Deep learning forest cover

Within my COBECORE project I promised to digitize and map past forest cover. This task has been finished, but a thorough analysis of this data would add a lot of value in terms of the disturbance history of the forests around Yangambi.

Data science environment gripes

I’ve been working on data science and deep learning problems for a while in both R and python. Yet, the python environment is prone to package conflicts, and the larger your install base the higher the likelihood of something being in conflict with, or not compatible, with something else.

Planning ahead

I got a lot of flack on Twitter these days for stating that you better skip post-doc positions when possible. With that I meant that you better start planning ahead, when considering unstable research employment, and aiming for more stable employment of any kind (tenure track or otherwise).

Automated data coverage statistics

Last week I finished the pre-processing code for aligning and screening the COBECORE digitized records. Friday I ran the alignment and classificatoin routine on “format 1” one of the more common data sheet formats in the dataset, which covers the 1950s. Today I processed some of the meta-data produced during the process.


© 2018. All rights reserved.

Powered by Hydejack v7.5.1