Submonthly Assessment of Temperate Forest Clear-Cuts in Mainland France DOI Creative Commons
Stéphane Mermoz, Juan Doblas, Milena Planells

et al.

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Journal Year: 2024, Volume and Issue: 17, P. 13743 - 13764

Published: Jan. 1, 2024

Remote sensing satellites allow large-scale and fast detections of forest loss. Operational loss detection systems have been mainly developed over tropical forests; however, it is increasingly important to access accurate up-to-date information on temperate forests. In this article, we adapted a Sentinel-1-based near real-time method, based the radar change ratio, detect French forests clear-cuts. Using ancillary data, annual submonthly clear-cuts were assessed for broadleaf conifer forests, various tree species, public private 967 validation plots, maps exhibited recall precision 80.9% 99.4%, respectively. The area shows remarkable stability time from 2020. We found seven times more in than although surface only three that It was also demonstrated 1.6% out 4 530 dieback reference 6.2% bark beetle attacks, confused with before actually occurred, which makes our complementary maps. Collectively, findings study could significant implications implementation radar-satellite-based system designed European

Language: Английский

Deforestation detection using a spatio-temporal deep learning approach with synthetic aperture radar and multispectral images DOI
Jonathan V. Solórzano, Jean‐François Mas, J. Alberto Gallardo-Cruz

et al.

ISPRS Journal of Photogrammetry and Remote Sensing, Journal Year: 2023, Volume and Issue: 199, P. 87 - 101

Published: April 8, 2023

Language: Английский

Citations

23
Monitoring road development in Congo Basin forests with multi-sensor satellite imagery and deep learning DOI Creative Commons
Bart Slagter, Kurt A. Fesenmyer, Matthew G. Hethcoat

et al.

Remote Sensing of Environment, Journal Year: 2024, Volume and Issue: unknown, P. 114380 - 114380

Published: Sept. 1, 2024

Language: Английский

Citations

5
How textural features can improve SAR-based tropical forest disturbance mapping DOI Creative Commons
Johannes Balling, Martin Herold, Johannes Reiche

et al.

International Journal of Applied Earth Observation and Geoinformation, Journal Year: 2023, Volume and Issue: 124, P. 103492 - 103492

Published: Sept. 20, 2023

Spatially and timely accurate information about tropical forest disturbances is crucial for tracking critical changes, supporting management, enabling law enforcement activities. In recent years, disturbance monitoring alerting using cloud-penetrating Synthetic Aperture Radar (SAR) imagery has proven effective at national pan-tropical scales. Related detection approaches mostly rely on detecting post-disturbance altered backscatter values in C or L-band SAR time series. Some are characterized by tree remnants debris. For the periods where these kinds of remain present surface, can be similar to those stable forest. This cause omission errors delayed it considered a key shortcoming current backscatter-based approaches. We hypothesized that despite fairly values, different orientation arrangement leads an heterogeneity neighboring pixel this quantified textural features. assessed six uncorrelated Gray-Level Co-Occurrence Matrix (GLCM) features dense Sentinel-1C-band Forest disturbances, based each GLCM feature pixel-based probabilistic change algorithm, were compared against results from mapped only data. studied impact speckle-filtering kernel sizes. developed method combine features, we evaluated its robustness variety natural human-induced types across Amazon Biome. Out tested Sum Average (SAVG) performed best. derived non-speckle filtered speckle-filtered data did not show noticeable accuracy. A combination SAVG resulted reduced error up 36% improved timeliness detections average 30 days, with individual showing even higher improvements level. The was found robust types. largest reduction greatest improvement evident sites large unfragmented patches (e.g., large-scale clearings, fires mining). increasing sizes, observed trade-off between combined commission errors. size 5 provide best reducing improving while introducing emphasize combining SAR-based overcome caused help improve consistency timelines short (C-band) long wavelength (L-band) operational alerting. Result maps visualized via: https://johannesballing.users.earthengine.app/view/forest-disturbance-texture.

Language: Английский

Citations

13
Integrating satellite-based forest disturbance alerts improves detection timeliness and confidence DOI Creative Commons
Johannes Reiche, Johannes Balling, Amy Pickens

et al.

