Xiaoye Liu

Dr. Xiaoye 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
Verified
Journal Article
Open access
PDF file
BABader Alshehri
Bader Alshehri
ZZZhenyu Zhang
Zhenyu Zhang
XLXiaoye Liu
Xiaoye Liu
Google Earth Engine (GEE) has become one of the most widely used platforms for Land Use and Land Cover (LULC) research, offering cloud-based access to petabyte-scale datasets and scalable analytical tools. While earlier reviews provided valuable overviews of data and applications, this study synthesizes 72 selected articles published between 2016 and February 2025 to examine the evolution of GEE–LULC research. Results show exponential growth in publications, with Landsat and Sentinel imagery dominating datasets and Random Forest (RF) and Support Vector Machine (SVM) remaining the most common classifiers. Geographically, output is concentrated in China and India, reflecting regional leadership in GEE adoption. Despite its strengths, GEE faces persistent challenges, including memory limits, restricted support for advanced Deep Learning (DL), and reliance on labeled data. Promising directions include integrating few-shot semantic segmentation and hybrid workflows combining GEE scalability with local Graphics Processing Unit (GPU) computing. By bridging platform-focused and application-focused studies, this review provides a comprehensive synthesis of GEE–LULC research and outlines actionable pathways for advancing scalable and Artificial Intelligence (AI)-enabled geospatial analysis.

21 June 2017 in International Journal of Digital Earth
Verified
Journal Article
Closed access
SKSaman Koswatte
Saman Koswatte
KMKevin McDougall
Kevin McDougall
XLXiaoye Liu
Xiaoye Liu
Volunteered geographic information (VGI) can be considered a subset of crowdsourced data (CSD) and its popularity has recently increased in a number of application areas. Disaster management is one of its key application areas in which the benefits of VGI and CSD are potentially very high. However, quality issues such as credibility, reliability and relevance are limiting many of the advantages of utilising CSD. Credibility issues arise as CSD come from a variety of heterogeneous sources including both professionals and untrained citizens. VGI and CSD are also highly unstructured and the quality and metadata are often undocumented. In the 2011 Australian floods, the general public and disaster management administrators used the Ushahidi Crowd-mapping platform to extensively communicate flood-related information including hazards, evacuations, emergency services, road closures and property damage. This study assessed the credibility of the Australian Broadcasting Corporation’s Ushahidi CrowdMap dataset using a Naïve Bayesian network approach based on models commonly used in spam email detection systems. The results of the study reveal that the spam email detection approach is potentially useful for CSD credibility detection with an accuracy of over 90% using a forced classification methodology.

20 July 2025 in Remote Sensing
Verified
Journal Article
Open access
PDF file
Zibonele BhebheZibonele Bhebhe
Zibonele Bhebhe
XLXiaoye Liu
Xiaoye Liu
ZZZhenyu Zhang
Zhenyu Zhang
Dev Raj PaudyalDev Raj Paudyal
Dev Raj Paudyal
Light Detection and Ranging (LiDAR) provides three-dimensional information that can be used to extract tree parameter measurements such as height (H), canopy volume (CV), canopy diameter (CD), canopy area (CA), and tree stand density. LiDAR data does not directly give diameter at breast height (DBH), an important input into allometric equations to estimate biomass. The main objective of this study is to estimate tree DBH using existing allometric models. Specifically, it compares three global DBH pantropical models to calculate DBH and to estimate the aboveground biomass (AGB) of the Lake Broadwater Forest located in Southeast (SE) Queensland, Australia. LiDAR data collected in mid-2022 was used to test these models, with field validation data collected at the beginning of 2024. The three DBH estimation models—the Jucker model, Gonzalez-Benecke model 1, and Gonzalez-Benecke model 2—all used tree H, and the Jucker and Gonzalez-Benecke model 2 additionally used CD and CA, respectively. Model performance was assessed using five statistical metrics: root mean squared error (RMSE), mean absolute error (MAE), mean absolute percentage error (MAPE), percentage bias (MBias), and the coefficient of determination (R2). The Jucker model was the best-performing model, followed by Gonzalez-Benecke model 2 and Gonzalez-Benecke model 1. The Jucker model had an RMSE of 8.7 cm, an MAE of −13.54 cm, an MAPE of 7%, an MBias of 13.73 cm, and an R2 of 0.9005. The Chave AGB model was used to estimate the AGB at the tree, plot, and per hectare levels using the Jucker model-calculated DBH and the field-measured DBH. AGB was used to estimate total biomass, dry weight, carbon (C), and carbon dioxide (CO2) sequestered per hectare. The Lake Broadwater Forest was estimated to have an AGB of 161.5 Mg/ha in 2022, a Total C of 65.6 Mg/ha, and a CO2 sequestered of 240.7 Mg/ha in 2022. These findings highlight the substantial carbon storage potential of the Lake Broadwater Forest, reinforcing the opportunity for landholders to participate in the carbon credit systems, which offer financial benefits and enable contributions to carbon mitigation programs, thereby helping to meet national and global carbon reduction targets.

14 February 2026 in Remote Sensing Applications: Society and Environment
Verified
Journal Article
Open access
ZYZhidong Yuan
Zhidong Yuan
XLXiaoye Liu
Xiaoye Liu
ZZZhenyu Zhang
Zhenyu Zhang
TMTek Maraseni
Tek Maraseni

10 September 2025 in Preprints.org
Verified
Preprint
Open access
PDF file
BABader Alshehri
Bader Alshehri
ZZZhenyu Zhang
Zhenyu Zhang
XLXiaoye Liu
Xiaoye Liu
Google Earth Engine (GEE) has emerged as a powerful tool for analyzing Land Use and Land Cover (LULC) changes in a wide range of research. While some GEE-related reviews exist, they primarily cover publications before 2020. This review examines the latest trends, applications, and challenges in using GEE for LULC change detection up to February 2025. In this study, 72 studies were selected from Google Scholar, Scopus, and Web of Science databases. Results reveal that GEE experienced exponential growth in the research field from 2011 to 2025. The journal “Remote Sensing” plays a significant role in the field, accounting for 25% of total publications. China leads in GEE-LULC-based studies with 27%, followed by India (13%). Landsat data appears in 65% of studies, making it the most utilized, followed by Sentinel data at 23%. Random Forest (RF) is the most used classification method (36%), surpassing Support Vector Machine (SVM) and Classification and Regression Tree (CART). Most studies validate classification results with overall accuracy rates from 80% to 98.68%, with the highest achieved using the combination of RF, CART, and SVM. GEE’s users noted challenges such as memory limits, slow processing, cloud cover issues, and limited support for advanced machine learning (ML) models. Unlike previous reviews focusing solely on GEE or LULC, this study integrates both, providing a dedicated analysis of their intersection and filling a clear gap in the literature. This study aims to provide a comprehensive review of how GEE is applied to LULC change detection, identifying current trends, methodological preferences, and practical challenges, and to guide future research on leveraging GEE in LULC change studies.

8 June 2026 in Remote Sensing Applications: Society and Environment
Verified
Journal Article
Open access
EMEric Mensah
Eric Mensah
XLXiaoye Liu
Xiaoye Liu
ZZZhenyu Zhang
Zhenyu Zhang
GCGlenn Campbell
Glenn Campbell