Land cover classification algorithm based on multi-modal collaboration and boundary-guided fusion DOI

Yanliang Zhang,

Jingyu Wang, Baohua Zhang

et al.

Journal of Applied Remote Sensing, Journal Year: 2024, Volume and Issue: 18(04)

Published: Nov. 19, 2024

The semantic imbalance of class boundary areas is a key factor in decreasing the classification accuracy remote sensing land cover algorithm. We propose multi-source image segmentation network based on multi-modal collaboration and boundary-guided fusion (BGF). BGF module uses information as restriction condition, embeds alignment strategies into encoder, enhances deep features each mode. On this basis, guidance strategy used to assign different weights internal area category guide feature fusion. Furthermore, reduce impact heterogeneity fusion, cross-modal collaborative constructed associate complementary between fully explore relationship images from both spatial channel domains. comparative experiments were conducted with representative algorithms WHU-OPT-SAR data set. experimental results show that proposed method has increased mean intersection over union overall indicators by 3.3% 2.2%, respectively, compared MCANet, especially road merger ratio 10.0% MCANet. proved effectiveness model.

Language: Английский

Reconstructing daytime and nighttime MODIS land surface temperature in desert areas using multi-channel singular spectrum analysis DOI Creative Commons
Fahime Arabi Aliabad, Mohammad Zare, Hamid Reza Ghafarian Malamiri

et al.

Ecological Informatics, Journal Year: 2024, Volume and Issue: unknown, P. 102830 - 102830

Published: Sept. 1, 2024

Language: Английский

Citations

6
Estimating Reactivation Times and Velocities of Slow-Moving Landslides via PS-InSAR and Their Relationship with Precipitation in Central Italy DOI Creative Commons
Ebrahim Ghaderpour, Claudia Masciulli, Marta Zocchi

et al.

Remote Sensing, Journal Year: 2024, Volume and Issue: 16(16), P. 3055 - 3055

Published: Aug. 20, 2024

Monitoring slow-moving landslides is a crucial task for socioeconomic risk prevention and/or mitigation. Persistent scatterer interferometric synthetic aperture radar (PS-InSAR) an advanced remote sensing method monitoring ground deformation. In this research, PS-InSAR time series derived from COSMO-SkyMed (descending orbit) and Sentinel-1 (ascending are analyzed region in Central Apennines Italy. The sequential turning point detection (STPD) implemented to detect the trend dates their directions within areas of interest susceptible landslides. monthly maps significant points years 2018, 2019, 2020, 2021 produced classified four Italian administrative regions, namely, Marche, Umbria, Abruzzo, Lazio. Monthly global precipitation measurement (GPM) images at 0.1∘×0.1∘ spatial resolution local also by STPD investigate when rate has changed how they might have reactivated Generally, strong correlation (r≥0.7) observed between GPM (satellite-based) (station-based) with similar results. Marche Abruzzo (the coastal regions) insignificant while Umbria Lazio increase 2017 2023. regions exhibit relatively lower amounts. results indicate accumulated displacement series, especially during summer fall where more change observed. findings study may guide stakeholders responsible authorities management mitigating damage infrastructures.

Language: Английский

Citations

4
Mid-Spine Belt of Beautiful China: future reversal of increasing vegetation greening in response to an evolving environment DOI Creative Commons
Jing Fu,

Baoling Su,

Jianxin Qin

et al.

International Journal of Digital Earth, Journal Year: 2025, Volume and Issue: 18(1)

Published: Jan. 7, 2025

SDG15 emphasizes the criticality of ecosystem sustainability. The interplay between vegetation and environment plays a crucial role in maintaining ecological equilibrium. Mid-Spine Belt Beautiful China (MSBBC), novel geographical designation, encompasses agro-pastoral production living spaces China. However, dynamics area remain incompletely characterized. Therefore, this study investigated spatiotemporal variations NDVI MSBBC from 2000 to 2022, introducing V-statistic simulate durations future trends. Since 2000, majority has experienced improvement, with significant enhancement observed 77.34% area. This trend is primarily driven by increased precipitation wind speed under climate warming, coupled afforestation efforts reduced livestock populations. Conversely, areas presenting degradation account for only 1.07% total, mainly due urbanization economic progress, partially explained decreased sunshine duration relative humidity. Evidently, China's long-standing commitment environmental preservation restoration greatly mitigated degradation. Importantly, greening projected stagnate over next decade. These findings deepen our understanding influenced climatic anthropogenic factors provide valuable reference devising innovative approaches remote sensing time series predictions.

