Assessment of Six Machine Learning Methods for Predicting Gross Primary Productivity in Grassland DOI Creative Commons
Hao Wang, Wei Shao, Dafang Zhuang

et al.

Remote Sensing, Journal Year: 2023, Volume and Issue: 15(14), P. 3475 - 3475

Published: July 10, 2023

Grassland gross primary productivity (GPP) is an important part of global terrestrial carbon flux, and its accurate simulation future prediction play role in understanding the ecosystem cycle. Machine learning has potential large-scale GPP prediction, but application accuracy impact factors still need further research. This paper takes Mongolian Plateau as research area. Six machine methods (multilayer perception, random forest, Adaboost, gradient boosting decision tree, XGBoost, LightGBM) were trained using remote sensing data (MODIS GPP) 14 factor carried out grassland GPP. Then, flux observation (positions stations) non-flux reference data, detailed evaluation comprehensive trade-offs are on results, key affecting performance explored. The results show that: (1) six highly consistent with change tendency demonstrating applicability prediction. (2) LightGBM best overall performance, small absolute error (mean less than 1.3), low degree deviation (root mean square 3.2), strong model reliability (relative percentage difference more 5.9), a high fit (regression determination coefficient 0.97), closest to bias only −0.034). (3) Enhanced vegetation index, normalized precipitation, land use/land cover, maximum air temperature, evapotranspiration, evapotranspiration significantly higher other determining factors, total contribution ratio exceeds 95%. They main influencing study can provide for also support

Language: Английский

Drought legacies and ecosystem responses to subsequent drought DOI
Lena Müller, Michael Bahn

Global Change Biology, Journal Year: 2022, Volume and Issue: 28(17), P. 5086 - 5103

Published: May 24, 2022

Climate change is expected to increase the frequency and severity of droughts. These events, which can cause significant perturbations terrestrial ecosystems potentially long-term impacts on ecosystem structure functioning after drought has subsided are often called 'drought legacies'. While immediate effects have been comparatively well characterized, our broader understanding legacies just emerging. Drought relate all aspects functioning, involving changes at species community scale as alterations soil properties. This consequences for responses subsequent drought. Here, we synthesize current knowledge underlying mechanisms. We highlight relevance legacy duration different processes using examples carbon cycling composition. present hypotheses characterizing how intrinsic (i.e. biotic abiotic properties processes) extrinsic timing, severity, frequency) factors could alter resilience trajectories under scenarios recurrent events. propose ways improving their implications needed assess longer-term droughts functioning.

Language: Английский

Citations

190
Drought trigger thresholds for different levels of vegetation loss in China and their dynamics DOI

Wenwen Guo,

Shengzhi Huang,

Qiang Huang

et al.

Agricultural and Forest Meteorology, Journal Year: 2023, Volume and Issue: 331, P. 109349 - 109349

Published: Jan. 31, 2023

Language: Английский

Citations

70
Evaluating the cumulative and time-lag effects of vegetation response to drought in Central Asia under changing environments DOI
Shixian Xu, Yonghui Wang, Yuan Liu

et al.

Journal of Hydrology, Journal Year: 2023, Volume and Issue: 627, P. 130455 - 130455

Published: Nov. 11, 2023

Language: Английский

Citations

56
Vapor pressure deficit (VPD) downscaling based on multi-source remote sensing, in-situ observation, and machine learning in China DOI Creative Commons
Mi Wang, Zhuowei Hu, Xiangping Liu

et al.

Journal of Hydrology Regional Studies, Journal Year: 2025, Volume and Issue: 57, P. 102192 - 102192

Published: Jan. 13, 2025

Language: Английский

Citations

3
Drought-related cumulative and time-lag effects on vegetation dynamics across the Yellow River Basin, China DOI Creative Commons

Cun Zhan,

Chuan Liang,

Lu Zhao

et al.

Ecological Indicators, Journal Year: 2022, Volume and Issue: 143, P. 109409 - 109409

Published: Sept. 7, 2022

Yellow River Basin (YRB), a climate-sensitive and ecologically compromised area in China, is increasingly affected by extreme climate events (especially droughts) resulting from change frequent human activity. Vegetation responds asymmetrically to drought with cumulative time-lag effects, whereas response across various climatic zones diverse vegetation types the YRB remains unclear. To address this deficiency, we examined spatiotemporal patterns of accumulated lagged effects on dynamics for period 1982 2015. The examination was based long-term Normalized Difference Index (NDVI) multiscale dataset Standardized Precipitation Evapotranspiration (SPEI). Cumulative (time-lag) were determined via maximum correlation between NDVI one- 12-month timescale SPEI (one-month SPEI), as well corresponding months optimal drought. main findings follows: (1) Accumulated significantly approximately 50% 60% vegetated YRB, respectively, strongest varying types. (2) In general, arid zone tended be more sensitive resistant drought, evidenced occurrence mostly short-term (one–three months) medium-term (six–eight months), respectively. This finding may related vegetation's strategy coping water deficits. (3) biome-level grassland cultivated stronger than those forests, which associated differences functional characteristics root systems. (4) Annual availability responded droughts multiple timescales, coefficients decreasing increasing average annual SPEI. These results indicate that areas low susceptible droughts. (5) Independent or type, cumulatively effects. study improves knowledge climate–vegetation relationships provides theoretical support addressing risk changing climate.

