publications
publications by categories in reversed chronological order.
2025
- Nature PortfolioEarlier planting fails to replicate historical production conditions for US spring wheat under future climatesSupriya Savalkar, Michael O Pumphrey, Kimberly G Campbell, and 5 more authorsCommunications Earth & Environment, 2025
Global warming and heat stress can adversely affect crop yields and quality. Earlier planting that shifts the growing season to cooler periods is a widely considered adaptation strategy in climate change literature. We ask: How effective is earlier planting in reducing high-temperature-exposure across growth stages? What are the associated temperature-exposure tradeoffs, and can historical conditions be matched? With US spring wheat as a case study, growth-stage-specific temperature exposure signatures are developed to estimate tradeoffs from earlier planting. While earlier planting does reduce exposure to critical and lethal high temperatures during reproductive stages, it fails to replicate historical production conditions. The Pacific Northwest is an exception, although tail-end growth stages may require management. Historically-equivalent planting windows narrow presenting logistical challenges. Therefore, while many climate-change assessments list earlier planting as an effective adaptation strategy, it may not be as effective when tradeoffs are considered, and consideration of other strategies will be important.
- IEEEGraph-Based Prediction of Spatio-Temporal Vaccine Hesitancy From Insurance Claims DataSifat Afroj Moon, Rituparna Datta, Tanvir Ferdousi, and 4 more authorsIEEE Access, 2025
Growing vaccine hesitancy is contributing to the decline in immunization rates for highly contagious, vaccine-preventable childhood diseases. Therefore, there has been a significant interest in understanding how hesitancy is spreading at higher spatio-temporal resolutions, enabling more targeted interventions. Motivated by this, we study the problem of prediction of vaccine hesitancy at the ZIP Code level, referred to as the VaxHesitancy problem. A significant challenge for this problem is the lack of high-resolution data that indicates hesitancy. Here, we develop a hybrid VaxHesSTL framework that combines a Graph Neural Network (GNN) and a Recurrent Neural Network (RNN) to address the VaxHesitancy problem. The GNN uses a ZIP Code-level network to capture spatial signals from neighboring areas, while the RNN models the temporal dynamics present in the data. We train and evaluate VaxHesSTL using a large dataset, namely the All-Payer Claims Databases (APCD), for Virginia, consisting of insurance claims from over five million individuals for six years. We find that an aggregated contact network or graph, developed from a detailed activity-based population network, plays an important role in the performance of VaxHesSTL, compared to graph models based solely on spatial proximity. Experiments demonstrate that VaxHesSTL outperforms a range of state-of-the-art baselines, which rely solely on historical time series data without accounting for spatial relationships. Since hesitancy data at higher spatial resolution is often unavailable or hard to get, we incorporate an active learning approach with our VaxHesSTL framework to optimize the training set without compromising the prediction performance. We find that hesitancy data for only 18% of ZIP Codes selected by active learning allows us to forecast hesitancy for all the ZIP Codes in the Virginia.
2024
- ElsevierSensitivity of snow magnitude and duration to hydrology model parametersBhupinderjeet Singh, Tanvir Ferdousi, John T Abatzoglou, and 3 more authorsJournal of Hydrology, 2024
Process-based hydrology models are critical for understanding streamflow and water supply under global change. However, these models require parameterization which introduces additional uncertainty into the models. The role that these parameters play in driving uncertainty is under-studied, especially for intermediary processes outside of streamflow. An important example in snowmelt dominant regions are intermediary processes related to snowpack accumulation and ablation. We examine the sensitivity of snow magnitude and duration to eleven parameters relevant to snow processes in the coupled crop-hydrology model VIC-CropSyst using a hybrid global–local Distributed Evaluation of Local Sensitivity Analysis approach. With the Pacific Northwest US as a case study, our specific research questions are: (a) What is the sensitivity response of peak snow water equivalent (SWE) and snow duration and how does it vary in the parameter space? (b) What are the key drivers of the sensitivity response? and (c) Which of the most sensitive parameters can we immediately improve by leveraging existing data products? Both target variables were sensitive to less than four of the eleven parameters. We found that peak SWE was most sensitive to either the precipitation partitioning temperature threshold or the albedo of new snow, depending on the geography and associated interplay between hydro-meteorological factors. In contrast, snow duration was primarily sensitive to the albedo of new snow and the albedo decay coefficient during snowmelt. Machine learning explainability workflows applied on the sensitivity response explained the model behavior and determined key geographic and hydro-meteorological drivers of the sensitivity response. Regions where the significant precipitation co-occurred with near-freezing temperature exhibited higher sensitivity of peak SWE to precipitation partitioning. In contrast, much colder high-elevation regions that have a delayed snowmelt-driven runoff when downward shortwave radiation is higher, displayed more sensitivity to albedo parameters. We also noted differences in the list of key parameters and in the level of sensitivity between our work and the limited comparable existing work. This highlights the need for comprehensive sensitivity analysis of snow metrics to become a routine component of hydrology model application studies in addition to streamflow. This is critical for us to better understand model behavior, identify key model parameters that can benefit from more dynamic representation in the models, and strategically improve models to best support decision-makers.
