GWL_FCS30: a global 30 m wetland map with a fine classification system using multi-sourced and time-series remote sensing imagery in 2020

Earth system science data, Journal Year: 2023, Volume and Issue: 15(1), P. 265 - 293

Published: Jan. 17, 2023

Abstract. Wetlands, often called the “kidneys of earth”, play an important role in maintaining ecological balance, conserving water resources, replenishing groundwater and controlling soil erosion. Wetland mapping is very challenging because its complicated temporal dynamics large spatial spectral heterogeneity. An accurate global 30 m wetland dataset that can simultaneously cover inland coastal zones lacking. This study proposes a novel method for by combining automatic sample extraction method, existing multi-sourced products, satellite time-series images stratified classification strategy. approach allowed generation first map with fine system (GWL_FCS30), including five sub-categories (permanent water, swamp, marsh, flooded flat saline) three tidal (mangrove, salt marsh flats), which was developed using Google Earth Engine platform. We combined expert knowledge, training refinement rules visual interpretation to generate geographically distributed samples. Second, we integrated Landsat reflectance products Sentinel-1 synthetic aperture radar (SAR) imagery various water-level phenological information capture heterogeneity wetlands. Third, applied strategy local adaptive random forest models produce at each 5∘×5∘geographical tile 2020. Lastly, GWL_FCS30, mosaicked 961 5∘×5∘ regional maps, validated 25 708 validation samples, achieved overall accuracy 86.44 % kappa coefficient 0.822. The cross-comparisons other demonstrated GWL_FCS30 performed better capturing patterns wetlands had significant advantages over diversity sub-categories. statistical analysis showed area reached 6.38 million km2, 6.03 km2 0.35 wetlands, approximately 72.96 were poleward 40∘ N. Therefore, conclude proposed suitable large-area product has potential provide vital support management. 2020 freely available https://doi.org/10.5281/zenodo.7340516 (Liu et al., 2022).

Language: Английский

---

GLC_FCS30D: the first global 30 m land-cover dynamics monitoring product with a fine classification system for the period from 1985 to 2022 generated using dense-time-series Landsat imagery and the continuous change-detection method

Earth system science data, Journal Year: 2024, Volume and Issue: 16(3), P. 1353 - 1381

Published: March 15, 2024

Abstract. Land-cover change has been identified as an important cause or driving force of global climate and is a significant research topic. Over the past few decades, land-cover mapping progressed; however, long-time-series land-cover-change monitoring data are still sparse, especially those at 30 m resolution. In this study, we describe GLC_FCS30D, novel dynamics dataset containing 35 subcategories covering period 1985–2022 in 26 time steps (maps were updated every 5 years before 2000 annually after 2000). GLC_FCS30D developed using continuous detection all available Landsat imagery based on Google Earth Engine platform. Specifically, first take advantage change-detection model full series observations to capture points changed pixels identify temporally stable areas. Then, apply spatiotemporal refinement method derive globally distributed high-confidence training samples from these Next, local adaptive classification models used update information for pixels, temporal-consistency optimization algorithm adopted improve their temporal stability suppress some false changes. Further, product validated 84 526 validation 2020. It achieves overall accuracy 80.88 % (±0.27 %) basic system (10 major types) 73.04 (±0.30 LCCS (Land Cover Classification System) level-1 (17 types). Meanwhile, two third-party time-series datasets United States Europe Union also collected analyzing variations, results show that offers terms variation across mean accuracies 79.50 (±0.50 81.91 (±0.09 over regions. Lastly, draw conclusions about dataset; namely, forest cropland variations have dominated 37 years, net loss forests reached 2.5 million km2, gain area approximately 1.3 km2. Therefore, accurate land-cover-dynamics benefits its diverse system, high spatial resolution, long span (1985–2022); thus, it will effectively support promote sustainable development analysis. The via https://doi.org/10.5281/zenodo.8239305 (Liu et al., 2023).

Language: Английский

---

A review of regional and Global scale Land Use/Land Cover (LULC) mapping products generated from satellite remote sensing

ISPRS Journal of Photogrammetry and Remote Sensing, Journal Year: 2023, Volume and Issue: 206, P. 311 - 334

Published: Nov. 28, 2023

Language: Английский

---

Mapping and classification of Liao River Delta coastal wetland based on time series and multi-source GaoFen images using stacking ensemble model

Ecological Informatics, Journal Year: 2024, Volume and Issue: 80, P. 102488 - 102488

Published: Jan. 20, 2024

Language: Английский

---

Global annual wetland dataset at 30 m with a fine classification system from 2000 to 2022

Scientific Data, Journal Year: 2024, Volume and Issue: 11(1)

Published: March 23, 2024

Abstract Wetlands play a key role in maintaining ecological balance and climate regulation. However, due to the complex variable spectral characteristics of wetlands, there are no publicly available global 30-meter time-series wetland dynamic datasets at present. In this study, we present novel 30 m annual maps (GWL_FCS30D) using Landsat imagery on Google Earth Engine platform, covering period 2000–2022 containing eight subcategories. Specifically, make full use our prior globally distributed training sample pool, adopt local adaptive classification spatiotemporal consistency checking algorithm generate maps. The GWL_FCS30D were found achieve an overall accuracy Kappa coefficient 86.95 ± 0.44% 0.822, respectively, 2020, show great temporal variability United States European Union. We expect dataset would provide vital support for ecosystems protection sustainable development.

