Souparno's research focuses on Bayesian hierarchical models, image modeling, bioinformatics and developing inferential methods for ML/DL models with applications in Digital Agriculture and Cancer Drug Response Prediction. His current projects include machine learning models for image and functional data, transfer learning from heterogeneous data, deep federated learning.

CV

Selected Funding

NSF: RESEARCH-PGR TRACK: Genetic basis of developmentally regulated heat stress response in rice (2025-2028), $600K, Co-PI (PI- Harkamal Walia, other Co-PI- Hongfeng Yu)

NCI-DOE: IMPROVE: Therapeutic response prediction model evaluation (2022-2025), $94,752, Subcontract PI (PI-Ranadip Pal)

NSF: Collaborative Research: FET: Small: Machine learning models for function-on-function regression (2020-2025), $140K, PI

NIH: R01GM122084-01: Framework for functional regression with applications to prediction and analysis of drug response curves (2016-2021), $644,910, Co-PI (PI: Ranadip Pal)

USDA: USDA-NRCS-TX-13-01: Innovative actions to help swift foxes flourish on the plains of west Texas (2013-2017), $75,541, Co-PI (PI: Philip Gipson, other Co-PI- Robert Cox)

Selected Awards

College of Arts and Sciences Excellence in Research Award (2017). College of Arts & Science, Texas Tech University.

NSF Research in Statistics in the Atmospheric and Oceanic Sciences Travel Award, (2011).

Emanuel Parzen Research Award for Outstanding Graduate Student, (2009). Department of Statistics, Texas A&M University.

IMS Laha Travel Award, (2009)

Selected Publications

Chopra, Y., Xie, X., Clothier, J., Ghosh, S., Yu, H., Walia, H., and Sattler, S. E. (2025). Hyperspectral imaging to characterize the vegetative tissue biochemical changes in response to water deficit conditions in sorghum (Sorghum bicolor). Frontiers in Plant Science

Dustin, D., Ghosh, S., and Clarke, B. (2025). Testing for the Important Components of Predictive Variance. Statistical Analysis and Data Mining: The ASA Data Science Journal

Zhang, R., Nolte, D., Sanchez-Villalobos, C., Ghosh, S., and Pal, R. (2024). Topological Regression in Quantitative Structure-Activity Relationship Modeling. Nature Communications

Rodene, E., Fernando, G. D., Piyush, V., Ge, Y., Schnable, J. C., Ghosh, S., and Yang, J. (2024). Image Filtering to Improve Maize Tassel Detection Accuracy Using Machine Learning Algorithms. Sensors

Ma, Z., Han, Z., Ghosh, S., Wu, L., and Wang, M. (2024) Sparse Bayesian variable selection in high dimensional logistic regression models with correlated priors. Statistical Analysis and Data Mining: The ASA Data Science Journal

Bandara, D., Ellingson, L., Ghosh, S., and Pal, R. (2023). A Modified Neighborhood Hypothesis Test for Population Mean in Functional Data. Journal of Agricultural, Biological and Environmental Statistics

Dao, M., Wang, M. and, Ghosh, S. (2022). A novel Bayesian method for variable selection and estimation in binary quantile regression. Statistical Analysis and Data Mining: The ASA Data Science Journal

Dao, M., Wang, M., Ghosh, S., and Ye, K. (2022). Bayesian variable selection and estimation in quantile regression using a quantile-specific prior. Computational Statistics

Bazgir, O., Ghosh, S., and Pal, R. (2021). Investigation of REFINED-CNN ensemble learning for anti-cancer drug sensitivity prediction. Bioinformatics

Kara, E., Rahman, A., Aulisa, E., Ghosh, S. (2020). Tumor ablation due to inhomogeneous anisotropic diffusion in generic three-dimensional topologies. Physical Review E

Bazgir, O., Rahman, R., Dhruba, S. R., Ghosh, S., and Pal, R. (2020). Representation of features as images with neighborhood dependencies for compatibility with convolutional neural networks. Nature Communications

Matlock, K., Rahman, R., Ghosh, S., and Pal R. (2019). Sstack: An R Package for Stacking with Applications to Scenarios Involving Sequential Addition of Samples and Features. Bioinformatics

Rahman, A., Ghosh, S., and Pal, R. (2018) Modeling of drug diffusion in a solid tumor leading to tumor cell death. Physical Review E

Mayer, J., Rahman, R.*, Ghosh, S., Pal, R. (2017). Sequential Feature Selection and Inference using Multivariate Random Forests. Bioinformatics

Gelfand, A. E., Ghosh, S. and Clark, J. S. (2013) Scaling Integral Projection Models for Analyzing Size Demography. Statistical Science

Ghosh, S., Gelfand, A. E. and Clark, J. S., (2012) Inference for Size Demography from Point Pattern Data using Integral Projection Models (with discussion). Journal of Agricultural, Biological and Environmental Statistics

Ghosh, S., Gelfand, A. E., Zhu, K. and Clark, J. S., (2012) The k−ZIG: Flexible Modeling for Zero-inflated Counts. Biometrics

Parzen, M., Ghosh, S., Lipsitz, S., Sinha, D., Fitzmaurice, G. M., Ibrahim, J. G. and Mallick, B. K., (2011) A Generalized Linear Mixed Model for Longitudinal Binary Data with a Marginal Logit Link Function. Annals of Applied Statistics