Open Thinkering


Tag: houses

Weeknote 42/2023

Aha! The same number weeknote as my age. Awesome.

This time next week we should be partly moved into our new (temporary) house. Thankfully, it’s not next to the River Wansbeck, which very nearly overwhelmed the flood defences installed after the events of a decade or so ago. The tree being swept away by the river in the above photo used to stand at the bottom of the garden of the house mentioned in this post. That sound you hear is of us dodging a bullet in deciding not to go ahead with purchasing it 😅

I’m composing this post pretty early on Sunday morning having just done some last-minute edits to Thought Shrapnel newsletter #444. If you haven’t subscribed yet, you don’t know what you’re missing. Or maybe you do, which is why you unsubscribed. Or maybe you use the RSS feed to get the posts without my additional solo waffle? You do you.

This week I have been mostly:

  • Completing a badged course in preparation for the postgraduate study I’m starting next month. I wrote about that here.
  • Pleased that Laura is back from her three-week sailing holiday. She seems to have had a good time and is well-rested. Laura’s moved her excellent newsletter to Substack, which you can subscribe to here.
  • Having a Covid booster jab. I’m in a ‘vulnerable group’ because I’m asthmatic, which means I get extra protection. I’m not complaining, although I feel a little achey this morning.
  • Packing boxes, given that we’re moving next week. We… have a lot of stuff and we’re moving ourselves by hiring a van. The house we’re moving to must only be about 500m away from where we currently live, as the crow flies.
  • Helping my daughter prepare for, and then interview, my parents about some family history. I wrote about it in this post.
  • Planning for the first Community Conversations workshop that WAO is running with Participate. We’re using the ORE community as an example to talk about value cycles. It’s free, so please do sign up!
  • Setting up a new project with MIT Digital Credentials Consortium (DCC). We’re getting onboarded and then helping with documentation and asset-creation.
  • Catching up with various people and talking to others I’ve never had the pleasure of talking with before via my virtual coffee calendar slots. Please do take one if you fancy a chat ☕
  • Getting involved with our monthly WAO co-op half-day. We did some reflection and planning, which was useful.
  • Attending a great SI Networks session entitled How to Communicate with Systems Maps. This is going to be an important practical part of my upcoming MSc, so I wanted to get a head start. There are some really interesting people doing some fascinating stuff!
  • Viewing some houses. People are still being a bit unrealistic about pricing, I think, given the state of the market.
  • Putting together a significant follow-up to Part 1 of Using Open Recognition to Map Real-World Skills and Attributes. In Part 2, which I’ll publish after my colleagues have added their thoughts and feedback, I not only provide a flowchart for the system I’d like to build, but wireframes for the main user experience workflow. I’m looking forward to publishing it, because I want someone to build this!

My children’s football matches were called off this weekend due to the storm, but my son’s basketball game went ahead. They absolutely smashed the opposition, and he scored three baskets and made three assists, playing Point Guard. I’m saying that as if I have any clue about basketball; I don’t, but enjoy watching him play, and he played well.

Next week, we’re following up some potential new work with Greenpeace, starting the work with MIT DCC, and running the workshop with Participate that I mentioned above. I’ve also got plenty more packing and logistics to get sorted, and then on Friday we should be exchanging contracts on our house and getting the keys to our rental. We’ve then got a week to move everything across before completion.

I may get some time to work on MSc-related things, in which case I might have a go at the Mastering Systems Thinking in Practice short course through OpenLearn. I do like a badge, after all 😉

House purchases, climate change, and AI

Just over nine years ago, Team Belshaw needed to find somewhere to live. I’d been told by my employer at the time that, for various reasons, our dream of moving to Gozo couldn’t go ahead. But we still wanted to sell our house. So we moved from a four-bedroom detached house into a two-bedroom terrace in Morpeth.

It all worked out well. We ended up buying the house and converting the loft. I had a home office as the garage, separate to the house, was already converted for that purpose. Our neighbours have proved been amazing. Being so close to the centre of town and their schools it’s been a lovely place to raise our kids.

However, it’s never been our long-term plan to stay put; we’ve always been looking for somewhere else. The pandemic and then our son’s GCSE exams put off the sale of our house, but this year we finally put it on the market. Two weeks later we accepted an offer. On the same day, we had an offer accepted on a house which backs onto a river.

Black and white cropped version of a photo by Flickr user johndal showing Morpeth floods in 2008
Not this house! Just an illustrative photo of the 2008 floods.

Now, anyone who knows Morpeth knows that it flooded quite spectacularly in 2008 and then again in 2012. The Environment Agency has spent a lot of money on various flood defences including an underground reservoir and even the building of reasonably-attractive walls in the gardens of potentially-affected properties. In fact, they did such a good job that the risk of flooding from the river is negligible for the foreseeable future.

Today, though, we pulled out of the purchase of the riverside house. Why? We commissioned a more detailed flood report after someone had set alarm bells ringing about the impact of climate change. To cut a long story short, the property is at high risk of surface water flooding, and (in our opinion) the Environment Agency’s river flood defences potentially exacerbate that risk.

The reason I wanted to note this, other than it being a significant event in my life, is to share what I’ve learned about cumulative risk. I also wanted to note how helpful ChatGPT 4 was at summarising and making calculations based on the report. It was quite technical in places and, while data is good, we needed to extract meaning.

At the end of the day, humans should make decisions. But having a very quick and technically-proficient assistant to pull out and interpret data is extraordinarily useful.

I used the AskYourPDF plugin for ChatGPT, beginning by asking it specifically to explain “in the simplest language possible” the risk from surface water flooding. I then asked if we were planning to live there for 20 years whether it would be a sensible purchase. While it wouldn’t make a specific recommendation, its responses erred on the side of caution.

