Geospatial Data Science for Public Health Surveillance


Paula Moraga, Ph.D. 

Assistant Professor of Statistics

King Abdullah University of Science
and Technology (KAUST), Saudi Arabia

   paulamoraga.bsky.social
   www.PaulaMoraga.com

a png
       a png

About me

Education

  • PhD Statistics, University of Valencia, 2012
  • MSc Biostatistics, Harvard University, 2011
  • MSc Mathematics, University of Valencia, 2006
    Erasmus Johannes Gutenberg University Mainz

Experience

Books

https://www.paulamoraga.com/book-geospatial/

      https://www.paulamoraga.com/book-spatial/

Letten Prize

I was honored to receive the Letten Prize for my work on disease surveillance by the Letten Foundation and the Young Academy of Norway

Letten Prize Day 2023. The Norwegian Academy of Science and Letters
Photo Credit: Thomas Barstad Eckhoff

Disease surveillance

Dengue emergency 2024

Mosquito-borne diseases

Diseases spread because when a mosquito bites an infected person it also swallows any viruses or parasites living in the blood of the infected person, and these can be transferred to the next person the mosquito bites

Guzman et al., Nature Reviews, 2016

Mosquito-borne diseases

Leta et al., International Journal of Infectious Diseases, 2018

Why are diseases spreading?

Rapid and unplanned urbanization and deforestation

Climate change









Ryan et al., PLOS NTDs, 2019
https://showyourstripes.info/

Global travel

What can we do to prevent the spread of infectious diseases?

Need to acknowledge connectivity between people, animals, and their shared environment and work together to prevent disease outbreaks and save lives

Access to healthcare
and education

Vaccine development and mosquito control

Early warning and response systems

Disease surveillance systems

Disease surveillance systems

Disease surveillance systems are critical to early detection of epidemics and the design of control strategies

Traditional surveillance systems rely on data gathered with a considerable delay and make surveillance systems ineffective for real-time surveillance


Digital data sources

Real-time digital information may enable to detect outbreaks earlier

“Flu plus fever, not a good way to start the weekend”

“I’m so irritated at this cough and fever”

“This flu, fever & throat ache won’t let me sleep”

Demographic and environmental risk factors

Digital health surveillance system

Data-gathering platform and modelling framework that integrates multiple data sources to produce local probabilistic predictions of disease activity

Interactive dashboard that alerts public health officials when elevated disease levels are anticipated, and provides insights about disease drivers

Disease surveillance systems

Overview of my research to help inform disease surveillance

  • Use of digital data for nowcasting dengue in Brazil
  • Dengue forecasting models to inform policymaking
  • Methodology projects to improve disease surveillance
  • Conclusions

Dengue nowcasting

Brazil faced a severe dengue epidemic in 2024

2024 has been the worst year for dengue cases on record, with over 10 million cases reported globally. Brazil has been one of the most affected countries with over 6 million confirmed cases and 6,000 deaths

Dengue epidemic in Brazil

During this time, health systems in Brazil were overwhelmed, making timely case reporting difficult. As a result, the official case numbers that were being reported were underestimating the real number of cases.
This limited the effectiveness of public health decisions

Reporting delays in official dengue cases

In Brazil, the InfoDengue system collects and generates indicators of dengue and other arboviruses:

In principle, dengue is meant to be reported within seven days of case identification. In practice,

  • Less than 50% cases are reported within one week
  • Less than 75% cases reported within four weeks
  • No more than 90% cases reported within nine weeks

Reported dengue cases in Rio de Janeiro, January 2011 to April 2012. Red line reported cases for those weeks.
Black line eventually reported cases after 10 weeks.

