Nico Lang
YOU?
Author Swipe
View article: Taxonomy-Aware Evaluation of Vision-Language Models
Taxonomy-Aware Evaluation of Vision-Language Models Open
When a vision-language model (VLM) is prompted to identify an entity depicted in an image, it may answer 'I see a conifer,' rather than the specific label 'norway spruce'. This raises two issues for evaluation: First, the unconstrained gen…
View article: Open-Insect: Benchmarking Open-Set Recognition of Novel Species in Biodiversity Monitoring
Open-Insect: Benchmarking Open-Set Recognition of Novel Species in Biodiversity Monitoring Open
Global biodiversity is declining at an unprecedented rate, yet little information is known about most species and how their populations are changing. Indeed, some 90% of Earth's species are estimated to be completely unknown. Machine learn…
View article: Multimodal Fusion Strategies for Mapping Biophysical Landscape Features
Multimodal Fusion Strategies for Mapping Biophysical Landscape Features Open
Multimodal aerial data are used to monitor natural systems, and machine learning can significantly accelerate the classification of landscape features within such imagery to benefit ecology and conservation. It remains under-explored, howe…
View article: Labeled Data Selection for Category Discovery
Labeled Data Selection for Category Discovery Open
Category discovery methods aim to find novel categories in unlabeled visual data. At training time, a set of labeled and unlabeled images are provided, where the labels correspond to the categories present in the images. The labeled data p…
View article: Nacala-Roof-Material: Drone Imagery for Roof Detection, Classification, and Segmentation to Support Mosquito-borne Disease Risk Assessment
Nacala-Roof-Material: Drone Imagery for Roof Detection, Classification, and Segmentation to Support Mosquito-borne Disease Risk Assessment Open
As low-quality housing and in particular certain roof characteristics are associated with an increased risk of malaria, classification of roof types based on remote sensing imagery can support the assessment of malaria risk and thereby hel…
View article: MMEarth: Exploring Multi-Modal Pretext Tasks For Geospatial Representation Learning
MMEarth: Exploring Multi-Modal Pretext Tasks For Geospatial Representation Learning Open
The volume of unlabelled Earth observation (EO) data is huge, but many important applications lack labelled training data. However, EO data offers the unique opportunity to pair data from different modalities and sensors automatically base…
View article: Familiarity-Based Open-Set Recognition Under Adversarial Attacks
Familiarity-Based Open-Set Recognition Under Adversarial Attacks Open
Open-set recognition (OSR), the identification of novel categories, can be a critical component when deploying classification models in real-world applications. Recent work has shown that familiarity-based scoring rules such as the Maximum…
View article: A high-resolution canopy height model of the Earth
A high-resolution canopy height model of the Earth Open
The worldwide variation in vegetation height is fundamental to the global carbon cycle and central to the functioning of ecosystems and their biodiversity. Geospatially explicit and, ideally, highly resolved information is required to mana…
View article: The overlooked contribution of trees outside forests to tree cover and woody biomass across Europe
The overlooked contribution of trees outside forests to tree cover and woody biomass across Europe Open
Trees are an integral part in European landscapes, but only forest resources are systematically assessed by national inventories. The contribution of urban and agricultural trees to national-level carbon stocks remains largely unknown. Her…
View article: Canopy height and biomass map for Europe
Canopy height and biomass map for Europe Open
Data Description These datasets were generated from the research article "The overlooked contribution of trees outside forests to tree cover and woody biomass across Europe". Here we publish aggregated version of canopy cover and height ma…
View article: ESA WorldCover 10 m 2020 v100 reprojected to the Sentinel-2 UTM Tiling Grid
ESA WorldCover 10 m 2020 v100 reprojected to the Sentinel-2 UTM Tiling Grid Open
This is a derived version of the ESA WorldCover 10 m 2020 v100 (Zanaga et al., 2021) reprojected to the Sentinel-2 UTM Tiling Grid for the global land surface. It can be used to work on data that is structured following Sentinel-2 tiles. T…
View article: Demo data for global-canopy-height-model
Demo data for global-canopy-height-model Open
Demo data for the example scripts provided in https://github.com/langnico/global-canopy-height-model. Please see the README in the github repository for further information and see Lang, et al. (2023) for more information. Reference: Lang,…
View article: Canopy top height models at 10m GSD from airborne LIDAR (derived from LVIS and small-footprint ALS)
Canopy top height models at 10m GSD from airborne LIDAR (derived from LVIS and small-footprint ALS) Open