Environmental Research Letters, Journal Year: 2024, Volume and Issue: 19(5), P. 054011 - 054011

Published: April 16, 2024

Abstract Satellite-based near-real-time forest disturbance alerting systems have been widely used to support law enforcement actions against illegal and unsustainable human activities in tropical forests. The availability of multiple optical radar-based alerts, each with varying detection capabilities depending mainly on the satellite sensor used, poses a challenge for users selecting most suitable system their monitoring needs workflow. Integrating alerts holds potential address limitations individual systems. We integrated RAdar Detecting Deforestation (RADD) (Sentinel-1), optical-based Global Land Analysis Discovery Sentinel-2 (GLAD-S2) GLAD-Landsat using two confidence rulesets at ten 1° sites across Amazon Basin. Alert integration resulted faster new disturbances by days months, also shortened delay increased confidence. An rate an average 97% when combining highlights complementary cloud-penetrating radar sensors detecting largely drivers environmental conditions, such as fires, selective logging, cloudy circumstances. improvement was observed integrating RADD GLAD-S2, capitalizing high temporal observation density spatially detailed 10 m Sentinel-1 2 data. introduced highest class addition low classes systems, showed that this displayed no false detection. Considering spatial neighborhood during alert enhanced overall labeled level, nearby mutually reinforced confidence, but it led detections. discuss implications study demonstrate is important data preparation step make use more user-friendly, providing stakeholders reliable consistent information timely manner. Google Earth Engine code integrate various datesets made openly available.

Language: Английский

Citations

3
Deep learning and automatic reference label harvesting for Sentinel-1 SAR-based rapid tropical dry forest disturbance mapping DOI Creative Commons
Adugna Mullissa, Johannes Reiche, Martin Herold

et al.

Remote Sensing of Environment, Journal Year: 2023, Volume and Issue: 298, P. 113799 - 113799

Published: Oct. 7, 2023

Language: Английский

Citations

9
A multi-source change detection algorithm supporting user customization and near real-time deforestation detections DOI
Ian R. McGregor, Grant M. Connette, Josh Gray

et al.

Remote Sensing of Environment, Journal Year: 2024, Volume and Issue: 308, P. 114195 - 114195

Published: May 11, 2024

Language: Английский

Citations

3
Detailed validation of large-scale Sentinel-2-based forest disturbance maps across Germany DOI Creative Commons
Eike Reinosch,

Julian Backa,

Petra Adler

et al.

Forestry An International Journal of Forest Research, Journal Year: 2024, Volume and Issue: unknown

Published: July 11, 2024

Abstract Monitoring forest areas with satellite data has become a vital tool to derive information on disturbances in European forests at large scales. An extensive validation of generated maps is essential evaluate their potential and limitations detecting various disturbance patterns. Here, we present the results for four study Germany using Sentinel-2 from 2018 2022. We apply time series filtering method map annual larger than 0.1 ha based spectral clustering change magnitude. The presented part research design precursor national German monitoring system. In this context, are used estimate affected timber volume related economic losses. To better understand thematic accuracies reliability area estimates, performed an independent product 20 sets embedded our comprising total 11 019 sample points. collected reference datasets expert interpretation high-resolution aerial imagery, including dominant tree species, cause, severity level. Our achieves overall accuracy 99.1 ± 0.1% separating disturbed undisturbed forest. This mainly indicative forest, as that class covers 97.2% area. For class, user’s 84.4 2.0% producer’s 85.1 3.4% similar indicate estimated accurately. However, 2022, observe overestimation extent, which attribute high drought stress year leading false detections, especially around edges. varies widely among seems severity, patch size. User’s range 31.0 8.4% 98.8 1.3%, while 60.5 37.3% 100.0 0.0% across sets. These variations highlight single local set not representative region diversity patterns, such Germany. emphasizes need assess large-scale products many different possible, cover sizes, severities, causes.

Language: Английский

Citations

3
How Sentinel-1 timeseries can improve the implementation of conservation programs in Brazil DOI Creative Commons

Antoine Pfefer,

Bertrand Ygorra, Frédéric Frappart

et al.

