Stochastic Environmental Research and Risk Assessment, Journal Year: 2023, Volume and Issue: 37(10), P. 3987 - 4011
Published: June 19, 2023
Language: Английский
Stochastic Environmental Research and Risk Assessment, Journal Year: 2023, Volume and Issue: 37(10), P. 3987 - 4011
Published: June 19, 2023
Language: Английский
Theoretical and Applied Climatology, Journal Year: 2025, Volume and Issue: 156(2)
Published: Jan. 10, 2025
Language: Английский
Citations
1Engineering Applications of Artificial Intelligence, Journal Year: 2023, Volume and Issue: 124, P. 106550 - 106550
Published: June 12, 2023
Language: Английский
Citations
21Field Crops Research, Journal Year: 2023, Volume and Issue: 302, P. 109057 - 109057
Published: July 25, 2023
Language: Английский
Citations
21Water Resources Research, Journal Year: 2024, Volume and Issue: 60(5)
Published: May 1, 2024
Abstract Droughts are among the most devastating natural hazards, occurring in all regions with different climate conditions. The impacts of droughts result significant damages annually around world. While drought is generally described as a slow‐developing hazardous event, rapidly developing type drought, so‐called flash has been revealed by recent studies. rapid onset and strong intensity require accurate real‐time monitoring. Addressing this issue, Generative Adversarial Network (GAN) developed study to monitor over Contiguous United States (CONUS). GAN contains two models: (a) discriminator (b) generator. architecture employs Markovian discriminator, which emphasizes spatial dependencies, modified U‐Net generator, tuned for optimal performance. To determine best loss function four networks functions, including Mean Absolute Error (MAE), adversarial loss, combination Square (MSE), MAE. Utilizing daily datasets collected from NLDAS‐2 Standardized Soil Moisture Index (SSI) maps, network trained SSI Comparative assessments reveal proposed GAN's superior ability replicate values Naïve models. Evaluation metrics further underscore that successfully identifies both fine‐ coarse‐scale patterns abrupt changes temporal important identification.
Language: Английский
Citations
8Theoretical and Applied Climatology, Journal Year: 2023, Volume and Issue: 155(4), P. 2997 - 3012
Published: Dec. 20, 2023
Language: Английский
Citations
17Ecological Informatics, Journal Year: 2023, Volume and Issue: 78, P. 102386 - 102386
Published: Nov. 25, 2023
Language: Английский
Citations
15Journal of Arid Land, Journal Year: 2024, Volume and Issue: 16(8), P. 1098 - 1117
Published: Aug. 1, 2024
Language: Английский
Citations
6International Journal of Climatology, Journal Year: 2024, Volume and Issue: 44(3), P. 812 - 830
Published: Jan. 9, 2024
Abstract Understanding the spatiotemporal historical drought pattern and their sensitivity effect on potential evapotranspiration (PET) vegetation coverage changes is essential for efficient mitigation policies under climate change. In this study, we used standardized precipitation index (SPEI) at multiple timescales, such as SPEI‐01, SPEI‐03, SPEI‐06, SPEI‐09 SPEI‐12; explored regional‐scale dry wet annual across seven sub‐regions of South Asia from 1902 to 2018. Results suggest that 1981 2018, extreme SPEI has increased in Asia, which mostly affects summer winter growing seasons, is, SPEI‐06 SPEI‐12 Asia. The frequency events during had an extremely year starting 1998 affected region. Data past 18 years showed land changing detection forests, cultivated land, arid savanna farmland; by contrast, there been significantly reduced permanent ice snow, mixed open shrub, grasslands, wetlands, water bodies evergreen broadleaf forests. Seasonal presented diverse characteristics showing a trend Afghanistan, India, Pakistan Sri Lanka autumn winter. Afghanistan Bhutan are compared with other occurring 45.3% 44.4%. Lanka, India driest regions due high frequency, duration intensity. correlation between PET crop stress (CWSI), regional ET p reduction (Er) indicated considerably negative correlation, while positive was found CWSI Er, NDVI Er. This study provides comprehensive assessment PET, SPEI, can help formulating long‐term adaptive strategies reduce cumulative impacts droughts.
Language: Английский
Citations
3Water, Journal Year: 2024, Volume and Issue: 16(11), P. 1466 - 1466
Published: May 21, 2024
Traditional univariate drought indices may not be sufficient to reflect comprehensive information on drought. Therefore, this paper proposes a new composite index that can comprehensively characterize meteorological and hydrological In study, the was established by combining standardized precipitation (SPI) baseflow (SBI) for Jiaojiang River Basin (JRB) using copula function. The prediction model training random forests past data, driving force behind combined explored through LIME algorithm. results show combines advantages of SPI SBI in forecasting. monthly annual droughts JRB showed an increasing trend from 1991 2020, but temporal characteristics changes each subregion were different. accuracies trained forest heavy Baizhiao (BZA) Shaduan (SD) stations 83% 88%, respectively. Furthermore, Local Interpretable Model-Agnostic Explanations (LIME) interpretation identified essential precipitation, baseflow, evapotranspiration features affect This study provides reliable valid multivariate indicators monitoring applied other regions.
Language: Английский
Citations
3Environmental Research Letters, Journal Year: 2024, Volume and Issue: 19(10), P. 104042 - 104042
Published: Aug. 23, 2024
Abstract
Weather
extremes
can
drive
substantial
crop
losses.
Farm-level
management
strategies
play
a
critical
role
in
mitigating
the
impacts
of
and
consequences
for
farmer
livelihoods
food
security.
While
extreme
weather
on
yields
are
well
documented
recent
studies,
these
predominantly
focused
expansive
geographical
scales
commonly
overlooked
practices
modulating
dynamics
weather-crop
sensitivities.
We
fill
this
gap
literature
by
using
unique
dataset
that
explores
timely
relationship
between
at
farm
level
Netherlands.
cover
10
types
crops
elucidate
soil
types,
irrigation
nutrient
application
crops,
estimating
fixed-effects
regression
models.
show
from
drought
during
growing-
harvesting
period
excessive
precipitation
planting-
growing
period.
Severe
droughts
significant
(
Language: Английский
Citations
3