To be held in conjunction with

Home

Challenge

Problem Description

For the second SensorKDD Challenge, to be held in conjunction with the 6th Workshop on Knowledge Discovery from Sensor Data (SensorKDD-2012), we pose a general and open-ended problem related to the workshop theme Climate Change, Energy Assurance, and Infrastructural Impacts. Specifically, we focus on the first component and provide a large climate dataset consisting of both model simulated and observed precipitation for a period of time.

Your task is to detect significant trends in the precipitation extremes. Note that the notion of extremes is open to interpretation and you are free to consider multiple indicator of extremes. We omit a precise definition here to invite creative problem definitions and solutions.

Data

Following is a short description of the model simulated and observed data.

1. The model simulated data consists of daily global precipitation measurements for the period 1961-2000 and also for 2061-2100 (see [1] for details). This data is also publicly available for download, for example from [3] (registration may be required). The data is available from multiple models. You can work with any one or a combination of these models.

   The data is stored in NetCDF files, a highly compressed data format specifically designed for high-dimensional data. We invite anyone interested in studying climate to get familiar with this format by visiting the following page:
   http://www.unidata.ucar.edu/software/netcdf/
   There you will find a detailed description of the file format as well as a number of tools and utilities to manipulate netCDF files. We also provide a code sample for reading the data with the open-source statistical software package R (www.r-project.org) using the ncdf package; similar utilities are available for Matlab, e.g. NetCDF Reader or MEXNC.
2. The observed precipitation over India is available for purchase from the website of Indian Meteorological Department (http://www.imd.gov.in/nccraindata.htm). However yearly maxima for each grid-point is available as a part of the supplementary information of [2]. Here is the link to it.

Submissions

We invite the submission of manuscripts addressing this challenge task following the format of the SensorKDD-2012 Workshop (maximum 9 pages, ACM standard format). Please include your definition of extremes. Entries will be evaluated subjectively based on their methodology and validation strategy. The deadline for submission is 30th May. Please email your submission to Sensorkdd2012@gmail.com with a subject "SensorKDD Challenge" and include your name, affiliations and contact details.

Award

Best Challenge Entry Award.

Contact Information

For questions about the challenge or to inquire about additional climate datasets, please contact:

Debasish Das
d.das@neu.edu
Phone: +1-617-373-3770

Challenge Organizers

Debasish Das, Northeastern University, Boston, MA and Temple University, Philadelphia, PA, USA.
Auroop R. Ganguly, Northeastern University, Boston, MA, USA.

References:

[1] Kao, S.-C. and A. R. Ganguly (2011), Intensity, duration, and frequency of precipitation extremes under 21st-century warming scenarios, Journal of Geophysical Research - Atmospheres, 116, D16119.

[2] Ghosh, S., D. Das, S.-C. Kao, A. R. Ganguly (2012), Lack of uniform trends but increasing spatial variability in observed Indian rainfall extremes, Nature Climate Change.

[3] IPCC Climate model datasets hosted in PCMDI. http://www-pcmdi.llnl.gov/ipcc/about_ipcc.php.