Kai Liu

Prof. Kai Liu

orcid

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

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

Representative Publications

View All Publications
18 April 2021 in Remote Sensing
Verified
Journal Article
Open access
PDF file
QHQian He
Qian He
ZJZiyu Jiang
Ziyu Jiang
MWMing Wang
Ming Wang
KLKai Liu
Kai Liu
Southeast Asia (SEA) is a region affected by landslide and wildfire; however, few studies on susceptibility modeling for the two hazards together have been conducted for this region, and the intersection and the uncertainty of the two hazards are rarely assessed. Thus, the intersection of landslide and wildfire susceptibility and the spatial uncertainty of the susceptibility maps were studied in this paper. Reliable landslide and wildfire susceptibility maps are necessary for disaster management and land use planning. This work used three advanced ensemble machine learning algorithms: RF (Random Forest), GBDT (Gradient Boosting Decision Tree) and AdaBoost (Adaptive Boosting) to assess the landslide and wildfire susceptibility for SEA. A geo-database was established with 2759 landslide locations, 1633 wildfire locations and 18 predictor variables in total. The performances of the models were assessed using the overall classification accuracy (ACC), Precision, the area under the ROC (receiver operating curve) (AUC) and confusion matrix values. The results showed RF performs superior in both landslide (ACC = 0.81, Precision = 0.78 and AUC= 0.89) and wildfire (ACC= 0.83, Precision = 0.83 and AUC = 0.91) susceptibility modeling, followed by GBDT and AdaBoost. The overall superiority of RF over other models indicates that it is potentially an efficient model for landslide and wildfire susceptibility mapping. The landslide and wildfire susceptibility were obtained using the RF model. This paper also conducted an overlay analysis of the two hazards. The uncertainty of the susceptibility was further assessed using the coefficient of variation (CV). Additionally, the distance to roads is relatively important in both landslide and wildfire susceptibility, which is the most important in landslides and the second most important in wildfires. The result of this paper is useful for mastering the whole situation of hazard susceptibility and proves that RF is a robust model in the hazard susceptibility assessment in SEA.

2 February 2021 in Remote Sensing
Verified
Journal Article
Open access
PDF file
JZJianxin Zhang
Jianxin Zhang
KLKai Liu
Kai Liu
MWMing Wang
Ming Wang
High-resolution and continuous hydrological products have tremendous importance for the prediction of water-related trends and enhancing the capability for sustainable water resources management under climate change and human impacts. In this study, we used the random forest (RF) and extreme gradient boosting (XGBoost) methods to downscale groundwater storage (GWS) from 1° (~110 km) to 1 km by downscaling Gravity Recovery and Climate Experiment (GRACE) and Global Land Data Assimilation System (GLDAS) data from 1° (~110 km) and 0.25° (~25 km) respectively, to 1 km for China. Three evaluation metrics were employed for the testing dataset for 2004−2016: The R2 ranged from 0.77−0.89 for XGBoost (0.74−0.86 for RF), the correlation coefficient (CC) ranged from 0.88−0.94 for XGBoost (0.88−0.93 for RF) and the root-mean-square error (RMSE) ranged from 0.37−2.3 for XGBoost (0.4−2.53 for RF). The R2 of the XGBoost models for GLDAS was 0.64−0.82 (0.63−0.82 for RF), the CC was 0.80−0.91 (0.80−0.90 for RF) and the RMSE was 0.63−1.75 (0.63−1.77 for RF). The downscaled GWS derived from GRACE and GLDAS were validated using in situ measurements by comparing the time series variations and the downscaled products maintained the accuracy of the original data. The interannual changes within 9 river basins between pre- and post-downscaling were consistent, emphasizing the reliability of the downscaled products. Ultimately, annual downscaled TWS, GLDAS and GWS products were provided from 2004 to 2016, providing a solid data foundation for studying local GWS changes, conducting finer-scale hydrological studies and adapting water resources management and policy formulation to local condition.

16 November 2022 in Remote Sensing
Verified
Journal Article
Open access
PDF file
BLBohao Li
Bohao Li
KLKai Liu
Kai Liu
MWMing Wang
Ming Wang
QHQian He
Qian He
ZJZiyu Jiang
Ziyu Jiang
NQNingning Qiao
Ningning Qiao
Precipitation is the main factor that triggers landslides. Rainfall-induced landslide susceptibility mapping (LSM) is crucial for disaster prevention and disaster losses mitigation, though most studies are temporally ambiguous and on a regional scale. To better reveal landslide mechanisms and provide more accurate landslide susceptibility maps for landslide risk assessment and hazard prediction, developing a global dynamic LSM model is essential. In this study, we used Google Earth Engine (GEE) as the main data platform and applied three tree-based ensemble machine learning algorithms to construct global, dynamic rainfall-induced LSM models based on dynamic and static landslide influencing factors. The dynamic perspective is used in LSM: dynamic changes in landslide susceptibility can be identified on a daily scale. We note that Random Forest algorithm offers robust performance for accurate LSM (AUC = 0.975) and although the classification accuracy of LightGBM is the highest (AUC = 0.977), the results do not meet the sufficient conditions of a landslide susceptibility map. Combined with quantitative precipitation products, the proposed model can be used for the release of historical and predictive global dynamic landslide susceptibility information.

