Sudipto Banerjee
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Sudipto Banerjee has a total of 178 co-authors. Here are the top co-authors by number of shared publications:
- Abhirup Datta
Department of Biostatistics, Johns Hopkins University
9 shared publications - Andrew O. Finley
Michigan State University
9 shared publications Abhirup Datta
Department of Biostatistics, Johns Hopkins University, Baltimore, MD, USA
8 shared publicationsGurumurthy Ramachandran
Department of Environmental Health and Engineering, Bloomberg School of Public Health, Johns Hopkins University, Baltimore, MD, USA
8 shared publicationsAndrew O. Finley
Departments of Forestry and Geography Michigan State University East Lansing Michigan USA
4 shared publicationsCaroline Groth
Division of Biostatistics, University of Minnesota, Minneapolis, MN 55455, USA
4 shared publications
Latest Publications
- Open Access
- 8 September 2026
- Published by Taylor & Francis in Journal of the American Statistical Association
- p. 1-14
Bayesian Spatiotemporal Wombling
1 IntroductionStatistical inference for rates of change in spatial random fields is instrumental in data-driven scientific discoveries. Such inference is pursued in diverse scientific investigation...
- 8 September 2026
- Published by Taylor & Francis in Journal of the American Statistical Association
- p. 1-14
Open AccessBayesian Spatiotemporal Wombling
1 IntroductionStatistical inference for rates of change in spatial random fields is instrumental in data-driven scientific discoveries. Such inference is pursued in diverse scientific investigation...
- Open Access
- 1 July 2026
- Published by Oxford University Press (OUP) in Biometrics
- Vol. 82 (3)
Spatial confounding in multivariate areal data analysis
We investigate spatial confounding in the presence of multivariate disease dependence. Although multiple methods have been proposed for adjusting statistical models to mitigate spatial confounding in estimating regression coefficients, the results on interactions between spatial confounding and multivariate dependence are very limited. We contribute to this domain by investigating spatial confounding from the “analysis” and “data generation” perspectives in a Bayesian coregionalized areal regression model. We derive novel results that show that under spatial confounding, posterior variance inflation is limited in multivariate areal models and spatial point estimators of fixed effects retain higher precision compared to their non-spatial counterparts. We demonstrate the favorable performance of spatial analysis compared to a non-spatial model in our simulation experiments, even in the presence of spatial confounding and a misspecified spatial structure. In this regard, we align with recommendations from several authors in preferring hierarchical spatial models. We analyze county-level data from the US on obesity/diabetes prevalence and diabetes-related cancer mortality, comparing the results with and without spatial random effects.
- 1 July 2026
- Published by Oxford University Press (OUP) in Biometrics
- Vol. 82 (3)
Open AccessSpatial confounding in multivariate areal data analysis
We investigate spatial confounding in the presence of multivariate disease dependence. Although multiple methods have been proposed for adjusting statistical models to mitigate spatial confounding in estimating regression coefficients, the results on interactions between spatial confounding and multivariate dependence are very limited. We contribute to this domain by investigating spatial confounding from the “analysis” and “data generation” perspectives in a Bayesian coregionalized areal regression model. We derive novel results that show that under spatial confounding, posterior variance inflation is limited in multivariate areal models and spatial point estimators of fixed effects retain higher precision compared to their non-spatial counterparts. We demonstrate the favorable performance of spatial analysis compared to a non-spatial model in our simulation experiments, even in the presence of spatial confounding and a misspecified spatial structure. In this regard, we align with recommendations from several authors in preferring hierarchical spatial models. We analyze county-level data from the US on obesity/diabetes prevalence and diabetes-related cancer mortality, comparing the results with and without spatial random effects.
- Open Access
Model-based Detection of Spatial Disease Boundaries Using Amortized Bayesian Inference
Disease boundary analysis identifies abrupt changes in health outcomes across geographic boundaries, guiding targeted public health interventions and outbreak surveillance. Current implementations often adopt a Bayesian "wombling" approach and largely rely on Markov Chain Monte Carlo (MCMC) posterior sampling, presenting scalability issues for large-scale disease surveillance. We leverage amortized Bayesian inference (ABI) to accelerate the detection of spatial health disparities between neighboring US counties by embedding neural posterior estimation within a Bayesian areal wombling framework. Exploiting the computational efficiency of ABI, we further introduce the Residual Disparity Elimination Target, a metric for the required reduction in mortality or prevalence for a region to eliminate a significant disparity with its neighbor. We analyze tracheal, bronchus, and lung cancer mortality rates across mainland US counties and achieve results concordant with MCMC analysis while scaling areal wombling to hundreds of outcomes and translating disparity detection into interpretable policy objectives.
