Post has attachment
Dear NILM researchers,

On behalf of the organizing committee, we would like to invite you to participate in the 4th International Workshop on Non-Intrusive Load Monitoring (NILM), which will be held in Austin, Texas on March 7-8 2018. As in 2014, this workshop will be co-located with the Pecan Street Annual Research Conference.

The agenda for the NILM2018 is still being defined, but the current proposal is to have two full-days of activities. There will be working groups, paper presentations and a poster session. We will post updates on this website as details become more finalized.

The mission of this workshop is to serve as a forum for bringing together all the researchers, practitioners, and students that are working on the topic of energy disaggregation around the world.

We are looking forward to welcoming you in Austin!


Mario Berges and Stephen Makonin
Workshop General Co-Chairs

Post has attachment

Post has attachment
Hi everyone,
Wanted to share my work on a computational sustainability problem. It's accepted as a paper at KDD 2016. Would love to meet up if you're around.

Here's a 2 minute video teaser:

Here's the abstract: The first step to saving energy in the home is often to create
an energy breakdown: the amount of energy used by
each individual appliance in the home. Unfortunately, current
techniques that produce an energy breakdown are not
scalable: they require hardware to be installed in each and
every home. In this paper, we propose a more scalable solution
called Gemello that estimates the energy breakdown
for one home by matching it with similar homes for which
the breakdown is already known. This matching requires
only the monthly energy bill and household characteristics
such as square footage of the home and the size of the household.
We evaluate this approach using 57 homes and results
indicate that the accuracy of Gemello is comparable to or
better than existing techniques that use sensing infrastructure
in each home. The information required by Gemello is
often publicly available and, as such, it can be immediately
applied to many homes around the world.

Here's the pdf:

Really happy to hear any feedback on the work!

Post has attachment
"interdisciplinary team of programmers, theorists, applied mathematicians, economists, biologists and environmental scientists have helped create a new field, computational sustainability, addressing challenges that computer scientists have not traditionally handled. Together, they tackle a range of issues from wildlife management to poverty-reduction."

Post has shared content
jWEATHER v1.1.6 released

jWEATHER (visit: is a web-based application that provides local environmental data like air temperature, pressure, wind speed, etc. It is a pure client-side application and bases on #javascript , #jquery , #ajax and #json. This helps to keep among others the data traffic low and increases the speed of the web-application. Currently you have access to over 200'000 stations. You get #environmental information like air temperature, air pressure, humidity, wind speed and wind direction, etc.

Post has shared content
This is why you love computational sustainability
(Project: you assist developing the metrics of on grid food supply)

Post has shared content
:-) just mixed a bit of #jquery & #json got finally this #plugin jquery.bigWEATHERws.js … much better than #yahoo #data

Post has shared content
Exceptional webinar ( #hangoutonair) The  CSIRO  +The Conservation Decisions Team   (CDT) and Environmental Decisions group (UQ) are pleased to announce Prof. Thomas Dietterich (OSU) Tuesday 1st of July (1pm Brisbane-Australia time), on New Artificial Intelligence Tools for Modeling and Managing Ecosystems  . Question answers are organized.
In this webinar (Hangout on air), Prof. +Thomas Dietterich  (+Oregon State University) will review new Artificial Intelligence Tools for Modeling and Managing Ecosystems, by focusing on three problems: (a) constructing a dynamical model of bird migration from bird watcher data, (b) managing the spread of the invasive Tamarisk in river networks, and (c) managing wildfire in Ponderosa Pine forests. We are developing new modeling and optimization tools for these problems. For bird migration, we have developed a new kind of probabilistic model, called the Collective Graphical Model, that is designed for fitting dynamical models when only aggregate, anonymous count data are observed (i.e., as opposed to observing tracks of marked animals). For the invasive species and wildfire problems, we are developing algorithms for finding near-optimal management policies when the dynamics are only available in the form of a computationally-expensive simulator. This is joint work with Dan Sheldon (Univ. of Massachusetts), Claire Montgomery (Oregon State Univ.), H. Jo Albers (Oregon State Univ.), the Cornell Lab of Ornithology (Steve Kelling and his team), and several undergraduate and graduate students.

Post has attachment
Quarterly Notes on Sustainable Water Management - Q01/2014

The most recent issue of the Quarterly Notes on Sustainable Water Management (Q01/2014) is freely available:

#Hydraulic #Fracking
#Virtual #Water
#Jordan Water Management

This release of the Notes comes along with a substantial diversification in terms of content. As with this issue the section '#Energy' is inserted immediately after the section '#Technology'. By this, it is intended to emphasise and consider the importance of water as an important energy carrier.

Sustainability Services via _kt75 | mirror:
Instant Updates via _kt75 | first reader:

Post has attachment
Brazil's hydroelectric dam boom is bringing tensions as well as energy

When it is completed in 2015, the Jirau hydroelectric dam will span 8km across the Madeira river and feature more giant turbines than any other dam in the world. Then there are the power lines, draped along 2,250km of forests and fields to carry electricity to Brazil's urban nerve centre, São Paulo.

_kt75 | mirror:
Wait while more posts are being loaded