Honglin ZHU

Ms. Honglin ZHU


Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
11 July 2023 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
HZHonglin ZHU
Honglin ZHU
HLHuizeng Liu
Huizeng Liu
QZQiming Zhou
Qiming Zhou
ACAihong CUI
Aihong CUI
Extreme precipitation events have caused severe societal, economic and environmental impacts through the disasters of floods, flash-floods and landslides. However, the coarse-resolution of satellite-derived precipitation data makes it difficult to quantitatively capture certain fine-scale heavy rainfall process. Therefore, to improve the spatial resolution and accuracy of satellite-based precipitation extremes, a downscaling-calibration scheme based on eXtreme Gradient Boosting (XGBoost_DC) was proposed in this study, where the XGBoost algorithm was applied in both downscaling and calibration procedures. The performance of XGBoost_DC was evaluated with other two comparative methods, in which XGBoost was only used in either downscaling (XGBoost_Spline) or calibration (Spline_XGBoost) process. The results showed that: (i) XGBoost_DC achieved the best performance, as it obtained the highest accuracy and well reproduced the occurrence and the spatial distribution of precipitation during typhoon events. (ii) XGBoost_DC could capture the spatial variations of the precipitation. Although Spline_XGBoost obtained results only slightly worse than the XGBoost_DC, it significantly underestimated the spatial variability. (iii) the model assessment between the XGBoost_DC and Spline_XGBoost illustrated the essential contribution of XGBoost algorithm in downscaling process, and improved our understanding of the capability of machine learning algorithm in reproducing spatial variance of precipitation. These findings imply that our proposed downscaling-calibration scheme can be applied for generating high-resolution and high-quality precipitation extremes during typhoon events, which would benefit the water and flood management, as well as other various applications in hydrological and meteorological modelling.

18 May 2023 in Remote Sensing
Verified
Journal Article
Open access
PDF file
HZHonglin ZHU
Honglin ZHU
HLHuizeng Liu
Huizeng Liu
Qiming ZhouQiming Zhou
Qiming Zhou
ACAihong CUI
Aihong CUI
Accurate high-spatial-resolution precipitation is significantly important in hydrological and meteorological modelling, especially in rain-gauge-sparse areas. Some methods and strategies have been applied for satellite-based precipitation downscaling, residual correction and precipitation calibration. However, which downscaling scheme can provide reliable high-resolution precipitation efficiently remains unanswered. To address this issue, this study aimed to present a framework combining the machine learning downscaling algorithm and post-process procedures. Firstly, four ML-based models, namely support vector regression, random forest, spatial random forest (SRF) and eXtreme gradient boosting (XGBoost), were tested for downscaling and compared with conventional downscaling methods. Then, the effectiveness of the residual correction process using ordinary Kriging and the calibration process using the geographical difference analysis (GDA) method was investigated. The results showed that the ML-based methods had better performance than the conventional regression and interpolation approaches. The SRF and XGBoost outperformed others in generating accurate precipitation estimation with a high resolution. The GDA calibration process significantly improved the downscaled results. However, the residual correction process decreased the downscaling performance of the ML-based models. Combining the SRF or XGBoost downscaling algorithm with the GDA calibration method could be a promising downscaling scheme for precipitation data. The scheme could be used to generate high-resolution precipitation, especially in areas urgently requiring data, which would benefit regional water resource management and hydrological disaster prevention.

10 March 2024 in Remote Sensing
Verified
Journal Article
Open access
PDF file
ACAihong CUI
Aihong CUI
Jianfeng LiJianfeng Li
Jianfeng Li
Qiming ZhouQiming Zhou
Qiming Zhou
HZHonglin ZHU
Honglin ZHU
HLHuizeng Liu
Huizeng Liu
QLQingquan Li
Qingquan Li
Gaining a comprehensive understanding of the characteristics and propagation of precipitation-based meteorological drought to terrestrial water storage (TWS)-derived hydrological drought is of the utmost importance. This study aims to disentangle the frequency–time relationship between precipitation-derived meteorological and TWS-based hydrological drought from June 2002 to June 2017 based on the Standardized Precipitation Index (SPI) and Standardized Terrestrial Water Storage Index (STI) by employing wavelet coherence rather than a traditional correlation coefficient. The possible influencing factors on drought propagation in 28 regions across the world are examined. The results show that the number of drought months detected by the STI is higher than that detected by the SPI worldwide, especially for slight and moderate drought. Generally, TWS-derived hydrological drought is triggered by and occurs later than precipitation-based meteorological drought. The propagation characteristics between meteorological and hydrological droughts vary by region across the globe. Apparent intra-annual and interannual scales are detected by wavelet analysis in most regions, but not in the polar climate region. Drought propagation differs in phase lags in different regions. The phase lag between hydrological and meteorological drought ranges from 0.5 to 4 months on the intra-annual scale and from 1 to 16 months on the interannual scale. Drought propagation is influenced by multiple factors, among which the El Niño–Southern Oscillation, North Atlantic Oscillation, and potential evapotranspiration are the most influential when considering one, two, or three factors, respectively. The findings of this study improve scientific understanding of drought propagation mechanisms over a global scale and provide support for water management in different subregions.