- AAMAS 2024Value-based Resource Matching with Fairness Criteria: Application to Agricultural Water TradingAbhijin Adiga, Yohai Trabelsi, Tanvir Ferdousi, and 8 more authorsProceedings of the 2024 International Conference on Autonomous Agents and Multiagent Systems, 2024
Optimal allocation of agricultural water in the event of droughts is an important global problem. In addressing this problem, many aspects, including the welfare of farmers, the economy, and the environment, must be considered. Under this backdrop, our work focuses on several resource-matching problems accounting for agents with multi-crop portfolios, geographic constraints, and fairness. First, we address a matching problem where the goal is to maximize a welfare function in two-sided markets where buyers’ requirements and sellers’ supplies are represented by value functions that assign prices (or costs) to specified volumes of water. For the setting where the value functions satisfy certain monotonicity properties, we present an efficient algorithm that maximizes a social welfare function. When there are minimum water requirement constraints, we present a randomized algorithm which ensures that the constraints are satisfied in expectation. For a single seller–multiple buyers setting with fairness constraints, we design an efficient algorithm that maximizes the minimum level of satisfaction of any buyer. We also present computational complexity results that highlight the limits on the generalizability of our results. We evaluate the algorithms developed in our work with experiments on both real-world and synthetic data sets with respect to drought severity, value functions, and seniority of agents.
2023
- MDPIPICTUREE—Aedes: A Web Application for Dengue Data Visualization and Case PredictionChunlin Yi, Aram Vajdi, Tanvir Ferdousi, and 2 more authorsPathogens, 2023
Dengue fever remains a significant public health concern in many tropical and subtropical countries, and there is still a need for a system that can effectively combine global risk assessment with timely incidence forecasting. This research describes an integrated application called PICTUREE—Aedes, which can collect and analyze dengue-related data, display simulation results, and forecast outbreak incidence. PICTUREE—Aedes automatically updates global temperature and precipitation data and contains historical records of dengue incidence (1960–2012) and Aedes mosquito occurrences (1960–2014) in its database. The application utilizes a mosquito population model to estimate mosquito abundance, dengue reproduction number, and dengue risk. To predict future dengue outbreak incidence, PICTUREE—Aedes applies various forecasting techniques, including the ensemble Kalman filter, recurrent neural network, particle filter, and super ensemble forecast, which are all based on user-entered case data. The PICTUREE—Aedes’ risk estimation identifies favorable conditions for potential dengue outbreaks, and its forecasting accuracy is validated by available outbreak data from Cambodia.
- UVA/BI C4GCEvaluating the Impact of Bailout Strategies on Financial NetworksHanyang Li and Tanvir FerdousiComputing for Global Challenges (C4GC) Symposium, 2023
Interbank lending can be considered an interconnected banking network comprising interbank liabilities and assets. In such networks, one bank’s failure to pay its liabilities can lead to a cascading effect, triggering a system-wide shockwave, as seen in the infamous 2008 financial crisis and the recent Silicon Valley Bank collapse. The Eisenberg-Noe model provides a framework to simulate cascading failures as financial contagions. We study and compare the effectiveness of graph centrality-based intervention strategies in mitigating financial contagions.