Rasterized canopy top height models (CTHM) at 10m ground sampling distance (GSD) derived from airborne LIDAR. The CTHMs were created to be comparable to GEDI canopy top heights (within 25m footprints) using two sources: 1) NASA's LVIS airb…
View article: Canopy top height models at 10m GSD from airborne LIDAR (derived from LVIS and small-footprint ALS)
Canopy top height models at 10m GSD from airborne LIDAR (derived from LVIS and small-footprint ALS) Open
Rasterized canopy top height models (CTHM) at 10m ground sampling distance (GSD) derived from airborne LIDAR. The CTHMs were created to be comparable to GEDI canopy top heights (within 25m footprints) using two sources: 1) NASA's LVIS airb…
View article: Demo data for global-canopy-height-model
Demo data for global-canopy-height-model Open
Demo data for the example scripts provided in https://github.com/langnico/global-canopy-height-model. Please see the README in the github repository for further information and see Lang, et al. (2023) for more information. Reference: Lang,…
View article: Filtered canopy top height estimates from GEDI LIDAR waveforms for 2019 and 2020
Filtered canopy top height estimates from GEDI LIDAR waveforms for 2019 and 2020 Open
Canopy top height (RH98) is estimated from GEDI L1B waveforms globally between 51.6° N & S from L1B Version 1 data for April-July 2019 and 2020. We refer to the original research article below for further information. The footprint data we…
View article: Filtered canopy top height estimates from GEDI LIDAR waveforms for 2019 and 2020
Filtered canopy top height estimates from GEDI LIDAR waveforms for 2019 and 2020 Open
Canopy top height (RH98) is estimated from GEDI L1B waveforms globally between 51.6° N & S from L1B Version 1 data for April-July 2019 and 2020. We refer to the original research article below for further information. The footprint data we…
View article: Global canopy top height estimates from GEDI LIDAR waveforms for 2020
Global canopy top height estimates from GEDI LIDAR waveforms for 2020 Open
Canopy top height (RH98) is estimated from GEDI L1B waveforms globally between 51.6° N & S from L1B Version 1 data from April-July 2020. The footprint level RH98 predictions are stored in hdf5 files corresponding to the orbit files of the …
View article: Global canopy top height estimates from GEDI LIDAR waveforms for 2020
Global canopy top height estimates from GEDI LIDAR waveforms for 2020 Open
Canopy top height (RH98) is estimated from GEDI L1B waveforms globally between 51.6° N & S from L1B Version 1 data from April-July 2020. The footprint level RH98 predictions are stored in hdf5 files corresponding to the orbit files of the …
View article: The overlooked contribution of trees outside forests to tree cover and woody biomass across Europe
The overlooked contribution of trees outside forests to tree cover and woody biomass across Europe Open
Trees are an integral part of almost all European landscapes, but only forest resources are systematically assessed by national inventories, and the extent to which trees in urban and agricultural areas contribute to biomass and carbon sto…
View article: Country-wide retrieval of forest structure from optical and SAR satellite imagery with deep ensembles
Country-wide retrieval of forest structure from optical and SAR satellite imagery with deep ensembles Open
Monitoring and managing Earth's forests in an informed manner is an important requirement for addressing challenges like biodiversity loss and climate change. While traditional in situ or aerial campaigns for forest assessments provide acc…
View article: Satellite-based high-resolution maps of cocoa planted area for Côte d'Ivoire and Ghana
Satellite-based high-resolution maps of cocoa planted area for Côte d'Ivoire and Ghana Open
Côte d'Ivoire and Ghana, the world's largest producers of cocoa, account for two thirds of the global cocoa production. In both countries, cocoa is the primary perennial crop, providing income to almost two million farmers. Yet precise map…
View article: Global canopy top height estimates from GEDI LIDAR waveforms for 2019
Global canopy top height estimates from GEDI LIDAR waveforms for 2019 Open
[Version 1.1 includes footprint level predictions] Canopy top height (RH98) is estimated from GEDI L1B waveforms globally between 51.6° N & S. The map is based on the first four months of L1B data (April-July 2019). The sparse predictions …
View article: Global canopy top height estimates from GEDI LIDAR waveforms for 2019
Global canopy top height estimates from GEDI LIDAR waveforms for 2019 Open
Canopy top height (RH98) is estimated from GEDI L1B waveforms globally between 51.6° N & S. The map is based on the first four months of L1B Version 1 data (April-July 2019). The sparse footprint level predictions are averaged at 0.5 degre…
View article: Global canopy top height estimates from GEDI LIDAR waveforms for 2019
Global canopy top height estimates from GEDI LIDAR waveforms for 2019 Open
Canopy top height (RH98) is estimated from GEDI L1B waveforms globally between 51.6° N & S. The map is based on the first four months of L1B Version 1 data (April-July 2019). The sparse footprint level predictions are averaged at 0.5 degre…