Social Impact

Why I love running RHoK


We’ve received a lot of RHoK love this year, but last weekend’s Melbourne and Sydney hacks was probably the most productive with respect to getting prototypes & solutions across the line, and the most satisfying in terms of how well the hackers and change makers connected with each other, and with their causes. It’s clear we’re doing something right ☺️

Now we get to relax for a couple of months (“and breath”… 🧘🏼‍♀️) before we prepare for the Winter Hackathon and find our next batch of amazing change makers. A massive congratulations to Eddie for a successful first hack as our new Melbourne Community Manager. Handovers are not always easy, unless of course your new Community Manager has been involved in RHoK before; as a change maker, a hacker, and steering committee member. We couldn’t have asked for a better person to take up the reigns.

– A.B.


Introducing the RHoK Australia – 2018 Summer Changemakers


The RHoK Australia – Melbourne Summer Hackathon is just over a month away and we have six fantastic organisations/social enterprises that we’ll be collaborating with. We also welcome DocDir, which is only at the very start of its social impact journey. DocDir aims to train GPs and other health professionals to have an integrated LBGTQI practice.

“We are looking for ‘Goldilocks’ problems; they need to be small enough so that they can be progressed over a weekend, but large enough to make a real difference.”
— Eddie Chapman, RHoK Community Manager

Kensington Neighbourhood House

Providing adult education, personal development, community building and childcare programs to their local community.



Providing free legal advice to Australians in need who can’t otherwise access it.


Moral Fairground

Creating awareness and raising the profile of ethical living and ethical business throughout the Australian community.


RPH Radio Reading Network

Supporting the Radio Reading network and the voice of print media in Australia, with a vision that print disability is not a barrier to participation.


She’s a Crowd

Ending gender-based violence by sharing stories to help decision-makers understand and address the issue.



Enriching the lives of people with a disability.


Revamping the RHoK Australia website

I spent most of yesterday revamping the RHoK Australia website in preparation for the next round of applications. There is still a lot more work to do to make it work more effectively, but I think we're getting there.

Recent changemakers and projects are yet to be added, as well as photos from our most recent hackathons.

The majority of my time was spent overhauling the Become a Changemaker  and  Become a RHoK star  pages, and making our reach or impact more visible. 

Showcasing our impact hasn't really been a priority for us but it's becoming increasingly more important. It enables us to standing out from other hackathons, and it makes it easier for us to attract quality Changemakers and to retain sponsors. Over the next couple of months i'll be focussing more on impact.

Then later on this year we will look at rebranding RHoK. Our logos and marketing materials look dated (they are at least 10+ years old) and they don't reflect our ability to deliver cutting edge technology solutions. 

The next step is to make sure our values and mission statement come across more clearly.



Predicting Urban Reservoir Levels Using Statistical Learning Techniques


Currently, about 50% of the world population lives in cities, and the World Bank has projected that by 2050, this number will grow to 65%. When paired with a changing hydrological environment, including an increased likelihood of droughts, rapid urban growth puts cities and their watersheds in a vulnerable position.

An interesting paper that employs supervised learning techniques to predict reservoir levels.


Obringer & Nateghi 2008, Scientific Reports, volume 8, Article number: 5164(2018).  doi:10.1038/s41598-018-23509-w

Obringer & Nateghi 2008, Scientific Reports, volume 8, Article number: 5164(2018).


The main focus for this study was Atlanta, Georgia, although Indianapolis, Indiana and Austin, Texas were also included in the analysis. The authors investigate the predictive power using a number of models: 

  • Generalized linear model (GLM)
  • Generalized additive model (GAM)
  • Multivariate adaptive regression splines (MARS)
  • Classification and regression tree (CART)
  • Bagged CART
  • Random forest, Support vector machine (SVM)
  • Bayesian additive regression tree (BART)

and attempt to understand which predictors (hydrological system inputs and outputs) – precipitation, streamflow, population, dew point temperature, humidity,  water use, soil moisture,  contribute the most to the predictive accuracy. Not surprisingly the importance of each predictor varies with system. Population and the ENSO index appear to have the largest relative effect. Interestingly  local rainfall (precipitation) was the least important variable.

The data and supplemental notes on the methodology are available on the Nature website. At some point I'll go back and look at this in more detail. It would be interesting to see if this could be applied to Cape Town.

The most important variables were the streamflow (into the reservoir), dew point temperature, and population, followed by soil moisture and the El Niño/Southern Oscillation (ENSO) index. Conversely, precipitation was the least important variable when trying to predict reservoir level.