Four yellow Ortliebs

I’m taking ten weeks off, starting tomorrow. I’ll have my bike with me,
four yellow Ortlieb bags and a small backpack. Direction: North.

I’ll be back in the middle of October, when the winter term starts.

ICPA outstanding graduate student award

Georg Ruß, Raj Khosla, at ICPA 2010, Denver, Colorado

Raj Khosla, Georg Ruß, Dwayne Westfall, at ICPA 2010, Denver, Colorado

The above photos are from http://www.flickr.com/photos/zimmcomm/sets/72157624407942663/, slightly cropped, scaled and edited. The originals are here: photo1, photo2. There are more photos of the conference in that flickr album.

I’m flying back today, via IAH. Yesterday we had an interesting session on
“Precision Livestock Management”, given by David Lamb from the University of
Queensland. He had with him a Kiwi guy who did the other half of the talks and
just to introduce himself and some language issues he gave a slide that looked
like the following:

Presenting my talk at the ICPA 2010

My talk on the hierarchical spatial clustering I’ve developed for the purpose
of management zone delineation worked out okay. I think that I did a good job
on adapting my talk to this totally different audience, judging from the
feedback I received after the talk. It was really nice not having to explain
too much details on the data I have because the audience just knew those
attributes. I might even have gotten the point across about what the advantages
of my clustering are in comparison to existing approaches. The presentation slides
are here: russ2010icpa-slides.pdf

Some miscellaneous stuff: As usual (for the US, that is), the temperatures in
the convention center are around 18 degrees Celsius, with a light breeze from
the airconditioning. Although I love A/C and really don’t have any issues with
getting sick of those temperatures, it felt a bit chilly after half a day,
especially compared to outside temperatures of around 35-38 degrees celsius. On
top of that, there’s lots of icy water to drink from. Along the same lines I
tested the fridge in my apartment which has a range of 2 degrees to -5 degrees
(min to max) — right, that’s a fridge, not a freezer. It’s just strange. RTD
light rail is also A/C, which is really convenient to travel in.

I’ll grab the best graduate student paper award later today, nice.

My work presented here is a continuation and extension of the IPMU work presented in Dortmund two weeks ago. Again, the emphasis is on getting data mining people into precision agriculture — they’re really needed there. The other aspect of my work is to make sure that spatial data are treated with spatial models, otherwise a lot of the assumptions for non-spatial models are violated and lead to misleading results.

In conjunction with the ICDM I’m holding my workshop on Data Mining in Agriculture for the first time. It’s going to be held this afternoon and so far I have only seen one of the three other presenters. The author of the book Data Mining in Agriculture, Antonio Mucherino, told me that he’s not about to come for personal, urgent reasons, which is a pity, but acceptable.

Some links to the above work: ICDM paper (in Springer LNAI series), DMA workshop paper, the workshop proceedings (of which I’m a co-editor).

Slides link: russ2010ipmu-slides.pdf

As usual, the paper is in our publication database: Data Mining in Precision Agriculture: Management of Spatial Information.

It also implements a more or less standard hierarchical agglomerative
clustering procedure on spatial data — there just was no existing work which
fit the problem and the data set, so I had to create my own algorithm using a
straightforward and easily explainable divide-and-conquer approach. I hope that
my reviewers at the IEEE ICDM conference like the idea.

I’m still looking for an easily pronouncable acronym, maybe HACSAD-PA
will do: hierarchical agglomerative clustering for spatially autocorrelated
data from precision agriculture :-)

Oh, right, I’m using the vim blogit plugin to operate my wordpress blog via VIm — there’s nothing better than VIm and I use it for everything. I even tried to get it to cooperate with Matlab, but that effort got pointless when I switched to R, anyway.

