About

Lelys Bravo De Guenni holds the position of Clinical Associate Professor in the Department of Statistics at the University of Illinois at Urbana-Champaign. She completed her PhD at Griffith University in Brisbane, Australia, within the Division of Environmental Sciences. With over 25 years of experience, she was a professor at the graduate programs of Statistics at Simón Bolivar University in Caracas, Venezuela. Her research areas include Environmental Statistics, Fundamental Research in Statistics, Statistics and Data Science Education, Data Science and Big Data Analytics, Biostatistics and Quantitative Biology, and Quantitative Methods in the Social Sciences. She has served as a member of the Science Steering Committee for the Biospherical Aspects of the Hydrological Cycle project from the International Geosphere-Biosphere Program (IGBP) and was a lead author of the Millennium Ecosystem Assessment report. Additionally, she has held visiting professorships at the University of California in Santa Cruz, Escuela Superior Politécnica del Litoral in Ecuador, Northern Illinois University, and the University of Illinois at Urbana-Champaign. She is an elected member of the International Statistical Institute (ISI) and is affiliated with the Center for Latin America and Caribbean Studies (CLACS).

Research topics

• Computer Science
• Mathematics
• Econometrics
• Statistics
• Meteorology
• Geography
• Environmental science
• Artificial Intelligence
• Geology
• Cartography
• Physics
• Climatology

Selected publications

• Bayesian spatial prediction of three medically important tick species in Illinois

  bioRxiv (Cold Spring Harbor Laboratory) · 2026-04-21

  articleOpen access

  Abstract Tick-borne diseases are now reported from nearly every county in Illinois, and three vector tick species ( Amblyomma americanum , Dermacentor variabilis , and Ixodes scapularis ) are of particular concern because these are responsible for most of the tick-borne disease transmission in the state. However, active surveillance is patchy, many counties have little or no sampling, and there is no statewide, quantitative map of relative abundance that can be used to anticipate risk in unsampled areas. To address these gaps, we developed Bayesian hierarchical spatial models to estimate the county-level abundance of these three vector tick species in Illinois. Using active surveillance data from 2019-2022, we modeled county-level abundance as a function of climate, land cover, forest fragmentation, and deer habitat suitability. Spatial dependence was captured using a Besag-York-Mollié 2 (BYM2) prior implemented in INLA, along with spatial 5-fold cross-validation to assess predictive performance. A. americanum showed the highest predicted abundance in southern and central Illinois, D. variabilis was widespread but diffuse, and I. scapularis was concentrated in northern and selected central counties. Together, these models provide the first spatial, statewide, uncertainty-aware assessment of tick abundance in Illinois, highlighting priority counties where surveillance lags disease risk.

  PublisherDOI

• Filling surveillance gaps: Bayesian INLA models for predicting tick distributions in data-sparse regions

  bioRxiv (Cold Spring Harbor Laboratory) · 2026-04-21

  articleOpen access

  Abstract Ticks impose major health and economic losses on the livestock sector of Pakistan, yet uncertainty-aware maps of tick burden remain scarce. We focused on the two most common disease transmitting tick species, Rhipicephalus microplus and Hyalomma anatolicum , to produce exposure-adjusted district-level abundance estimates and predictions for unsampled areas in Punjab and Khyber Pakhtunkhwa (KPK). We compiled heterogeneous tick count records and standardized them per 100,000 animals. District-level climate and physiographic covariates were summarized via principal components analysis. Bayesian spatial models were fit in R-INLA using Gaussian likelihoods and BYM2 over a hybrid adjacency matrix. Competing non-spatial and spatial models were compared, and the best model was used to generate posterior predictions and 95% credible intervals for unsampled districts. Spatial models outperformed non-spatial alternatives and calibrated well. Model robustness was confirmed through eight independent 80/20 train-test splits, showing strong generalization with consistent predictions across seeds. For unsampled areas, R. microplus exhibited a pronounced north-south gradient with high predicted means but wide intervals in the northern highlands, indicating information gaps. H. anatolicum predictions were highest and most precise in southern Punjab. Sensitivity analysis highlighted a dominant spatial component, with modest contributions from PC1 and PC2. The Bayesian spatial models using the Besag-York-Mollié framework delivered comparable, exposure-adjusted tick abundance maps while quantifying uncertainty to guide surveillance. Results suggest a need for immediate control in confirmed hotspots and recommend targeted field sampling in high-uncertainty districts. The workflow generalizes to other vectors, pathogens, and regions for evidence-based livestock health planning.