Open AccessModel-based Detection of Spatial Disease Boundaries Using Amortized Bayesian Inference
Disease boundary analysis identifies abrupt changes in health outcomes across geographic boundaries, guiding targeted public health interventions and outbreak surveillance. Current implementations often adopt a Bayesian "wombling" approach and largely rely on Markov Chain Monte Carlo (MCMC) posterior sampling, presenting scalability issues for large-scale disease surveillance. We leverage amortized Bayesian inference (ABI) to accelerate the detection of spatial health disparities between neighboring US counties by embedding neural posterior estimation within a Bayesian areal wombling framework. Exploiting the computational efficiency of ABI, we further introduce the Residual Disparity Elimination Target, a metric for the required reduction in mortality or prevalence for a region to eliminate a significant disparity with its neighbor. We analyze tracheal, bronchus, and lung cancer mortality rates across mainland US counties and achieve results concordant with MCMC analysis while scaling areal wombling to hundreds of outcomes and translating disparity detection into interpretable policy objectives.
Leveraging Artificial Intelligence in Allergy, Asthma, and Immunology With Environmental Exposures
Artificial intelligence (AI) in environmental health science is revolutionizing data analysis and problem‐solving approaches. These technologies facilitate the prediction of environmental exposures and disease outcomes and enable the identification of causal relationships for subsequent hypothesis testing. AI techniques improve pollution research through the analysis of satellite imagery and the modeling of pollutant dispersion, while AI advances chemical safety evaluations in toxicology by examining extensive datasets. AI is instrumental in addressing pressing environmental challenges, including remediation of polluted sites and ensuring equitable healthcare applications to mitigate biases. The expanding availability of large‐scale environmental, geospatial, and health outcome databases offers unprecedented opportunities for innovative applications. Their predictive capabilities are essential in disaster management, enabling real‐time analysis and optimizing resource deployment amid climate‐related crises. AI‐driven approaches play a critical role in carbon capture and waste management efforts aimed at reducing environmental impact. Furthermore, AI can elucidate complex relationships between the exposome—defined as the totality of exposures throughout an individual's life—and health outcomes, facilitating preventative strategies. This review examines the capabilities and limitations of AI in environmental health and safety, providing insights into its judicious and effective use for environmental management and healthcare.
Leveraging Artificial Intelligence in Allergy, Asthma, and Immunology With Environmental Exposures
Artificial intelligence (AI) in environmental health science is revolutionizing data analysis and problem‐solving approaches. These technologies facilitate the prediction of environmental exposures and disease outcomes and enable the identification of causal relationships for subsequent hypothesis testing. AI techniques improve pollution research through the analysis of satellite imagery and the modeling of pollutant dispersion, while AI advances chemical safety evaluations in toxicology by examining extensive datasets. AI is instrumental in addressing pressing environmental challenges, including remediation of polluted sites and ensuring equitable healthcare applications to mitigate biases. The expanding availability of large‐scale environmental, geospatial, and health outcome databases offers unprecedented opportunities for innovative applications. Their predictive capabilities are essential in disaster management, enabling real‐time analysis and optimizing resource deployment amid climate‐related crises. AI‐driven approaches play a critical role in carbon capture and waste management efforts aimed at reducing environmental impact. Furthermore, AI can elucidate complex relationships between the exposome—defined as the totality of exposures throughout an individual's life—and health outcomes, facilitating preventative strategies. This review examines the capabilities and limitations of AI in environmental health and safety, providing insights into its judicious and effective use for environmental management and healthcare.
- Open Access
- 1 June 2026
- Published by The R Foundation in The R Journal
- Vol. 18 (2) , 71-84
nimblewomble: An R package for Bayesian Wombling with nimble
- 1 June 2026
- Published by The R Foundation in The R Journal
- Vol. 18 (2) , 71-84
Open Accessnimblewomble: An R package for Bayesian Wombling with nimble
- Open Access
- 25 January 2026
- Published by Wiley in Environmetrics
- Vol. 37 (2)
Bayesian Inference for Spatially‐Temporally Misaligned Data Using Predictive Stacking
Air pollution remains a major environmental risk factor that is often associated with adverse health outcomes. However, quantifying and evaluating its effects on human health is challenging due to the complex nature of exposure data. Recent technological advances have led to the collection of various indicators of air pollution at increasingly high spatial‐temporal resolutions (e.g., daily averages of pollutant levels at spatial locations referenced by latitude‐longitude). However, health outcomes are typically aggregated over several spatial‐temporal coordinates (e.g., annual prevalence for a county) to comply with survey regulations. This article develops a Bayesian hierarchical model to analyze such spatially‐temporally misaligned exposure and health outcome data. We develop Bayesian predictive stacking for spatially and temporally misaligned data to optimally combine inference from multiple predictive spatial‐temporal models. Stacking allows us to avoid iterative estimation algorithms such as Markov chain Monte Carlo that struggle due to convergence issues inflicted by the presence of weakly identified parameters. We apply our proposed method to study the effects of ozone on asthma in the state of California.