3 May 2023 in Nature Communications
Verified
Journal Article
Open access
PDF file
KLKai Liu
Kai Liu
QWQianzhi Wang
Qianzhi Wang
MWMing Wang
Ming Wang
EKElco Koks
Elco Koks
Transportation infrastructures are generally designed to have multi-decadal service lives. Transport infrastructure design, however, is largely based on historical conditions. Yet, in the face of global warming, we are likely going to experience more intense and frequent extreme events, which may put infrastructure at severe risk. In this study, we comprehensively analyze the exposure of road and railway infrastructure assets to changes in precipitation return periods globally. Under ~2 degrees of warming in mid-century (RCP 8.5 scenario), 43.6% of the global transportation assets are expected to experience at least a 25% decrease in design return period of extreme rainfall (a 33% increase in exceedance probability), which may increase to 69.9% under ~4 degrees of warming by late-21st century. To accommodate for such increases, we propose to incorporate a safety factor for climate change adaptation during the transportation infrastructure design process to ensure transportation assets will maintain their designed risk level in the future. Our results show that a safety factor of 1.2 would work sufficient for most regions of the world for quick design process calculations following the RCP4.5 path.

31 January 2023 in Remote Sensing
Verified
Journal Article
Open access
PDF file
ZJZiyu Jiang
Ziyu Jiang
MWMing Wang
Ming Wang
KLKai Liu
Kai Liu
Landslide is a natural disaster that seriously affects human life and social development. In this study, the characteristics and effectiveness of convolutional neural network (CNN) and conventional machine learning (ML) methods in a landslide susceptibility assessment (LSA) are compared. Six ML methods used in this study are Adaboost, multilayer perceptron neural network (MLP-NN), random forest (RF), naive Bayes, decision tree (DT), and gradient boosting decision tree (GBDT). First, the basic knowledge and structures of the CNN and ML methods, and the steps of the LSA are introduced. Then, 11 conditioning factors in three categories in the Hongxi River Basin, Pingwu County, Mianyang City, Sichuan Province are chosen to build the train, validation, and test samples. The CNN and ML models are constructed based on these samples. For comparison, indicator methods, statistical methods, and landslide susceptibility maps (LSMs) are used. The result shows that the CNN can obtain the highest accuracy (86.41%) and the highest AUC (0.9249) in the LSA. The statistical methods represented by the mean and variance of TP and TN perform more firmly on the possibility of landslide occurrence. Furthermore, the LSMs show that all models can successfully identify most of the landslide points, but for areas with a low frequency of landslides, some models are insufficient. The CNN model demonstrates better results in the recognition of the landslides’ cluster region, this is also related to the convolution operation that takes the surrounding environment information into account. The higher accuracy and more concentrative possibility of CNN in LSA is of great significance for disaster prevention and mitigation, which can help the efficient use of human and material resources. Although CNN performs better than other methods, there are still some limitations, the identification of low-cluster landside areas can be enhanced by improving the CNN model.

21 November 2023 in Earth's Future
Verified
Journal Article
Open access
BLBohao Li
Bohao Li
KLKai Liu
Kai Liu
MWMing Wang
Ming Wang
QWQianzhi Wang
Qianzhi Wang
QHQian He
Qian He
CLChenxia Li
Chenxia Li
The increase in record‐breaking extreme events caused by climate change poses a threat to human health and well‐being. Understanding the future impacts of such events on global populations can provide decision‐making support for policies aiming to mitigate climate change. Here, we investigated the population exposure to eight climate extreme indices and drivers of exposure trajectories based on National Aeronautics and Space Administration Earth Exchange Global Daily Downscaled Projections Coupled Model Intercomparison Project 6 and population projection data under four shared socioeconomic pathway scenarios at a spatial resolution of 0.25° × 0.25°. The results show that by the mid‐twenty‐first century, most regions worldwide, especially Africa and South America, will continue to experience record‐breaking temperatures and compound drought and heatwaves (CDHWs). Regarding population exposure, under SSP3‐7.0 in the late twenty‐first century, the mean value of the multimodel median expected annual exposure (EAE) of all extreme temperature indices and CDHW reaches 8.12 billion persons per year. Population exposure hotspots will be concentrated in Central Africa, South Asia, Southeast Asia, and East Asia, mostly in developing countries, where 55.01%–87.42% of the EAE is found. The drivers of exposure trajectories are spatially heterogeneous. The increase in record‐breaking probability contributes more than population growth to EAE growth in most regions of the world except Central Asia, the Middle East, and most of Africa. These findings reveal the future trajectories of record‐breaking probabilities and population exposures for climate extremes, which can inform understanding of the intersections between climate change and population change and future risk management.