4.7 Article

Very high resolution canopy height maps from RGB imagery using self-supervised vision transformer and convolutional decoder trained on aerial lidar

Related references

Note: Only part of the references are listed.
Article Remote Sensing

Large-Scale Date Palm Tree Segmentation from Multiscale UAV-Based and Aerial Images Using Deep Vision Transformers

Mohamed Barakat A. Gibril et al.

Summary: This study investigates the reliability and efficiency of different deep vision transformers in extracting date palm trees from multiscale and multisource VHSR images. Among the models evaluated, the Segformer model performs the best on UAV-based and multiscale testing datasets, and outperforms all evaluated CNN models on an additional unseen UAV testing dataset.

DRONES (2023)

Review Environmental Sciences

Use-Specific Considerations for Optimising Data Quality Trade-Offs in Citizen Science: Recommendations from a Targeted Literature Review to Improve the Usability and Utility for the Calibration and Validation of Remotely Sensed Products

Alice Schacher et al.

Summary: The growth of citizen science provides valuable calibration and validation data for environmental remote sensing. However, the mismatch between data-quality requirements for remote-sensing-product development and current data quality assurance in citizen science presents a challenge if widespread use of these data sources is to be achieved. This study conducts a literature review to identify the challenges and trade-offs in data quality assurance in citizen science, and formulates guiding questions to inform decision making in implementing optimal data-quality strategies.

REMOTE SENSING (2023)

Article Environmental Sciences

Global canopy height regression and uncertainty estimation from GEDI LIDAR waveforms with deep ensembles

Nico Lang et al.

Summary: NASA's GEDI mission aims to advance understanding of forests' role in the global carbon cycle. A novel supervised machine learning approach has been developed to interpret GEDI waveforms and regress canopy top height globally with reliable predictive uncertainty estimates.

REMOTE SENSING OF ENVIRONMENT (2022)

Article Environmental Sciences

Fusing simulated GEDI, ICESat-2 and NISAR data for regional aboveground biomass mapping

Carlos Alberto Silva et al.

Summary: This study presents a multi-sensor data fusion approach for accurate mapping of forest aboveground biomass (AGB) using data from GEDI, ICESat-2, and NISAR missions. Testing in Sonoma County, USA, demonstrates that the fusion framework provides more accurate AGB estimates compared to individual mission data, highlighting opportunities for improved AGB mapping through data fusion.

REMOTE SENSING OF ENVIRONMENT (2021)

Article Environmental Sciences

Mapping global forest canopy height through integration of GEDI and Landsat data

Peter Potapov et al.

Summary: The study utilized GEDI and Landsat data to create a global forest canopy height map, enabling monitoring of forest height and dynamics. The integration of GEDI data with optical imagery demonstrated in the study provides new possibilities for historical analysis and future monitoring.

REMOTE SENSING OF ENVIRONMENT (2021)

Article Forestry

The Contribution of Trees Outside of Forests to Landscape Carbon and Climate Change Mitigation in West Africa

David L. Skole et al.

Summary: This study highlights the importance of developing individual tree cover maps using high-resolution remote sensing, showing the significant contribution of trees outside of forests to landscape tree cover and carbon stocks in sub-Saharan Africa. Global-scale remote sensing biomass and carbon maps greatly underestimate the invisible carbon in sparse tree-based systems, indicating the need for more accurate measurement methods for carbon in these landscapes.

FORESTS (2021)

Article Multidisciplinary Sciences

High aboveground carbon stock of African tropical montane forests

Aida Cuni-Sanchez et al.

Summary: The study reveals that the aboveground carbon stock of a montane African forest network is comparable to that of a lowland African forest network, and is two-thirds higher than default values for these montane forests. The research provides country-specific montane forest AGC stock estimates modeled from the plot network, aiming to guide forest conservation and reforestation interventions. The findings emphasize the need to conserve these biodiverse and carbon-rich ecosystems.