Bastos et al., Statistics in Medicine, 2019

Dengue nowcasting by combining official and alternative data sources

We decided to investigate alternative data sources to complement official surveillance data to produce more accurate predictions that help support decision-making

Fritz et al., Nature Sustainability, 2019

Aim: improving dengue nowcasting in Brazil using real-time search query data

Dengue nowcasting in Brazil

We assessed the value of Google Trends for weekly dengue nowcasting in the 27 Brazilian states

Each week from March 2024 to January 2025:

  • Download official number of dengue cases reported in InfoDengue and Google Trends indices
  • Fit several nowcasting models using different information
  • Performance evaluated comparing nowcasts with the actual cases (cases reported after 15 weeks) using error and uncertainty measures

Results

Results vary by state. In general, Google Trends and joint model for reported cases and delay distribution by InfoDengue are the best-performing approaches

Xiao, … and Moraga, PLOS Neglected Tropical Diseases, 2025

Weekly dengue nowcasts March to June, 2024

Weekly dengue nowcasts in Rio de Janeiro, March to June, 2024

Dengue tracker in Brazil

Dengue-tracker provides weekly updates on the number of dengue cases per state in Brazil

We present official and corrected case counts incorporating information from Google Trends

Reports assist policymakers
and the general public in understanding dengue levels
and guide their decisions

Dengue tracker in Brazil

Dengue tracker in Brazil

Impact Dengue-tracker

Dengue-tracker has been used to inform the Brazilian Ministry of Health and has been crucial in several situations:

  • Several weeks official dengue cases were not reported and the InfoDengue model was unable to produce nowcasts
  • Espirito Santo state stopped reporting at the beginning of the season
  • In these situations, Dengue-tracker was the only source of information

We also disseminated Dengue-tracker in social media and among contacts so general population could be better informed about dengue activity levels

Conclusions

  • We demonstrated the value of Google Trends data for dengue surveillance during Brazil’s 2024 dengue epidemic

  • Further research is needed to understand the use of digital data for disease information (e.g., ChatGPT)

  • Need to understand biases in digital data (not all individuals use search engines, just more educated and younger, internet penetration not same in all regions)

  • This study highlights the need for multiple, complementary data sources rather than a single data source for disease surveillance, especially during disease outbreaks

Forecasting

Disease forecasting

Nowcasting methods allow us to understand current disease activity levels and make better informed decisions

It is also important to predict the number of cases that will occur in the future so we have more time to be prepared and reduce disease impacts

During the 2024 epidemic, the Brazilian Ministry of Health requested 2025 dengue predictions to help inform their response and surveillance activities

Disease forecasting

We developed a neural network model for dengue forecasting. The model accounts for complex delayed and non-linear effects of climate variables, and spatial information to obtain improved predictions of future dengue cases

Chen and Moraga, BMC Public Health, 2025

Weekly dengue incidence rate (cases per 100K) in 27 Brazilian states

Climate covariates

Dengue forecasting methods improve their accuracy by including risk factors such as climate and environmental variables known to affect transmission

Climate covariates

We utilize a suite of covariates known to affect dengue transmission
from the Copernicus ERA5 Reanalysis Data summarized by week

Variable Unit Description
Minimum Temperature °C Lowest temperature recorded within the week, based on reanalysis hourly data.
Mean Temperature °C Average temperature across the week.
Maximum Temperature °C Highest temperature recorded within the week.
Minimum Precipitation Rate mm/h Lowest hourly precipitation rate recorded during the week.
Average Precipitation Rate mm/h Weekly average of hourly precipitation rates.
Maximum Precipitation Rate mm/h Highest hourly precipitation rate recorded during the week.
Total Precipitation mm Cumulative precipitation over the week.
Minimum Atmospheric Pressure atm Lowest atmospheric pressure measured at sea level during the week.
Average Atmospheric Pressure atm Weekly mean atmospheric pressure at sea level.
Maximum Atmospheric Pressure atm Highest atmospheric pressure measured at sea level during the week.
Minimum Relative Humidity % Lowest relative humidity value recorded during the week.
Mean Relative Humidity % Weekly average relative humidity.
Maximum Relative Humidity % Highest relative humidity recorded during the week.
Thermal Range °C Difference between the daily maximum and minimum temperatures.
Rainy Days Days Number of days within the week where the total precipitation exceeded 0.03 mm.

