Khurram Nadeem

Khurram Nadeem
Assistant Professor, Statistics
Email: 
nadeemk@uoguelph.ca
Phone number: 
519-824-4120 x53136
Office: 
MacNaughton 517

RESEARCH  INTERESTS: Predictive modeling of ecological and environmental processes via big data analytics; Wildland fire occurrence prediction; modeling of spatio-temporal processes.

Seeking academic or industry partnerships in the area(s) of:  Forest Fire Analytics, Agriculture and Environmetrics, Quantitative Ecology 

Available positions for grads/undergrads/postdoctoral fellows: Currently looking for graduate students having interest in applied statistics with strong programming skills (RStudio, Python). I also co-supervises graduate students in the Bioinformatics program at the University of Guelph.

Research Themes:

My research focuses on leveraging innovative techniques and methods in computing and statistical machine learning to extract meaningful and actionable insights from massive volumes of high-dimensional data. His work focuses on predictive modeling of ecological and environmental processes via big data analytics. Key research themes include:

  1. Wildland fire occurrence prediction. My research harnesses the availability of large scale historical environmental, wildland fire and demographic data in Canada to spatially predict severe and large forest fires for two weeks ahead into the future. Apart from contributing to improvements to the Canadian Interagency Forest Fire Centre’s (CIFFC) management, coordination and information services, this research has implications for sustainable forest management in the face of changing climate and increasing human anthropogenic activity. The outcomes of this ongoing work will have significant impact on Canada’s ability to efficiently respond to the danger of severe wildland fires and to understand fire-weather dynamics in the wake of changing Earth climate.
  2. Agro-environmental science. Within agro-environmental science, data across multiple sources and scales are increasingly becoming available, encompassing the full spectrum of four V’s of big data: volume, variety, velocity, and veracity. Sources of these datasets range from agronomic data through precision agriculture such as monitoring site-specific soil characteristics and harvest yield on geo-spatial scales; to functional crop genomics data, to agroeconomics data. Data availability in such volume and variety presents an opportunity to integrate and analyze these data streams for evidence-based decision making in implementing sustainable agricultural practices. I am interested in: i) leveraging the availability of varied data sources to answer important large-scale comprehensive research questions related to agricultural productivity and its interaction with the environment, ii) developing a digital framework to identify, collect and integrate relevant data from various sources to develop databases and decision-support tools, and iii) employing advanced statistical and computational techniques, including machine learning and artificial intelligence methods, to develop predictive models for answering the key research questions, and to deploy them in a decision-support system. Key agricultural research problems to explore are: i) how climate change will impact food productivity and security in Canada and to what extent northern areas will become suitable for agriculture, and ii) how biodiversity components and ecosystem services interact across a wide range of agricultural landscapes and farming practices.

Media Coverage:

Wildland Fire

Food from Thought

 

 

PhD, Statistics 2013 University of Alberta, Edmonton, AB, Canada. Advisor: Dr. Subhash R. Lele Dissertation Title: Estimability and Likelihood Inference for General Hierarchical Models using Data Cloning.

MSc, Statistics  2005 University of Karachi, Pakistan, Advisor: Dr. Javed Iqbal Dissertation Title: Exploring the causal relationship among social, real, monetary and infrastructure development in Pakistan.

BSc (Honours), Statistics 2003 University of Karachi, Pakistan. First Class Second Position.

PEER-REVIEWED 

Nadeem, K., Chen, E., Zhang, Y. (2018) A novel hierarchical multinomial approach to modelling age-specific harvest data. 27th Annual Conference of the International Environmetrics Society joint with Biennal GRASPA Conference: Graspa Working Papers.

Dean, C. B., Bull, S. B., Nadeem, K. and Wolters, M. A. (2017) Big data in biosciences  PUBLICATIONS  Wiley StatsRef: Statistics Reference Online, 1–9.
 
Nadeem, K., Moore, J. E., Zhang, Y., & Chipman, H. (2016) Integrating  population dynamics models and distance sampling data: a spatial hierarchical state‐space approach. Ecology, 97, 1735–1745.
 Zhang, Y., P. Cabilio, and Nadeem, K (2016) Improved seasonal Mann–Kendall tests for trend analysis in water resources time series. Advances in Time Series Methods and Applications. Springer New York, 215-229.
 
Nadeem, K., & Lele, S. R. (2012) Likelihood based population viability analysis in the presence of observation error. Oikos, 121, 1656-1664.
 
Luong C. et al. (2011) Antenatal sildenafil treatment attenuates pulmonary hypertension in experimental congenital diaphragmatic hernia. Circulation, 123, 2120-2131.
 
Lele, S. R., Nadeem, K. and Schmuland, B. (2010) Estimability and likelihood inference for generalized linear mixed models using data cloning. Journal of the American Statistical Association, 105, 1617-1625.
 
Iqbal, J. and Nadeem, K. (2006) Exploring the causal relationship among social, real, monetary and infrastructure development in Pakistan. Pakistan Economic and Social Review, Volume XLIV, No. 1, 39-56.
 

  • Major funding, Awards, National or International Recognition, Prestigious affiliations, Memberships on editorial boards or societies
  • Nova Scotia Habitat Conservation Fund Award, 2014-2015
  • MITACS Accelerate Postdoctoral Fellowship Award, 2013-2015
  • CANSSI Postdoctoral Fellowship Award, 2014-2015