  PublisherOA PDFDOI

• Using machine learning to overcome mosquito collections missing data for malaria modeling

  bioRxiv (Cold Spring Harbor Laboratory) · 2026-04-17

  articleOpen accessSenior author

  Abstract Entomological surveillance plays a crucial role in areas where malaria remains endemic, yet gathering data on mosquito populations is often expensive and complicated, particularly in remote locations with challenging logistics and inconsistent sampling schedules. Access to extensive time series data on mosquito species at specific sites would greatly enhance insights into seasonal trends and the biting habits of vectors of malaria parasites. Gaps in mosquito count records pose a significant challenge for researchers and public health officials seeking to establish early warning systems and effective vector control programs. In this study, we apply quantitative machine learning techniques to address missing data in estimates of mosquito abundance collected from 2009 to 2016 in Bolívar State, Venezuela. We evaluated Linear Regression, Stochastic Linear Regression, K Nearest-Neighbor, and Gradient Boosting methods for imputing missing counts of Anopheles mosquitoes, employing a leave-one-out cross-validation strategy. Additionally, we developed a predictive malaria transmission model incorporating mosquito abundance and climate variables (El Niño 3.4 Index, rainfall, and mean air temperature) as covariates. Our generalized time series model forecasts malaria incidence of Plasmodium vivax and Plasmodium falciparum based on climate dynamics and imputed mosquito data. Model performance was assessed using root mean square error, mean absolute error, and mean absolute percentage error. The final results demonstrated that machine learning imputation significantly improved the accuracy and reliability of P. vivax malaria incidence predictions but failed to predict P. falciparum incidence. The study demonstrates that method choice significantly influences the reconstruction of seasonal abundance patterns and the performance of malaria incidence models. Nevertheless, the proposed models strengthen the foundation for targeted interventions and surveillance in endemic regions. Despite limitations in data continuity and coverage, the findings highlight the value of combining multiyear entomological data sets with robust imputation and sensitivity analyses to improve predictive modeling in resource-constrained, malaria-endemic settings.

  PublisherOA PDFDOI

• Poisson Distribution and Its Application in Statistics

  International Encyclopedia of Statistical Science · 2025-01-01

  book-chapter1st authorCorresponding
  PublisherDOI

• Long Short‐Term Memory Wavelet Neural Network for Renewable Energy Generation Forecasting

  International Journal of Intelligent Systems · 2025-01-01 · 3 citations

  articleOpen access

  Renewable energy forecasting is crucial for pollution prevention, management, and long‐term sustainability. In response to the challenges associated with energy forecasting, the simultaneous deployment of several data‐processing approaches has been used in a variety of studies in order to improve the energy–time‐series analysis, finding that, when combined with the wavelet analysis, deep learning techniques can achieve high accuracy in energy forecasting applications. Consequently, we investigate the implementation of various wavelets within the structure of a long short‐term memory neural network (LSTM), resulting in the new LSTM wavelet (LSTMW) neural network. In addition, and as an improvement phase, we modeled the uncertainty and incorporated it into the forecast so that systemic biases and deviations could be accounted for (LSTMW with luster: LSTMWL). The models were evaluated using data from six renewable power generation plants in Chile. When compared to other approaches, experimental results show that our method provides a prediction error within an acceptable range, achieving a coefficient of determination ( R 2 ) between 0.73 and 0.98 across different test scenarios, and a consistent alignment between forecasted and observed values, particularly during the first 3 prediction steps.

  PublisherOA PDFDOI

• Normal Scores

  International Encyclopedia of Statistical Science · 2025-01-01

  book-chapter1st authorCorresponding
  PublisherDOI

• Characterization of larval habitats of Anopheles (Nyssorhynchus) darlingi and associated species in malaria areas in western Brazilian Amazon

  Memórias do Instituto Oswaldo Cruz · 2024-01-01 · 2 citations

  articleOpen access

  BACKGROUND: Anopheles darlingi is the most efficient vector of malaria parasites in the Neotropics. Nevertheless, the specificities of its larval habitats are still poorly known. OBJECTIVES: Characterize permanent larval habitats, and population dynamics of An. darlingi and other potential vectors in relation to climate, physicochemical variables, insect fauna and malaria cases. METHODS: A 14-month longitudinal study was conducted in Porto Velho, Rondônia, western Brazilian Amazon. Monthly, 21 permanent water bodies were sampled. Immature anophelines and associated fauna were collected, physicochemical characteristics, and climate variables were recorded and analyzed. FINDINGS: Five types of habitats were identified: lagoon, stream, stream combined with lagoon, stream combined with dam, and fishpond. A total of 60,927 anophelines were collected. The most abundant species in all habitats were Anopheles braziliensis and An. darlingi. The highest density was found in the lagoon, while streams had the highest species richness. Abundance was higher during the transition period wet-dry season. There was a lag of respectively four and five months between the peak of rainfall and the Madeira River level and the highest abundance of An. darlingi larvae, which were positively correlated with habitats partially shaded, pH close to neutrality, increase dissolved oxygen and sulphates. MAIN CONCLUSIONS: The present study provides data on key factors defining permanent larval habitats for the surveillance of An. darlingi and other potential vectors as well as a log-linear Negative Binomial model based on immature mosquito abundance and climate variables to predict the increase in the number of malaria cases.