- WSC 2023A Machine Learning Framework to Explain Complex Geospatial Simulations: A Climate Change Case StudyTanvir Ferdousi, Mingliang Liu, Kirti Rajagopalan, and 7 more authorsWinter Simulation Conference, 2023
The explainability of large and complex simulation models is an open problem. We present a framework to analyze such models by processing multidimensional data through a pipeline of target variable computation, clustering, supervised classification, and feature importance analysis. As a use case, the well-known large-scale hydrology and crop systems simulator VIC-CropSyst is utilized to evaluate how climate change may affect water availability in Washington, United States. We study how snowmelt varies with climate variables (temperature, precipitation) to identify different response characteristics. Based on these characteristics, spatial units are clustered into six distinct classes. A random forest classifier is used with Shapley values to rank static soil and land parameters that help detect each class. The results also include an analysis of risk across different classes to identify areas vulnerable to climate change. This paper demonstrates the usefulness of the proposed framework in providing explainability for large and complex simulations.
2022
- eScience 2022A Web-Based System for Contagion Simulations on Networked PopulationsTanvir Ferdousi, Aparna Kishore, Lucas Machi, and 3 more authors2022 IEEE 18th International Conference on e-Science (e-Science), 2022
Motivated by a wide range of applications, research on agent-based models of contagion propagation over networks has attracted a lot of attention in the literature. Many of the available software systems for simulating such agent-based models require users to download software, build the executable, and set up execution environments. Further, running the resulting executable may require access to high performance computing clusters. Our work describes an open access software system (NetSimS) that works under the “Modeling and Simulation as a Service” (MSaaS) paradigm. It enables users to run simulations by selecting models and parameter values, initial conditions, and networks through a web interface. The system supports a variety of models and networks with millions of nodes and edges. In addition to the simulator, the system includes components that enable users to choose initial conditions for simulations in a variety of ways, to analyze the data generated through simulations, and to produce plots from the data. We describe the components of NetSimS and carry out a performance evaluation of the system. We also discuss two case studies carried out on large networks using the system. NetSimS is a major component within net.science, a cyberinfrastructure for network science.
2021
- PhD ThesisComputational models and tools for analysis, prediction, and control of infectious diseasesTanvir FerdousiKansas State University, 2021
Infectious disease modeling is used to examine pathogen transmission retrospectively and forecast outbreaks preemptively. Model results help public health authorities to optimize disease control measures, preventing catastrophic loss of lives in humans and animals. Yet, several fundamental challenges arise in infectious disease modeling. A critical problem involves modeling new and evolving pathogens for realistic simulations and reliable predictions of outcomes. Another concern is the lack of data related to infectious diseases. Epidemic modelers often face data inadequacy with host networks and disease incidence. This dissertation proposes remedies to challenges associated with infectious disease modeling, outbreak prediction, and host movement data. In response to vector-borne disease modeling challenges, this dissertation first takes a mechanistic approach. To realistically model the infection process, a novel interconnected network model is designed for the mosquito-vectored Zika virus, which links homogeneous vector populations with heterogeneous human contact networks. The model incorporates seasonal variations in mosquito abundance and characterizes hosts based on age group and gender. The aim is to develop a detailed model for an accurate representation of pathogen dynamics while keeping it computationally tractable. An event-based simulation tool is developed based on the non-Markovian Gillespie algorithm. This work investigates effects of seasonal variations on outbreak size, the role of sexual transmission in sustaining the pathogen, and relative contributions of key model parameters using a sensitivity analysis. A framework to improve machine learning performance for predicting dengue fever cases is developed in a data-driven approach. The goal is to fill in temporally limited human case data from spatially adjacent populations. The method ranks and sorts time-series data from peripheral locations around a target location as predictor variables commonly referred to as features. Metrics are computed from windowed time-shifted cross-correlation of incidence data, spatial distance, and historical prevalence to rank feature variables. A window detection method presented in this work analyzes incidence data to identify time intervals with significant outbreaks. The framework achieves improved prediction performance and works well with recurrent neural network (RNN) architectures. Performance gains are compared using different time window allocation methods for three distinct prediction models: linear, long short-term memory (LSTM), and gated recurrent units (GRU). Availability of data also