold) -- a clear cross-asset separation, although not a Bonferroni-robust rejection; and (v) walk-forward Diebold-Mariano evaluation against ten candidates -- including standard time-series baselines (RW with drift, auto-ARIMA, ETS, local-linear-trend) -- shows the in-sample winner (multi-sigmoid) is among the worst long-horizon forecasters, while the simple power law dominates 12-24 month horizons against every standard baseline at $p < 0.05$, precisely because it does not commit to specific wave shapes. The fit-prediction tradeoff is the practical counterpart of the descriptive findings.

stat.AP↗

arXiv2025

A Zero-Inflated Spatio-Temporal Model for Integrating Fishery-Dependent and Independent Data under Preferential Sampling

Sustainable management of marine ecosystems is vital for maintaining healthy fishery resources, and benefits from advanced scientific tools to accurately assess species distribution patterns. In fisheries science, two primary data sources are used: fishery-independent data (FID), collected through systematic surveys, and fishery-dependent data (FDD), obtained from commercial fishing activities. While these sources provide complementary information, their distinct sampling schemes - systematic for FID and preferential for FDD - pose significant integration challenges. This study introduces a novel spatio-temporal model that integrates FID and FDD, addressing challenges associated with zero-inflation and preferential sampling (PS) common in ecological data. The model employs a six-layer structure to differentiate between presence-absence and biomass observations, offering a robust framework for ecological studies affected by PS biases. Simulation results demonstrate the model's accuracy in parameter estimation across diverse PS scenarios and its ability to detect preferential signals. Application to the study of the distribution patterns of the European sardine populations along the southern Portuguese continental shelf illustrates the model's effectiveness in integrating diverse data sources and incorporating environmental and vessel-specific covariates. The model reveals spatio-temporal variability in sardine presence and biomass, providing actionable insights for fisheries management. Beyond ecology, this framework offers broad applicability to data integration challenges in other disciplines.

stat.AP↗

arXiv2025

Joint model for zero-inflated data combining fishery-dependent and fishery-independent sources

Accurately identifying spatial patterns of species distribution is crucial for scientific insight and societal benefit, aiding our understanding of species fluctuations. The increasing quantity and quality of ecological datasets present heightened statistical challenges, complicating spatial species dynamics comprehension. Addressing the complex task of integrating multiple data sources to enhance spatial fish distribution understanding in marine ecology, this study introduces a pioneering five-layer Joint model. The model adeptly integrates fishery-independent and fishery-dependent data, accommodating zero-inflated data and distinct sampling processes. A comprehensive simulation study evaluates the model performance across various preferential sampling scenarios and sample sizes, elucidating its advantages and challenges. Our findings highlight the model's robustness in estimating preferential parameters, emphasizing differentiation between presence-absence and biomass observations. Evaluation of estimation of spatial covariance and prediction performance underscores the model's reliability. Augmenting sample sizes reduces parameter estimation variability, aligning with the principle that increased information enhances certainty. Assessing the contribution of each data source reveals successful integration, providing a comprehensive representation of biomass patterns. Empirical validation within a real-world context further solidifies the model's efficacy in capturing species' spatial distribution. This research advances methodologies for integrating diverse datasets with different sampling natures further contributing to a more informed understanding of spatial dynamics of marine species.

stat.ME↗

arXiv2025

Distributed Generalized Linear Models: A Privacy-Preserving Approach

This paper presents a novel approach to classical linear regression, enabling model computation from data streams or in a distributed setting while preserving data privacy in federated environments. We extend this framework to generalized linear models (GLMs), ensuring scalability and adaptability to diverse data distributions while maintaining privacy-preserving properties. To assess the effectiveness of our approach, we conduct numerical studies on both simulated and real datasets, comparing our method with conventional maximum likelihood estimation for GLMs using iteratively reweighted least squares. Our results demonstrate the advantages of the proposed method in distributed and federated settings.

stat.CO↗

arXiv2021

Estimating Active Cases of COVID-19

Having accurate and timely data on confirmed active COVID-19 cases is challenging, since it depends on testing capacity and the availability of an appropriate infrastructure to perform tests and aggregate their results. In this paper, we propose methods to estimate the number of active cases of COVID-19 from the official data (of confirmed cases and fatalities) and from survey data. We show that the latter is a viable option in countries with reduced testing capacity or suboptimal infrastructures.

physics.soc-ph↗

arXiv2020

Geostatistical models for zero-inflated data and extreme values

Understanding the spatial distribution of animals, during all their life phases, as well as how the distributions are influenced by environmental covariates, is a fundamental requirement for the effective management of animal populations. Several geostatistical models have been proposed in the literature, however often the data structure presents an excess of zeros and extreme values, which can lead to unreliable estimates when these are ignored in the modelling process. To deal with these issues, we propose a point-referenced zero-inflated model to model the probability of presence together with the positive observations and a point-referenced generalised Pareto model for the extremes. Finally, we combine the results of these two models to get the spatial predictions of the variable of interest. We follow a Bayesian approach and the inference is made using the package R-INLA in the software R. Our proposed methodology was illustrated through the analysis of the spatial distribution of sardine eggs density (eggs/$m^3$). The results showed that the combined model for zero-inflated and extreme values improved the spatial prediction accuracy. Accordingly, our conclusion is that it is relevant to consider the data structure in the modelling process. Also, the hierarchical model considered can be widely applicable in many ecological problems and even in other contexts.

stat.AP↗

arXiv2020

CoronaSurveys: Using Surveys with Indirect Reporting to Estimate the Incidence and Evolution of Epidemics

The world is suffering from a pandemic called COVID-19, caused by the SARS-CoV-2 virus. National governments have problems evaluating the reach of the epidemic, due to having limited resources and tests at their disposal. This problem is especially acute in low and middle-income countries (LMICs). Hence, any simple, cheap and flexible means of evaluating the incidence and evolution of the epidemic in a given country with a reasonable level of accuracy is useful. In this paper, we propose a technique based on (anonymous) surveys in which participants report on the health status of their contacts. This indirect reporting technique, known in the literature as network scale-up method, preserves the privacy of the participants and their contacts, and collects information from a larger fraction of the population (as compared to individual surveys). This technique has been deployed in the CoronaSurveys project, which has been collecting reports for the COVID-19 pandemic for more than two months. Results obtained by CoronaSurveys show the power and flexibility of the approach, suggesting that it could be an inexpensive and powerful tool for LMICs.

cs.DC↗