Estimating mean groundwater levels in peatlands using a Bayesian belief network approach with remote sensing data DOI Creative Commons
Marta Stachowicz, Piotr Banaszuk, Pouya Ghezelayagh

et al.

Scientific Review Engineering and Environmental Sciences (SREES), Journal Year: 2024, Volume and Issue: unknown, P. 1 - 21

Published: Oct. 29, 2024

Large-scale management, protection, and restoration of wetlands require knowledge their hydrology, i.e., the status dynamics groundwater table, which determine evolution wetland ecosystem, its conservation value, possible economic use. Unfortunately, in many cases, hydrological monitoring data are unavailable, resulting search for a proxy average annual depth level (GWL). This study presents an approach to estimating mean GWL peatlands using Bayesian belief network (BBN) model, leveraging long-term remote sensing Biebrza National Park Poland. The employed includes synthetic aperture radar (SAR) backscatter coefficient, peat subsidence, rate distance watercourses. BBN model achieved predictive accuracy 83.3% 73.1%, depending on validation used. Among variables considered, SAR coefficient was most sensitive predicting peatlands. However, multiple uncertainties from limitations available data, low variability class combinations conditional probability lack upscaling other regions performed. Despite these uncertainties, developed remains valuable next step reaching goal efficient peatland management.

Language: Английский

High-resolution mapping of peatland CO2 fluxes using drone multispectral images DOI Creative Commons
Romain Walcker,

Clara Le Lay,

Laure Gandois

et al.

Ecological Informatics, Journal Year: 2025, Volume and Issue: unknown, P. 103060 - 103060

Published: Jan. 1, 2025

Language: Английский

Citations

0
Monitoring of Incipient Habitat Deterioration in Small Temperate Mires Using Aerial and Satellite Imagery: Verification Using Ground-Based Vegetation Data DOI
Lubomír Tichý, Patrícia Singh, Petra Hájková

et al.

Published: Jan. 1, 2025

Language: Английский

Citations

0
CMKD-Net: A Cross-Modal Knowledge Distillation Method for Remote Sensing Image Classification DOI
Huaxiang Song, Junping Xie, Yingying Duan

et al.

Advances in Space Research, Journal Year: 2025, Volume and Issue: unknown

Published: April 1, 2025

Language: Английский

Citations

0
Estimating mean groundwater levels in peatlands using a Bayesian belief network approach with remote sensing data DOI Creative Commons
Marta Stachowicz, Piotr Banaszuk, Pouya Ghezelayagh

et al.

Scientific Review Engineering and Environmental Sciences (SREES), Journal Year: 2024, Volume and Issue: unknown, P. 1 - 21

Published: Oct. 29, 2024

Large-scale management, protection, and restoration of wetlands require knowledge their hydrology, i.e., the status dynamics groundwater table, which determine evolution wetland ecosystem, its conservation value, possible economic use. Unfortunately, in many cases, hydrological monitoring data are unavailable, resulting search for a proxy average annual depth level (GWL). This study presents an approach to estimating mean GWL peatlands using Bayesian belief network (BBN) model, leveraging long-term remote sensing Biebrza National Park Poland. The employed includes synthetic aperture radar (SAR) backscatter coefficient, peat subsidence, rate distance watercourses. BBN model achieved predictive accuracy 83.3% 73.1%, depending on validation used. Among variables considered, SAR coefficient was most sensitive predicting peatlands. However, multiple uncertainties from limitations available data, low variability class combinations conditional probability lack upscaling other regions performed. Despite these uncertainties, developed remains valuable next step reaching goal efficient peatland management.

Language: Английский

Citations

2