NATURE (2021)

Article Biochemical Research Methods

A benchmark dataset for canopy crown detection and delineation in co-registered airborne RGB, LiDAR and hyperspectral imagery from the National Ecological Observation Network

Ben G. Weinstein et al.

Summary: The study established a benchmark dataset to evaluate crown detection and delineation methods for canopy trees in dominant forest types in the United States, consisting of thousands of image-annotated crowns and field-annotated crowns, as well as training crowns. Standardizing evaluation metrics helped streamline comparisons between different methods.

PLOS COMPUTATIONAL BIOLOGY (2021)

Article Environmental Sciences

Deep Neural Networks with Transfer Learning for Forest Variable Estimation Using Sentinel-2 Imagery in Boreal Forest

Heikki Astola et al.

Summary: Estimation of forest structural variables is crucial for forestry and environmental sectors. This study investigated the use of Sentinel-2 imagery, topography data, and canopy height model with deep neural networks to predict growing stock volume in four forestry districts in Central Finland. The combination of RGB and NIR bands, imaging and sun angles, and topography features achieved the best prediction accuracy.

REMOTE SENSING (2021)

Article Environmental Sciences

Improving uncertainty in forest carbon accounting for REDD plus mitigation efforts

R. D. Yanai et al.

ENVIRONMENTAL RESEARCH LETTERS (2020)

Article Environmental Sciences

Biomass estimation from simulated GEDI, ICESat-2 and NISAR across environmental gradients in Sonoma County, California

Laura Duncanson et al.

REMOTE SENSING OF ENVIRONMENT (2020)

Article Multidisciplinary Sciences

Mapping carbon accumulation potential from global natural forest regrowth

Susan C. Cook-Patton et al.

NATURE (2020)

Article Multidisciplinary Sciences

An unexpectedly large count of trees in the West African Sahara and Sahel

Martin Brandt et al.

NATURE (2020)

Article Multidisciplinary Sciences

Monitoring tropical forest carbon stocks and emissions using Planet satellite data

Ovidiu Csillik et al.

SCIENTIFIC REPORTS (2019)

Article Computer Science, Artificial Intelligence

Monocular depth estimation with hierarchical fusion of dilated CNNs and soft-weighted-sum inference

Bo Li et al.

PATTERN RECOGNITION (2018)

Article Biodiversity Conservation

Monitoring Young Tropical Forest Restoration Sites: How Much to Measure?

Ricardo A. G. Viani et al.

TROPICAL CONSERVATION SCIENCE (2018)

Article Environmental Sciences

The Ice, Cloud, and land Elevation Satellite-2 (ICESat-2): Science requirements, concept, and implementation

Thorsten Markus et al.

REMOTE SENSING OF ENVIRONMENT (2017)

Article Environmental Sciences

Humid tropical forest disturbance alerts using Landsat data

Matthew C. Hansen et al.

ENVIRONMENTAL RESEARCH LETTERS (2016)

News Item Multidisciplinary Sciences

The hunt for the world's missing carbon

Gabriel Popkin

NATURE (2015)

Article Remote Sensing

Estimating area and map accuracy for stratified random sampling when the strata are different from the map classes

Stephen V. Stehman

INTERNATIONAL JOURNAL OF REMOTE SENSING (2014)

Article Multidisciplinary Sciences

Rate of tree carbon accumulation increases continuously with tree size

N. L. Stephenson et al.

NATURE (2014)

Review Environmental Sciences

Good practices for estimating area and assessing accuracy of land change

Pontus Olofsson et al.

REMOTE SENSING OF ENVIRONMENT (2014)

Article Multidisciplinary Sciences

High-Resolution Global Maps of 21st-Century Forest Cover Change

M. C. Hansen et al.

SCIENCE (2013)

Article Multidisciplinary Sciences

Old-growth forests as global carbon sinks

Sebastiaan Luyssaert et al.

NATURE (2008)