Language: Английский

Citations

0
Modeling soil heat flux from MODIS products for arid regions DOI Creative Commons
Fahime Arabi Aliabad, Ebrahim Ghaderpour

Ecological Informatics, Journal Year: 2025, Volume and Issue: unknown, P. 103005 - 103005

Published: Jan. 1, 2025

Language: Английский

Citations

0
Land use cover changes abated terrestrial ecosystem carbon sink in China during the past four decades DOI Creative Commons

Xueqing Jiang,

Jinxun Liu, Changhui Peng

et al.

All Earth, Journal Year: 2025, Volume and Issue: 37(1), P. 1 - 14

Published: Jan. 15, 2025

Changes in land use and cover can strongly affect terrestrial carbon balance, which turn the calculation of sinks that will keep future temperature within desired limits. Understanding how changes influence is challenging. Here, we simulated net balance across China with full consideration between 1981 2020 using dynamic global vegetation model. The results indicated sink ecosystem have grown steadily particularly since 2001, average values primary productivity, productivity biome were 3317 TgC • yr−1, 325 yr−1 70 yr−1. However, during period, cumulatively reduced by 1,353.00 TgC, 1,290.71 226.93 TgC. Land created a source effect abated 1981. Our findings may help guide policies to regulate order achieve neutrality future.

Language: Английский

Citations

0
Time series trend detection and forecasting of SUHI in Tabriz, Iran DOI

Mohammad Ali Koushesh Vatan,

Mohammad Nemati,

Aliihsan Şekertekin

et al.

Urban Climate, Journal Year: 2025, Volume and Issue: 59, P. 102321 - 102321

Published: Jan. 29, 2025

Language: Английский

Citations

0
Land Use and Land Cover Classification for Change Detection Studies Using Convolutional Neural Network DOI Creative Commons

V Pushpalatha,

P. Mallikarjuna,

H N Mahendra

et al.

Applied Computing and Geosciences, Journal Year: 2025, Volume and Issue: unknown, P. 100227 - 100227

Published: Jan. 1, 2025

Language: Английский

Citations

0
Enhancing Climate Resilience: A Data-Driven North Rift Weather Prediction System for Real-Time Forecasting and Agricultural Decision Support DOI Creative Commons
John W. Makokha, Peter Wawire Barasa, Geoffrey W. Khamala

et al.

Heliyon, Journal Year: 2025, Volume and Issue: 11(4), P. e42549 - e42549

Published: Feb. 1, 2025

Highlights•XGBoost Boosts NRWPS: NDVI and BSI integration improves predictive accuracy.•Comprehensive Monitoring: NRWPS integrates environmental data for land management.•Climate Impacts Vegetation: Post-2000 temperature rise causes loss; rainfall aids recovery.•Land Degradation Effect: Rising BSI, declining indicate soil exposure, vegetation loss.•Sustainability & Resilience: supports adaptation, food security, conservation.AbstractThis study presents the development of models Normalized Difference Vegetation Index (NDVI) Bare Soil (BSI) using XGBoost algorithm within North Rift Weather Prediction System (NRWPS) to enhance ecosystem monitoring in Kenya's region. Trained on a comprehensive dataset spanning 1995 2020, which includes precipitation (from Climate Hazards Group InfraRed Precipitation with Station (CHIRPS)), (TerraClimate), historical (Landsat 4-5 Thematic Mapper 2013) Landsat 7 Enhanced plus (ETM+) 2014 2020)), (SoilGrids) data, effectively capture complex relationships between factors health. The model achieved an MSE 0.029, MAE 0.019, R-squared score 0.93, while yielded 0.002, 0.024, 0.945. These results demonstrate models' strong accuracy, enabling precise assessments health bare exposure. By analyzing temporal variations degradation from identifies significant inverse relationship where increasing exposure corresponds analysis also reveals that climatic particularly (minimum maximum) play critical role shaping these trends, high temperatures after 2000 associated reduced NDVI, regions higher show healthier lower BSI. successful provides opportunities informing management strategies, conservation efforts, agricultural practices, data-driven decision-making. Moreover, its into larger decision support systems allows proactive interventions mitigate climate change stressors. This emphasizes importance sustainable land-use practices adaptation strategies preserve manage vulnerabilities wake regional region most affected.

Language: Английский

Citations

0
Adaptive meta-modeling of evapotranspiration in arid agricultural regions of Saudi Arabia using climatic factors, drought indices and MODIS data DOI
Osama Elsherbiny, Salah Elsayed, Obaid Aldosari

et al.

Journal of Hydrology Regional Studies, Journal Year: 2025, Volume and Issue: 59, P. 102279 - 102279

Published: March 17, 2025

Language: Английский

Citations

0
Land surface temperature variability and climate change assessment for Ludhiana’s tehsils using google earth engine DOI
Aarti Kochhar,

Shashikant Patel,

Ritika Gupta

et al.

Theoretical and Applied Climatology, Journal Year: 2025, Volume and Issue: 156(4)

Published: April 1, 2025

Language: Английский

Citations

0