Nabin K. Malakar, Ph.D.

NASA JPL
I am a computational physicist working on societal applications of machine-learning techniques.

Research Links

My research interests span multi-disciplinary fields involving Societal applications of Machine Learning, Decision-theoretic approach to automated Experimental Design, Bayesian statistical data analysis and signal processing.

Linkedin


Interested about the picture? Autonomous experimental design allows us to answer the question of where to take the measurements. More about it is here...

Hobbies

I addition to the research, I also like to hike, bike, read and play with water color.

Thanks for the visit. Please feel free to visit my Weblogs.

Welcome to nabinkm.com. Please visit again.

Showing posts with label travel. Show all posts
Showing posts with label travel. Show all posts

Wednesday, January 1, 2014

Presentations for 94th American Meteorological Society Annual Meeting Atlanta, GA


Monday, 3 February 2014: 11:15 AM

Regional estimates of ground level Aerosol using Satellite Remote Sensing and Machine-Learning
Room C204 (The Georgia World Congress Center )
Nabin Malakar, City College of New York, New York, NY; and A. Atia, B. Gross, F. Moshary, S. Ahmed, and D. Lary
The ground-level aerosols are known to have harmful impact on people's health. The Moderate Imaging resolution Spectroradiometer (MODIS) sensors onboard aqua and terra satellites retrieve aerosol optical depth (AOD) at various bands. The comparison between the AOD measured from the satellite MODIS instruments and the ground-based Aerosol Robotic Network (AERONET) system at 550 nm shows that there is a bias between the two data products. In this study we explore the factors that can delineate these extrema, and/or explain them statistically. We use the MODIS 3 km and 10 km resolution AOD products, and develop a machine-learning framework to compare the Aqua and Terra MODIS-retrieved AODs with the ground- based AERONET observations. The analysis uses several measured variables such as the MODIS AOD, surface type, land use, etc. as input in order to train a neural network in regression mode with a special emphasis on biases observed over non vegetative urban surfaces. The result is the estimator of the bias-corrected estimates of AOD. This research is part of our goal to provide air quality information, with special focus on the northeast region of the USA, which can also be useful for developing regional-level decision support tools.

Tuesday, 4 February 2014: 4:00 PM
A Regional NN estimator of PM2.5 using satellite AOD and WRF meteorology measurements
Room C206 (The Georgia World Congress Center )
Lina Cordero, City College of New York, New York, NY; and N. Malakar, D. Vidal, R. Latto, B. Gross, F. Moshary, and S. Ahmed
Besides affecting the global energy balance, aerosols can have a significant health impact. In particular, extended exposure ultrafine particles is a major concern and regulations by the EPA are constituted to deal with this issue. Unfortunately, measuring surface aerosols over wide areas is costly and difficult so the potential of using satellite remote sensing and/or models becomes an important area of study. In this presentation, we explore the potential of combining meteorological data together with column integrated AOD within a Neural Network approach. To begin, the study is isolated to New York City where accurate AERONET AOD as well as Lidar derived PBL heights along with weather station meteorology is included. The main result of this isolated study illustrates that beyond AOD, the next important factor is the PBL height. This result motivates an extended study where MODIS mosaic AOD's are combined with WRF weather forecast model inputs including PBL height. To use WRF PBL, a matchup between WRF and Calipso is given for single layer cases illustrating strong correlations in spring and summer when PM25 is most important. In particular, we find that with seasonal training, we are able to generally improve on the existing approach utilized by the IDEA (Infusing satellite Data into Environmental air quality Applications) product which utilizes MODIS AOD and GEOS-CHEM PM25/AOD factors. In addition, we explore potential improvements that can occur if we can filter aloft plumes from the processing stream using the NAAPS air forecast model as well as the use of EOF's to fill missing gaps in the AOD spatial imagery.

Thursday, 6 February 2014: 9:00 AM
Use of NN based approaches to create high resolution climate meteorological forecasts
Room C101 (The Georgia World Congress Center )
Nabin Malakar, City College, New York, NY; and B. Gross, J. E. Gonzalez, P. Yang, and F. Moshary
The effects of global climate forecasts on regional scale domains requires that the low resolution GCM forecast data can be intelligently modified so that it can be injected into high resolution models such as terrestrial ecosystems etc. This is often called downscaling in the climate forecast literature and is usually performed using one of 2 different strategies. In the first strategy, the use of purely statistical approaches such as interpolation is applied to the GCM low resolution data to provide the high resolution data. Of course, the “high” resolution data really does not possess any high resolution inputs that can drive regional scale models. In particular, valuable high resolution information such as land surface identification and potential emission sources is not used. On the other hand, the potential of using regional Meteorological Models such as WRF can be attempted where the GCM conditions and the forecasted land surface properties are encoded into a future time slice. Of course, this approach is extremely computer intensive and the performance may not be worth the computer resources. In this presentation, we make use of another intermediate approach where low resolution meteorological data including both surface and column integrated parameters are combined with high resolution land surface classification parameters within a NN training scheme in an attempt to improve on purely interpolative approaches. In particular, our study region is the North East domain [{35N,45N} x {-85W,-65W}] . In particular, we focus on High and Low temperature extremes which are the outputs to be considered are obtained within the PRISM data set while the low resolution climatology parameters at low resolution (.5 deg) MET data including Tmax, Tmin, Rhum, Wind Speed, Radiation, Precip and Planetary Boundary Layer height are obtained from the ISI-MIP climatology forecast database. In addition, a high resolution land surface map is used based on the 2006 USGS land surface map. Preliminary results show that the NN approach can result in improved high resolution performance in areas where land surface features change rapidly. In addition, we will make comparisons using the WRF model for the time periods from 2006-2011.

