Hydrology and Climate Change Article Summaries

The study finds that canopy temperature is projected to increase significantly more than air temperature over the 21st century due to rising air dryness, implying that current Earth System Models (ESMs) underestimate future constraints on vegetation growth and the land carbon sink.

The study develops a Thermodynamic-Enhanced Physics-Informed Neural Network (TE-PINN) that integrates thermodynamic priors into an LSTM framework to improve the accuracy and physical consistency of soil temperature forecasting. The model effectively reduces error accumulation in long-term predictions and enhances spatial generalization across different latitudes.

The study proposes a multi-source data fusion algorithm for remote sensing image recognition that leverages weakly labeled data and multimodal features to improve fine-grained classification and cross-domain generalization.

The study quantifies the joint influence of urban morphology and background climate on the urban heat island (UHI) effect across 2,213 cities globally, revealing that while denser structures universally increase heat, the climatic drivers vary by region.

This study uses downscaled CMIP6 projections to analyze future drought trends in Australia, identifying significant increases in drought frequency and duration in southern and south-western regions.

This study evaluates a pre-routing, grid-scale runoff bias-correction framework for the GEOGLOWS River Forecast System to improve streamflow simulations in ungauged basins. The approach improves global median KGE from 0.16 to 0.22, with the most significant gains occurring in data-limited regions like South America and Africa.

The study proposes a framework combining machine learning and Monte Carlo simulations to estimate the probability of flood flowrates within hydrographic basins.

This study evaluates how different envelope materials influence the drainage performance of subsurface pipe systems and their effectiveness in regulating water and salt levels in agricultural land.

The study develops a soil moisture threshold-based irrigation strategy (SMTIS) for cotton in Xinjiang, China, using the AquaCrop model and a nonlinear optimization framework. The results demonstrate that SMTIS significantly reduces irrigation water use and increases water productivity and economic benefits under both historical and future climate change scenarios.

The paper proposes the Mask-informed Spectral-temporal Transformer (MISTR), a framework designed to reconstruct missing values in long-term satellite time series (STS) by utilizing mask-informed embeddings and adaptive spectral-temporal blocks.

This study develops an interpretable machine learning framework to assess urban flood susceptibility in Yancheng, China, demonstrating that XGBoost provides the highest predictive accuracy and that flood drivers vary significantly across different geomorphic zones.

This study analyzes the spatiotemporal patterns and drivers of meteorological flash droughts (MFDs) in China from 1980 to 2024, revealing that humid regions are experiencing increasing frequency and accelerated onset despite an overall national decline in MFD frequency.

This study developed a node-based water supply security assessment framework for the Feng River Basin, demonstrating that while basin-wide reliability remains stable, engineering-based water allocation can redistribute and concentrate risks at specific intake nodes during extreme droughts.

The study developed a physically guided deep learning framework integrating Earth observation data and water balance modeling to estimate high-resolution (500 m) irrigation water use (IWU) across China from 2004 to 2019.

This study evaluates the impact of climate change on streamflow and paddy yields in the Bharathapuzha Basin, Kerala, using SWAT and CMIP6 models, predicting significant declines in crop production and altered hydrological regimes by 2100.

The study develops a harmonized global daily solar-induced chlorophyll fluorescence (SIF) product (HSIF) for the period 2003–2023 by integrating data from three satellite platforms using CDF matching and machine learning.

This study evaluates the application of remote sensing and AI in irrigation management for fruit and vegetable crops. The findings indicate that these technologies can enhance water use efficiency by 15–22%.

The study proposes an integrated precision irrigation system combining hyperspectral remote sensing and IoT technology to optimize water management for small-scale farmers in India.

The study develops and applies a Change-Based Drought Severity Index (WCDI) using fused Sentinel-1 and Sentinel-2 satellite data within Google Earth Engine to quantify drought impacts on two wetlands in Central Iran.

The study develops a quantitative identification method for drought–flood abrupt alternation (DFAA) events in the Yellow River Basin (YRB) using SPEI data from 1982 to 2021, revealing an increasing trend in event frequency, particularly in the middle and lower reaches.