Language: Английский

---

Coastal wetland degradation and ecosystem service value change in the Yellow River Delta, China

Global Ecology and Conservation, Journal Year: 2023, Volume and Issue: 44, P. e02501 - e02501

Published: May 7, 2023

The characteristics of changes in wetlands different coastal areas vary, so it is necessary to select representative experimental research wetland degradation, ecosystem service values (ESVs) and differences among various types ecological function fields. goal this study better realize the spatiotemporal degradation ESV order balance economic advancement protection. evolution ESVs was analyzed by using equivalent correction technique contribution degree. random forest (RF) classification model utilized extract information Yellow River Delta (YRD) four years (1990, 2000, 2010, 2020). Thoroughly exploring mechanism impact proposing reasonable suggestions based on a close combination services are conducive healthy development global wetlands. results demonstrated that total area expanded from 1459.5 km2 1990–1975.5 2020, an increase 28.5 %, with artificial increasing 151.4 1059.1 natural decreasing 1308.1 916.5 km2. increased 18.4 billion USD 1990–28.6 2020. transformation between tended ESV, while constructed reduced ESV. tidal flats herbaceous have great value terms not only hydrological regulation but also gene diversity climate regulation. significant cause functions promote Wetland protection, restoration, reconstruction, rational utilization must be incorporated into urban land planning, parks protection zones should established according local conditions. This above can provide typical examples references for sustainable development.

Language: Английский

---

Vegetation Classification and Evaluation of Yancheng Coastal Wetlands Based on Random Forest Algorithm from Sentinel-2 Images

Remote Sensing, Journal Year: 2024, Volume and Issue: 16(7), P. 1124 - 1124

Published: March 22, 2024

The identification of wetland vegetation is essential for environmental protection and management as well monitoring wetlands’ health assessing ecosystem services. However, some limitations on classification may be related to remote sensing technology, confusion between plant species, challenges inadequate data accuracy. In this paper, in the Yancheng Coastal Wetlands studied evaluated from Sentinel-2 images based a random forest algorithm. Based consistent time series observations, characteristic patterns were better captured. Firstly, spectral features, indices, phenological characteristics extracted images, products obtained by constructing dense using dataset Google Earth Engine (GEE). Then, machine learning algorithm obtained, with an overall accuracy 95.64% kappa coefficient 0.94. Four indicators (POP, SOS, NDVIre, B12) main contributors importance weight analysis all features. Comparative experiments conducted different results show that method proposed paper has classification.

Language: Английский

---

The distribution of global tidal marshes from Earth observation data

Global Ecology and Biogeography, Journal Year: 2024, Volume and Issue: 33(8)

Published: May 9, 2024

Abstract Aim Tidal marsh ecosystems are heavily impacted by human activities, highlighting a pressing need to address gaps in our knowledge of their distribution. To better understand the global distribution and changes tidal extent, identify opportunities for conservation restoration, it is critical develop spatial base occurrence. Here, we globally consistent map year 2020 at 10‐m resolution. Location Global. Time period 2020. Major taxa studied marshes. Methods location world's marshes resolution, applied random forest classification model Earth observation data from We trained with reference dataset developed support mapping coastal ecosystems, predicted between 60° N S. validated using standard accuracy assessment methods, final having an overall score 0.85. Results estimate extent be 52,880 km 2 (95% CI: 32,030 59,780 ) distributed across 120 countries territories. centred temperate Arctic regions, nearly half occurring Northern Atlantic (45%) region. At national scale, over third (18,510 ; 11,200–20,900) occurs within USA. Main conclusions Our analysis provides most detailed on date shows that occur more greater proportion coastline than previous studies. fills major gap regarding baseline needed measuring estimating value terms ecosystem services.

Language: Английский

---

Remote Data for Mapping and Monitoring Coastal Phenomena and Parameters: A Systematic Review

Remote Sensing, Journal Year: 2024, Volume and Issue: 16(3), P. 446 - 446

Published: Jan. 23, 2024

Since 1971, remote sensing techniques have been used to map and monitor phenomena parameters of the coastal zone. However, updated reviews only considered one phenomenon, parameter, data source, platform, or geographic region. No review has offered an overview that can be accurately mapped monitored with data. This systematic was performed achieve this purpose. A total 15,141 papers published from January 2021 June 2023 were identified. The 1475 most cited screened, 502 eligible included. Web Science Scopus databases searched using all possible combinations between two groups keywords: geographical names in areas platforms. demonstrated that, date, many (103) (39) (e.g., coastline land use cover changes, climate change, urban sprawl). Moreover, authors validated 91% retrieved parameters, 39 1158 times (88% combined together other parameters), 75% over time, 69% several compared results each available products. They obtained 48% different methods, their 17% GIS model techniques. In conclusion, addressed requirements needed more effectively analyze employing integrated approaches: they data, merged

Language: Английский

---

The Water Table Model (WTM) (v2.0.1): coupled groundwater and dynamic lake modelling

Geoscientific model development, Journal Year: 2025, Volume and Issue: 18(5), P. 1463 - 1486

Published: March 10, 2025

Abstract. Ice-free land comprises 26 % of the Earth's surface and holds liquid water that delineates ecosystems, affects global geochemical cycling, modulates sea levels. However, we currently lack capacity to simulate predict these terrestrial changes across full range relevant spatial (watershed global) temporal (monthly millennial) scales. To address this knowledge gap, present Water Table Model (WTM), which integrates coupled components compute dynamic lake groundwater The component solves 2D horizontal flow equation using non-linear solvers from C++ PETSc (Portable, Extensible Toolkit for Scientific Computation) library. makes use Fill–Spill–Merge (FSM) algorithm move into lakes, where it may evaporate or affect flow. In a proof-of-concept application, demonstrate continental-scale capabilities WTM by simulating steady-state climate-driven table day Last Glacial Maximum (LGM; 21 000 calendar years before present) North American continent. During LGM, America stored an additional 14.98 cm sea-level equivalent (SLE) in lakes compared present-day scenario. We compare result other simulations real-world data. Open-source code is available on GitHub Zenodo.

Language: Английский

---