Borrowing information from neighbors

Neighbors assumed to be regions sharing a common boundary

Goias: Tocantins, Bahia, Minas Gerais, Mato Grosso, Mato Grosso do Sul and Distrito Federal

Model’s performance assessment

We use the first 6 years to train the model and predict the number of dengue cases 1, 2, 3, 4, 8 and 12 weeks ahead. Then, we move the window one week keeping 6 years for training to predict the number of cases weeks ahead

We assessed the model’s performance using error and uncertainty measures in comparison with other approaches that only use cases or climate information

Results

Model proposed performs well overall except northern states. These are regions in the Amazon which are less connected with their neighbors

Performance measures forecasts 4-weeks ahead

Federal Unit (FU) Code LSTM-Cases LSTM-Climate LSTM-Climate-Spatial Bayesian Baseline
MAE MAPE CRPS MAE MAPE CRPS MAE MAPE CRPS MAE MAPE CRPS
Acre (AC) 12 305.19 45.50% 90.91 129.76 22.30% 35.68 136.83 24.89% 37.34 382.77 47.23% 96.13
Alagoas (AL) 27 177.96 43.29% 38.14 79.24 30.54% 16.27 61.08 23.17% 12.98 69.39 24.28% 13.41
Amapá (AP) 16 51.21 47.90% 34.05 22.45 23.49% 5.35 27.45 26.98% 6.02 30.53 34.09% 7.12
Amazonas (AM) 13 188.17 41.56% 32.14 100.21 19.63% 19.23 111.60 21.64% 22.44 143.57 28.79% 31.40
Bahia (BA) 29 886.64 29.94% 165.30 639.44 23.20% 123.86 532.46 17.13% 120.50 718.63 22.84% 137.74
Ceará (CE) 23 562.67 46.52% 108.09 245.17 27.54% 52.99 187.56 15.51% 35.01 315.69 30.16% 60.26
Distrito Federal (DF) 53 1040.21 26.69% 244.60 926.73 23.24% 219.97 767.30 16.72% 211.70 997.42 24.57% 249.25
Espírito Santo (ES) 32 8431.94 30.90% 1713.56 7262.14 30.35% 1310.95 6300.78 23.06% 1308.43 6967.74 25.93% 1552.96
Goiás (GO) 52 1708.00 30.34% 310.44 1277.24 27.36% 226.00 1195.70 19.87% 222.87 1722.08 29.75% 321.36
Maranhão (MA) 21 143.59 56.31% 26.44 102.87 38.07% 18.93 59.27 23.91% 10.88 147.31 53.05% 28.14
Mato Grosso (MT) 51 657.81 34.65% 189.42 563.40 26.97% 142.56 340.72 16.69% 72.73 624.21 28.36% 125.27
Mato Grosso do Sul (MS) 50 1711.05 75.23% 342.47 568.10 59.97% 108.71 404.48 40.11% 81.94 1646.17 50.03% 344.61
Minas Gerais (MG) 31 15099.46 52.28% 3253.80 7730.47 33.33% 1648.53 5088.71 24.52% 1035.86 14220.67 40.19% 3472.85
Pará (PA) 15 319.85 47.03% 72.72 256.88 26.23% 53.97 159.61 19.43% 34.75 210.77 21.89% 56.14
Paraná (PR) 41 651.62 44.56% 145.98 532.44 26.62% 104.80 391.02 20.01% 81.55 603.78 22.63% 117.92
Pernambuco (PE) 26 501.76 41.95% 96.53 358.33 32.90% 69.27 257.65 19.53% 58.65 355.72 26.02% 72.60
Piauí (PI) 22 319.75 43.87% 57.96 263.10 30.81% 50.76 194.54 20.75% 41.58 298.91 28.17% 57.16
Rio de Janeiro (RJ) 33 1034.84 32.60% 217.36 861.35 25.10% 194.52 717.22 18.02% 175.08 910.87 22.58% 210.46
Rio Grande do Norte (RN) 24 313.87 49.58% 68.70 252.68 30.67% 47.31 171.49 19.76% 35.35 259.23 24.48% 49.58
Rio Grande do Sul (RS) 43 823.57 31.88% 155.09 679.61 28.42% 122.36 548.03 21.42% 98.53 736.82 25.74% 149.61
Rondônia (RO) 11 371.50 79.49% 103.44 300.93 42.08% 79.71 285.61 40.93% 69.17 323.33 43.03% 104.34
Roraima (RR) 14 9.33 40.63% 6.03 6.52 43.27% 5.02 6.36 44.31% 5.93 8.66 52.55% 2.55
Santa Catarina (SC) 42 7381.10 79.16% 1765.31 1585.71 56.28% 395.28 1556.58 15.21% 294.09 3028.00 40.68% 831.25
São Paulo (SP) 35 9544.39 49.61% 2196.34 4088.67 31.97% 921.95 3068.46 17.28% 612.34 8468.53 31.64% 1961.50
Sergipe (SE) 28 54.35 20.82% 13.07 45.92 17.48% 9.43 41.52 16.50% 8.11 86.08 31.38% 18.57
Tocantins (TO) 17 124.25 49.07% 31.51 103.21 37.89% 28.46 92.55 29.12% 20.44 128.97 45.07% 27.20