Going further, I asked about the impact of climate change on the property, to which it responded about things we’d already considered (increased rainfall, urbanisation), and things we hadn’t (sea level rise, decreased snowfall). This gave us further pause for thought.

The next day, already thinking that this wouldn’t be a wise investment, I asked ChatGPT to “come up with a range of 5 personas and explain how they would approach a purchasing decision for this property.” I specifically asked it to include the notion of “risk appetite” as part of this. The results were interesting. I followed up by enquiring “If these personas talked to one another and had to make one decision based on their discussion, what would be that decision?” Somewhat predictably, the personas consensus view was not to go ahead with the purchase.

The next step was to use it to calculate cumulative risk, which we’d realised hadn’t been specified in the report. It’s been a while since I did this kind of Maths, and doing it manually is somewhat confusing to my brain. So I asked ChatGPT:

Thank you for providing access to the document again. Based on the extracted information:

- The property is shown to be located within an area of **High surface water flood risk**.
- The definitions for the risk levels are as follows:
  - **High risk**: annual chance of flooding of greater than 3.3%.
  - **Medium risk**: annual chance of flooding of between 1% and 3.3%.
  - **Low risk**: annual chance of flooding of between 0.1% and 1%.
  - **Very Low risk**: annual chance of flooding of less than 0.1%.

Given that the property is in the high-risk category, the upper bound annual flood risk for surface water flooding is 3.3%. However, you've also asked for calculations for 5%, 6%, and 7%. We've already provided the 20-year cumulative risk for 5%, so let's calculate for 6% and 7%:

For 6%:
\[ \text{Risk over 20 years} = 1 - (0.94)^{20} \]
\[ \text{Risk over 20 years} \approx 74.0% \]

For 7%:
\[ \text{Risk over 20 years} = 1 - (0.93)^{20} \]
\[ \text{Risk over 20 years} \approx 80.7% \]

So, to summarize:
- For a 3.3% annual risk, the 20-year cumulative risk is approximately 49.4%.
- For a 5% annual risk, the 20-year cumulative risk is approximately 64.2%.
- For a 6% annual risk, the 20-year cumulative risk is approximately 74.0%.
- For a 7% annual risk, the 20-year cumulative risk is approximately 80.7%.

So a probability greater than a coin toss that, based on the current situation, the garden would be flooded. And this wasn’t taking into account other factors that weren’t covered by the data in the report.

The final step was to think about the risk of surface water flooding being so bad that it potentially enters the house. This was mentioned in the report as the ‘low-risk scenario’ of between 0.1% and 1% that up to 0.6m of water would be adjacent to the dwelling

So if we stayed there for 20 years, what's the cumulative risk from the annual low risk scenario?

Given the range for the low-risk scenario is between 0.1% and 1%, let's calculate the cumulative risk over 20 years for both the lower and upper bounds of this range.

Using the formula:
\[ \text{Risk over period} = 1 - (1 - \text{annual risk})^{n} \]

1. **For the lower bound of 0.1% (0.001)**:
\[ \text{Risk over 20 years} = 1 - (0.999)^{20} \]
\[ \text{Risk over 20 years} \approx 2.0% \]

2. **For the upper bound of 1% (0.01)**:
\[ \text{Risk over 20 years} = 1 - (0.99)^{20} \]
\[ \text{Risk over 20 years} \approx 18.2% \]

So, for the low-risk scenario:
- Over a 20-year period, there's approximately a 2.0% cumulative risk at the lower bound (0.1% annual risk) and an 18.2% cumulative risk at the upper bound (1% annual risk) of the property experiencing a flooding event.

So, even without the uncertainty of climate change, if we take the middle of the upper and lower bounds of cumulative risk, there’s a 1 in 10 chance that there will be up to 60cm of flood water adjacent to the property? No thanks.

Having pulled out of the purchase, this morning I’ve been to register our details with a bunch of estate agents for rentals. The chances are we’ll have to bide our time to get the exact house we want. That will be annoying, but not too much of a hardship. Especially as the next house we buy we’ll probably be staying in for a while.

Photo modified from an original CC BY SA johndal

On having a space to myself

“I’m gonna buy me a caravan” are words I never thought I’d here myself think, never mind say. But that’s exactly what I’m considering doing. Why? It’s all about having a space to myself. :p

The housing market in England, as you may or may not know, is a little crazy at the moment. House prices are at an all-time high and (in my opinion) most houses are vastly overpriced. The chances of Hannah, Ben and I, therefore, getting a 3 bedroomed house with a study in a decent area for the amount we can afford are nigh-on zero.

(click to enlarge)

Which is where the caravan comes in. We’re not talking your common-or-garden caravan here. Oh no. The advert above (found serendipitiously in the magazine of The Guardian, which I hardly ever buy) includes a competition to win an Airstream trailer. This brought back memories of Kathy Sierra’s blog post back in 2006 about productivity and happiness. Within that post, she showed her readers her Airstream and waxed lyrical about how wonderful it was:

Finally, after two years of looking (and saving), I found and bought a vintage 1966 (recently restored) 23-foot Silver Streak trailer. (Silver Streak is a “fork” of the original Airstream.) This is my new baby, with my dog Clover in the doorway:

And it’s perfect. It’s parked exactly two feet away from the side of the house (a house I share with my horse trainer and his wife), and the wifi from the house works beautifully. I haven’t felt this good working in years.

I don’t think I need a 23-footer. We’re unlikely to have the space on the drive of our next house – if we even have a drive – to accommodate such a behemoth. I think they do smaller ones, but even so I’d better get saving

Whilst I love my family to bits and enjoy very much the time I spend with them, I have to be able to spend time on my own. How else would I be able to churn out these blog posts? 😉