Land Use Cover Datasets: A Review

García-Álvarez, David; Nanu, Sabina Florina

doi:10.1007/978-3-030-90998-7_4

Cited by 8 publications

(5 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Plenty of detailed, high-quality datasets are now available, providing LC information for the European continent, such as: HILDA, CORINE, PELCOM, Urban Atlas, etc. Of all the European LC datasets, Coordination of Information on the Environment (CORINE) Land Cover (CLC) is one of the best-known, oldest, and most-used [43]. The CLC project can be considered the most-relevant European LUC database for several reasons, but primarily because of its history, comprehensive coverage, method of production, and degree of detail [43][44][45].…”

Section: Methodsmentioning

confidence: 99%

“…Of all the European LC datasets, Coordination of Information on the Environment (CORINE) Land Cover (CLC) is one of the best-known, oldest, and most-used [43]. The CLC project can be considered the most-relevant European LUC database for several reasons, but primarily because of its history, comprehensive coverage, method of production, and degree of detail [43][44][45]. We, therefore, used CLC to post-process the maps generated by our pipeline, making sure that the estimates are available only for land cover classes the model is trained to handle.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

A Deep Learning Approach to Estimate Soil Organic Carbon from Remote Sensing

Pavlovic,

Ilic,

Ralevic

et al. 2024

Remote Sensing

View full text Add to dashboard Cite

Monitoring soil organic carbon (SOC) typically assumes conducting a labor-intensive soil sampling campaign, followed by laboratory testing, which is both expensive and impractical for generating useful, spatially continuous data products. The present study leverages the power of machine learning (ML) and, in particular, deep neural networks (DNNs) for segmentation, as well as satellite imagery, to estimate the SOC remotely. We propose a new two-stage pipeline for remote SOC estimation, which relies on using a DNN trained to classify land cover to perform feature extraction, while the SOC estimation is performed by a different ML model. The first stage is an image segmentation DNN with the U-Net architecture, which is trained to estimate the land cover for an observed geographical region, based on multi-spectral images taken by the Sentinel-2 satellite constellation. This estimator is subsequently used to extract the latent feature vector for each of the output pixels, by rolling back from the output (dense) layer of the U-Net and accessing the last available convolutional layer of the same dimension as our desired output. The second stage is trained on a set of feature vectors extracted at the coordinates for which manual SOC measurements exist. We tested a variety of ML models and report on their performance. Using the best extremely randomized trees model, we generated a spatially continuous map of SOC estimations for the region of Tuscany, in Italy, with a resolution of 10 m, to share with the researchers as a means of validating the results and to demonstrate the efficiency of the proposed approach, which can can easily be scaled to create a global continuous SOC map.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

A Deep Learning Approach to Estimate Soil Organic Carbon from Remote Sensing

Pavlovic,

Ilic,

Ralevic

et al. 2024

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…The spatial resolution of LC maps is determined by the ground resolution of the image data, which is typically upward of 10 m for public satellite data [15]. Although sufficient for some purposes, commonly available coarse-resolution LC maps preclude the accurate surveying and monitoring of small-scale, patchily distributed habitats and of fragmented or mosaic habitats at a landscape scale [16].…”

Section: Introductionmentioning

confidence: 99%

Multi-Stage Semantic Segmentation Quantifies Fragmentation of Small Habitats at a Landscape Scale

van der Plas,

Geikie,

Alexander

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

Land cover (LC) maps are used extensively for nature conservation and landscape planning, but low spatial resolution and coarse LC schemas typically limit their applicability to large, broadly defined habitats. In order to target smaller and more-specific habitats, LC maps must be developed at high resolution and fine class detail using automated methods that can efficiently scale to large areas of interest. In this work, we present a Machine Learning approach that addresses this challenge. First, we developed a multi-stage semantic segmentation approach that uses Convolutional Neural Networks (CNNs) to classify LC across the Peak District National Park (PDNP, 1439 km2) in the UK using a detailed, hierarchical LC schema. High-level classes were predicted with 95% accuracy and were subsequently used as masks to predict low-level classes with 72% to 92% accuracy. Next, we used these predictions to analyse the degree and distribution of fragmentation of one specific habitat—wet grassland and rush pasture—at the landscape scale in the PDNP. We found that fragmentation varied across areas designated as primary habitat, highlighting the importance of high-resolution LC maps provided by CNN-powered analysis for nature conservation.

show abstract

“…The rapid advancements in sensing technologies have made multimodal data increasingly crucial in Earth Observation (EO) [38]. With the growing availability of remote sensing data, such as high-resolution imagery and point clouds there's an opportunity to capture comprehensive information about a scene across spectral, textural, and 3D domains [133].…”

Section: Motivationmentioning

confidence: 99%

Multi-Modal earth observation and deep learning for urban scene understanding

Maiti

View full text Add to dashboard Cite

show abstract

Land Use Cover Datasets: A Review

Cited by 8 publications

References 31 publications

A Deep Learning Approach to Estimate Soil Organic Carbon from Remote Sensing

A Deep Learning Approach to Estimate Soil Organic Carbon from Remote Sensing

Multi-Stage Semantic Segmentation Quantifies Fragmentation of Small Habitats at a Landscape Scale

Multi-Modal earth observation and deep learning for urban scene understanding

Contact Info

Product

Resources

About