Welcome to the Lab News Page!

I'll post stuff on occasion about the lab members here.

Lab Meetings are scheduled here. Lab guidelines.


Kellylabbers at GIS Day

We had a great time at 2014 GIS Day! The event took place in Mulford Hall Wednesday Nov 19th from 5-8:30pm. We had about 200 attendees who participated in workshops, listened to talks, saw posters, and networked with other like-minded GIS-enthusiasts.

Here are some of the ladies of the Kelly Lab, from left: Anu, Sarah, Alice, Jenny, Maggi, Stefania, and KellySee the agenda here: http://gif.berkeley.edu/gisday.html.



Kelly labbers enjoy cake

Not the band, but real cake. Here in support of Stefania and her soon to be baby, we all enjoy some delicious cream sponge cake. From left: Shufei, Kelly, Stefania, Maggi, Peng Feng, Jenny, Alice (and Mr. C), and Jason.


First Graduate Certificate in GIST awarded to Miriam!

It is official! ESPM's (and the campus') first GIST certificate awardee will be Miriam Tsalyuk.

She is broadly interested in applying interdisciplinary landscape-level approach for biodiversity conservation. More specifically, she uses geographic information systems (GIS) and remote sensing for monitoring and conservation of rangelands in California and Southern Africa. For my PhD dissertation she is using such information to understand the environmental parameters that guide African Elephants' movement decisions across Etosha National Park, Namibia. Such understanding can inform resource management in the reserve and address human-wildlife conflict around the park.

Congrats to Miriam!


Kellylab summer lunch pic

Kellylab summer lunch!


Marek's paper wins ASPRS award!

Marek's paper "Predicting surface fuel models and fuel metrics using lidar and CIR imagery in a dense, mountainous forest" has been awarded the 2014 ERDAS Award for Best Scientific Paper in Remote Sensing by ASPRS. They bestowed the award for an outstanding paper of scientific merit that advances the knowledge of remote sensing technology.

In the paper we compared the ability of several classification and regression algorithms to predict forest stand structure metrics and standard surface fuel models. We used clustering, regression trees, and support vector machine algorithms to analyze high density (average 9 pulses/m2), discrete return, smallfootprint lidar data, along with multispectral imagery.

Jakubowski, M. K., Q. Guo, B. Collins, S. Stephens, and M. Kelly. 2013. Predicting surface fuel models and fuel metrics using lidar and CIR imagery in a dense, mountainous forest. Photogrammetric Engineering and Remote Sensing 79(1):37-49

For more on the paper, see the abstract here.