-->

Thursday, October 25, 2012

Attending #CIDU2012 in Boulder Colorado

I am currently attending Conference on Intelligent Data Understanding (CIDU) here in Boulder.
The conference theme for this year is "Bringing Data and Models Together". The presentations consist of scientists from a wide variety of fields: Space Science, Earth and Environment Systems, and Aerospace and Engineering Systems. This is a great conference bringing researchers practicing data mining, machine learning or computational intelligence.
I am enjoying all the talks. The final agenda for CIDU 2012 can be found  here.

This is the first time that the CIDU is being held in NCAR, Boulder, away from its "home".

I presented yesterday. First day first slot: nice!!
It was about "Estimation and Bias Correction of  Aerosol Abundance using  Data driven Machine Learning and Remote Sensing ". Basically this paper discusses a general framework to choosing the optimal set of variables for machine learning/bias correction. Neural network was used, however one can insert his/her favorite Machine learning tool (SVM, DT, RF, GP etc). This involves massive number crunching for brute force search among all possible combination of variables. For 15 variable case, it has more than 32 thousands of combinations to try. I wonder if Bayes Net can help me to intelligently reduce the search.

Forgot my SD card, and it is cloudy+started to snow. While driving down the road, I saw nice mountains!! However, no pictures on this post!
(Happy Dashain!!)
-->

Monday, July 11, 2011

Attending MaxEnt 2011 in Waterloo, Canada

I am attending MaxEnt 2011 in Waterloo Canada.

Travelling to Waterloo was slightly involved because of the few reasons. The first one was the visa issues. At least, I am thankful that it arrived a week before my departure. Few of my friends could not make it due to the delays. Another one was that the airfare to the nearby airport was  very very expensive.  So, I travelled via Toronto (about an hour drive).
However, the best part of the airport was that the the wifi was free. So, I quickly joined the network and started calling people while waiting for my shuttle to arrive.

Here, in MaxEnt 2011, I will be presenting my work on collaborative experimental design by two intelligent agents.  The abstract of the talk can be found here ...(PDF!)
The work is the result of the overall successful (past) developments (by the Giants) of the Bayesian method of inference, experimental design techniques and the order-theoretic approach to questions. 
We view the intelligent agents as the question asking machines and we want them to be able to design experiments in an automated fashion to achieve the given goal.  Here we illustrate how the joint entropy turns out to be the useful quantity when we want the intelligent agents to efficiently learn together.
The details are in paper, which will be put in arxiv soon.

On the side notes:

Google detected right away that I "moved" to canada. So they wanted to offer Google.ca

yahoo music does not seem to work!

Pandora does not work.
Interesting!

Saturday, July 4, 2009

Heading for MaxEnt2009, Ole, Mississippi


Today I am heading to Oxford, Mississippi for MaxEnt2009 conference.

http://www.olemiss.edu/conf/maxent2009/

This is a week long conference discussing on wide variety of topics on Bayesian Inference and Maximum Entropy Methods in Science and Engineering. Topics range from foundations of probability theory, information theory, and inference and inquiry to astronomy and astrophysics, genetics, geophysics, medical imaging, material science, nanoscience, source separation, particle physics, quantum mechanics, plasma physics, chemistry, earth science, climate studies, engineering and robotics.

It gives a thrilling experience to see all the dignified scientists in the same conference and have an opportunity to present the work.



I will be presenting my work on Spatial Sensititivity Function (SSF) of a point sensor in the conference.

Experimental Guys should find it to be an interesting piece of application of  Bayesian Inference Methods (BIM).

Details will be posted as I put my work on arxiv.


Last year the conference was organized in Sao Paulo,Brazil.

http://www.nabinkm.com/2008/07/heading-for-maxent-2008-brazil-today.html

Sunday, May 10, 2009

Constellations in the Southern Sky

Last summer, 2008, I was in Sao Paulo Brazil for MaxEnt 2008 conference. Aside the academic matters, we had chance to see the night sky. I have to tell you that the night sky in southern Hemisphere is very very different.
Because of the orientation of the earth, the spiral of the milky way towards center of Galaxy could be seen. It was equally exciting to see the Alpha Centauri from there.

After the Anonymous commented, I wanted to write a little bit on it: (Thanks Anonymy!)
The Milky way galaxy we see in the northern sky is going from north to south. In there, we can see the spiral arm of the Milky way and the center of the galaxy; which is exciting! The Alpha Centauri was also saying hello! from about four and half light years, the whole night sky was so gorgeous! I don't know if you have seen the beauty of sky in the darkness!

See the apod:
The picture is "Astronomy picture of the day". The sky was not much different.
 Stargazing Basics: Getting Started in Recreational AstronomyNightWatch: A Practical Guide to Viewing the UniverseStargazing

Friday, July 4, 2008

Heading for MaxEnt 2008, Brazil: Today!

I am visiting Brazil for one week to participate in a conference:
MAXENT2008.

http://www.brastex.info/maxent2008/


There, I will be presenting my works.
Last year, MAXENT2007 was held in Saratoga Springs, NY. I was also a part of it as a local organizer. The conference brings a lot of international scientist from different fields into a common place to discuss their works and progresses made during the year. This enables a one-to one interaction with the dignified scientists in the respective field.

I will be flying from JFK, NY, USA to Sao Paulo, Brazil : tonight at 10PM.
WISH ME ALL THE BEST!!!

Related:
http://www.supelec.fr/lss/MaxEnt2000/



 Maximum Entropy and Bayesian Methods (Fundamental Theories of Physics)Maximum Entropy and Bayesian Methods (Fundamental Theories of Physics)   Bayesian Inference and Maximum Entropy Methods in Science and Engineering: 25th International Workshop on Bayesian Inference and Maximum Entropy ... / Mathematical and Statistical Physics)