Anomaly Detection on Mars  Using Deep Learning
March 28th, 2021

Anomaly detection on the surface of Mars has a few unique challenges. For example, finding publically available datasets like landing images, using deep convolutional networks and exploring the large variety of surface anomalies. Still, a team of 30+ engineers took on t

Read More

Tags: , ,

How to Webscrape 700,000 PDFs for Natural Language Processing in 14 Hours to Help the Planet
March 6th, 2021

In order to identify financial incentives for forest and landscape restoration in LATAM, we needed to webscrape policy documents from government pages combining more than 1,300 keywords for each of the 108 targetted states. We did this 61x times faster (than using a lap

Read More

Tags: , , ,

Harnessing AI and Open Source Satellite Imagery to Address Global Problems
March 1st, 2021

Omdena successfully combines AI and ML methodologies with open source, low resolution satellite imagery to create actionable solutions for powerful insights.   Introduction Every day, millions of images are captured from space by an ever-growing number of satellite

Read More

Tags: , , ,

Unsupervised Learning for Land Cover Classification in Satellite Imagery
February 22nd, 2021

K-Means, Principal Component Analysis, Autoencoders, and Transfer Learning applied for land cover classification in a challenging data scenario. By Clive Fernandes, Debaleena Misra, Marvin Oluoch, Abhilasha Sinha Location: Kenya, Africa.   The problem background &n

Read More

Tags: ,

A Damage Assessment Solution of the Desert Locust Surge in Kenya Using AI and Satellite Imagery
February 15th, 2021

  Applying Machine Learning to dynamically assess vegetation health changes before and after desert locust attacks. By Rasha Salim, Debaleena Misra, Kanmani Subramanian, Joshua Sant’Anna   In 2020, as desert locust outbreaks were raging throughout the Horn

Read More

Tags: , , ,

Understanding Nature-Based Solutions through Natural Language Processing and Machine Learning
January 13th, 2021

Nature-based solutions (NbS) can help societies and ecosystems adapt to drastic changes in the climate and mitigate the adverse impacts of such changes. By Bala Priya, Simone Perazzoli, Nishrin Kachwala, Anju Mercian, Priya Krishnamoorthy, and Rosana de Oliveira Gomes &

Read More

Tags: , , ,