Machine Learning, News

ii2030 Challenge: AI for Earth Observation

Identifying sustainable business models for open machine learning ready Earth observation repositories

When Gedeon Jean first realized the power of Earth observation (EO) data to detect environmental changes, he was mesmerized. As a Machine Learning Research Engineer, he saw the potential of combining machine learning (ML) and EO to develop diverse predictive applications for Rwanda, his native country. Rwanda is increasingly experiencing natural disasters due to climate change, including landslides, floods, and earthquakes, which take a socio-economic toll on an already vulnerable population.

Gedeon decided to write a ML algorithm that could find patterns in remote sensing data to forewarn when flooding could occur. Flood prediction models map flood-prone areas and can improve the accuracy of early warning systems to minimize the destruction of natural habitats, food sources, infrastructure, and loss of human lives, which is associated with floods. But building the application proved to be trickier as he struggled to find high-quality labeled training data that were ML-ready, on which he could train his model. In addition, the lack of training data relevant to his area of interest is known to produce biased or incorrect results. Training data, the building block for ML algorithms, needs to capture the geographical diversity of real-world data to help the model identify patterns more accurately.

Community Voices, Machine Learning

Data Challenge Winner: Q&A with Christian Ayala Lauroba

A conversation with the First Place winning team’s lead of the AI4FoodSecurity Data Challenge.

Hosted on ESA’s AI4EO platform, the AI4FoodSecurity data challenge brought together participants worldwide to find the best machine learning/AI solutions for crop identification using Planet Fusion data and Sentinel-1 and -2 data. The challenge covered two areas of interest, Germany and South Africa, with high-quality cadastral data on field boundaries and crop types as ground truth input. It was organized by Planet, TUM/DLR, and Radiant Earth from 4 October to 19 December 2021. 188 competed for a chance to win one of the fantastic prizes that included internships, subscriptions to various platforms, and scholarships. In this Q&A, we sat down with Christian Ayala Lauroba from Spain, the leader of the team that won first place in both the …

Machine Learning

Enabling Agricultural Dataflows in Radiant MLHub for Geospatial Machine Learning Analytics

How Radiant MLHub strengthens the data collection to analytics pipeline for agriculture projects.

Radiant Earth Foundation is strengthening geospatial machine learning (ML) workflows for organizations working on agriculture projects by streamlining the process, from ground reference data collection to insight analytics, through Radiant MLHub.

Radiant MLHub is an open-access library dedicated to geospatial training data and ML models. Since its inception in 2019, Radiant has focused on developing and aggregating geo-diverse benchmark data that practitioners can use to create applications and enable data-driven policies that impact lives worldwide. The datasets vary from…

Community Voices

Radiant MLHub Spotlight Q&A: Victor Faraggi

Accelerating climate change applications with machine learning models and remote sensing data.

Standards

Next Week: See an Incredible Selection of Cloud-Native Geo Talks

I am very pleased to announce the schedule for the Cloud-Native Geospatial Outreach Event that I’m organizing with the Open Geospatial Consortium next week (April 19th and 20th). We’ll have over 70 5-minute lightning talks, along with 6 in-depth tutorials, from an incredible set of speakers. The event will be entirely virtual and completely free and is spread across time zones to be friendly to a global audience. The talks will also be posted as quickly as possible, so everyone can see the ones that aren’t in the right time zone.

Standards

Join us for the Cloud-Native Geospatial Outreach Event!

April 19th and 20th brings together the COGSTACZarr & COPC communities to share experiences and welcome new users. 

I’m pleased to announce that we have just opened registration for the Cloud-Native Geospatial Outreach Event we’re putting on with the OGC on April 19th and 20th. You can read more background in my previous post and in the recap from the first event. The core idea is to highlight an exciting new trend in geospatial, welcoming new users to learn about some incredible communities. From the sign-up page:

Standards

Get funded to code software for STAC

Standards

Save the date! Cloud-Native Geospatial Outreach Event on April 19–20

Mark it on your calendars and apply now to speak about COGSTACZarr or COPC.

Standards

STAC Updates, February 2022

In the last update post, I shared that we had a great set of sponsors come in to further the greater STAC ecosystem. I’m pleased to share that we had a first successful ‘funders call’ to determine the priorities for the money we raised. This probably slowed the process a bit, but it was super valuable for the STAC Project Steering Committee to hear from key sponsors what they see as most needed in the STAC ecosystem. It was a great conversation, and I look forward to future calls.

Machine Learning

Detecting Agricultural Croplands from Sentinel-2 Satellite Imagery

A guide to identifying croplands with reasonable accuracy using a semantic segmentation model. We developed UNet-Agri, a benchmark machine learning model that classifies croplands using open-access Sentinel-2 imagery at 10m spatial resolution with ground reference data provided by the Western Cape Department of Agriculture in South Africa. This post is a step-by-step walkthrough of how we developed the model and evaluated its performance. Understanding what UNet-Agri does will help you build your model and deploy it for a similar application.