19 February 2024 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
HZHonglin ZHU
Honglin ZHU
Qiming ZhouQiming Zhou
Qiming Zhou
Improving the spatial resolution of satellite-based precipitation data is crucial in expanding the application of quantitative precipitation estimation. Many machine learning-based techniques have been proposed for the downscaling of satellite-derived precipitation. However, these methods often highly rely on the availability of observation data, posing limitations on their applicability in data-scarce regions. To address this issue, a novel approach based on deep transfer learning (TL) was introduced to improve the precipitation downscaling in data-scarce areas. The proposed framework implemented the fine-tuning to transfer the pre-trained convolutional neural network-based downscaling model from the source domain to two target domains. Results showed that compared with the original satellite data, the correlation coefficient of the downscaled precipitation using fine-tuning increased to 0.715 and 0.622 in the two target domains, respectively. The transferred models with three fine-tuned layers achieved the highest performance, and models with one fine-tuned layer was the most efficient. The simplest transferred models with four frozen layers obtained the worst performance (with CC values of 0.586 and 0.519 in two target domains). By incorporating at least one fine-tunable layer, the TL models demonstrated significant improvements. Meanwhile, the transferred downscaling models had better performance under higher precipitation intensity, and worse for low precipitation intensity. They received more accurate downscaled results during the wet season than the dry season. This study provided a promising transfer leaning-based approach in generating high-resolution precipitation in data-sparse regions, which has great significance to the meteorological, hydrological and ecological research in such areas.

5 December 2023 in ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Verified
Journal Article
Open access
PDF file
HZHonglin ZHU
Honglin ZHU
Qiming ZhouQiming Zhou
Qiming Zhou
ACAihong CUI
Aihong CUI
Precipitation estimation with high accuracy and resolution is crucial for hydrological and meteorological applications, particularly in ungauged river basins and regions with scarce water resources. Many machine learning (ML) algorithms have been employed in the downscaling of precipitation, however, it remains unclear which algorithm can outperform others. To address this issue, this study evaluates the performance of four ML based downscaling methods to generate high-resolution precipitation estimates at an annual scale. The satellite-derived precipitation data, environmental variables, such as, latitude, longitude, normalized difference vegetation index (NDVI), digital elevation model (DEM), and land surface temperature (LST), as well as the observations from rainfall gauges were used to constructed the regression models. The performance of the four ML algorithms including the Support Vector Regression (SVR), Random Forest (RF), Spatial Random Forest (SRF), and Extreme Gradient Boosting (XGBoost) algorithms was compared with three conventional methods: Multiple Linear Regression (MLR), geographically weighted regression (GWR) and Kriging interpolation model. Results showed that ML-based method generally outperformed traditional interpolation methods in precipitation downscaling, as they had higher accuracy and were better at reproducing the spatial distribution of rainfall. Out of ML approaches, XGBoost received the best performance, followed by SRF, RF and SVR, indicating its robustness of capturing nonlinear relationships. After the XGBoost, better performance of SRF than RF and SVR was found. This might be because the SRF just introduced the spatial autocorrelation into the RF models, which illustrated the importance of capturing spatial variations in ML algorithms. These findings regarding the comparison and assessment provided a novel downscaling method for generating high-resolution precipitation data, which could benefit regional flood forecasting, drought monitoring, and irrigation planning.

24 September 2025 in Water Resources Research
Verified
Journal Article
Open access
PDF file
QFQingqing Fang
Qingqing Fang
YXYuding Xia
Yuding Xia
SZShanghong Zhang
Shanghong Zhang
Guoqiang WangGuoqiang Wang
Guoqiang Wang
BXBaolin Xue
Baolin Xue
MSMurugesu Sivapalan
Murugesu Sivapalan
The parsimony of the Budyko water balance model has prompted its extensive use for analyzing climate–vegetation–water interactions. Existence of time–space symmetry in the Budyko model, governing the hydrological predictions across both temporal (short‐term annual) and spatial (long‐term mean annual) domains, has enabled its application in ungauged basins through use of space‐for‐time substitution (SFTS). However, time–space symmetry in the relationship between the Budyko shape parameter and in vegetation changes has not been well studied. The Budyko curve, which varies spatially across regions due to differences of vegetation, also varies temporally as vegetation evolves over time. Here, we investigate this problem in a representative basin with several sub‐catchments, which includes sensitivity to vegetation dynamics and climate change using two shape parameters (n1 and n2) and the vegetation cover, M. Interestingly, time–space symmetry was found between M/Φ and n1/Φ or exp(−n2)/Φ, compared to just M versus n separately (which produces asymmetry), implying a coupled ecohydrological adjustment mechanism between vegetation functioning and hydrological structure co‐regulated in response to climatic constraints counteracting the effects of spatio‐temporal heterogeneity on water balance partitioning. Our study proposes a novel and streamlined ecohydrological model within the time–space equivalence hypothesis and recognizes that the symmetry/asymmetry is crucial for accurate SFTS application.