SCSnigdhansu Chatterjee

Snigdhansu Chatterjee

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Snigdhansu Chatterjee has a total of 57 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Non-canonical subthalamic nucleus projections regulate motor variability

    by Oluwatomiwa A. Oladunni, Sophie K. Elvig, Hunter C. Bennis, Laila A. Elzaree, Siddhartha Nandy, Yuting Liu, Snigdhansu Chatterjee, Brian N. Mathur, Steffen B.E. Wolff

    Regulation of motor variability is a key hallmark of motor skill learning, balancing motor exploration with optimization of identified task solutions. Nevertheless, the underlying circuit mechanisms in the mammalian brain remain largely unknown. Subnuclei of the dorsal striatum in the basal ganglia promote stereotyped or variable behavior, respectively, and deep brain stimulation of the downstream subthalamic nucleus (STN) can alter motor variability. We therefore tested whether the STN regulates motor variability via non-canonical projections to striatum. We discovered that silencing STN neurons projecting to dorsolateral striatum impaired motor variability reduction in rats developing complex stereotyped movement patterns. In contrast, silencing STN neurons projecting to the anterior thalamic nuclei, or neurons in these nuclei that receive STN input and project to dorsomedial striatum, accelerated variability reduction. These results deepen our anatomical and functional understanding of subcortical motor circuits and reveal unknown roles for STN's non-canonical striatal projections in motor variability regulation.

  • Robust causality and false attribution in data-driven earth science discoveries

    by Elizabeth Eldhose, Auroop R. Ganguly, Snigdhansu Chatterjee, Tejasvi Chauhan, Vikram Chandel, Subimal Ghosh

    Causal and attribution studies are essential for earth scientific discoveries and critical for informing climate, ecology, and water policies. However, the current generation of methods needs to keep pace with the complexity of scientific, data availability, and stakeholder challenges, combined with the adequacy of data-driven methods. Unless carefully informed by physics, they run the risk of conflating correlation with causation or getting overwhelmed by estimation inaccuracies. In particular, information-theoretic approaches such as transfer entropy (TE), despite their recent popularity and widespread use, can yield spurious causal links, even when statistical significance testing is applied. To address this, we introduce CAST (Causal Analysis Spuriousness Test), a subsample-based ensemble framework that quantifies the robustness of inferred links via the CAST index. Through extensive simulations across systems with varying dynamics as well as applications to real-world climate datasets, we demonstrate that CAST effectively filters unreliable connections while preserving true causal relationships. Our findings underscore the need for consistency-based evaluation in causal discovery and provide a generalizable strategy to enhance the reliability of TE-based and other data-driven causal methods in Earth sciences.


  • Open Access

    Discovering melting temperature prediction models of inorganic solids by combining supervised and unsupervised learning

    by Vahe Gharakhanyan, Luke J. Wirth, Jose A. Garrido Torres, Ethan Eisenberg, Ting Wang, Dallas R. Trinkle, Snigdhansu Chatterjee, Alexander Urban

    The melting temperature is important for materials design because of its relationship with thermal stability, synthesis, and processing conditions. Current empirical and computational melting point estimation techniques are limited in scope, computational feasibility, or interpretability. We report the development of a machine learning methodology for predicting melting temperatures of binary ionic solid materials. We evaluated different machine-learning models trained on a dataset of the melting points of 476 non-metallic crystalline binary compounds using materials embeddings constructed from elemental properties and density-functional theory calculations as model inputs. A direct supervised-learning approach yields a mean absolute error of around 180 K but suffers from low interpretability. We find that the fidelity of predictions can further be improved by introducing an additional unsupervised-learning step that first classifies the materials before the melting-point regression. Not only does this two-step model exhibit improved accuracy, but the approach also provides a level of interpretability with insights into feature importance and different types of melting that depend on the specific atomic bonding inside a material. Motivated by this finding, we used a symbolic learning approach to find interpretable physical models for the melting temperature, which recovered the best-performing features from both prior models and provided additional interpretability.


  • A Bayesian Semi-parametric Modelling Approach for Area Level Small Area Studies

    by Marten Thompson, Snigdhansu Chatterjee

    We present a new semiparametric extension of the Fay-Herriot model, termed the agnostic Fay-Herriot model (AGFH), in which the sampling-level model is expressed in terms of an unknown general function [ ]. Thus, the AGFH model can express any distribution in the sampling model since the choice of [ ] is extremely broad. We propose a Bayesian modelling scheme for AGFH where the unknown function [ ] is assigned a Gaussian Process prior. Using a Metropolis within Gibbs sampling Markov Chain Monte Carlo scheme, we study the performance of the AGFH model, along with that of a hierarchical Bayesian extension of the Fay-Herriot model. Our analysis shows that the AGFH is an excellent modelling alternative when the sampling distribution is non-Normal, especially in the case where the sampling distribution is bounded. It is also the best choice when the sampling variance is high. However, the hierarchical Bayesian framework and the traditional empirical Bayesian framework can be good modelling alternatives when the signal-to-noise ratio is high, and there are computational constraints. AMS subject classification: 62D05; 62F15