Mobility

To tackle this, instead of assuming connectivity between adjacent regions, we assumed connectivity if there were people traveling between regions

Consider dataset on mobility spanning air, road, and waterway transport (Oliveira et al., The Lancet Digital Health, 2024)

Spatial modeling including mobility data

Consider contribution of cases imported into each city \(i\) from others in week \(t\): \[ \text{Imported Cases}_{i, t} = \sum_{j \in \mathcal{N}_i} \text{Mobility}_{ji} \cdot \frac{\text{Cases}_{j, t}}{\text{Population}_j} \]

\(\mathcal{N}_i\): set of cities with connections with city \(i\),  \(\text{Mobility}_{ji}\): people from city \(j\) to \(i\),  \(\text{Cases}_{j, t}\): number cases in city \(j\) and week \(t\),  \(\text{Population}_j\) city \(j\)

Results

We assessed the performance of the improved model in selected cities representing different climatic zones and disease dynamics profiles. Results demonstrate the incorporation of human movement patterns improves prediction compared with models that use spatial adjacency structures

Chen and Moraga, Infectious Disease Modelling, 2025

Conclusions

  • Developed a forecasting model integrating cases, climate and mobility
  • Model is generalizable and can be applied to forecast other diseases influenced by climate and mobility in other settings
  • Findings in open access papers, code publicly available for reproducibility

Translation of research into action and inform policymaking

Forecasting 2025 dengue cases in Brazil

Brazilian Ministry of Health requested 2025 dengue predictions to help inform their response and surveillance activities

We participated in the Infodengue-Mosqlimate Dengue Challenge (IMDC) to produce actionable forecasts of the 2025 dengue season

We collaborated with 6 teams from different countries. Each team provided forecasts using a number of statistical and machine learning approaches that leveraged historical data as well as information on climate and environment. Then, individual forecasts were combined to produce a final dengue forecast ensemble for 2025. GitHub Dengue-Forecast-Ensemble

Ensemble forecast for dengue in Brazil, 2025

Predictions for the states of Amazonas (AM), Ceará (CE), Goiás (GO), Paraná (PR), and Minas Gerais (MG)

Correa, …, Moraga, et al., Proceedings of the National Academy of Sciences (PNAS), 2026

Dengue forecasting challenge results

The results of the challenge published in September 2024 as a technical report in Portuguese ensuring it reached key decision-makers in Ministry of Health

Dengue forecasting challenge results

  • Forecasting methods code and results publicly available for reproducibility
  • We continue our collaboration working on better models to provide improved dengue projections to help inform prevention and control strategies by the Brazilian Ministry of Health

