Review on Convolutional Neural Networks (CNN) in vegetation remote sensing

T Kattenborn, J Leitloff, F Schiefer, S Hinz - ISPRS journal of …, 2021 - Elsevier
Identifying and characterizing vascular plants in time and space is required in various
disciplines, eg in forestry, conservation and agriculture. Remote sensing emerged as a key …

Uncovering ecological patterns with convolutional neural networks

PG Brodrick, AB Davies, GP Asner - Trends in ecology & evolution, 2019 - cell.com
Using remotely sensed imagery to identify biophysical components across landscapes is an
important avenue of investigation for ecologists studying ecosystem dynamics. With high …

Mapping forest tree species in high resolution UAV-based RGB-imagery by means of convolutional neural networks

F Schiefer, T Kattenborn, A Frick, J Frey, P Schall… - ISPRS Journal of …, 2020 - Elsevier
The use of unmanned aerial vehicles (UAVs) in vegetation remote sensing allows a time-
flexible and cost-effective acquisition of very high-resolution imagery. Still, current methods …

Seasonal Arctic sea ice forecasting with probabilistic deep learning

TR Andersson, JS Hosking, M Pérez-Ortiz… - Nature …, 2021 - nature.com
Anthropogenic warming has led to an unprecedented year-round reduction in Arctic sea ice
extent. This has far-reaching consequences for indigenous and local communities, polar …

Convolutional Neural Networks enable efficient, accurate and fine-grained segmentation of plant species and communities from high-resolution UAV imagery

T Kattenborn, J Eichel, FE Fassnacht - Scientific reports, 2019 - nature.com
Recent technological advances in remote sensing sensors and platforms, such as high-
resolution satellite imagers or unmanned aerial vehicles (UAV), facilitate the availability of …

Individual tree crown segmentation and crown width extraction from a heightmap derived from aerial laser scanning data using a deep learning framework

C Sun, C Huang, H Zhang, B Chen, F An… - Frontiers in plant …, 2022 - frontiersin.org
Deriving individual tree crown (ITC) information from light detection and ranging (LiDAR)
data is of great significance to forest resource assessment and smart management. After …

Land use land cover classification with U-net: Advantages of combining sentinel-1 and sentinel-2 imagery

JV Solórzano, JF Mas, Y Gao, JA Gallardo-Cruz - Remote Sensing, 2021 - mdpi.com
The U-net is nowadays among the most popular deep learning algorithms for land use/land
cover (LULC) mapping; nevertheless, it has rarely been used with synthetic aperture radar …

[HTML][HTML] Spatially autocorrelated training and validation samples inflate performance assessment of convolutional neural networks

T Kattenborn, F Schiefer, J Frey, H Feilhauer… - ISPRS Open Journal of …, 2022 - Elsevier
Deep learning and particularly Convolutional Neural Networks (CNN) in concert with remote
sensing are becoming standard analytical tools in the geosciences. A series of studies has …

Deep learning segmentation and classification for urban village using a worldview satellite image based on U-Net

Z Pan, J Xu, Y Guo, Y Hu, G Wang - Remote Sensing, 2020 - mdpi.com
Unplanned urban settlements exist worldwide. The geospatial information of these areas is
critical for urban management and reconstruction planning but usually unavailable …

Individual tree detection and species classification of Amazonian palms using UAV images and deep learning

MP Ferreira, DRA de Almeida… - Forest Ecology and …, 2020 - Elsevier
Abstract Information regarding the spatial distribution of palm trees in tropical forests is
crucial for commercial exploitation and management. However, spatially continuous …