affects applicability of mechanistic models. In the United States, farm animal movements are not tracked by a central authority. Lack of animal movement data is a significant obstacle in using network models to analyze infectious outbreaks in meat producing industries. As an immediate solution, a novel method is presented to generate movement networks from limited data available in the public domain. A custom configuration model is developed for network generation that uses aggregate data from farm animal movement-related surveys and the U.S. agricultural census. A hypothetical spread of the African swine fever virus (ASFV) is simulated in a generated network to analyze how network structure affects pathogen dispersal. A node centrality-based analysis is performed to identify important farm operation types and evaluate how targeted control measures affect outbreaks. The experience of working with infectious disease models for the U.S. meat-producing industry revealed fundamental problems linked to trust and business data sharing. The U.S. beef cattle industry lacks adequate traceability, as most farm owners consider such data confidential, possibly harming their businesses if exposed. Blockchains, also known as distributed ledgers, have gained popularity in industrial supply chains because of their unique features of data immutability and transparency. A smart contract-based supply chain framework is designed using a private blockchain network. This system supports anonymity for users to protect their identities and lets everyone store data locally while ensuring the blockchain records any change in data with cryptographic proofs. The framework presented contains functionalities to perform business transactions, transfer animal data, conduct anonymous surveys, and trace animals. This work has original contributions in network epidemic models, data-driven prediction tools, network generation algorithms, and data management frameworks. It combines knowledge from social network analysis, graph theory, epidemiology, machine learning, statistics, cryptography, computer networks, and computational science to improve infectious disease modeling, analysis, and control. The knowledge gained here is generalizable to applications beyond specific cases presented in this dissertation.
- IEEEA Windowed Correlation-Based Feature Selection Method to Improve Time Series Prediction of Dengue Fever CasesTanvir Ferdousi, Lee W Cohnstaedt, and Caterina M ScoglioIEEE Access, 2021
The performance of data-driven models depends on training samples. For accurately predicting dengue fever cases, historical incidence data are inadequate in many locations. This work aims to enhance temporally limited dengue case data by methodological addition of epidemically relevant case data from nearby locations as predictors (features). A novel framework is presented for windowing incidence data and computing time-shifted correlation-based metrics to quantify feature relevance. The framework ranks incidence data of adjacent locations around a target by combining metrics based on correlation, spatial distance, and local prevalence. Recurrent neural network models achieve up to 33.6% accuracy improvement on average using the proposed method. These models achieve mean absolute error (MAE) values as low as 0.128 on [0, 1] normalized incidence data for a municipality with the highest dengue prevalence in Brazil’s Espirito Santo. When predicting aggregate cases over geographical ecoregions, the models improve by 16.5%, using only 6.5% of ranked incidence data. This paper also presents two correlation window allocation methods: fixed-size and outbreak detection. Both perform comparably well, although the outbreak detection method uses less data for computations. The proposed framework is generalized, and it can be used to improve time-series predictions of many spatiotemporal datasets.
2020
- IEEEA Permissioned Distributed Ledger for the US Beef Cattle Supply ChainTanvir Ferdousi, Don Gruenbacher, and Caterina M ScoglioIEEE Access, 2020
Distributed ledgers using blockchain have gained traction in the supply chain industry due to their unique features of immutability and transparency. They have given people the abilities to solve business problems which were impossible using traditional systems. The US beef cattle industry lacks adequate traceability as most of the farm owners consider such data confidential; possibly harming their businesses if exposed. This article attempts to solve this problem by proposing a smart contract-based supply chain framework using a permissioned blockchain network. This system supports anonymity for the users to protect identities and lets every user store their data locally, while ensuring that the changes are recorded in the chain with cryptographic proofs (hashes). The proposed framework also has methods for the users to perform business transactions and transfer animal-related data to new owners as required. In addition to that, smart contracts have been added to conduct anonymous surveys for data aggregation. The technical contribution of this article is in the system design on how users, data, and communications are handled to maintain data ownership and user privacy while ensuring immutability and confidentiality at different levels of data aggregation. This article also contains an evaluation of the system using integration tests where the outcomes meet the expected design requirements. The framework can be applied to the US beef cattle industry as well as other supply chains with minimal modifications.