Methodology projects to improve disease surveillance

Spatio-temporal modeling of infectious diseases

Spatio-temporal disease prediction integrating compartment and point process models

          COVID-19 cases in Cali, Colombia, 2020

LGCP model

Fit a log-Gaussian Cox process for the locations of infected individuals in the studied region and time, with mean depending on population at risk, number of infected over time and random effects

\[\begin{align} N(A, t) &\sim \text{Poisson}\left(\int_{A}\Lambda(\mathbf{x}, t)d\mathbf{x}\right) \\ \Lambda(\mathbf{x}, t) &= \lambda_{0}(\mathbf{x}, t)\ I(t)\ \exp(S({\mathbf{x}, t})) \nonumber \\ \end{align}\] \[\begin{align} \lambda_{0}(\mathbf{x}, t):\ &\text{Proportional to the population density and integrates to 1}\\ I(t):\ &\text{Number of infected people at time } t\ \text{obtained from SIR model}\\ S(\mathbf{x}, t):\ &\text{Spatial Gaussian random field with Matern covariance function} \nonumber \\ \end{align}\]


Diggle, Moraga, Rowlingson and Taylor, Statistical Science, 2013

SIR model

Fit SIR (Susceptible, Infected, Recovered) compartment model to aggregated data for each time to predict the number of infectious individuals at each time

Number individuals in population \(S(t) + I(t) + R(t) = N\) constant

Disease parameters:
\(\beta > 0\) infectious rate
\(\gamma > 0\) recovery rate

\[\begin{align*} \frac{dS(t)}{dt} &= -\beta S(t) \frac{I(t)}{N} \\ \frac{dI(t)}{dt} &= +\beta S(t) \frac{I(t)}{N} - \gamma I(t) \\ \frac{dR(t)}{dt} &= +\gamma I(t) \end{align*}\]

SIR model could be extended to consider more compartments (e.g.,
\(I_S(t)\) symptomatic, \(I_A(t)\) asymptomatic)


Kermack and McKendrick, Proceedings of the Royal Society, 1927

SIR with age-stratified contact information

We extend the SIR model to incorporate age-stratified contact information, and estimate the spatio-temporal intensity for each population group

Contact matrix with the average number of contacts of individuals with different age groups

Individuals in all age groups tend to mix with others of similar age.
This pattern most pronounced in those aged 5–24 years, least pronounced in those aged 55–69

Children mix with adults 30–39. Middle-aged adults mix with elderly

Mossong et al., PLOS Medicine, 2008

SIR + LGCP with age contact information

Using simulations and real data, we showed SIR+LGCP model has better performance than LGCP models that do not do use information from the SIR model, especially when making predictions

Ribeiro, Gonzalez and Moraga, SERRA, 2022

Spatio-temporal disease intensity

SIR+LGCP model allows us to identify high-risk locations and vulnerable populations to better develop strategies for disease prevention and control

Velocities of disease spread


The spatio-temporal disease intensity obtained can be used to calculate the velocities of disease spread

Directions and magnitudes of the velocities can be mapped at specific times to better examine the spread of the disease throughout the region



Rodriguez, Mateu and Moraga, International Statistical Review, 2026

Spatial data misalignment

Spatial data

In disease surveillance, we need to analyze data available at different spatial and spatio-temporal resolutions and that come from different sources

Spatial data misalignment

The analysis of spatial data at different spatial resolutions entails a number of statistical challenges. These may occur in several inference problems:

Data fusion

Better predict a variable by combining data available at several spatial resolutions

Estimate air pollution by combining point- and area-level data

Interpolation

Predict a variable at locations or areal units different from those of its original collection

Downscale health outcomes from state to municipality level

Regression

Relationship between response variable and explanatory variables at different spatial scales

Relationship between dengue at county level and temperature given at point locations

Gotway and Young, JAMA, 2002

Data fusion

   Ground measurements (points)       +      Satellite derived measurements (grid)

