We just submitted TerraTrend Observatory to the 2026 NASA Space Apps Challenge as Team GreenGen, from Kisumu, Kenya. This post covers what we built, how the statistics work, what was hard, and what we would do next.

The challenge

Our challenge was "Be An Earth System Trend Detective!". Build a tool that picks Earth science variables, shows how they change over time, and answers four questions: what is changing, where, how much, and whether the change is significant.

Climate arguments often end in anecdotes: one hot year, one late rainy season. NASA holds decades of observations, but most students, journalists, teachers and local planners never touch scientific APIs. We wanted a three-step tool: pick a place, pick what to track, read the finding.

What it does

  • Search for a city, a feature or coordinates, or click anywhere on a NASA Blue Marble world map.
  • Pick one of six variables. All six are live NASA POWER data: Earth skin temperature, precipitation, surface albedo, soil moisture, 10 m wind speed and solar irradiance (from MERRA-2, CERES and GPM-based products).
  • Get a verdict badge, a trend chart and a plain-words explanation.

Example from the live app: Utqiagvik, Alaska skin temperature rose about +0.58 °C per decade from 1985 to 2024 (p < 0.001, 95% CI 0.40 to 0.76). Mann-Kendall agrees, with a Sen's slope of +0.47 °C per decade.

How the statistics work

  1. Fetch. An Express server requests 40 years (1985-2024, 480 months) of monthly point data from the NASA POWER API. It caches responses for 30 minutes and serves recorded live data, clearly labeled, if NASA is unreachable.
  2. Deseasonalize. We subtract each calendar month's average, so the chart shows long-term drift instead of summer-versus-winter swings.
  3. Two tests must agree. We fit an ordinary least-squares trend with a 95% confidence band and p-value, then cross-check with the non-parametric Mann-Kendall test and Sen's slope.
  4. Explain. A plain-words panel turns the numbers into sentences. It also states that R² can be small while a trend is real, and that a trend is not a cause.

Honest limits

Every result shows its source label. NASA POWER gives gridded reanalysis and satellite-derived estimates for a point, not a ground-station reading. Significance is evidence under the tests we used, not proof of a cause.

What was hard

The hackathon weekend overlapped with Kisumu Market Day, where I was also taking part, so a lot of my coding happened late at night. We also had to cut scope. The repo has a 3D globe, region comparison and a satellite image wipe, but we shipped a simpler dashboard so the deployed app would be reliable before the deadline.

Tools

TypeScript, React 19, Vite, Tailwind CSS, SVG charts, Node.js with Express, the NASA POWER API, NASA GIBS imagery and Open-Meteo geocoding. We wrote the statistics ourselves and cover them with a science test suite. The app is deployed on Render.

Links

Team and thanks

Built by Team GreenGen: Victor Ouma (team owner), Stanley Chege Thuita, Hellen Onyango, Jack Omosh, Chepkorir Miriam Chemeres and Christian Amos Otieno. Thank you to NASA Space Apps Challenge, and a shout-out to the Kisumu tech community at Zone01 Kisumu and LakeHub.

I also received my participant certificate: Galactic Problem Solver. 🌍

Some of this post and the demo slide text were drafted with AI assistance; the numbers and screenshots come from the live app.