  PublisherDOI

• Climate change impacts on rainfall intensity–duration–frequency curves in local scale catchments

  Environmental Monitoring and Assessment · 2024 · 19 citations

  • Climatology
  • Environmental science
  • Meteorology

  The increasing intensity and frequency of rainfall events, a critical aspect of climate change, pose significant challenges in the construction of intensity-duration-frequency (IDF) curves for climate projection. These curves are crucial for infrastructure development, but the non-stationarity of extreme rainfall raises concerns about their adequacy under future climate conditions. This research addresses these challenges by investigating the reasons behind the IPCC climate report's evidence about the validity that rainfall follows the Clausius-Clapeyron (CC) relationship, which suggests a 7% increase in precipitation per 1 °C increase in temperature. Our study provides guidelines for adjusting IDF curves in the future, considering both current and future climates. We calculate extreme precipitation changes and scaling factors for small urban catchments in Barranquilla, Colombia, a tropical region, using the bootstrapping method. This reveals the occurrence of a sub-CC relationship, suggesting that the generalized 7% figure may not be universally applicable. In contrast, our comparative analysis with Illinois, USA, an inland city in the north temperate zone, shows adherence to the CC relationship. This emphasizes the need for local parameter calculations rather than relying solely on the generalized 7% figure.

  PublisherOA PDFDOI

• Catalysing virtual collaboration: The experience of the remote TIES working groups

  Environmetrics · 2024-05-23

  articleOpen access

  Abstract During the COVID‐19 pandemic, the idea of collaboration and scientific exchange between members of the scientific community was enhanced by technology. Virtual meetings and work platforms have become common resources to continue generating research, partially replacing instances of joint in‐person work before, during or after a conference. The idea of teleworking played a fundamental role in remote collaboration groups within The International Statistical Society (TIES), a community of interdisciplinary scientists such as statisticians, mathematicians, meteorologists, and biologists, among others working on quantitative methods to enhance solutions to environmental problems. In 2021 the Society launched three working groups with the aim of improving networking across the Society's members and develop creative collaboration, while advancing statistical and computational methods motivated by real‐world driven applications in environmental research. Here, we provide insights from this virtual collaborative initiative.

  PublisherOA PDFDOI

• Assessing Water Quality Spatial Heterogeneity from Multiple Pollution Sources in the Boung Cheung Ek Wetland, Phnom Penh, Cambodia

  Water · 2023-12-19 · 3 citations

  articleOpen access1st authorCorresponding

  Phnom Penh, the capital of Cambodia, as with many other world megacities, is exposed to multiple major ecological and environmental hazards. Without a proper wastewater treatment facility, it is difficult for local residents to obtain a health-compliant water supply. In this study, a hybrid aggregation method using principal component analysis (PCA) and weighted means was used to calculate a water quality index (WQI) to map the water quality of the entire Boeung Cheung Ek (BCE) wetland region. We used Universal Kriging to map eight water quality parameters: DO, pH, TDS, F, Cl, NO3−, PO43−, and NH4+. The restricted maximum likelihood method was used for model fitting. Data were collected from groundwater and surface water for different rainfall seasons between March 2017 and February 2018. The principal component analysis (PCA) used to compute a water quality index (WQI) is based on the resulting dimensions of the highest variation among all water quality parameters. The results show that the northern part of the study area has a worse water quality than the southern region, which is caused by the discharge of municipal wastewater directly into the BCE wetland area. The results for different rainfall seasons also show that groundwater has a relatively better quality than surface water. The results of this analysis can serve as a supplementary study to support sustainable development goals because they might confirm the need for a wastewater treatment facility being under construction at the time of writing this article with funding from the Japan International Cooperation Agency (JICA).

  PublisherOA PDFDOI

Frequent coauthors

• Michel Meybeck

  20 shared

• Charles I. Vörösmarty

  University of New Hampshire at Manchester

  11 shared

• Martin Claußen

  9 shared

• J. H. C. Gash

  University of Lisbon

  9 shared

• Ronald Hutjes

  8 shared

• Paul A. Dirmeyer

  George Mason University

  8 shared

• Sabine Lütkemeier

  Potsdam Institute for Climate Impact Research

  8 shared

• P. Kabat

  Wageningen University & Research

  8 shared

Education

• PhD taken at the Division of Environmental Sciences, Environmental Sciences

  Griffith University

  1991

• Master in Water Resources Engineering and Planning, Procesos y Sistemas

  Universidad Simón Bolivar

  1982

• Bachelor in Mathematics, Pure and Applied Mathematics

  Universidad Simón Bolivar

  1980

Awards & honors

• Elected Member of the International Statistical Institute (I…