Programming for the planet
summary
A reproducible pipeline built in OCaml (the urrent DSL) composes satellite inputs, Dockerized science scripts and Python wrappers into traceable dataflows, runs over terabytes of satellite data from hundreds of sensors, and adds a self‑adjusting incremental engine for low‑latency updates. Applied to Sierra Leone’s Gola project it computes 2.2% additionality by matching controls with 50–100 covariates, detects leakage and permanence, surfaces epoch/versioning drift in source products, and yields interactive UIs — a working system already enabling repeatable conservation analyses.
AI-written summary · about
chapters (9)
- 0:00Introduction
- 1:47Research for planetary crises
- 6:18Rainforest health with satellites
- 14:22Additionality leakage permanence
- 22:06Functional programming for ecology
- 32:57Pipeline for biodiversity metrics
- 41:01Data versioning for satellites
- 51:53Academic research challenges
- 56:24Q&A
related talks
17mWhat we talk about when we talk about scientific programming
32mDiscussion on multidisciplinary PROPL-work
23mTech for Good- Open Source Solution for Climate and Healthcare.
34mData pipelines powered by Open source and fun
24mProgramming Opportunities for the Global Biodiversity Observation Network
35mStreamlining the Cosmos: Pythonic Workflow Management for Astronomical Analysis
42mOS-Climate: A Breakthrough Open Data and Open Source Analytics Collaboration for...
45mPanel Discussion: Cost-Effective and Scalable Measurement of On...