By
@Hamerenoh
An interactive flood risk map for Ethiopian regions. Click any point on the map and it fetches real elevation and rainfall forecast data, then calculates a flood risk level (Low/Moderate/High) using a transparent, explainable formula — combining low elevation with high rain probability.
@Hamerenoh
on
flood-risk-index
Built Flood Risk Index — an interactive map that estimates flood risk for
any point using real elevation and rainfall data, not a black-box model.
Click anywhere on the map, and it fetches that location’s actual
elevation and rain forecast, then calculates a Low/Moderate/High risk
level using a transparent formula: lower elevation combined with higher
rain chance means higher risk.
The most unexpected challenge was the map itself — the tile provider I’d
originally set up started requiring an API key partway through building,
and the whole map was covered in “API KEY REQUIRED” watermarks. I fixed
it by switching to OpenStreetMap’s free tiles and using a CSS trick to
keep the dark visual style I wanted, instead of depending on a paid
service.
I’m proud that I wrote the actual risk-calculation logic myself — the
rules combining elevation and rainfall into a risk score — and that every
result the app shows is fully explainable, not hidden inside a model no
one can inspect. The original idea for this project involved a trained
CNN on satellite imagery, which isn’t realistic to build honestly in this
timeframe, so I deliberately scoped it down to something transparent and
fully working instead.
To test it: click anywhere on the map (try a low-lying area near a river
or coast vs. a mountainous region) and watch the readout panel show the
real elevation, rain chance, and resulting risk level with a gauge visual.
.png)
@Hamerenoh
on
flood-risk-index
2h 50m 33s logged
Built the core risk-calculation logic for Flood Risk Index today. Ran
into a real problem first: the map tiles I’d originally set up (CartoDB
dark tiles) started requiring an API key I don’t have — the whole map
was covered in “API KEY REQUIRED” watermarks. Fixed it by switching to
OpenStreetMap’s standard tiles (permanently free, no key) and using a
CSS color-inversion trick to keep the dark navy look I wanted.
Then wrote calculateRisk() myself — it takes real elevation and rainfall
data for any point someone clicks on the map, and combines them into a
Low/Moderate/High risk score using simple, transparent rules (low
elevation + high rain chance = higher risk). Also wrote a full README
explaining the project, and being upfront that this uses a rule-based
formula rather than a trained ML model on satellite imagery — that’s a
deliberate scope decision (real, explainable results now) rather than an
unfinished feature, with the ML version listed as future work.
.png)
.png)