2019
- Nature PortfolioUnderstanding the survival of Zika virus in a vector interconnected sexual contact networkTanvir Ferdousi, Lee W Cohnstaedt, David Scott Mcvey, and 1 more authorScientific Reports, 2019
The recent outbreaks of the insect-vectored Zika virus have demonstrated its potential to be sexually transmitted, which complicates modeling and our understanding of disease dynamics. Autochthonous outbreaks in the US mainland may be a consequence of both modes of transmission, which affect the outbreak size, duration, and virus persistence. We propose a novel individual-based interconnected network model that incorporates both insect-vectored and sexual transmission of this pathogen. This model interconnects a homogeneous mosquito vector population with a heterogeneous human host contact network. The model incorporates the seasonal variation of mosquito abundance and characterizes host dynamics based on age group and gender in order to produce realistic projections. We use a sexual contact network which is generated on the basis of real world sexual behavior data. Our findings suggest that for a high relative transmissibility of asymptomatic hosts, Zika virus shows a high probability of sustaining in the human population for up to 3 months without the presence of mosquito vectors. Zika outbreaks are strongly affected by the large proportion of asymptomatic individuals and their relative transmissibility. The outbreak size is also affected by the time of the year when the pathogen is introduced. Although sexual transmission has a relatively low contribution in determining the epidemic size, it plays a role in sustaining the epidemic and creating potential endemic scenarios.
- Nature PortfolioEstimation of swine movement network at farm level in the US from the Census of Agriculture dataSifat A Moon, Tanvir Ferdousi, Adrian Self, and 1 more authorScientific Reports, 2019
Swine movement networks among farms/operations are an important source of information to understand and prevent the spread of diseases, nearly nonexistent in the United States. An understanding of the movement networks can help the policymakers in planning effective disease control measures. The objectives of this work are: (1) estimate swine movement probabilities at the county level from comprehensive anonymous inventory and sales data published by the United States Department of Agriculture - National Agriculture Statistics Service database, (2) develop a network based on those estimated probabilities, and (3) analyze that network using network science metrics. First, we use a probabilistic approach based on the maximum information entropy method to estimate the movement probabilities among different swine populations. Then, we create a swine movement network using the estimated probabilities for the counties of the central agricultural district of Iowa. The analysis of this network has found evidence of the small-world phenomenon. Our study suggests that the US swine industry may be vulnerable to infectious disease outbreaks because of the small-world structure of its movement network. Our system is easily adaptable to estimate movement networks for other sets of data, farm animal production systems, and geographic regions.
- PLoSGeneration of swine movement network and analysis of efficient mitigation strategies for African swine fever virusTanvir Ferdousi, Sifat Afroj Moon, Adrian Self, and 1 more authorPLoS ONE, 2019
Animal movement networks are essential in understanding and containing the spread of infectious diseases in farming industries. Due to its confidential nature, movement data for the US swine farming population is not readily available. Hence, we propose a method to generate such networks from limited data available in the public domain. As a potentially devastating candidate, we simulate the spread of African swine fever virus (ASFV) in our generated network and analyze how the network structure affects the disease spread. We find that high in-degree farm operations (i.e., markets) play critical roles in the disease spread. We also find that high in-degree based targeted isolation and hypothetical vaccinations are more effective for disease control compared to other centrality-based mitigation strategies. The generated networks can be made more robust by validation with more data whenever more movement data will be available.
2018
- AIMSQuantifying the impact of early-stage contact tracing on controlling Ebola diffusionNarges Montazeri Shahtori, Tanvir Ferdousi, Caterina Scoglio, and 1 more authorMathematical Biosciences & Engineering,, 2018
Recent experience of the Ebola outbreak in 2014 highlighted the importance of immediate response measure to impede transmission in the early stage. To this aim, efficient and effective allocation of limited resources is crucial. Among the standard interventions is the practice of following up with the recent physical contacts of the infected individuals – known as contact tracing. In an effort to understand the effects of contact tracing protocols objectively, we explicitly develop a model of Ebola transmission incorporating contact tracing. Our modeling framework is individual-based, patient-centric, stochastic and parameterizable to suit early-stage Ebola transmission. Notably, we propose an activity driven network approach to contact tracing, and estimate the basic reproductive ratio of the epidemic growth in different scenarios. Exhaustive simulation experiments suggest that early contact tracing paired with rapid hospitalization can effectively impede the epidemic growth. Resource allocation needs to be carefully planned to enable early detection of the contacts and rapid hospitalization of the infected people.