Language: Английский

Citations

57
Increased Sensitivity of Global Vegetation Productivity to Drought Over the Recent Three Decades DOI

Xiaonan Wei,

Wei He, Yanlian Zhou

et al.

Journal of Geophysical Research Atmospheres, Journal Year: 2023, Volume and Issue: 128(7)

Published: March 27, 2023

Abstract Intensified droughts have been weakening global vegetation productivity, yet how the sensitivity of productivity to drought changes over time is not well known. Here, using simulated long‐term gross primary production (GPP) with an improved two‐leaf light use efficiency model and Standardized Precipitation Evapotranspiration Index (SPEI), we studied drought, quantified by corresponding scale SPEI strongest impact on GPP, analyzed in two periods (1993–2005 2006–2018). Compared first period, were more widespread severer around world second as evidenced increased range (increased 4.43%) intensity (SPEI03 decreased 103%). Globally, area significant correlation between GPP 25.53%, 14.75%, enhanced 13.76%; changing directions pretty similar across various types, mostly showing increasing trend. Moreover, regions consistently decreasing moisture was affected most strongly experienced greatest change (enhanced 10.99%), indicating that arid semi‐arid ecosystems should be considered a research priority future. Our results reveal strengthened recent decades climate transition regions, which could improve our understanding behavior fate terrestrial climate.

Language: Английский

Citations

41
Influence of drought duration and severity on drought recovery period for different land cover types: evaluation using MODIS-based indices DOI Creative Commons
Amin Fathi-Taperasht, Hossein Shafizadeh‐Moghadam, Masoud Minaei

et al.

Ecological Indicators, Journal Year: 2022, Volume and Issue: 141, P. 109146 - 109146

Published: July 9, 2022

Drought is a slow-onset phenomenon driven by the lack of precipitation, affecting performance plants and functionality terrestrial ecosystems. In addition to length severity drought, period it takes for return normal conditions critical. Remote sensing data with appropriate spatial temporal coverage facilitates monitoring drought its consequences on local global scales. This study investigated influence duration recovery (DRP) different land use cover (LULC) types in Iran. The moderate resolution imaging spectroradiometer (MODIS)-based vegetation health index (VHI) was used monitor 2000–2020. results identified 2000, 2001, 2008 as years. DRP estimated using gross primary productivity (GPP). findings revealed that shrubland cropland experienced more prolonged droughts than forests, which shortest duration. Similarly, shrublands croplands had most recovery, forests time. A direct relationship observed between all LULC types, however correlation time better heterogeneity relationships. provides valuable information resilience achieving management deeper understanding drought.

Language: Английский

Citations

39
Grassland cover dynamics and their relationship with climatic factors in China from 1982 to 2021 DOI
Liang Liu,

Jianghua Zheng,

Jingyun Guan

et al.

The Science of The Total Environment, Journal Year: 2023, Volume and Issue: 905, P. 167067 - 167067

Published: Sept. 17, 2023

Language: Английский

Citations

31
Cumulative effects of drought have an impact on net primary productivity stability in Central Asian grasslands DOI
Liang Liu, Jingyun Guan,

Jianghua Zheng

et al.

Journal of Environmental Management, Journal Year: 2023, Volume and Issue: 344, P. 118734 - 118734

Published: Aug. 10, 2023

Language: Английский

Citations

27
Quantitatively analyzing the driving factors of vegetation change in China: Climate change and human activities DOI Creative Commons
Yang Chen, Tingbin Zhang, Xuan Zhu

et al.

Ecological Informatics, Journal Year: 2024, Volume and Issue: 82, P. 102667 - 102667

Published: June 5, 2024

Understanding the impact of climate change and human activities on vegetation dynamics is crucial for ecosystem management. Employing Residual Trend method integrating Normalized Difference Vegetation Index (NDVI) data with land use/cover, this study assesses impacts across China from 2000 to 2018. The findings indicate a consistent upward trend China's Growing Season NDVI (GSN), averaging rate 0.0032/yr. Human are primary drivers change, contributing 82.47% GSN in China, while accounts 17.53%. effect showed considerable variation different river basins, Huaihe River Basin experiencing highest (93.53%) Continental lowest (76.27%). Conversely, experienced greatest (23.73%), compared minimal influence (6.47%). results offer contribution rates each type changed unchanged use, persistent forestland, grassland, cropland, grassland forest conversion 28.65%, 22.09%, 13.76%, 4.61%, respectively. Persistent forestland emerges as most efficacious use facilitating restoration. Within forestlands Yangtze, Pearl, Southeast Basins, accounted 26.99%, 42.18%, 43.50% alterations, These provide scientific basis formulating effective management protection strategies.

Language: Английский

Citations

15