      European Environment Agency (EEAA) https://www.eea.europe.eu.   NASA Socioeconomic Data and Applications Center (SEDAC) https://sedac.ciesin.columbia.edu

Fast and flexible spatial modeling by assuming a spatially continuous variable underlying all observations modeled using a Gaussian random field

Moraga et al., Spatial Statistics, 2017

Fast and flexible spatial modeling

Assume there is a spatially continuous variable underlying all observations that can be modeled using a zero-mean Gaussian random field \(S=\{S(\boldsymbol{x}): \boldsymbol{x} \in D \subset \mathbb{R}^2 \}\). Inference INLA + custom matrix SPDE

\[Y(\boldsymbol{x})|S(\boldsymbol{x}) \sim N(\mu(\boldsymbol{x})+S(\boldsymbol{x}),\tau^2)\]

  • Point data observed at \(\boldsymbol{x}_i \in D\) \[E[Y(\boldsymbol{x}_i)] = \mu(\boldsymbol{x}_i)+S(\boldsymbol{x}_i)\]

  • Areal data arise as region averages in regions \(B_j \subset D\) \[E[Y(B_j)]=|B_j|^{-1}\int_{B_j}(\mu(\boldsymbol{x})+S(\boldsymbol{x}))d\boldsymbol{x},\ |B_j|>0\] Moraga et al., Spatial Statistics, 2017

Multivariate downscaling of air pollutants

\[\begin{split} \text{PM}_{2.5}(\mathbf{s}) & = \alpha_1 + z_{1}(\mathbf{s}) + e_1(\mathbf{s}) \\ \text{PM}_{10}(\mathbf{s}) & = \alpha_2 + \lambda_1 z_{1}(\mathbf{s})+z_2(\mathbf{s})+ e_2(\mathbf{s})\\ \text{Ozone}(\mathbf{s}) & = \alpha_3 + \lambda_2 z_{1}(\mathbf{s})+\lambda_3 z_2(\mathbf{s})+z_3(\mathbf{s}) +e_3(\mathbf{s}) \end{split}\]

Improve resolution from 10 to 2 km, reveal dependencies among pollutants

Rodriguez, Chacon and Moraga, The American Statistician, 2025

Spatio-temporal downscaling model

Spatio-temporal Gaussian field \(S = \{S(\boldsymbol{x}, t): \boldsymbol{x} \in D \subset \mathbb{R}^2, t \in T \subset \mathbb{R}^{+} \}\)

\[Y(\boldsymbol{x}, t) | S(\boldsymbol{x}, t) \sim N(\mu(\boldsymbol{x}, t) + S(\boldsymbol{x}, t), \tau^2)\]

  • Observations at locations \(\boldsymbol{x_i}\) and times \(t_k\)

\[E[Y(\boldsymbol{x_i}, t_k)] = \mu(\boldsymbol{x_i}, t_k) + S(\boldsymbol{x_i}, t_k)\]

  • Observations at areas \(B_j \subset D\) and periods of time \(\tau_l \in T\), averages of the process in space and time

\[E[Y(B_j, \tau_l)] = |B_j|^{-1} |\tau_l|^{-1} \int_{B_j} \int_{\tau_l}(\mu(\boldsymbol{x}, t) + S(\boldsymbol{x}, t)) d \boldsymbol{x} dt,\] where \(|B_j|>0\) and \(|\tau_l|>0\)

Spatio-temporal downscaling of air pollutants

Spatial resolution from 80 to 30 km and temporal resolution from 3 to 1 hour

Rodriguez and Moraga, under review, 2025

Precision disease mapping

Disease mapping is important to understand geographic and temporal patterns of diseases and allocate resources where most needed

Often, maps given at an areal resolution which difficulties decision-making

Map shows malaria prevalence in Mozambique. However, disease risk varies continuously in space & areal data unable to show how risk varies within areas

Areal estimates make difficult targeting health interventions and directing resources where most needed