  • Open Access

    A Bayesian framework for studying climate anomalies and social conflicts

    by Ujjal Kumar Mukherjee, Benjamin E. Bagozzi, Snigdhansu Chatterjee

    Climate change stands to have a profound impact on human society, and on political and other conflicts in particular. However, the existing literature on understanding the relation between climate change and societal conflicts has often been criticized for using data that suffer from sampling and other biases, often resulting from being too narrowly focused on a small region of space or a small set of events. These studies have likewise been critiqued for not using suitable statistical tools that () address spatio‐temporal dependencies, () obtain probabilistic uncertainty quantification, and () lead to consistent statistical inferences. In this article, we propose a Bayesian framework to address these challenges. We find that there is a strong and substantial association between temperature anomalies on aggregated material conflicts and verbal conflicts globally. Going deeper, we also find significant evidence to suggest that positive temperature anomalies are associated with social conflict primarily through government‐civilian and government‐rebel material conflicts, as in civilian protests, rebel attacks against government resources, or acts of state repression. We find that majority of the conflicts associated with climate anomalies are triggered by rebel actors, and others react to such acts of conflict. Our results exhibit considerably nuanced relationships between temperature deviations and social conflicts that have not been noticed in previous studies. Methodologically, the proposed Bayesian framework can help social scientists explore similar domains involving large‐scale spatial and temporal dependencies. Our code and a synthetic dataset has been made publicly available.


  • Open Access

    Predictions of damages from Atlantic tropical cyclones: a hierarchical Bayesian study on extremes

    by Lindsey Dietz, Sakshi Arya, Snigdhansu Chatterjee

    Bayesian hierarchical models are proposed for modeling tropical cyclone characteristics and their damage potential in the Atlantic basin. We model the joint probability distribution of tropical cylone characteristics and their damage potential at two different temporal scales, while taking several climate indices into account. First, a predictive model for an entire season is developed that forecasts the number of cyclone events that will take place, the probability of each cyclone causing some amount of damage, and the monetized value of damages. Then, specific characteristics of individual cyclones are considered to predict the monetized value of the damage it will cause. Robustness studies are conducted and excellent prediction power is demonstrated across different data science models and evaluation techniques.

  • Open Access

    Machine Learning Methods for Multiscale Physics and Urban Engineering Problems

    by Somya Sharma, Marten Thompson, Debra Laefer, Michael Lawler, Kevin McIlhany, Olivier Pauluis, Dallas R. Trinkle, Snigdhansu Chatterjee

    We present an overview of four challenging research areas in multiscale physics and engineering as well as four data science topics that may be developed for addressing these challenges. We focus on multiscale spatiotemporal problems in light of the importance of understanding the accompanying scientific processes and engineering ideas, where “multiscale” refers to concurrent, non-trivial and coupled models over scales separated by orders of magnitude in either space, time, energy, momenta, or any other relevant parameter. Specifically, we consider problems where the data may be obtained at various resolutions; analyzing such data and constructing coupled models led to open research questions in various applications of data science. Numeric studies are reported for one of the data science techniques discussed here for illustration, namely, on approximate Bayesian computations.

  • On weighted multivariate sign functions

    by Subhabrata Majumdar, Snigdhansu Chatterjee

  • Open Access

    Winsorization for Robust Bayesian Neural Networks

    by Somya Sharma, Snigdhansu Chatterjee

    With the advent of big data and the popularity of black-box deep learning methods, it is imperative to address the robustness of neural networks to noise and outliers. We propose the use of Winsorization to recover model performances when the data may have outliers and other aberrant observations. We provide a comparative analysis of several probabilistic artificial intelligence and machine learning techniques for supervised learning case studies. Broadly, Winsorization is a versatile technique for accounting for outliers in data. However, different probabilistic machine learning techniques have different levels of efficiency when used on outlier-prone data, with or without Winsorization. We notice that Gaussian processes are extremely vulnerable to outliers, while deep learning techniques in general are more robust.


  • Open Access

    On Weighted Multivariate Sign Functions

    by Subhabrata Majumdar, Snigdhansu Chatterjee

    Multivariate sign functions are often used for robust estimation and inference. We propose using data dependent weights in association with such functions. The proposed weighted sign functions retain desirable robustness properties, while significantly improving efficiency in estimation and inference compared to unweighted multivariate sign-based methods. Using weighted signs, we demonstrate methods of robust location estimation and robust principal component analysis. We extend the scope of using robust multivariate methods to include robust sufficient dimension reduction and functional outlier detection. Several numerical studies and real data applications demonstrate the efficacy of the proposed methodology.