Remote Sensing Applications Society and Environment, Journal Year: 2024, Volume and Issue: 35, P. 101241 - 101241

Published: May 11, 2024

Cumulative Sum (CuSum) change detection was applied on a Sentinel-1 backscatter time series at spatial scale of 10 m as part conservation program implemented in Acre, Brazil, requiring the monitoring deforestation activities by participants program. This study evaluated results CuSum and compared them to those obtained from conventional products, demonstrating how this method can improve implementation such programs. We aimed map events with minimum resolution 0.1 ha maximise event while minimising false positives, which could lead unfair penalties for participants. The remarkable precision (ranging 87.3 % 96.1 %) short delay algorithm make it suitable implementing program, illustrated study. Moreover, has potential accurately assess extent future deforestation. contributes development effective strategies within framework programmes facilitate improved farming practices climate mitigation. code is available https://github.com/Pfefer/cusum.

Language: Английский

Citations

2
ALOS-2 PALSAR-2 ScanSAR and Sentinel-1 data for timely tropical forest disturbance mapping: A case study for Sumatra, Indonesia DOI Creative Commons
Johannes Balling, Bart Slagter, Sietse van der Woude

et al.

International Journal of Applied Earth Observation and Geoinformation, Journal Year: 2024, Volume and Issue: 132, P. 103994 - 103994

Published: July 7, 2024

Precise and prompt information on forest disturbances in the tropics is critical to support law enforcement protect tropical forests. In 2023, medium resolution ALOS-2 ScanSAR data (∼100 m spatial resolution) was made available for Southeast Asia, marking first freely accessible large-area L-Band dataset. We assessed its potential disturbance mapping combination with high-resolution C-band Sentinel-1 (∼20 resolution). mapped Sumatra, Indonesia year 2021 based separately, subsequently combined disturbances. Forest detected by both L-band SAR using a probabilistic change algorithm were at product level merging sets of detections. The added benefit combining sensors particularly evident higher detection rates, as indicated an improved producer accuracy (78.9 ± 11.9 %) compared detections single sensor (40.8 6.3 (63.3 9.6 %). Both showed negligible false advantages overcoming limited capability detect large-sized events characterized post-disturbance tree remnants, occurring locations large-scale agricultural clearings. approximately 100 restricts small-scale disturbances, resulting missed delay up 17.8 days solely data. Combining Sentinel-1-based resulted timeliness, average improvement 16.5 Furthermore, we observed rates our ScanSAR-based those JICA-JAXA Early Warning System Tropics (JJ-FAST) alerting product. This suggests that operational monitoring systems not currently fully realized. Comparing SAR-based from this study existing optical-based products (GFC GLAD-L) suggested accuracies sensor-specific omission errors when optical demonstrated improving efforts radar satellites expected be amplified upcoming satellite missions like NiSAR (2024) ROSE-L (2028), which will provide resolution.

Language: Английский

Citations

2
Due Diligence for Deforestation-Free Supply Chains with Copernicus Sentinel-2 Imagery and Machine Learning DOI Open Access

Ivan Reading,

Konstantina Bika,

Toby Drakesmith

et al.

Forests, Journal Year: 2024, Volume and Issue: 15(4), P. 617 - 617

Published: March 28, 2024

At COP26, the Glasgow Leaders Declaration committed to ending deforestation by 2030. Implementing deforestation-free supply chains is of growing importance importers and exporters but challenging due complexity for agricultural commodities which are driving tropical deforestation. Monitoring tools needed that alert companies forest losses around their source farms. ForestMind has developed compliance monitoring chains. The system delivers reports based on automated satellite image analysis loss We describe an algorithm Python Earth Observation (PyEO) package deliver near-real-time alerts from Sentinel-2 imagery machine learning. A Forest Analyst interprets multi-layer raster analyst report creates company conclude extension PyEO with its hybrid change detection a random model NDVI differencing produces actionable farm-scale in support EU Deforestation Regulation. user accuracy was 96.5% Guatemala 93.5% Brazil. provides operational insights into farms countries imported.

Language: Английский

Citations

1