Disaggregate area-level data

High-resolution estimates permit to find differences in disease risk within study regions, and identify areas and groups of people at higher risk

Alahmadi and Moraga, SERRA, 2025

Open-Source Disease Surveillance System

Open-Source Disease Surveillance System

KAUST and KSA collaborations

KAUST Rapid Research Response for COVID-19

As a member of the KAUST Rapid Research Response Team for COVID-19, I collaborated with researchers from the KAUST CEMSE and BESE Divisions, the Saudi Arabia’s Ministry of Health, Aramco, and Johns Hopkins Aramco Healthcare to address urgent public health challenges during the pandemic

COVID-19 pandemic and associated lockdown as a “Global Human Confinement Experiment”

Assessing the age and gender dependence of the severity and case fatality rates of COVID-19

Developed an approach to obtain case fatality rates adjusted by ascertainment and censoring biases. We found that COVID-19 was highly influenced by age and gender with higher case fatality rates in older ages and males.

Moraga, Ketcheson, Ombao and Duarte, Wellcome Open Research, 2020

SARS-CoV-2 genomes from Saudi Arabia show N protein mutations linked to disease severity

Current research

Spatial data science for health surveillance including models and computational tools to better inform public health policymaking

Spatio-temporal disease risk models in settings where areal boundaries change over time

Datasets where areal boundaries change over time are becoming increasingly common. Standard spatio-temporal models cannot deal with this type of data. We will develop geospatial methods and software to address temporal misalignment by constructing models that assume an underlying continuous risk surface that induces spatial and temporal correlation between areas

Disease burden in Saudi Arabia

In Saudi Arabia, cardiovascular diseases, diabetes and respiratory infections major public health concern. Models will quantify geographic and temporal patterns in incidence and mortality. This will help policymakers understand inequalities, changes over time to design strategies for prevention and control

Disease surveillance in Saudi Arabia

Disease surveillance methods to monitor chronic and infectious diseases. Collaboration with national health organizations to provide tools that empower them to utilize their data to make better informed decisions

Acknowledgements

Team


Xiang
Chen
Yang
Xiao
Guilherme
Soares
Andre Victor
Ribeiro Amaral

Fernando
Rodriguez
Ruiman
Zhong
Hanan
Alahmadi
Jonatan
Gonzalez

PhD graduates

Visit Fiocruz and InfoDengue group, Brazil

Visit Ministry of Health and University, Malaysia

Visit Ministry of Health and University, Malaysia

Capacity Building

Courses equip researchers on methods and tools to quantify disease burden, understand geographic and temporal patterns, identify risk factors, and measure inequalities

They also show how to easily turn analyses into visually informative and interactive reports and dashboards that facilitate the communication of insights to collaborators and policymakers

Books

https://www.paulamoraga.com/book-geospatial/

      https://www.paulamoraga.com/book-spatial/

Geospatial Health Data: Modeling and Visualization (2019) http://www.paulamoraga.com/book-geospatial/

   

  • Manipulate and transform point, areal, raster data, create maps with R

  • Fit and interpret Bayesian spatial, spatio-temporal models with INLA, SPDE

  • Interactive visualizations, reproducible reports, dashboards and Shiny apps

Spatial Statistics for Data Science: Theory and Practice with R (2023) http://www.paulamoraga.com/book-spatial/

  • Spatial data: types, retrieval, manipulation and visualization. Statistical methods and models to analyze spatial data using R

  • Areal data: spatial neighborhood matrices, autocorrelation, models

  • Geostatistical data: interpolation, model-based geostatistics

  • Point patterns: intensity estimation, clustering, point process models

  • Reproducible examples in environment, ecology, epidemiology, crime, real estate

Teaching undergraduate and postgraduate

Teaching at KAUST

STAT Courses

Linear models, 2021, 2022, 2023, 2024, 2025

Spatial Data Science with R, 2022, 2023, 2024, 2025

Statistical Data Science Software, 2022
AMCS/STAT School Geospatial Data Science, 2021, 2023
Aramco Master’s Data Science & Analytics, 2022, 2026

