Percentage accuracy of each LULC category in transitioning from one land use type to another between two time steps, under the influence of a given change driver.

Percentage accuracy of each LULC category in transitioning from one land use type to another between two time steps, under the influence of a given change driver.

<p>Percentage accuracy of each LULC category in transitioning from one land use type to another between two time steps, under the influence of a given change driver.</p>

Saved in:

Bibliographic Details
Main Author:	Yisa Ginath Yuh (20370814) (author)
Other Authors:	Kouamé Paul N’Goran (20370817) (author), Angela Kross (19773221) (author), Marco Heurich (676039) (author), H. Damon Matthews (14826542) (author), Sarah E. Turner (8478309) (author)
Published:	2024
Subjects:	Ecology Science Policy Environmental Sciences not elsewhere classified Biological Sciences not elsewhere classified Information Systems not elsewhere classified supervised classification algorithm quantify decadal changes markov chain algorithms machine learning algorithms human population growth google earth engine 2000 – 2010 spatial modeling tools quantitative results required 2010 – 2020 1990 – 2000 monitoring forest cover dense forest cover e ., 174 div >< p 7 – 4 5 ), suggesting 3 – 12 forest degradation within 1990 – 2020 totaling approximately 8 land use change 860 – 204 2 </ sup forest cover land use approximately 12 forest degradation provide spatial climate change 860 km random forest forest fragmentation projected 3 year period validated results supporting long study represents region ’ reduce emissions novel application many endemic global hotspot endangered species effective planning congo basin assessing long 938 km 803 km 658 km 642 km 608 km 502 km 161 km 046 km
Tags:	Add Tag No Tags, Be the first to tag this record!

Be the first to leave a comment!

Cannot write session to /tmp/vufind_sessions/sess_cavpap2mjenj8dbh76prct80fc