Development of an object-based classification model for mapping mountainous forest cover at high elevation using aerial photography

2016 ◽  
Author(s):  
Mustapha Lateb ◽  
Chariton Kalaitzidis ◽  
Maria Tompoulidou ◽  
Ioannis Gitas
2015 ◽  
Author(s):  
Madhava Meegaskumbura ◽  
Nayana Wijayathilaka ◽  
Nirodha Abayalath ◽  
Gayani Senevirathne

Endemic to Sri Lanka, genus Adenomus contains two torrent-associated toad species whose ecology and natural history in the wild is virtually unknown. Adenomus kelaartii is relatively common, with a wide geographic distribution. Its sister species, A. kandianus, however, is restricted to two isolated populations in fast-disappearing montane and sub-montane forests. Formally declared extinct after not being recorded for over a century, a few A. kandianus were rediscovered in 2012 and redescribed as "the world's rarest toad". Here we report the results of a two-year study of the occurrence, habits and habitat associations of adult and larval A. kandianus using both general surveys and quadrat sampling. We show this to be a secretive species with a patchy distribution. Non-breeding female toads dwell in primary-forest habitats, but after heavy and sudden downpours they form large mating congregations in large streams. Amplexed pairs swim synchronously, enabling them to traverse fast currents. Egg-laying sites remain unknown, but the ability to dive and vocalize underwater, and characteristics of the eggs, suggest that they lay eggs in dark recesses of the stream. Tadpoles show microhabitat partitioning within the stream, with the greatest diversity of stages in slow-flowing rocky areas. The more robust stages possessing sucker discs exploit rocky-rapids, while metamorphic stages inhabit stream margins. We use DNA-barcoding to show the existence of two disparate toad populations. Distribution modeling with forest-cover layers added, predict a very small remaining area of suitable habitats. Conservation of this climatically and ecologically restricted species hinge largely on the preservation of high-elevation primary and riparian forests and unpolluted torrents.


2020 ◽  
Vol 12 (3) ◽  
pp. 343 ◽  
Author(s):  
Emilio Guirado ◽  
Domingo Alcaraz-Segura ◽  
Javier Cabello ◽  
Sergio Puertas-Ruíz ◽  
Francisco Herrera ◽  
...  

Accurate tree cover mapping is of paramount importance in many fields, from biodiversity conservation to carbon stock estimation, ecohydrology, erosion control, or Earth system modelling. Despite this importance, there is still uncertainty about global forest cover, particularly in drylands. Recently, the Food and Agriculture Organization of the United Nations (FAO) conducted a costly global assessment of dryland forest cover through the visual interpretation of orthoimages using the Collect Earth software, involving hundreds of operators from around the world. Our study proposes a new automatic method for estimating tree cover using artificial intelligence and free orthoimages. Our results show that our tree cover classification model, based on convolutional neural networks (CNN), is 23% more accurate than the manual visual interpretation used by FAO, reaching up to 79% overall accuracy. The smallest differences between the two methods occurred in the driest regions, but disagreement increased with the percentage of tree cover. The application of CNNs could be used to improve and reduce the cost of tree cover maps from the local to the global scale, with broad implications for research and management.


Oecologia ◽  
2014 ◽  
Vol 175 (1) ◽  
pp. 25-35 ◽  
Author(s):  
Shu-Ping Huang ◽  
Warren P. Porter ◽  
Ming-Chung Tu ◽  
Chyi-Rong Chiou

Author(s):  
Xiaoxiao Li ◽  
Soe W. Myint ◽  
Yujia Zhang ◽  
Chritopher Galletti ◽  
Xiaoxiang Zhang ◽  
...  

2009 ◽  
Vol 30 (19) ◽  
pp. 4979-4990 ◽  
Author(s):  
D. Sheeren ◽  
N. Bastin ◽  
A. Ouin ◽  
S. Ladet ◽  
G. Balent ◽  
...  

Author(s):  
Rastislav Rasi ◽  
René Beuchle ◽  
Catherine Bodart ◽  
Michael Vollmar ◽  
Roman Seliger ◽  
...  

Sign in / Sign up

Export Citation Format

Share Document