Using Bi-Temporal Lidar to Evaluate Canopy Structure and Ecotone Influence on Landsat Vegetation Index Trends Within a Boreal Wetland Complex

Applied Sciences, Journal Year: 2025, Volume and Issue: 15(9), P. 4653 - 4653

Published: April 23, 2025

Wetland ecosystems are sensitive to climate variation, yet tracking vegetation type and structure changes through time remains a challenge. This study examines how Landsat-derived indices (NDVI EVI) correspond with lidar-derived canopy height model (CHM) from 2000 2018 across the wetland landscape of Peace–Athabasca Delta (PAD), Canada. By comparing CHM change NDVI EVI trends woody herbaceous land covers, this fills gap in understanding long-term responses northern wetlands. Findings show that ~35% area experienced growth, while 2% saw reduction height. revealed 11% ecotonal expansion, where shrub treed swamps encroached on meadow marsh areas. correlated significantly (p < 0.001) CHM, particularly (r2 = 0.40, 0.35) upland forests r2 0.37). However, aligned more strongly captured mature tree growth drying, indicated by rising surface temperatures (LST). These results highlight contrasting EVI—NDVI being moisture-related such as aligning closely structural changes—emphasizing value combining lidar satellite monitor warming climate.

Language: Английский

---

A Summary of Recent Advances in the Literature on Machine Learning Techniques for Remote Sensing of Groundwater Dependent Ecosystems (GDEs) from Space

Remote Sensing, Journal Year: 2025, Volume and Issue: 17(8), P. 1460 - 1460

Published: April 19, 2025

While groundwater-dependent ecosystems (GDEs) occupy only a small portion of the Earth’s surface, they hold significant ecological value by providing essential ecosystem services such as habitat for flora and fauna, carbon sequestration, erosion control. However, GDE functionality is increasingly threatened human activities, rainfall variability, climate change. To address these challenges, various methods have been developed to assess, monitor, understand GDEs, aiding sustainable decision-making conservation policy implementation. Among these, remote sensing advanced machine learning (ML) techniques emerged key tools improving evaluation dryland GDEs. This study provides comprehensive overview progress made in applying ML algorithms assess monitor It begins with systematic literature review following PRISMA framework, followed an analysis temporal geographic trends applications research. Additionally, it explores different their across types. The paper also discusses challenges mapping GDEs proposes mitigation strategies. Despite promise studies, field remains its early stages, most research concentrated China, USA, Germany. enable high-quality classification at local global scales, model performance highly dependent on data availability quality. Overall, findings underscore growing importance potential geospatial approaches generating spatially explicit information Future should focus enhancing models through hybrid transformative techniques, well fostering interdisciplinary collaboration between ecologists computer scientists improve development result interpretability. insights presented this will help guide future efforts contribute improved management

Language: Английский

---

Evaluation of ICESat-2 Laser Altimetry for Inland Water Level Monitoring: A Case Study of Canadian Lakes

Water, Journal Year: 2025, Volume and Issue: 17(7), P. 1098 - 1098

Published: April 6, 2025

This study evaluates the performance of ICESat-2 ATL13 altimetry product for estimating water levels in 182 Canadian lakes by integrating satellite-derived observations with situ gauge measurements and applying spatial filtering using HydroLAKES dataset. The analysis compares ATL13-derived lake surface elevations hydrometric data from national monitoring stations, providing a robust framework assessing measurement accuracy. Statistical metrics—including root mean square error (RMSE), absolute (MAE), bias (MBE)—are employed to quantify discrepancies between datasets. Importantly, application HydroLAKES-based reduces RMSE 1.53 m 1.40 m, further exclusion high-error lowers it 0.96 m. Larger deeper exhibit lower margins, while smaller complex shorelines show greater variability. Regression confirms excellent agreement satellite (R2 = 0.9999; Pearson’s r 0.9999, n lakes, p < 0.0001). Temporal trends reveal declining 134 increasing 48 2018 2024, potentially reflecting climatic variability human influence. These findings highlight potential utility large-scale inland when combined techniques such as HydroLAKES.

Language: Английский

---