Invited short courses

20+ invited courses in statistical conferences and workshops around the world
including Joint Statistical Meetings (JSM), USA, Royal Statistical Society (RSS) Conferences, UK, and Institute of Statistical Mathematics (ISM), Japan

Professional service

Associate Editor of statistical journals

I actively contribute to professional societies, serving as Associate Editor of Journal of the Royal Statistical Society Series A, Stochastic Environmental Research and Risk Assessment, npj Digital Public Health, Editorial Board Member of Spatial Statistics and Spatial and Spatio-temporal Epidemiology, rOpenSci’s project for developing a peer review system for statistical software

JRSSA logo

rOpenSci logo

Committees of conferences and awards

Member of scientific and organizing committees of conferences, research awards, and reviewer of scientific journals and research proposals

GEOMED 2026, Spain, 4th E-Vigilancia Congress, Brazil, FOSS4G 2024, Brazil, METMA XI, UK, GEOMED 2024, Belgium, Geostats2024, Portugal, geoENV2024, Greece, KAUST 2023 Workshop on Statistics, geoENV2022, Italy, METMA4, Italy, New England Statistics Symposium 2023, USA

  

Faculty Search Committees

External expert in the Faculty Search Committee for a position of Associate Professor in Spatial Epidemiology, University of Lausanne, Switzerland


Member of PhD Dissertation Committees

University of Bath, Lancaster University, Hasselt University, Umea University, Universidad Miguel Hernandez of Elche, Universita di Corsica Pasquale Paoli, Federal University of Toulouse Midi-Pyrenees, University Jyvaskyla, KAUST, National Institute of Public Health Mexico, Stockholm University,
London School of Hygiene & Tropical Medicine, Monash University

Reviewer of Research Proposals

Swiss National Science Foundation Logo Research Council of Norway Logo
Wellcome Trust Logo Ministry of Spain Logo
European Commission Logo

Research communication

Invited and Keynote presentations

80+ invited and Keynote presentations around the world, and many contributed talks at conferences and outreach events

  • Keynote. useR! 2022, the Annual International R user’s conference, Global
  • Keynote. 13th Intl. Conf. Geostatistics for Environmental Applications, Italy
  • Keynote. XX Spanish Biostatistics Conference, Spain

Invited and Keynote presentations

80+ invited and Keynote presentations around the world, and many contributed talks at conferences and outreach events

  • Invited Speaker. Workshop Spatial Modeling, Fields Institute, Canada
  • Invited Speaker and Panelist. NeurIPS Workshop Gaussian Processes, USA
  • Panelist. FOSS4G: Free and Open Source Software for Geospatial, Argentina

Outreach events

  • 1st International Day of Women in Statistics and Data Science
  • Women in Data Science (WiDS) Jeddah at Effat University
  • World Statistics Congress, Int’l Society for Neglected Tropical Diseases
  • KAUST events at KFUPM and Imam Abdulrahman Bin Faisal University

Research communication to the public

Science podcasts, blog posts, the World Federation of Science Journalists,
TV and radio interviews (BBC News in the UK, News programs in Spain), and general-interest articles in Arab News, La Vanguardia, and other publications


Research communication to the public

Conclusions

Conclusions

Disease spread has no borders and it is urgent that we work together

Data is crucial for public health decision-making. We need data but not just any data. We need reliable, relevant, timely and detailed data to understand how different populations and regions are doing and be able to take efficient and effective actions to reduce disease burden and protect all populations

Collaborative research, data, and analytical tools crucial for solving health challenges, achieving sustainable development, and leaving no one behind

Aligned with the priorities of KAUST and Saudi Vision 2030, my work will strengthen the Kingdom’s leadership in health innovation to support healthier and longer lives for people in Saudi Arabia and beyond

Thank you!


Thanks!

Paula Moraga

   paulamoraga.bsky.social
   www.PaulaMoraga.com

a png
       a png