- 25 January 2026
- Published by Wiley in Environmetrics
- Vol. 37 (2)
Open AccessBayesian Inference for Spatially‐Temporally Misaligned Data Using Predictive Stacking
Air pollution remains a major environmental risk factor that is often associated with adverse health outcomes. However, quantifying and evaluating its effects on human health is challenging due to the complex nature of exposure data. Recent technological advances have led to the collection of various indicators of air pollution at increasingly high spatial‐temporal resolutions (e.g., daily averages of pollutant levels at spatial locations referenced by latitude‐longitude). However, health outcomes are typically aggregated over several spatial‐temporal coordinates (e.g., annual prevalence for a county) to comply with survey regulations. This article develops a Bayesian hierarchical model to analyze such spatially‐temporally misaligned exposure and health outcome data. We develop Bayesian predictive stacking for spatially and temporally misaligned data to optimally combine inference from multiple predictive spatial‐temporal models. Stacking allows us to avoid iterative estimation algorithms such as Markov chain Monte Carlo that struggle due to convergence issues inflicted by the presence of weakly identified parameters. We apply our proposed method to study the effects of ozone on asthma in the state of California.
- Open Access
- 8 December 2025
- Published by Taylor & Francis in Journal of the American Statistical Association
- Vol. 121 (554) , 1-13
Bayesian Geostatistics Using Predictive Stacking
We develop Bayesian predictive stacking for geostatistical models, where the primary inferential objective is to provide inference on the latent spatial random field and conduct spatial predictions at arbitrary locations. We exploit analytically tractable posterior distributions for regression coefficients of predictors and the realizations of the spatial process conditional upon process parameters. We subsequently combine such inference by stacking these models across the range of values of the hyper-parameters. We devise stacking of means and posterior densities in a manner that is computationally efficient without resorting to iterative algorithms such as Markov chain Monte Carlo (MCMC) and can exploit the benefits of parallel computations. We offer novel theoretical insights into the resulting inference within an infill asymptotic paradigm and through empirical results showing that stacked inference is comparable to full sampling-based Bayesian inference at a significantly lower computational cost.
- 8 December 2025
- Published by Taylor & Francis in Journal of the American Statistical Association
- Vol. 121 (554) , 1-13
Open AccessBayesian Geostatistics Using Predictive Stacking
We develop Bayesian predictive stacking for geostatistical models, where the primary inferential objective is to provide inference on the latent spatial random field and conduct spatial predictions at arbitrary locations. We exploit analytically tractable posterior distributions for regression coefficients of predictors and the realizations of the spatial process conditional upon process parameters. We subsequently combine such inference by stacking these models across the range of values of the hyper-parameters. We devise stacking of means and posterior densities in a manner that is computationally efficient without resorting to iterative algorithms such as Markov chain Monte Carlo (MCMC) and can exploit the benefits of parallel computations. We offer novel theoretical insights into the resulting inference within an infill asymptotic paradigm and through empirical results showing that stacked inference is comparable to full sampling-based Bayesian inference at a significantly lower computational cost.
- Open Access
- 12 September 2025
- Published by American Association for the Advancement of Science (AAAS) in Science Advances
- Vol. 11 (37) , eadr6684
Investigating the Aliso Canyon gas blowout disaster and adverse birth outcomes: A quasiexperimental approach
On 23 October 2015, operators at the Aliso Canyon Natural Gas Storage field in Northern Los Angeles reported an uncontrolled natural gas leak. The blowout persisted for 112 days, releasing ~109,000 metric tons of methane into the atmosphere. Elevated air toxics and fine particle pollutant levels were also measured in nearby communities. We used California’s birth records and a quasiexperimental design to assess whether pregnant women living in affected communities during the disaster experienced more adverse birth outcomes than expected. Overall, the prevalence of low birthweight and term low birthweight were 45 to 100% higher than expected among women living in the affected communities whose late pregnancy overlapped with the blowout. The strongest effects were observed among women living directly south and southwest of the facility. Furthermore, we observed a dose-response effect, where the odds of low birthweight were highest among women living closest to the well and attenuated out.
