Hakim Abdi
Nomination for WWF's "Environmental Hero" award

In mid-September I got an email that said “ditt arbete med Birding Therapy som en av de nominerade av Årets Miljöhjälte i kategorin biologisk mångfald” (your work with Birding Therapy is one of the nominees for this year’s Environmental Hero award in the biodiversity category"). At first I didn’t know what to think and thought it was a phishing/malware type of spam. But then it sunk in that this is real, and it’s difficult to put into words how I felt. I didn’t think that anyone was paying attention to the small side project I started to get more people, particularly underrepresented groups, out into nature and birding.

Hakim Abdi
TEDx talk on “Satellites for Everyone”

My TEDx talk is now available on YouTube. The basic premise of the talk is that when you put all the recent advances in perspective, it results in a democratization of data on one hand, and science on the other. It means that anyone with a computer and a decent internet connection can have access to satellite data, process them using open source methods and extract information for their own use. This not only helps accelerate the rate at which scientific discoveries are made but also makes knowledge sharing and international development more equitable and inclusive.

R

Perform a Mann-Kendall trend test on satellite image time series in R

The Mann-Kendall trend test has become popular in the remote sensing community to test whether a time series of satellite observations is consistently increasing or decreasing. In this post, I developed a function in R that can take in raster stacks or bricks to perform the Mann-Kendall trend test and calculate its statistical significance (p values).

,

Tutorial: Machine learning classification of Sentinel-2 satellite imagery using R [Updated]

,

Note: This tutorial was updated on April 20th, 2020 based on reader feedback.

In this short post, I would like to help you conduct your own machine learning classification of Sentinel-2 data using the open source package R. The process is pretty straightforward if you have experience in remote sensing and image classification. Even if you don’t have extensive experience, basic knowledge of remote sensing terminology is sufficient.

Test pixelwise correlation between two time series of gridded satellite data in R

Satellite time series data are useful for studying biophysical how variables change over time and understanding what causes those changes. Recently, I was looking into correlating two time series datasets over Africa to look at the relationship between net primary production (NPP) and rainfall. After a futile attempt to find an “out-of-the-box” software package that does this, I created an R function to speed things up.