On first sight, it might seem strange that a computer scientist who’s pursuing
a PhD in computer science is working in the area of agriculture. At least, this
is what a lot of my colleagues think when they hear what I’m working on. Then,
when giving a talk at a conference or a meeting, they’re first astonished by
the sheer advances in agriculture. After that, they’re surprised about the data
acquisition and collection which take place in precision agriculture. And once
they’ve come to grasp the data and its implications, they’re usually hooked and
really interested in what can be done with these data. This experience is
reproducible everytime at computer science conferences. I’ve recently and
successfully worked on yield prediction, identifying useful sensors and
management zones — identifying some flaws in existing data processing and
fixing those has been rather straightforward from a computer science
perspective. I’m not surprised by the above reactions any more, yet I’ve come
to some conclusions about the future of precision agriculture in conjunction
with computer science — these are given in the following.

Since precision agriculture is becoming a more and more data-driven area, this
clearly creates the need for someone familiar with analysing the large amounts
of harvested data. This specialist is usually called a data miner: he
tries to find the gold nuggets of information hidden in huge databases.

From my point of view it is clear that the field of precision agriculture
requires those specialists, since data are at the core of precision
agriculture. A classical data miner is, on the one hand, rather generalistic:
he knows and applies techniques and methods of prediction, modeling and
classification, for example. On the other hand, he usually specialises to a
specific area where data mining shall be applied — such as precision
agriculture. He can draw conclusions from the available data and tap the hidden
information reservoir, suggesting possible solutions to specific agricultural
problems or acting according to information-theoretic criteria to extract facts
of interest.

I therefore see data miners, computer scientists and geostatisticians at the
core of the precision agriculture field. Nevertheless, since they are usually
not agriculture specialists, they are to be embedded: first, at the
interface from agriculture to data and, second, on the other end of the process
where their solutions are required to be interpreted by domain experts. This
process is natural, and it has happened before in such diverse fields as
environmental modelling, business intelligence and industry automation, among others.
Wherever data are collected, data mining specialists come into play sooner or
later to tackle business questions from the data side.

From what I see at Agri Con GmbH, Germany, it is
obvious that the upscale of precision agriculture in most of Europe will be
driven by enormous incentives both for the environment and the farming
companies. However, precision agriculture companies are still partly
research-based as the area of PA is rather novel and often somewhat uncharted,
at least when data mining comes into play.

Therefore, I see my role as a computer scientist with a strong interest in
precision agriculture along the above lines. I’ve taken a strong liking to
being positioned at the interface between agriculture and computer science. I
also like the idea of creating novel results and computational outcomes based
on real data, being applied to the real world. Combining the abovementioned
needs, I’ve decided to hold a first workshop on data mining in
agriculture} in July 2010: http://dma2010.de.

The workshop is actually closed for submissions now, we’ve had five submissions, of which four were accepted for publication and presentation on July 14th, 2010, in Berlin, Germany. Not bad for a first-type event.

I’ll try to acquire some photos at the ICPA awards ceremony on July 20th, in Denver, Colorado.

Hmmm, as a side note, I’ve gotten used to being in Australia at least once a year and my work is certainly relevant for the IEEE ICDM. Well, we’ll see…

• First, it’s not so much the specifics of the modeling solution that I presented. The most interesting part for the audience is rather the fact that agriculture is turning into a data-driven discipline. I caught a lot of comments along the lines of “It’s amazing what kind and what amounts of data are nowadays collected in agriculture.”
• The other thing is that the specific modeling setup I presented is likely to be valid since the results obtained with this setup are the ones that would normally be expected. So, it’s not so much the result that REIP49 is the best predictor, but rather that the setup I created may be used for future variable importance assessment as new data come in.

I already guessed the first point, but the second one only occurred to me in hindsight. Seems to happen rather often in research, though.

Biosphere II, Arizona, USA

My previous talk at UW went rather smoothly. When listening to the IDA sessions yesterday I already had a few more ideas to make my thesis somewhat more reviewer-proof — seems like a side-effect of conferences when other people’s work has an inspiring effect on one’s own work.