- 12 September 2025
- Published by American Association for the Advancement of Science (AAAS) in Science Advances
- Vol. 11 (37) , eadr6684
Open AccessInvestigating the Aliso Canyon gas blowout disaster and adverse birth outcomes: A quasiexperimental approach
On 23 October 2015, operators at the Aliso Canyon Natural Gas Storage field in Northern Los Angeles reported an uncontrolled natural gas leak. The blowout persisted for 112 days, releasing ~109,000 metric tons of methane into the atmosphere. Elevated air toxics and fine particle pollutant levels were also measured in nearby communities. We used California’s birth records and a quasiexperimental design to assess whether pregnant women living in affected communities during the disaster experienced more adverse birth outcomes than expected. Overall, the prevalence of low birthweight and term low birthweight were 45 to 100% higher than expected among women living in the affected communities whose late pregnancy overlapped with the blowout. The strongest effects were observed among women living directly south and southwest of the facility. Furthermore, we observed a dose-response effect, where the odds of low birthweight were highest among women living closest to the well and attenuated out.
- Open Access
- 30 July 2025
- Published by Taylor & Francis in Journal of Computational and Graphical Statistics
- Vol. 35 (1) , 173-183
Nonstationary Spatial Process Models with Spatially Varying Covariance Kernels
Building spatial process models that capture nonstationary behavior while delivering computationally efficient inference is challenging. Nonstationary spatially varying kernels (see, e.g., Paciorek, 2003) offer flexibility and richness, but computation is impeded by high-dimensional parameter spaces resulting from spatially varying process parameters. Matters are exacerbated if the number of locations recording measurements is massive. With limited theoretical tractability, obviating computational bottlenecks requires synergy between model construction and algorithm development. We build a class of scalable nonstationary spatial process models using spatially varying covariance kernels. We implement a Bayesian modeling framework using Hybrid Monte Carlo with nested interweaving. We conduct experiments on synthetic data sets to explore model selection and parameter identifiability, and assess inferential improvements accrued from nonstationary modeling. We illustrate strengths and pitfalls with a data set on remote sensed normalized difference vegetation index.
- 30 July 2025
- Published by Taylor & Francis in Journal of Computational and Graphical Statistics
- Vol. 35 (1) , 173-183
Open AccessNonstationary Spatial Process Models with Spatially Varying Covariance Kernels
Building spatial process models that capture nonstationary behavior while delivering computationally efficient inference is challenging. Nonstationary spatially varying kernels (see, e.g., Paciorek, 2003) offer flexibility and richness, but computation is impeded by high-dimensional parameter spaces resulting from spatially varying process parameters. Matters are exacerbated if the number of locations recording measurements is massive. With limited theoretical tractability, obviating computational bottlenecks requires synergy between model construction and algorithm development. We build a class of scalable nonstationary spatial process models using spatially varying covariance kernels. We implement a Bayesian modeling framework using Hybrid Monte Carlo with nested interweaving. We conduct experiments on synthetic data sets to explore model selection and parameter identifiability, and assess inferential improvements accrued from nonstationary modeling. We illustrate strengths and pitfalls with a data set on remote sensed normalized difference vegetation index.
- Open Access
Bayesian Data Sketching for Varying Coefficient Regression Models
Varying coefficient models are popular for estimating nonlinear regression functions in functional data models. Their Bayesian variants have received limited attention in large data applications, primarily due to prohibitively slow posterior computations using Markov chain Monte Carlo (MCMC) algorithms. We introduce Bayesian data sketching for varying coefficient models to obviate computational challenges presented by large sample sizes. To address the challenges of analyzing large data, we compress the functional response vector and predictor matrix by a random linear transformation to achieve dimension reduction and conduct inference on the compressed data. Our approach distinguishes itself from several existing methods for analyzing large functional data in that it requires neither the development of new models or algorithms, nor any specialized computational hardware while delivering fully model-based Bayesian inference. Well-established methods and algorithms for varying coefficient regression models can be applied to the compressed data.
Open AccessBayesian Data Sketching for Varying Coefficient Regression Models
Varying coefficient models are popular for estimating nonlinear regression functions in functional data models. Their Bayesian variants have received limited attention in large data applications, primarily due to prohibitively slow posterior computations using Markov chain Monte Carlo (MCMC) algorithms. We introduce Bayesian data sketching for varying coefficient models to obviate computational challenges presented by large sample sizes. To address the challenges of analyzing large data, we compress the functional response vector and predictor matrix by a random linear transformation to achieve dimension reduction and conduct inference on the compressed data. Our approach distinguishes itself from several existing methods for analyzing large functional data in that it requires neither the development of new models or algorithms, nor any specialized computational hardware while delivering fully model-based Bayesian inference. Well-established methods and algorithms for varying coefficient regression models can be applied to the compressed data.